[ { "name": "", "class": "LTX2VideoTransformer3DModel", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "proj_in", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 128, "out_features": 4096, "bias": true, "skip": false }, { "name": "audio_proj_in", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 128, "out_features": 2048, "bias": true, "skip": false }, { "name": "time_embed", "class": "LTX2AdaLayerNormSingle", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "time_embed.emb", "class": "PixArtAlphaCombinedTimestepSizeEmbeddings", "module": "diffusers.models.embeddings" }, { "name": "time_embed.emb.time_proj", "class": "Timesteps", "module": "diffusers.models.embeddings" }, { "name": "time_embed.emb.timestep_embedder", "class": "TimestepEmbedding", "module": "diffusers.models.embeddings" }, { "name": "time_embed.emb.timestep_embedder.linear_1", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 256, "out_features": 4096, "bias": true, "skip": false }, { "name": "time_embed.emb.timestep_embedder.act", "class": "SiLU", "module": "torch.nn.modules.activation" }, { "name": "time_embed.emb.timestep_embedder.linear_2", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "time_embed.silu", "class": "SiLU", "module": "torch.nn.modules.activation" }, { "name": "time_embed.linear", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 36864, "bias": true, "skip": false }, { "name": "audio_time_embed", "class": "LTX2AdaLayerNormSingle", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "audio_time_embed.emb", "class": "PixArtAlphaCombinedTimestepSizeEmbeddings", "module": "diffusers.models.embeddings" }, { "name": "audio_time_embed.emb.time_proj", "class": "Timesteps", "module": "diffusers.models.embeddings" }, { "name": "audio_time_embed.emb.timestep_embedder", "class": "TimestepEmbedding", "module": "diffusers.models.embeddings" }, { "name": "audio_time_embed.emb.timestep_embedder.linear_1", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 256, "out_features": 2048, "bias": true, "skip": false }, { "name": "audio_time_embed.emb.timestep_embedder.act", "class": "SiLU", "module": "torch.nn.modules.activation" }, { "name": "audio_time_embed.emb.timestep_embedder.linear_2", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "audio_time_embed.silu", "class": "SiLU", "module": "torch.nn.modules.activation" }, { "name": "audio_time_embed.linear", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 18432, "bias": true, "skip": false }, { "name": "av_cross_attn_video_scale_shift", "class": "LTX2AdaLayerNormSingle", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "av_cross_attn_video_scale_shift.emb", "class": "PixArtAlphaCombinedTimestepSizeEmbeddings", "module": "diffusers.models.embeddings" }, { "name": "av_cross_attn_video_scale_shift.emb.time_proj", "class": "Timesteps", "module": "diffusers.models.embeddings" }, { "name": "av_cross_attn_video_scale_shift.emb.timestep_embedder", "class": "TimestepEmbedding", "module": "diffusers.models.embeddings" }, { "name": "av_cross_attn_video_scale_shift.emb.timestep_embedder.linear_1", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 256, "out_features": 4096, "bias": true, "skip": false }, { "name": "av_cross_attn_video_scale_shift.emb.timestep_embedder.act", "class": "SiLU", "module": "torch.nn.modules.activation" }, { "name": "av_cross_attn_video_scale_shift.emb.timestep_embedder.linear_2", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "av_cross_attn_video_scale_shift.silu", "class": "SiLU", "module": "torch.nn.modules.activation" }, { "name": "av_cross_attn_video_scale_shift.linear", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 16384, "bias": true, "skip": false }, { "name": "av_cross_attn_audio_scale_shift", "class": "LTX2AdaLayerNormSingle", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "av_cross_attn_audio_scale_shift.emb", "class": "PixArtAlphaCombinedTimestepSizeEmbeddings", "module": "diffusers.models.embeddings" }, { "name": "av_cross_attn_audio_scale_shift.emb.time_proj", "class": "Timesteps", "module": "diffusers.models.embeddings" }, { "name": "av_cross_attn_audio_scale_shift.emb.timestep_embedder", "class": "TimestepEmbedding", "module": "diffusers.models.embeddings" }, { "name": "av_cross_attn_audio_scale_shift.emb.timestep_embedder.linear_1", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 256, "out_features": 2048, "bias": true, "skip": false }, { "name": "av_cross_attn_audio_scale_shift.emb.timestep_embedder.act", "class": "SiLU", "module": "torch.nn.modules.activation" }, { "name": "av_cross_attn_audio_scale_shift.emb.timestep_embedder.linear_2", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "av_cross_attn_audio_scale_shift.silu", "class": "SiLU", "module": "torch.nn.modules.activation" }, { "name": "av_cross_attn_audio_scale_shift.linear", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 8192, "bias": true, "skip": false }, { "name": "av_cross_attn_video_a2v_gate", "class": "LTX2AdaLayerNormSingle", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "av_cross_attn_video_a2v_gate.emb", "class": "PixArtAlphaCombinedTimestepSizeEmbeddings", "module": "diffusers.models.embeddings" }, { "name": "av_cross_attn_video_a2v_gate.emb.time_proj", "class": "Timesteps", "module": "diffusers.models.embeddings" }, { "name": "av_cross_attn_video_a2v_gate.emb.timestep_embedder", "class": "TimestepEmbedding", "module": "diffusers.models.embeddings" }, { "name": "av_cross_attn_video_a2v_gate.emb.timestep_embedder.linear_1", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 256, "out_features": 4096, "bias": true, "skip": false }, { "name": "av_cross_attn_video_a2v_gate.emb.timestep_embedder.act", "class": "SiLU", "module": "torch.nn.modules.activation" }, { "name": "av_cross_attn_video_a2v_gate.emb.timestep_embedder.linear_2", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "av_cross_attn_video_a2v_gate.silu", "class": "SiLU", "module": "torch.nn.modules.activation" }, { "name": "av_cross_attn_video_a2v_gate.linear", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "av_cross_attn_audio_v2a_gate", "class": "LTX2AdaLayerNormSingle", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "av_cross_attn_audio_v2a_gate.emb", "class": "PixArtAlphaCombinedTimestepSizeEmbeddings", "module": "diffusers.models.embeddings" }, { "name": "av_cross_attn_audio_v2a_gate.emb.time_proj", "class": "Timesteps", "module": "diffusers.models.embeddings" }, { "name": "av_cross_attn_audio_v2a_gate.emb.timestep_embedder", "class": "TimestepEmbedding", "module": "diffusers.models.embeddings" }, { "name": "av_cross_attn_audio_v2a_gate.emb.timestep_embedder.linear_1", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 256, "out_features": 2048, "bias": true, "skip": false }, { "name": "av_cross_attn_audio_v2a_gate.emb.timestep_embedder.act", "class": "SiLU", "module": "torch.nn.modules.activation" }, { "name": "av_cross_attn_audio_v2a_gate.emb.timestep_embedder.linear_2", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "av_cross_attn_audio_v2a_gate.silu", "class": "SiLU", "module": "torch.nn.modules.activation" }, { "name": "av_cross_attn_audio_v2a_gate.linear", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "prompt_adaln", "class": "LTX2AdaLayerNormSingle", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "prompt_adaln.emb", "class": "PixArtAlphaCombinedTimestepSizeEmbeddings", "module": "diffusers.models.embeddings" }, { "name": "prompt_adaln.emb.time_proj", "class": "Timesteps", "module": "diffusers.models.embeddings" }, { "name": "prompt_adaln.emb.timestep_embedder", "class": "TimestepEmbedding", "module": "diffusers.models.embeddings" }, { "name": "prompt_adaln.emb.timestep_embedder.linear_1", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 256, "out_features": 4096, "bias": true, "skip": false }, { "name": "prompt_adaln.emb.timestep_embedder.act", "class": "SiLU", "module": "torch.nn.modules.activation" }, { "name": "prompt_adaln.emb.timestep_embedder.linear_2", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "prompt_adaln.silu", "class": "SiLU", "module": "torch.nn.modules.activation" }, { "name": "prompt_adaln.linear", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 8192, "bias": true, "skip": false }, { "name": "audio_prompt_adaln", "class": "LTX2AdaLayerNormSingle", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "audio_prompt_adaln.emb", "class": "PixArtAlphaCombinedTimestepSizeEmbeddings", "module": "diffusers.models.embeddings" }, { "name": "audio_prompt_adaln.emb.time_proj", "class": "Timesteps", "module": "diffusers.models.embeddings" }, { "name": "audio_prompt_adaln.emb.timestep_embedder", "class": "TimestepEmbedding", "module": "diffusers.models.embeddings" }, { "name": "audio_prompt_adaln.emb.timestep_embedder.linear_1", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 256, "out_features": 2048, "bias": true, "skip": false }, { "name": "audio_prompt_adaln.emb.timestep_embedder.act", "class": "SiLU", "module": "torch.nn.modules.activation" }, { "name": "audio_prompt_adaln.emb.timestep_embedder.linear_2", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "audio_prompt_adaln.silu", "class": "SiLU", "module": "torch.nn.modules.activation" }, { "name": "audio_prompt_adaln.linear", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 4096, "bias": true, "skip": false }, { "name": "rope", "class": "LTX2AudioVideoRotaryPosEmbed", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "audio_rope", "class": "LTX2AudioVideoRotaryPosEmbed", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "cross_attn_rope", "class": "LTX2AudioVideoRotaryPosEmbed", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "cross_attn_audio_rope", "class": "LTX2AudioVideoRotaryPosEmbed", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.0", "class": "LTX2VideoTransformerBlock", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.0.norm1", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.0.attn1", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.0.attn1.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.0.attn1.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.0.attn1.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.0.attn1.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.0.attn1.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.0.attn1.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.0.attn1.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.0.attn1.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.0.attn1.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.0.audio_norm1", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.0.audio_attn1", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.0.audio_attn1.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.0.audio_attn1.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.0.audio_attn1.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.0.audio_attn1.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.0.audio_attn1.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.0.audio_attn1.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.0.audio_attn1.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.0.audio_attn1.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.0.audio_attn1.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.0.norm2", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.0.attn2", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.0.attn2.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.0.attn2.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.0.attn2.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.0.attn2.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.0.attn2.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.0.attn2.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.0.attn2.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.0.attn2.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.0.attn2.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.0.audio_norm2", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.0.audio_attn2", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.0.audio_attn2.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.0.audio_attn2.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.0.audio_attn2.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.0.audio_attn2.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.0.audio_attn2.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.0.audio_attn2.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.0.audio_attn2.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.0.audio_attn2.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.0.audio_attn2.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.0.audio_to_video_norm", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.0.audio_to_video_attn", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.0.audio_to_video_attn.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.0.audio_to_video_attn.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.0.audio_to_video_attn.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.0.audio_to_video_attn.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.0.audio_to_video_attn.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.0.audio_to_video_attn.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.0.audio_to_video_attn.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.0.audio_to_video_attn.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.0.audio_to_video_attn.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.0.video_to_audio_norm", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.0.video_to_audio_attn", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.0.video_to_audio_attn.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.0.video_to_audio_attn.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.0.video_to_audio_attn.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.0.video_to_audio_attn.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.0.video_to_audio_attn.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.0.video_to_audio_attn.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.0.video_to_audio_attn.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.0.video_to_audio_attn.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.0.video_to_audio_attn.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.0.norm3", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.0.ff", "class": "FeedForward", "module": "diffusers.models.attention" }, { "name": "transformer_blocks.0.ff.net", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.0.ff.net.0", "class": "GELU", "module": "diffusers.models.activations" }, { "name": "transformer_blocks.0.ff.net.0.proj", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 16384, "bias": true, "skip": false }, { "name": "transformer_blocks.0.ff.net.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.0.ff.net.2", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 16384, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.0.audio_norm3", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.0.audio_ff", "class": "FeedForward", "module": "diffusers.models.attention" }, { "name": "transformer_blocks.0.audio_ff.net", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.0.audio_ff.net.0", "class": "GELU", "module": "diffusers.models.activations" }, { "name": "transformer_blocks.0.audio_ff.net.0.proj", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 8192, "bias": true, "skip": false }, { "name": "transformer_blocks.0.audio_ff.net.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.0.audio_ff.net.2", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 8192, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.1", "class": "LTX2VideoTransformerBlock", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.1.norm1", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.1.attn1", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.1.attn1.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.1.attn1.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.1.attn1.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.1.attn1.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.1.attn1.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.1.attn1.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.1.attn1.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.1.attn1.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.1.attn1.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.1.audio_norm1", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.1.audio_attn1", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.1.audio_attn1.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.1.audio_attn1.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.1.audio_attn1.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.1.audio_attn1.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.1.audio_attn1.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.1.audio_attn1.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.1.audio_attn1.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.1.audio_attn1.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.1.audio_attn1.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.1.norm2", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.1.attn2", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.1.attn2.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.1.attn2.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.1.attn2.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.1.attn2.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.1.attn2.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.1.attn2.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.1.attn2.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.1.attn2.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.1.attn2.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.1.audio_norm2", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.1.audio_attn2", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.1.audio_attn2.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.1.audio_attn2.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.1.audio_attn2.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.1.audio_attn2.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.1.audio_attn2.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.1.audio_attn2.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.1.audio_attn2.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.1.audio_attn2.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.1.audio_attn2.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.1.audio_to_video_norm", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.1.audio_to_video_attn", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.1.audio_to_video_attn.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.1.audio_to_video_attn.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.1.audio_to_video_attn.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.1.audio_to_video_attn.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.1.audio_to_video_attn.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.1.audio_to_video_attn.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.1.audio_to_video_attn.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.1.audio_to_video_attn.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.1.audio_to_video_attn.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.1.video_to_audio_norm", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.1.video_to_audio_attn", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.1.video_to_audio_attn.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.1.video_to_audio_attn.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.1.video_to_audio_attn.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.1.video_to_audio_attn.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.1.video_to_audio_attn.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.1.video_to_audio_attn.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.1.video_to_audio_attn.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.1.video_to_audio_attn.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.1.video_to_audio_attn.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.1.norm3", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.1.ff", "class": "FeedForward", "module": "diffusers.models.attention" }, { "name": "transformer_blocks.1.ff.net", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.1.ff.net.0", "class": "GELU", "module": "diffusers.models.activations" }, { "name": "transformer_blocks.1.ff.net.0.proj", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 16384, "bias": true, "skip": false }, { "name": "transformer_blocks.1.ff.net.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.1.ff.net.2", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 16384, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.1.audio_norm3", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.1.audio_ff", "class": "FeedForward", "module": "diffusers.models.attention" }, { "name": "transformer_blocks.1.audio_ff.net", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.1.audio_ff.net.0", "class": "GELU", "module": "diffusers.models.activations" }, { "name": "transformer_blocks.1.audio_ff.net.0.proj", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 8192, "bias": true, "skip": false }, { "name": "transformer_blocks.1.audio_ff.net.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.1.audio_ff.net.2", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 8192, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.2", "class": "LTX2VideoTransformerBlock", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.2.norm1", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.2.attn1", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.2.attn1.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.2.attn1.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.2.attn1.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.2.attn1.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.2.attn1.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.2.attn1.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.2.attn1.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.2.attn1.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.2.attn1.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.2.audio_norm1", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.2.audio_attn1", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.2.audio_attn1.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.2.audio_attn1.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.2.audio_attn1.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.2.audio_attn1.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.2.audio_attn1.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.2.audio_attn1.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.2.audio_attn1.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.2.audio_attn1.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.2.audio_attn1.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.2.norm2", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.2.attn2", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.2.attn2.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.2.attn2.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.2.attn2.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.2.attn2.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.2.attn2.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.2.attn2.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.2.attn2.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.2.attn2.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.2.attn2.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.2.audio_norm2", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.2.audio_attn2", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.2.audio_attn2.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.2.audio_attn2.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.2.audio_attn2.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.2.audio_attn2.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.2.audio_attn2.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.2.audio_attn2.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.2.audio_attn2.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.2.audio_attn2.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.2.audio_attn2.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.2.audio_to_video_norm", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.2.audio_to_video_attn", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.2.audio_to_video_attn.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.2.audio_to_video_attn.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.2.audio_to_video_attn.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.2.audio_to_video_attn.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.2.audio_to_video_attn.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.2.audio_to_video_attn.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.2.audio_to_video_attn.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.2.audio_to_video_attn.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.2.audio_to_video_attn.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.2.video_to_audio_norm", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.2.video_to_audio_attn", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.2.video_to_audio_attn.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.2.video_to_audio_attn.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.2.video_to_audio_attn.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.2.video_to_audio_attn.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.2.video_to_audio_attn.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.2.video_to_audio_attn.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.2.video_to_audio_attn.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.2.video_to_audio_attn.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.2.video_to_audio_attn.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.2.norm3", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.2.ff", "class": "FeedForward", "module": "diffusers.models.attention" }, { "name": "transformer_blocks.2.ff.net", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.2.ff.net.0", "class": "GELU", "module": "diffusers.models.activations" }, { "name": "transformer_blocks.2.ff.net.0.proj", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 16384, "bias": true, "skip": false }, { "name": "transformer_blocks.2.ff.net.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.2.ff.net.2", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 16384, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.2.audio_norm3", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.2.audio_ff", "class": "FeedForward", "module": "diffusers.models.attention" }, { "name": "transformer_blocks.2.audio_ff.net", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.2.audio_ff.net.0", "class": "GELU", "module": "diffusers.models.activations" }, { "name": "transformer_blocks.2.audio_ff.net.0.proj", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 8192, "bias": true, "skip": false }, { "name": "transformer_blocks.2.audio_ff.net.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.2.audio_ff.net.2", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 8192, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.3", "class": "LTX2VideoTransformerBlock", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.3.norm1", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.3.attn1", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.3.attn1.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.3.attn1.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.3.attn1.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.3.attn1.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.3.attn1.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.3.attn1.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.3.attn1.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.3.attn1.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.3.attn1.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.3.audio_norm1", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.3.audio_attn1", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.3.audio_attn1.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.3.audio_attn1.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.3.audio_attn1.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.3.audio_attn1.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.3.audio_attn1.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.3.audio_attn1.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.3.audio_attn1.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.3.audio_attn1.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.3.audio_attn1.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.3.norm2", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.3.attn2", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.3.attn2.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.3.attn2.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.3.attn2.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.3.attn2.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.3.attn2.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.3.attn2.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.3.attn2.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.3.attn2.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.3.attn2.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.3.audio_norm2", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.3.audio_attn2", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.3.audio_attn2.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.3.audio_attn2.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.3.audio_attn2.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.3.audio_attn2.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.3.audio_attn2.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.3.audio_attn2.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.3.audio_attn2.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.3.audio_attn2.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.3.audio_attn2.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.3.audio_to_video_norm", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.3.audio_to_video_attn", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.3.audio_to_video_attn.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.3.audio_to_video_attn.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.3.audio_to_video_attn.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.3.audio_to_video_attn.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.3.audio_to_video_attn.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.3.audio_to_video_attn.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.3.audio_to_video_attn.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.3.audio_to_video_attn.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.3.audio_to_video_attn.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.3.video_to_audio_norm", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.3.video_to_audio_attn", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.3.video_to_audio_attn.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.3.video_to_audio_attn.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.3.video_to_audio_attn.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.3.video_to_audio_attn.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.3.video_to_audio_attn.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.3.video_to_audio_attn.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.3.video_to_audio_attn.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.3.video_to_audio_attn.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.3.video_to_audio_attn.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.3.norm3", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.3.ff", "class": "FeedForward", "module": "diffusers.models.attention" }, { "name": "transformer_blocks.3.ff.net", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.3.ff.net.0", "class": "GELU", "module": "diffusers.models.activations" }, { "name": "transformer_blocks.3.ff.net.0.proj", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 16384, "bias": true, "skip": false }, { "name": "transformer_blocks.3.ff.net.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.3.ff.net.2", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 16384, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.3.audio_norm3", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.3.audio_ff", "class": "FeedForward", "module": "diffusers.models.attention" }, { "name": "transformer_blocks.3.audio_ff.net", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.3.audio_ff.net.0", "class": "GELU", "module": "diffusers.models.activations" }, { "name": "transformer_blocks.3.audio_ff.net.0.proj", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 8192, "bias": true, "skip": false }, { "name": "transformer_blocks.3.audio_ff.net.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.3.audio_ff.net.2", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 8192, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.4", "class": "LTX2VideoTransformerBlock", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.4.norm1", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.4.attn1", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.4.attn1.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.4.attn1.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.4.attn1.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.4.attn1.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.4.attn1.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.4.attn1.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.4.attn1.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.4.attn1.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.4.attn1.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.4.audio_norm1", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.4.audio_attn1", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.4.audio_attn1.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.4.audio_attn1.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.4.audio_attn1.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.4.audio_attn1.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.4.audio_attn1.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.4.audio_attn1.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.4.audio_attn1.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.4.audio_attn1.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.4.audio_attn1.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.4.norm2", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.4.attn2", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.4.attn2.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.4.attn2.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.4.attn2.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.4.attn2.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.4.attn2.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.4.attn2.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.4.attn2.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.4.attn2.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.4.attn2.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.4.audio_norm2", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.4.audio_attn2", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.4.audio_attn2.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.4.audio_attn2.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.4.audio_attn2.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.4.audio_attn2.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.4.audio_attn2.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.4.audio_attn2.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.4.audio_attn2.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.4.audio_attn2.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.4.audio_attn2.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.4.audio_to_video_norm", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.4.audio_to_video_attn", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.4.audio_to_video_attn.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.4.audio_to_video_attn.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.4.audio_to_video_attn.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.4.audio_to_video_attn.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.4.audio_to_video_attn.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.4.audio_to_video_attn.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.4.audio_to_video_attn.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.4.audio_to_video_attn.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.4.audio_to_video_attn.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.4.video_to_audio_norm", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.4.video_to_audio_attn", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.4.video_to_audio_attn.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.4.video_to_audio_attn.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.4.video_to_audio_attn.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.4.video_to_audio_attn.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.4.video_to_audio_attn.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.4.video_to_audio_attn.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.4.video_to_audio_attn.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.4.video_to_audio_attn.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.4.video_to_audio_attn.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.4.norm3", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.4.ff", "class": "FeedForward", "module": "diffusers.models.attention" }, { "name": "transformer_blocks.4.ff.net", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.4.ff.net.0", "class": "GELU", "module": "diffusers.models.activations" }, { "name": "transformer_blocks.4.ff.net.0.proj", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 16384, "bias": true, "skip": false }, { "name": "transformer_blocks.4.ff.net.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.4.ff.net.2", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 16384, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.4.audio_norm3", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.4.audio_ff", "class": "FeedForward", "module": "diffusers.models.attention" }, { "name": "transformer_blocks.4.audio_ff.net", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.4.audio_ff.net.0", "class": "GELU", "module": "diffusers.models.activations" }, { "name": "transformer_blocks.4.audio_ff.net.0.proj", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 8192, "bias": true, "skip": false }, { "name": "transformer_blocks.4.audio_ff.net.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.4.audio_ff.net.2", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 8192, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.5", "class": "LTX2VideoTransformerBlock", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.5.norm1", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.5.attn1", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.5.attn1.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.5.attn1.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.5.attn1.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.5.attn1.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.5.attn1.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.5.attn1.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.5.attn1.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.5.attn1.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.5.attn1.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.5.audio_norm1", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.5.audio_attn1", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.5.audio_attn1.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.5.audio_attn1.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.5.audio_attn1.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.5.audio_attn1.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.5.audio_attn1.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.5.audio_attn1.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.5.audio_attn1.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.5.audio_attn1.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.5.audio_attn1.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.5.norm2", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.5.attn2", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.5.attn2.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.5.attn2.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.5.attn2.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.5.attn2.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.5.attn2.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.5.attn2.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.5.attn2.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.5.attn2.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.5.attn2.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.5.audio_norm2", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.5.audio_attn2", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.5.audio_attn2.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.5.audio_attn2.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.5.audio_attn2.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.5.audio_attn2.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.5.audio_attn2.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.5.audio_attn2.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.5.audio_attn2.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.5.audio_attn2.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.5.audio_attn2.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.5.audio_to_video_norm", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.5.audio_to_video_attn", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.5.audio_to_video_attn.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.5.audio_to_video_attn.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.5.audio_to_video_attn.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.5.audio_to_video_attn.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.5.audio_to_video_attn.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.5.audio_to_video_attn.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.5.audio_to_video_attn.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.5.audio_to_video_attn.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.5.audio_to_video_attn.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.5.video_to_audio_norm", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.5.video_to_audio_attn", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.5.video_to_audio_attn.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.5.video_to_audio_attn.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.5.video_to_audio_attn.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.5.video_to_audio_attn.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.5.video_to_audio_attn.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.5.video_to_audio_attn.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.5.video_to_audio_attn.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.5.video_to_audio_attn.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.5.video_to_audio_attn.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.5.norm3", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.5.ff", "class": "FeedForward", "module": "diffusers.models.attention" }, { "name": "transformer_blocks.5.ff.net", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.5.ff.net.0", "class": "GELU", "module": "diffusers.models.activations" }, { "name": "transformer_blocks.5.ff.net.0.proj", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 16384, "bias": true, "skip": false }, { "name": "transformer_blocks.5.ff.net.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.5.ff.net.2", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 16384, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.5.audio_norm3", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.5.audio_ff", "class": "FeedForward", "module": "diffusers.models.attention" }, { "name": "transformer_blocks.5.audio_ff.net", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.5.audio_ff.net.0", "class": "GELU", "module": "diffusers.models.activations" }, { "name": "transformer_blocks.5.audio_ff.net.0.proj", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 8192, "bias": true, "skip": false }, { "name": "transformer_blocks.5.audio_ff.net.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.5.audio_ff.net.2", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 8192, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.6", "class": "LTX2VideoTransformerBlock", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.6.norm1", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.6.attn1", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.6.attn1.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.6.attn1.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.6.attn1.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.6.attn1.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.6.attn1.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.6.attn1.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.6.attn1.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.6.attn1.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.6.attn1.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.6.audio_norm1", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.6.audio_attn1", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.6.audio_attn1.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.6.audio_attn1.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.6.audio_attn1.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.6.audio_attn1.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.6.audio_attn1.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.6.audio_attn1.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.6.audio_attn1.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.6.audio_attn1.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.6.audio_attn1.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.6.norm2", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.6.attn2", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.6.attn2.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.6.attn2.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.6.attn2.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.6.attn2.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.6.attn2.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.6.attn2.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.6.attn2.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.6.attn2.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.6.attn2.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.6.audio_norm2", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.6.audio_attn2", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.6.audio_attn2.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.6.audio_attn2.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.6.audio_attn2.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.6.audio_attn2.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.6.audio_attn2.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.6.audio_attn2.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.6.audio_attn2.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.6.audio_attn2.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.6.audio_attn2.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.6.audio_to_video_norm", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.6.audio_to_video_attn", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.6.audio_to_video_attn.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.6.audio_to_video_attn.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.6.audio_to_video_attn.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.6.audio_to_video_attn.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.6.audio_to_video_attn.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.6.audio_to_video_attn.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.6.audio_to_video_attn.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.6.audio_to_video_attn.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.6.audio_to_video_attn.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.6.video_to_audio_norm", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.6.video_to_audio_attn", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.6.video_to_audio_attn.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.6.video_to_audio_attn.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.6.video_to_audio_attn.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.6.video_to_audio_attn.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.6.video_to_audio_attn.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.6.video_to_audio_attn.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.6.video_to_audio_attn.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.6.video_to_audio_attn.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.6.video_to_audio_attn.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.6.norm3", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.6.ff", "class": "FeedForward", "module": "diffusers.models.attention" }, { "name": "transformer_blocks.6.ff.net", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.6.ff.net.0", "class": "GELU", "module": "diffusers.models.activations" }, { "name": "transformer_blocks.6.ff.net.0.proj", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 16384, "bias": true, "skip": false }, { "name": "transformer_blocks.6.ff.net.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.6.ff.net.2", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 16384, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.6.audio_norm3", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.6.audio_ff", "class": "FeedForward", "module": "diffusers.models.attention" }, { "name": "transformer_blocks.6.audio_ff.net", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.6.audio_ff.net.0", "class": "GELU", "module": "diffusers.models.activations" }, { "name": "transformer_blocks.6.audio_ff.net.0.proj", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 8192, "bias": true, "skip": false }, { "name": "transformer_blocks.6.audio_ff.net.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.6.audio_ff.net.2", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 8192, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.7", "class": "LTX2VideoTransformerBlock", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.7.norm1", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.7.attn1", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.7.attn1.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.7.attn1.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.7.attn1.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.7.attn1.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.7.attn1.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.7.attn1.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.7.attn1.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.7.attn1.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.7.attn1.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.7.audio_norm1", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.7.audio_attn1", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.7.audio_attn1.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.7.audio_attn1.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.7.audio_attn1.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.7.audio_attn1.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.7.audio_attn1.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.7.audio_attn1.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.7.audio_attn1.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.7.audio_attn1.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.7.audio_attn1.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.7.norm2", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.7.attn2", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.7.attn2.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.7.attn2.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.7.attn2.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.7.attn2.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.7.attn2.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.7.attn2.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.7.attn2.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.7.attn2.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.7.attn2.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.7.audio_norm2", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.7.audio_attn2", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.7.audio_attn2.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.7.audio_attn2.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.7.audio_attn2.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.7.audio_attn2.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.7.audio_attn2.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.7.audio_attn2.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.7.audio_attn2.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.7.audio_attn2.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.7.audio_attn2.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.7.audio_to_video_norm", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.7.audio_to_video_attn", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.7.audio_to_video_attn.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.7.audio_to_video_attn.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.7.audio_to_video_attn.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.7.audio_to_video_attn.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.7.audio_to_video_attn.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.7.audio_to_video_attn.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.7.audio_to_video_attn.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.7.audio_to_video_attn.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.7.audio_to_video_attn.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.7.video_to_audio_norm", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.7.video_to_audio_attn", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.7.video_to_audio_attn.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.7.video_to_audio_attn.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.7.video_to_audio_attn.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.7.video_to_audio_attn.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.7.video_to_audio_attn.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.7.video_to_audio_attn.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.7.video_to_audio_attn.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.7.video_to_audio_attn.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.7.video_to_audio_attn.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.7.norm3", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.7.ff", "class": "FeedForward", "module": "diffusers.models.attention" }, { "name": "transformer_blocks.7.ff.net", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.7.ff.net.0", "class": "GELU", "module": "diffusers.models.activations" }, { "name": "transformer_blocks.7.ff.net.0.proj", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 16384, "bias": true, "skip": false }, { "name": "transformer_blocks.7.ff.net.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.7.ff.net.2", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 16384, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.7.audio_norm3", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.7.audio_ff", "class": "FeedForward", "module": "diffusers.models.attention" }, { "name": "transformer_blocks.7.audio_ff.net", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.7.audio_ff.net.0", "class": "GELU", "module": "diffusers.models.activations" }, { "name": "transformer_blocks.7.audio_ff.net.0.proj", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 8192, "bias": true, "skip": false }, { "name": "transformer_blocks.7.audio_ff.net.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.7.audio_ff.net.2", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 8192, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.8", "class": "LTX2VideoTransformerBlock", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.8.norm1", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.8.attn1", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.8.attn1.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.8.attn1.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.8.attn1.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.8.attn1.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.8.attn1.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.8.attn1.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.8.attn1.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.8.attn1.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.8.attn1.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.8.audio_norm1", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.8.audio_attn1", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.8.audio_attn1.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.8.audio_attn1.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.8.audio_attn1.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.8.audio_attn1.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.8.audio_attn1.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.8.audio_attn1.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.8.audio_attn1.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.8.audio_attn1.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.8.audio_attn1.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.8.norm2", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.8.attn2", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.8.attn2.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.8.attn2.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.8.attn2.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.8.attn2.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.8.attn2.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.8.attn2.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.8.attn2.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.8.attn2.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.8.attn2.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.8.audio_norm2", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.8.audio_attn2", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.8.audio_attn2.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.8.audio_attn2.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.8.audio_attn2.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.8.audio_attn2.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.8.audio_attn2.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.8.audio_attn2.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.8.audio_attn2.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.8.audio_attn2.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.8.audio_attn2.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.8.audio_to_video_norm", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.8.audio_to_video_attn", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.8.audio_to_video_attn.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.8.audio_to_video_attn.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.8.audio_to_video_attn.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.8.audio_to_video_attn.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.8.audio_to_video_attn.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.8.audio_to_video_attn.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.8.audio_to_video_attn.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.8.audio_to_video_attn.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.8.audio_to_video_attn.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.8.video_to_audio_norm", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.8.video_to_audio_attn", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.8.video_to_audio_attn.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.8.video_to_audio_attn.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.8.video_to_audio_attn.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.8.video_to_audio_attn.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.8.video_to_audio_attn.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.8.video_to_audio_attn.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.8.video_to_audio_attn.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.8.video_to_audio_attn.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.8.video_to_audio_attn.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.8.norm3", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.8.ff", "class": "FeedForward", "module": "diffusers.models.attention" }, { "name": "transformer_blocks.8.ff.net", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.8.ff.net.0", "class": "GELU", "module": "diffusers.models.activations" }, { "name": "transformer_blocks.8.ff.net.0.proj", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 16384, "bias": true, "skip": false }, { "name": "transformer_blocks.8.ff.net.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.8.ff.net.2", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 16384, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.8.audio_norm3", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.8.audio_ff", "class": "FeedForward", "module": "diffusers.models.attention" }, { "name": "transformer_blocks.8.audio_ff.net", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.8.audio_ff.net.0", "class": "GELU", "module": "diffusers.models.activations" }, { "name": "transformer_blocks.8.audio_ff.net.0.proj", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 8192, "bias": true, "skip": false }, { "name": "transformer_blocks.8.audio_ff.net.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.8.audio_ff.net.2", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 8192, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.9", "class": "LTX2VideoTransformerBlock", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.9.norm1", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.9.attn1", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.9.attn1.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.9.attn1.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.9.attn1.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.9.attn1.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.9.attn1.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.9.attn1.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.9.attn1.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.9.attn1.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.9.attn1.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.9.audio_norm1", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.9.audio_attn1", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.9.audio_attn1.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.9.audio_attn1.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.9.audio_attn1.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.9.audio_attn1.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.9.audio_attn1.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.9.audio_attn1.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.9.audio_attn1.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.9.audio_attn1.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.9.audio_attn1.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.9.norm2", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.9.attn2", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.9.attn2.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.9.attn2.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.9.attn2.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.9.attn2.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.9.attn2.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.9.attn2.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.9.attn2.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.9.attn2.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.9.attn2.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.9.audio_norm2", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.9.audio_attn2", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.9.audio_attn2.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.9.audio_attn2.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.9.audio_attn2.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.9.audio_attn2.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.9.audio_attn2.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.9.audio_attn2.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.9.audio_attn2.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.9.audio_attn2.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.9.audio_attn2.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.9.audio_to_video_norm", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.9.audio_to_video_attn", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.9.audio_to_video_attn.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.9.audio_to_video_attn.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.9.audio_to_video_attn.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.9.audio_to_video_attn.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.9.audio_to_video_attn.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.9.audio_to_video_attn.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.9.audio_to_video_attn.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.9.audio_to_video_attn.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.9.audio_to_video_attn.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.9.video_to_audio_norm", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.9.video_to_audio_attn", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.9.video_to_audio_attn.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.9.video_to_audio_attn.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.9.video_to_audio_attn.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.9.video_to_audio_attn.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.9.video_to_audio_attn.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.9.video_to_audio_attn.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.9.video_to_audio_attn.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.9.video_to_audio_attn.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.9.video_to_audio_attn.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.9.norm3", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.9.ff", "class": "FeedForward", "module": "diffusers.models.attention" }, { "name": "transformer_blocks.9.ff.net", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.9.ff.net.0", "class": "GELU", "module": "diffusers.models.activations" }, { "name": "transformer_blocks.9.ff.net.0.proj", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 16384, "bias": true, "skip": false }, { "name": "transformer_blocks.9.ff.net.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.9.ff.net.2", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 16384, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.9.audio_norm3", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.9.audio_ff", "class": "FeedForward", "module": "diffusers.models.attention" }, { "name": "transformer_blocks.9.audio_ff.net", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.9.audio_ff.net.0", "class": "GELU", "module": "diffusers.models.activations" }, { "name": "transformer_blocks.9.audio_ff.net.0.proj", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 8192, "bias": true, "skip": false }, { "name": "transformer_blocks.9.audio_ff.net.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.9.audio_ff.net.2", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 8192, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.10", "class": "LTX2VideoTransformerBlock", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.10.norm1", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.10.attn1", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.10.attn1.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.10.attn1.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.10.attn1.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.10.attn1.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.10.attn1.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.10.attn1.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.10.attn1.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.10.attn1.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.10.attn1.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.10.audio_norm1", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.10.audio_attn1", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.10.audio_attn1.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.10.audio_attn1.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.10.audio_attn1.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.10.audio_attn1.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.10.audio_attn1.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.10.audio_attn1.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.10.audio_attn1.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.10.audio_attn1.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.10.audio_attn1.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.10.norm2", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.10.attn2", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.10.attn2.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.10.attn2.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.10.attn2.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.10.attn2.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.10.attn2.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.10.attn2.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.10.attn2.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.10.attn2.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.10.attn2.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.10.audio_norm2", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.10.audio_attn2", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.10.audio_attn2.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.10.audio_attn2.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.10.audio_attn2.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.10.audio_attn2.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.10.audio_attn2.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.10.audio_attn2.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.10.audio_attn2.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.10.audio_attn2.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.10.audio_attn2.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.10.audio_to_video_norm", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.10.audio_to_video_attn", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.10.audio_to_video_attn.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.10.audio_to_video_attn.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.10.audio_to_video_attn.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.10.audio_to_video_attn.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.10.audio_to_video_attn.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.10.audio_to_video_attn.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.10.audio_to_video_attn.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.10.audio_to_video_attn.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.10.audio_to_video_attn.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.10.video_to_audio_norm", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.10.video_to_audio_attn", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.10.video_to_audio_attn.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.10.video_to_audio_attn.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.10.video_to_audio_attn.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.10.video_to_audio_attn.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.10.video_to_audio_attn.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.10.video_to_audio_attn.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.10.video_to_audio_attn.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.10.video_to_audio_attn.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.10.video_to_audio_attn.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.10.norm3", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.10.ff", "class": "FeedForward", "module": "diffusers.models.attention" }, { "name": "transformer_blocks.10.ff.net", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.10.ff.net.0", "class": "GELU", "module": "diffusers.models.activations" }, { "name": "transformer_blocks.10.ff.net.0.proj", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 16384, "bias": true, "skip": false }, { "name": "transformer_blocks.10.ff.net.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.10.ff.net.2", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 16384, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.10.audio_norm3", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.10.audio_ff", "class": "FeedForward", "module": "diffusers.models.attention" }, { "name": "transformer_blocks.10.audio_ff.net", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.10.audio_ff.net.0", "class": "GELU", "module": "diffusers.models.activations" }, { "name": "transformer_blocks.10.audio_ff.net.0.proj", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 8192, "bias": true, "skip": false }, { "name": "transformer_blocks.10.audio_ff.net.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.10.audio_ff.net.2", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 8192, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.11", "class": "LTX2VideoTransformerBlock", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.11.norm1", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.11.attn1", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.11.attn1.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.11.attn1.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.11.attn1.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.11.attn1.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.11.attn1.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.11.attn1.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.11.attn1.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.11.attn1.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.11.attn1.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.11.audio_norm1", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.11.audio_attn1", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.11.audio_attn1.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.11.audio_attn1.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.11.audio_attn1.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.11.audio_attn1.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.11.audio_attn1.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.11.audio_attn1.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.11.audio_attn1.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.11.audio_attn1.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.11.audio_attn1.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.11.norm2", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.11.attn2", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.11.attn2.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.11.attn2.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.11.attn2.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.11.attn2.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.11.attn2.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.11.attn2.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.11.attn2.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.11.attn2.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.11.attn2.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.11.audio_norm2", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.11.audio_attn2", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.11.audio_attn2.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.11.audio_attn2.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.11.audio_attn2.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.11.audio_attn2.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.11.audio_attn2.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.11.audio_attn2.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.11.audio_attn2.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.11.audio_attn2.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.11.audio_attn2.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.11.audio_to_video_norm", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.11.audio_to_video_attn", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.11.audio_to_video_attn.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.11.audio_to_video_attn.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.11.audio_to_video_attn.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.11.audio_to_video_attn.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.11.audio_to_video_attn.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.11.audio_to_video_attn.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.11.audio_to_video_attn.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.11.audio_to_video_attn.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.11.audio_to_video_attn.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.11.video_to_audio_norm", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.11.video_to_audio_attn", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.11.video_to_audio_attn.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.11.video_to_audio_attn.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.11.video_to_audio_attn.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.11.video_to_audio_attn.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.11.video_to_audio_attn.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.11.video_to_audio_attn.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.11.video_to_audio_attn.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.11.video_to_audio_attn.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.11.video_to_audio_attn.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.11.norm3", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.11.ff", "class": "FeedForward", "module": "diffusers.models.attention" }, { "name": "transformer_blocks.11.ff.net", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.11.ff.net.0", "class": "GELU", "module": "diffusers.models.activations" }, { "name": "transformer_blocks.11.ff.net.0.proj", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 16384, "bias": true, "skip": false }, { "name": "transformer_blocks.11.ff.net.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.11.ff.net.2", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 16384, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.11.audio_norm3", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.11.audio_ff", "class": "FeedForward", "module": "diffusers.models.attention" }, { "name": "transformer_blocks.11.audio_ff.net", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.11.audio_ff.net.0", "class": "GELU", "module": "diffusers.models.activations" }, { "name": "transformer_blocks.11.audio_ff.net.0.proj", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 8192, "bias": true, "skip": false }, { "name": "transformer_blocks.11.audio_ff.net.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.11.audio_ff.net.2", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 8192, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.12", "class": "LTX2VideoTransformerBlock", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.12.norm1", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.12.attn1", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.12.attn1.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.12.attn1.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.12.attn1.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.12.attn1.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.12.attn1.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.12.attn1.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.12.attn1.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.12.attn1.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.12.attn1.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.12.audio_norm1", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.12.audio_attn1", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.12.audio_attn1.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.12.audio_attn1.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.12.audio_attn1.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.12.audio_attn1.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.12.audio_attn1.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.12.audio_attn1.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.12.audio_attn1.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.12.audio_attn1.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.12.audio_attn1.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.12.norm2", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.12.attn2", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.12.attn2.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.12.attn2.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.12.attn2.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.12.attn2.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.12.attn2.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.12.attn2.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.12.attn2.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.12.attn2.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.12.attn2.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.12.audio_norm2", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.12.audio_attn2", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.12.audio_attn2.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.12.audio_attn2.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.12.audio_attn2.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.12.audio_attn2.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.12.audio_attn2.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.12.audio_attn2.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.12.audio_attn2.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.12.audio_attn2.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.12.audio_attn2.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.12.audio_to_video_norm", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.12.audio_to_video_attn", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.12.audio_to_video_attn.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.12.audio_to_video_attn.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.12.audio_to_video_attn.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.12.audio_to_video_attn.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.12.audio_to_video_attn.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.12.audio_to_video_attn.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.12.audio_to_video_attn.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.12.audio_to_video_attn.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.12.audio_to_video_attn.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.12.video_to_audio_norm", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.12.video_to_audio_attn", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.12.video_to_audio_attn.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.12.video_to_audio_attn.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.12.video_to_audio_attn.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.12.video_to_audio_attn.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.12.video_to_audio_attn.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.12.video_to_audio_attn.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.12.video_to_audio_attn.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.12.video_to_audio_attn.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.12.video_to_audio_attn.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.12.norm3", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.12.ff", "class": "FeedForward", "module": "diffusers.models.attention" }, { "name": "transformer_blocks.12.ff.net", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.12.ff.net.0", "class": "GELU", "module": "diffusers.models.activations" }, { "name": "transformer_blocks.12.ff.net.0.proj", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 16384, "bias": true, "skip": false }, { "name": "transformer_blocks.12.ff.net.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.12.ff.net.2", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 16384, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.12.audio_norm3", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.12.audio_ff", "class": "FeedForward", "module": "diffusers.models.attention" }, { "name": "transformer_blocks.12.audio_ff.net", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.12.audio_ff.net.0", "class": "GELU", "module": "diffusers.models.activations" }, { "name": "transformer_blocks.12.audio_ff.net.0.proj", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 8192, "bias": true, "skip": false }, { "name": "transformer_blocks.12.audio_ff.net.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.12.audio_ff.net.2", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 8192, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.13", "class": "LTX2VideoTransformerBlock", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.13.norm1", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.13.attn1", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.13.attn1.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.13.attn1.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.13.attn1.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.13.attn1.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.13.attn1.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.13.attn1.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.13.attn1.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.13.attn1.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.13.attn1.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.13.audio_norm1", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.13.audio_attn1", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.13.audio_attn1.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.13.audio_attn1.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.13.audio_attn1.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.13.audio_attn1.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.13.audio_attn1.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.13.audio_attn1.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.13.audio_attn1.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.13.audio_attn1.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.13.audio_attn1.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.13.norm2", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.13.attn2", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.13.attn2.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.13.attn2.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.13.attn2.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.13.attn2.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.13.attn2.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.13.attn2.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.13.attn2.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.13.attn2.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.13.attn2.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.13.audio_norm2", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.13.audio_attn2", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.13.audio_attn2.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.13.audio_attn2.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.13.audio_attn2.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.13.audio_attn2.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.13.audio_attn2.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.13.audio_attn2.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.13.audio_attn2.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.13.audio_attn2.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.13.audio_attn2.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.13.audio_to_video_norm", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.13.audio_to_video_attn", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.13.audio_to_video_attn.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.13.audio_to_video_attn.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.13.audio_to_video_attn.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.13.audio_to_video_attn.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.13.audio_to_video_attn.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.13.audio_to_video_attn.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.13.audio_to_video_attn.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.13.audio_to_video_attn.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.13.audio_to_video_attn.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.13.video_to_audio_norm", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.13.video_to_audio_attn", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.13.video_to_audio_attn.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.13.video_to_audio_attn.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.13.video_to_audio_attn.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.13.video_to_audio_attn.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.13.video_to_audio_attn.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.13.video_to_audio_attn.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.13.video_to_audio_attn.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.13.video_to_audio_attn.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.13.video_to_audio_attn.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.13.norm3", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.13.ff", "class": "FeedForward", "module": "diffusers.models.attention" }, { "name": "transformer_blocks.13.ff.net", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.13.ff.net.0", "class": "GELU", "module": "diffusers.models.activations" }, { "name": "transformer_blocks.13.ff.net.0.proj", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 16384, "bias": true, "skip": false }, { "name": "transformer_blocks.13.ff.net.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.13.ff.net.2", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 16384, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.13.audio_norm3", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.13.audio_ff", "class": "FeedForward", "module": "diffusers.models.attention" }, { "name": "transformer_blocks.13.audio_ff.net", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.13.audio_ff.net.0", "class": "GELU", "module": "diffusers.models.activations" }, { "name": "transformer_blocks.13.audio_ff.net.0.proj", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 8192, "bias": true, "skip": false }, { "name": "transformer_blocks.13.audio_ff.net.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.13.audio_ff.net.2", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 8192, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.14", "class": "LTX2VideoTransformerBlock", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.14.norm1", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.14.attn1", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.14.attn1.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.14.attn1.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.14.attn1.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.14.attn1.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.14.attn1.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.14.attn1.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.14.attn1.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.14.attn1.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.14.attn1.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.14.audio_norm1", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.14.audio_attn1", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.14.audio_attn1.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.14.audio_attn1.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.14.audio_attn1.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.14.audio_attn1.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.14.audio_attn1.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.14.audio_attn1.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.14.audio_attn1.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.14.audio_attn1.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.14.audio_attn1.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.14.norm2", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.14.attn2", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.14.attn2.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.14.attn2.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.14.attn2.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.14.attn2.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.14.attn2.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.14.attn2.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.14.attn2.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.14.attn2.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.14.attn2.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.14.audio_norm2", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.14.audio_attn2", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.14.audio_attn2.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.14.audio_attn2.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.14.audio_attn2.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.14.audio_attn2.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.14.audio_attn2.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.14.audio_attn2.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.14.audio_attn2.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.14.audio_attn2.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.14.audio_attn2.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.14.audio_to_video_norm", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.14.audio_to_video_attn", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.14.audio_to_video_attn.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.14.audio_to_video_attn.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.14.audio_to_video_attn.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.14.audio_to_video_attn.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.14.audio_to_video_attn.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.14.audio_to_video_attn.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.14.audio_to_video_attn.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.14.audio_to_video_attn.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.14.audio_to_video_attn.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.14.video_to_audio_norm", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.14.video_to_audio_attn", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.14.video_to_audio_attn.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.14.video_to_audio_attn.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.14.video_to_audio_attn.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.14.video_to_audio_attn.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.14.video_to_audio_attn.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.14.video_to_audio_attn.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.14.video_to_audio_attn.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.14.video_to_audio_attn.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.14.video_to_audio_attn.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.14.norm3", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.14.ff", "class": "FeedForward", "module": "diffusers.models.attention" }, { "name": "transformer_blocks.14.ff.net", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.14.ff.net.0", "class": "GELU", "module": "diffusers.models.activations" }, { "name": "transformer_blocks.14.ff.net.0.proj", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 16384, "bias": true, "skip": false }, { "name": "transformer_blocks.14.ff.net.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.14.ff.net.2", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 16384, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.14.audio_norm3", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.14.audio_ff", "class": "FeedForward", "module": "diffusers.models.attention" }, { "name": "transformer_blocks.14.audio_ff.net", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.14.audio_ff.net.0", "class": "GELU", "module": "diffusers.models.activations" }, { "name": "transformer_blocks.14.audio_ff.net.0.proj", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 8192, "bias": true, "skip": false }, { "name": "transformer_blocks.14.audio_ff.net.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.14.audio_ff.net.2", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 8192, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.15", "class": "LTX2VideoTransformerBlock", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.15.norm1", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.15.attn1", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.15.attn1.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.15.attn1.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.15.attn1.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.15.attn1.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.15.attn1.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.15.attn1.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.15.attn1.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.15.attn1.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.15.attn1.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.15.audio_norm1", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.15.audio_attn1", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.15.audio_attn1.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.15.audio_attn1.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.15.audio_attn1.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.15.audio_attn1.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.15.audio_attn1.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.15.audio_attn1.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.15.audio_attn1.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.15.audio_attn1.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.15.audio_attn1.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.15.norm2", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.15.attn2", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.15.attn2.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.15.attn2.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.15.attn2.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.15.attn2.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.15.attn2.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.15.attn2.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.15.attn2.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.15.attn2.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.15.attn2.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.15.audio_norm2", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.15.audio_attn2", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.15.audio_attn2.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.15.audio_attn2.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.15.audio_attn2.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.15.audio_attn2.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.15.audio_attn2.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.15.audio_attn2.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.15.audio_attn2.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.15.audio_attn2.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.15.audio_attn2.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.15.audio_to_video_norm", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.15.audio_to_video_attn", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.15.audio_to_video_attn.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.15.audio_to_video_attn.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.15.audio_to_video_attn.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.15.audio_to_video_attn.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.15.audio_to_video_attn.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.15.audio_to_video_attn.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.15.audio_to_video_attn.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.15.audio_to_video_attn.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.15.audio_to_video_attn.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.15.video_to_audio_norm", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.15.video_to_audio_attn", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.15.video_to_audio_attn.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.15.video_to_audio_attn.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.15.video_to_audio_attn.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.15.video_to_audio_attn.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.15.video_to_audio_attn.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.15.video_to_audio_attn.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.15.video_to_audio_attn.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.15.video_to_audio_attn.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.15.video_to_audio_attn.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.15.norm3", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.15.ff", "class": "FeedForward", "module": "diffusers.models.attention" }, { "name": "transformer_blocks.15.ff.net", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.15.ff.net.0", "class": "GELU", "module": "diffusers.models.activations" }, { "name": "transformer_blocks.15.ff.net.0.proj", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 16384, "bias": true, "skip": false }, { "name": "transformer_blocks.15.ff.net.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.15.ff.net.2", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 16384, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.15.audio_norm3", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.15.audio_ff", "class": "FeedForward", "module": "diffusers.models.attention" }, { "name": "transformer_blocks.15.audio_ff.net", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.15.audio_ff.net.0", "class": "GELU", "module": "diffusers.models.activations" }, { "name": "transformer_blocks.15.audio_ff.net.0.proj", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 8192, "bias": true, "skip": false }, { "name": "transformer_blocks.15.audio_ff.net.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.15.audio_ff.net.2", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 8192, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.16", "class": "LTX2VideoTransformerBlock", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.16.norm1", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.16.attn1", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.16.attn1.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.16.attn1.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.16.attn1.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.16.attn1.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.16.attn1.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.16.attn1.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.16.attn1.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.16.attn1.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.16.attn1.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.16.audio_norm1", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.16.audio_attn1", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.16.audio_attn1.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.16.audio_attn1.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.16.audio_attn1.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.16.audio_attn1.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.16.audio_attn1.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.16.audio_attn1.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.16.audio_attn1.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.16.audio_attn1.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.16.audio_attn1.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.16.norm2", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.16.attn2", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.16.attn2.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.16.attn2.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.16.attn2.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.16.attn2.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.16.attn2.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.16.attn2.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.16.attn2.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.16.attn2.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.16.attn2.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.16.audio_norm2", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.16.audio_attn2", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.16.audio_attn2.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.16.audio_attn2.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.16.audio_attn2.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.16.audio_attn2.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.16.audio_attn2.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.16.audio_attn2.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.16.audio_attn2.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.16.audio_attn2.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.16.audio_attn2.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.16.audio_to_video_norm", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.16.audio_to_video_attn", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.16.audio_to_video_attn.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.16.audio_to_video_attn.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.16.audio_to_video_attn.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.16.audio_to_video_attn.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.16.audio_to_video_attn.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.16.audio_to_video_attn.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.16.audio_to_video_attn.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.16.audio_to_video_attn.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.16.audio_to_video_attn.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.16.video_to_audio_norm", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.16.video_to_audio_attn", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.16.video_to_audio_attn.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.16.video_to_audio_attn.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.16.video_to_audio_attn.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.16.video_to_audio_attn.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.16.video_to_audio_attn.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.16.video_to_audio_attn.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.16.video_to_audio_attn.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.16.video_to_audio_attn.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.16.video_to_audio_attn.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.16.norm3", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.16.ff", "class": "FeedForward", "module": "diffusers.models.attention" }, { "name": "transformer_blocks.16.ff.net", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.16.ff.net.0", "class": "GELU", "module": "diffusers.models.activations" }, { "name": "transformer_blocks.16.ff.net.0.proj", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 16384, "bias": true, "skip": false }, { "name": "transformer_blocks.16.ff.net.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.16.ff.net.2", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 16384, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.16.audio_norm3", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.16.audio_ff", "class": "FeedForward", "module": "diffusers.models.attention" }, { "name": "transformer_blocks.16.audio_ff.net", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.16.audio_ff.net.0", "class": "GELU", "module": "diffusers.models.activations" }, { "name": "transformer_blocks.16.audio_ff.net.0.proj", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 8192, "bias": true, "skip": false }, { "name": "transformer_blocks.16.audio_ff.net.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.16.audio_ff.net.2", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 8192, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.17", "class": "LTX2VideoTransformerBlock", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.17.norm1", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.17.attn1", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.17.attn1.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.17.attn1.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.17.attn1.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.17.attn1.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.17.attn1.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.17.attn1.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.17.attn1.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.17.attn1.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.17.attn1.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.17.audio_norm1", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.17.audio_attn1", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.17.audio_attn1.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.17.audio_attn1.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.17.audio_attn1.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.17.audio_attn1.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.17.audio_attn1.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.17.audio_attn1.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.17.audio_attn1.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.17.audio_attn1.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.17.audio_attn1.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.17.norm2", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.17.attn2", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.17.attn2.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.17.attn2.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.17.attn2.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.17.attn2.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.17.attn2.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.17.attn2.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.17.attn2.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.17.attn2.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.17.attn2.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.17.audio_norm2", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.17.audio_attn2", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.17.audio_attn2.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.17.audio_attn2.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.17.audio_attn2.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.17.audio_attn2.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.17.audio_attn2.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.17.audio_attn2.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.17.audio_attn2.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.17.audio_attn2.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.17.audio_attn2.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.17.audio_to_video_norm", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.17.audio_to_video_attn", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.17.audio_to_video_attn.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.17.audio_to_video_attn.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.17.audio_to_video_attn.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.17.audio_to_video_attn.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.17.audio_to_video_attn.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.17.audio_to_video_attn.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.17.audio_to_video_attn.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.17.audio_to_video_attn.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.17.audio_to_video_attn.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.17.video_to_audio_norm", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.17.video_to_audio_attn", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.17.video_to_audio_attn.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.17.video_to_audio_attn.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.17.video_to_audio_attn.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.17.video_to_audio_attn.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.17.video_to_audio_attn.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.17.video_to_audio_attn.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.17.video_to_audio_attn.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.17.video_to_audio_attn.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.17.video_to_audio_attn.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.17.norm3", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.17.ff", "class": "FeedForward", "module": "diffusers.models.attention" }, { "name": "transformer_blocks.17.ff.net", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.17.ff.net.0", "class": "GELU", "module": "diffusers.models.activations" }, { "name": "transformer_blocks.17.ff.net.0.proj", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 16384, "bias": true, "skip": false }, { "name": "transformer_blocks.17.ff.net.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.17.ff.net.2", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 16384, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.17.audio_norm3", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.17.audio_ff", "class": "FeedForward", "module": "diffusers.models.attention" }, { "name": "transformer_blocks.17.audio_ff.net", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.17.audio_ff.net.0", "class": "GELU", "module": "diffusers.models.activations" }, { "name": "transformer_blocks.17.audio_ff.net.0.proj", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 8192, "bias": true, "skip": false }, { "name": "transformer_blocks.17.audio_ff.net.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.17.audio_ff.net.2", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 8192, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.18", "class": "LTX2VideoTransformerBlock", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.18.norm1", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.18.attn1", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.18.attn1.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.18.attn1.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.18.attn1.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.18.attn1.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.18.attn1.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.18.attn1.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.18.attn1.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.18.attn1.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.18.attn1.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.18.audio_norm1", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.18.audio_attn1", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.18.audio_attn1.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.18.audio_attn1.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.18.audio_attn1.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.18.audio_attn1.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.18.audio_attn1.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.18.audio_attn1.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.18.audio_attn1.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.18.audio_attn1.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.18.audio_attn1.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.18.norm2", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.18.attn2", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.18.attn2.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.18.attn2.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.18.attn2.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.18.attn2.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.18.attn2.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.18.attn2.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.18.attn2.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.18.attn2.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.18.attn2.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.18.audio_norm2", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.18.audio_attn2", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.18.audio_attn2.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.18.audio_attn2.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.18.audio_attn2.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.18.audio_attn2.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.18.audio_attn2.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.18.audio_attn2.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.18.audio_attn2.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.18.audio_attn2.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.18.audio_attn2.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.18.audio_to_video_norm", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.18.audio_to_video_attn", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.18.audio_to_video_attn.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.18.audio_to_video_attn.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.18.audio_to_video_attn.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.18.audio_to_video_attn.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.18.audio_to_video_attn.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.18.audio_to_video_attn.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.18.audio_to_video_attn.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.18.audio_to_video_attn.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.18.audio_to_video_attn.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.18.video_to_audio_norm", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.18.video_to_audio_attn", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.18.video_to_audio_attn.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.18.video_to_audio_attn.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.18.video_to_audio_attn.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.18.video_to_audio_attn.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.18.video_to_audio_attn.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.18.video_to_audio_attn.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.18.video_to_audio_attn.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.18.video_to_audio_attn.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.18.video_to_audio_attn.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.18.norm3", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.18.ff", "class": "FeedForward", "module": "diffusers.models.attention" }, { "name": "transformer_blocks.18.ff.net", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.18.ff.net.0", "class": "GELU", "module": "diffusers.models.activations" }, { "name": "transformer_blocks.18.ff.net.0.proj", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 16384, "bias": true, "skip": false }, { "name": "transformer_blocks.18.ff.net.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.18.ff.net.2", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 16384, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.18.audio_norm3", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.18.audio_ff", "class": "FeedForward", "module": "diffusers.models.attention" }, { "name": "transformer_blocks.18.audio_ff.net", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.18.audio_ff.net.0", "class": "GELU", "module": "diffusers.models.activations" }, { "name": "transformer_blocks.18.audio_ff.net.0.proj", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 8192, "bias": true, "skip": false }, { "name": "transformer_blocks.18.audio_ff.net.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.18.audio_ff.net.2", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 8192, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.19", "class": "LTX2VideoTransformerBlock", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.19.norm1", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.19.attn1", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.19.attn1.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.19.attn1.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.19.attn1.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.19.attn1.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.19.attn1.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.19.attn1.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.19.attn1.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.19.attn1.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.19.attn1.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.19.audio_norm1", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.19.audio_attn1", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.19.audio_attn1.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.19.audio_attn1.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.19.audio_attn1.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.19.audio_attn1.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.19.audio_attn1.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.19.audio_attn1.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.19.audio_attn1.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.19.audio_attn1.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.19.audio_attn1.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.19.norm2", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.19.attn2", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.19.attn2.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.19.attn2.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.19.attn2.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.19.attn2.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.19.attn2.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.19.attn2.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.19.attn2.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.19.attn2.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.19.attn2.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.19.audio_norm2", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.19.audio_attn2", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.19.audio_attn2.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.19.audio_attn2.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.19.audio_attn2.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.19.audio_attn2.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.19.audio_attn2.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.19.audio_attn2.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.19.audio_attn2.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.19.audio_attn2.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.19.audio_attn2.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.19.audio_to_video_norm", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.19.audio_to_video_attn", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.19.audio_to_video_attn.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.19.audio_to_video_attn.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.19.audio_to_video_attn.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.19.audio_to_video_attn.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.19.audio_to_video_attn.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.19.audio_to_video_attn.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.19.audio_to_video_attn.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.19.audio_to_video_attn.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.19.audio_to_video_attn.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.19.video_to_audio_norm", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.19.video_to_audio_attn", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.19.video_to_audio_attn.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.19.video_to_audio_attn.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.19.video_to_audio_attn.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.19.video_to_audio_attn.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.19.video_to_audio_attn.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.19.video_to_audio_attn.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.19.video_to_audio_attn.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.19.video_to_audio_attn.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.19.video_to_audio_attn.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.19.norm3", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.19.ff", "class": "FeedForward", "module": "diffusers.models.attention" }, { "name": "transformer_blocks.19.ff.net", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.19.ff.net.0", "class": "GELU", "module": "diffusers.models.activations" }, { "name": "transformer_blocks.19.ff.net.0.proj", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 16384, "bias": true, "skip": false }, { "name": "transformer_blocks.19.ff.net.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.19.ff.net.2", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 16384, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.19.audio_norm3", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.19.audio_ff", "class": "FeedForward", "module": "diffusers.models.attention" }, { "name": "transformer_blocks.19.audio_ff.net", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.19.audio_ff.net.0", "class": "GELU", "module": "diffusers.models.activations" }, { "name": "transformer_blocks.19.audio_ff.net.0.proj", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 8192, "bias": true, "skip": false }, { "name": "transformer_blocks.19.audio_ff.net.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.19.audio_ff.net.2", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 8192, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.20", "class": "LTX2VideoTransformerBlock", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.20.norm1", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.20.attn1", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.20.attn1.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.20.attn1.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.20.attn1.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.20.attn1.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.20.attn1.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.20.attn1.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.20.attn1.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.20.attn1.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.20.attn1.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.20.audio_norm1", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.20.audio_attn1", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.20.audio_attn1.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.20.audio_attn1.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.20.audio_attn1.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.20.audio_attn1.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.20.audio_attn1.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.20.audio_attn1.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.20.audio_attn1.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.20.audio_attn1.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.20.audio_attn1.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.20.norm2", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.20.attn2", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.20.attn2.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.20.attn2.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.20.attn2.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.20.attn2.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.20.attn2.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.20.attn2.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.20.attn2.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.20.attn2.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.20.attn2.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.20.audio_norm2", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.20.audio_attn2", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.20.audio_attn2.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.20.audio_attn2.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.20.audio_attn2.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.20.audio_attn2.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.20.audio_attn2.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.20.audio_attn2.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.20.audio_attn2.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.20.audio_attn2.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.20.audio_attn2.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.20.audio_to_video_norm", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.20.audio_to_video_attn", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.20.audio_to_video_attn.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.20.audio_to_video_attn.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.20.audio_to_video_attn.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.20.audio_to_video_attn.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.20.audio_to_video_attn.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.20.audio_to_video_attn.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.20.audio_to_video_attn.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.20.audio_to_video_attn.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.20.audio_to_video_attn.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.20.video_to_audio_norm", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.20.video_to_audio_attn", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.20.video_to_audio_attn.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.20.video_to_audio_attn.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.20.video_to_audio_attn.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.20.video_to_audio_attn.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.20.video_to_audio_attn.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.20.video_to_audio_attn.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.20.video_to_audio_attn.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.20.video_to_audio_attn.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.20.video_to_audio_attn.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.20.norm3", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.20.ff", "class": "FeedForward", "module": "diffusers.models.attention" }, { "name": "transformer_blocks.20.ff.net", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.20.ff.net.0", "class": "GELU", "module": "diffusers.models.activations" }, { "name": "transformer_blocks.20.ff.net.0.proj", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 16384, "bias": true, "skip": false }, { "name": "transformer_blocks.20.ff.net.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.20.ff.net.2", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 16384, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.20.audio_norm3", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.20.audio_ff", "class": "FeedForward", "module": "diffusers.models.attention" }, { "name": "transformer_blocks.20.audio_ff.net", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.20.audio_ff.net.0", "class": "GELU", "module": "diffusers.models.activations" }, { "name": "transformer_blocks.20.audio_ff.net.0.proj", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 8192, "bias": true, "skip": false }, { "name": "transformer_blocks.20.audio_ff.net.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.20.audio_ff.net.2", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 8192, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.21", "class": "LTX2VideoTransformerBlock", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.21.norm1", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.21.attn1", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.21.attn1.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.21.attn1.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.21.attn1.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.21.attn1.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.21.attn1.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.21.attn1.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.21.attn1.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.21.attn1.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.21.attn1.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.21.audio_norm1", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.21.audio_attn1", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.21.audio_attn1.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.21.audio_attn1.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.21.audio_attn1.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.21.audio_attn1.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.21.audio_attn1.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.21.audio_attn1.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.21.audio_attn1.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.21.audio_attn1.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.21.audio_attn1.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.21.norm2", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.21.attn2", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.21.attn2.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.21.attn2.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.21.attn2.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.21.attn2.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.21.attn2.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.21.attn2.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.21.attn2.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.21.attn2.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.21.attn2.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.21.audio_norm2", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.21.audio_attn2", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.21.audio_attn2.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.21.audio_attn2.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.21.audio_attn2.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.21.audio_attn2.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.21.audio_attn2.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.21.audio_attn2.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.21.audio_attn2.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.21.audio_attn2.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.21.audio_attn2.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.21.audio_to_video_norm", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.21.audio_to_video_attn", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.21.audio_to_video_attn.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.21.audio_to_video_attn.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.21.audio_to_video_attn.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.21.audio_to_video_attn.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.21.audio_to_video_attn.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.21.audio_to_video_attn.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.21.audio_to_video_attn.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.21.audio_to_video_attn.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.21.audio_to_video_attn.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.21.video_to_audio_norm", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.21.video_to_audio_attn", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.21.video_to_audio_attn.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.21.video_to_audio_attn.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.21.video_to_audio_attn.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.21.video_to_audio_attn.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.21.video_to_audio_attn.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.21.video_to_audio_attn.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.21.video_to_audio_attn.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.21.video_to_audio_attn.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.21.video_to_audio_attn.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.21.norm3", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.21.ff", "class": "FeedForward", "module": "diffusers.models.attention" }, { "name": "transformer_blocks.21.ff.net", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.21.ff.net.0", "class": "GELU", "module": "diffusers.models.activations" }, { "name": "transformer_blocks.21.ff.net.0.proj", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 16384, "bias": true, "skip": false }, { "name": "transformer_blocks.21.ff.net.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.21.ff.net.2", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 16384, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.21.audio_norm3", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.21.audio_ff", "class": "FeedForward", "module": "diffusers.models.attention" }, { "name": "transformer_blocks.21.audio_ff.net", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.21.audio_ff.net.0", "class": "GELU", "module": "diffusers.models.activations" }, { "name": "transformer_blocks.21.audio_ff.net.0.proj", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 8192, "bias": true, "skip": false }, { "name": "transformer_blocks.21.audio_ff.net.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.21.audio_ff.net.2", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 8192, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.22", "class": "LTX2VideoTransformerBlock", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.22.norm1", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.22.attn1", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.22.attn1.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.22.attn1.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.22.attn1.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.22.attn1.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.22.attn1.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.22.attn1.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.22.attn1.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.22.attn1.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.22.attn1.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.22.audio_norm1", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.22.audio_attn1", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.22.audio_attn1.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.22.audio_attn1.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.22.audio_attn1.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.22.audio_attn1.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.22.audio_attn1.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.22.audio_attn1.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.22.audio_attn1.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.22.audio_attn1.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.22.audio_attn1.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.22.norm2", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.22.attn2", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.22.attn2.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.22.attn2.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.22.attn2.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.22.attn2.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.22.attn2.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.22.attn2.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.22.attn2.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.22.attn2.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.22.attn2.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.22.audio_norm2", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.22.audio_attn2", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.22.audio_attn2.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.22.audio_attn2.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.22.audio_attn2.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.22.audio_attn2.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.22.audio_attn2.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.22.audio_attn2.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.22.audio_attn2.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.22.audio_attn2.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.22.audio_attn2.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.22.audio_to_video_norm", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.22.audio_to_video_attn", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.22.audio_to_video_attn.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.22.audio_to_video_attn.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.22.audio_to_video_attn.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.22.audio_to_video_attn.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.22.audio_to_video_attn.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.22.audio_to_video_attn.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.22.audio_to_video_attn.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.22.audio_to_video_attn.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.22.audio_to_video_attn.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.22.video_to_audio_norm", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.22.video_to_audio_attn", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.22.video_to_audio_attn.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.22.video_to_audio_attn.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.22.video_to_audio_attn.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.22.video_to_audio_attn.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.22.video_to_audio_attn.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.22.video_to_audio_attn.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.22.video_to_audio_attn.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.22.video_to_audio_attn.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.22.video_to_audio_attn.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.22.norm3", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.22.ff", "class": "FeedForward", "module": "diffusers.models.attention" }, { "name": "transformer_blocks.22.ff.net", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.22.ff.net.0", "class": "GELU", "module": "diffusers.models.activations" }, { "name": "transformer_blocks.22.ff.net.0.proj", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 16384, "bias": true, "skip": false }, { "name": "transformer_blocks.22.ff.net.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.22.ff.net.2", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 16384, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.22.audio_norm3", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.22.audio_ff", "class": "FeedForward", "module": "diffusers.models.attention" }, { "name": "transformer_blocks.22.audio_ff.net", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.22.audio_ff.net.0", "class": "GELU", "module": "diffusers.models.activations" }, { "name": "transformer_blocks.22.audio_ff.net.0.proj", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 8192, "bias": true, "skip": false }, { "name": "transformer_blocks.22.audio_ff.net.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.22.audio_ff.net.2", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 8192, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.23", "class": "LTX2VideoTransformerBlock", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.23.norm1", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.23.attn1", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.23.attn1.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.23.attn1.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.23.attn1.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.23.attn1.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.23.attn1.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.23.attn1.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.23.attn1.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.23.attn1.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.23.attn1.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.23.audio_norm1", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.23.audio_attn1", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.23.audio_attn1.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.23.audio_attn1.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.23.audio_attn1.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.23.audio_attn1.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.23.audio_attn1.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.23.audio_attn1.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.23.audio_attn1.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.23.audio_attn1.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.23.audio_attn1.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.23.norm2", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.23.attn2", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.23.attn2.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.23.attn2.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.23.attn2.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.23.attn2.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.23.attn2.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.23.attn2.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.23.attn2.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.23.attn2.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.23.attn2.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.23.audio_norm2", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.23.audio_attn2", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.23.audio_attn2.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.23.audio_attn2.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.23.audio_attn2.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.23.audio_attn2.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.23.audio_attn2.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.23.audio_attn2.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.23.audio_attn2.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.23.audio_attn2.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.23.audio_attn2.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.23.audio_to_video_norm", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.23.audio_to_video_attn", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.23.audio_to_video_attn.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.23.audio_to_video_attn.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.23.audio_to_video_attn.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.23.audio_to_video_attn.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.23.audio_to_video_attn.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.23.audio_to_video_attn.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.23.audio_to_video_attn.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.23.audio_to_video_attn.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.23.audio_to_video_attn.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.23.video_to_audio_norm", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.23.video_to_audio_attn", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.23.video_to_audio_attn.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.23.video_to_audio_attn.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.23.video_to_audio_attn.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.23.video_to_audio_attn.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.23.video_to_audio_attn.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.23.video_to_audio_attn.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.23.video_to_audio_attn.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.23.video_to_audio_attn.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.23.video_to_audio_attn.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.23.norm3", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.23.ff", "class": "FeedForward", "module": "diffusers.models.attention" }, { "name": "transformer_blocks.23.ff.net", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.23.ff.net.0", "class": "GELU", "module": "diffusers.models.activations" }, { "name": "transformer_blocks.23.ff.net.0.proj", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 16384, "bias": true, "skip": false }, { "name": "transformer_blocks.23.ff.net.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.23.ff.net.2", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 16384, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.23.audio_norm3", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.23.audio_ff", "class": "FeedForward", "module": "diffusers.models.attention" }, { "name": "transformer_blocks.23.audio_ff.net", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.23.audio_ff.net.0", "class": "GELU", "module": "diffusers.models.activations" }, { "name": "transformer_blocks.23.audio_ff.net.0.proj", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 8192, "bias": true, "skip": false }, { "name": "transformer_blocks.23.audio_ff.net.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.23.audio_ff.net.2", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 8192, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.24", "class": "LTX2VideoTransformerBlock", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.24.norm1", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.24.attn1", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.24.attn1.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.24.attn1.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.24.attn1.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.24.attn1.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.24.attn1.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.24.attn1.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.24.attn1.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.24.attn1.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.24.attn1.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.24.audio_norm1", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.24.audio_attn1", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.24.audio_attn1.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.24.audio_attn1.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.24.audio_attn1.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.24.audio_attn1.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.24.audio_attn1.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.24.audio_attn1.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.24.audio_attn1.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.24.audio_attn1.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.24.audio_attn1.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.24.norm2", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.24.attn2", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.24.attn2.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.24.attn2.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.24.attn2.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.24.attn2.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.24.attn2.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.24.attn2.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.24.attn2.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.24.attn2.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.24.attn2.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.24.audio_norm2", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.24.audio_attn2", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.24.audio_attn2.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.24.audio_attn2.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.24.audio_attn2.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.24.audio_attn2.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.24.audio_attn2.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.24.audio_attn2.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.24.audio_attn2.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.24.audio_attn2.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.24.audio_attn2.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.24.audio_to_video_norm", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.24.audio_to_video_attn", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.24.audio_to_video_attn.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.24.audio_to_video_attn.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.24.audio_to_video_attn.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.24.audio_to_video_attn.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.24.audio_to_video_attn.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.24.audio_to_video_attn.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.24.audio_to_video_attn.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.24.audio_to_video_attn.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.24.audio_to_video_attn.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.24.video_to_audio_norm", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.24.video_to_audio_attn", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.24.video_to_audio_attn.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.24.video_to_audio_attn.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.24.video_to_audio_attn.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.24.video_to_audio_attn.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.24.video_to_audio_attn.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.24.video_to_audio_attn.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.24.video_to_audio_attn.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.24.video_to_audio_attn.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.24.video_to_audio_attn.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.24.norm3", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.24.ff", "class": "FeedForward", "module": "diffusers.models.attention" }, { "name": "transformer_blocks.24.ff.net", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.24.ff.net.0", "class": "GELU", "module": "diffusers.models.activations" }, { "name": "transformer_blocks.24.ff.net.0.proj", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 16384, "bias": true, "skip": false }, { "name": "transformer_blocks.24.ff.net.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.24.ff.net.2", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 16384, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.24.audio_norm3", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.24.audio_ff", "class": "FeedForward", "module": "diffusers.models.attention" }, { "name": "transformer_blocks.24.audio_ff.net", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.24.audio_ff.net.0", "class": "GELU", "module": "diffusers.models.activations" }, { "name": "transformer_blocks.24.audio_ff.net.0.proj", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 8192, "bias": true, "skip": false }, { "name": "transformer_blocks.24.audio_ff.net.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.24.audio_ff.net.2", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 8192, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.25", "class": "LTX2VideoTransformerBlock", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.25.norm1", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.25.attn1", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.25.attn1.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.25.attn1.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.25.attn1.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.25.attn1.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.25.attn1.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.25.attn1.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.25.attn1.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.25.attn1.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.25.attn1.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.25.audio_norm1", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.25.audio_attn1", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.25.audio_attn1.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.25.audio_attn1.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.25.audio_attn1.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.25.audio_attn1.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.25.audio_attn1.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.25.audio_attn1.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.25.audio_attn1.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.25.audio_attn1.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.25.audio_attn1.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.25.norm2", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.25.attn2", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.25.attn2.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.25.attn2.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.25.attn2.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.25.attn2.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.25.attn2.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.25.attn2.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.25.attn2.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.25.attn2.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.25.attn2.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.25.audio_norm2", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.25.audio_attn2", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.25.audio_attn2.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.25.audio_attn2.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.25.audio_attn2.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.25.audio_attn2.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.25.audio_attn2.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.25.audio_attn2.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.25.audio_attn2.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.25.audio_attn2.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.25.audio_attn2.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.25.audio_to_video_norm", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.25.audio_to_video_attn", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.25.audio_to_video_attn.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.25.audio_to_video_attn.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.25.audio_to_video_attn.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.25.audio_to_video_attn.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.25.audio_to_video_attn.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.25.audio_to_video_attn.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.25.audio_to_video_attn.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.25.audio_to_video_attn.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.25.audio_to_video_attn.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.25.video_to_audio_norm", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.25.video_to_audio_attn", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.25.video_to_audio_attn.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.25.video_to_audio_attn.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.25.video_to_audio_attn.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.25.video_to_audio_attn.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.25.video_to_audio_attn.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.25.video_to_audio_attn.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.25.video_to_audio_attn.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.25.video_to_audio_attn.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.25.video_to_audio_attn.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.25.norm3", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.25.ff", "class": "FeedForward", "module": "diffusers.models.attention" }, { "name": "transformer_blocks.25.ff.net", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.25.ff.net.0", "class": "GELU", "module": "diffusers.models.activations" }, { "name": "transformer_blocks.25.ff.net.0.proj", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 16384, "bias": true, "skip": false }, { "name": "transformer_blocks.25.ff.net.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.25.ff.net.2", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 16384, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.25.audio_norm3", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.25.audio_ff", "class": "FeedForward", "module": "diffusers.models.attention" }, { "name": "transformer_blocks.25.audio_ff.net", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.25.audio_ff.net.0", "class": "GELU", "module": "diffusers.models.activations" }, { "name": "transformer_blocks.25.audio_ff.net.0.proj", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 8192, "bias": true, "skip": false }, { "name": "transformer_blocks.25.audio_ff.net.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.25.audio_ff.net.2", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 8192, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.26", "class": "LTX2VideoTransformerBlock", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.26.norm1", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.26.attn1", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.26.attn1.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.26.attn1.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.26.attn1.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.26.attn1.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.26.attn1.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.26.attn1.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.26.attn1.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.26.attn1.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.26.attn1.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.26.audio_norm1", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.26.audio_attn1", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.26.audio_attn1.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.26.audio_attn1.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.26.audio_attn1.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.26.audio_attn1.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.26.audio_attn1.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.26.audio_attn1.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.26.audio_attn1.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.26.audio_attn1.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.26.audio_attn1.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.26.norm2", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.26.attn2", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.26.attn2.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.26.attn2.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.26.attn2.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.26.attn2.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.26.attn2.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.26.attn2.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.26.attn2.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.26.attn2.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.26.attn2.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.26.audio_norm2", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.26.audio_attn2", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.26.audio_attn2.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.26.audio_attn2.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.26.audio_attn2.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.26.audio_attn2.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.26.audio_attn2.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.26.audio_attn2.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.26.audio_attn2.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.26.audio_attn2.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.26.audio_attn2.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.26.audio_to_video_norm", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.26.audio_to_video_attn", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.26.audio_to_video_attn.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.26.audio_to_video_attn.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.26.audio_to_video_attn.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.26.audio_to_video_attn.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.26.audio_to_video_attn.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.26.audio_to_video_attn.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.26.audio_to_video_attn.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.26.audio_to_video_attn.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.26.audio_to_video_attn.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.26.video_to_audio_norm", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.26.video_to_audio_attn", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.26.video_to_audio_attn.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.26.video_to_audio_attn.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.26.video_to_audio_attn.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.26.video_to_audio_attn.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.26.video_to_audio_attn.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.26.video_to_audio_attn.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.26.video_to_audio_attn.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.26.video_to_audio_attn.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.26.video_to_audio_attn.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.26.norm3", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.26.ff", "class": "FeedForward", "module": "diffusers.models.attention" }, { "name": "transformer_blocks.26.ff.net", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.26.ff.net.0", "class": "GELU", "module": "diffusers.models.activations" }, { "name": "transformer_blocks.26.ff.net.0.proj", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 16384, "bias": true, "skip": false }, { "name": "transformer_blocks.26.ff.net.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.26.ff.net.2", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 16384, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.26.audio_norm3", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.26.audio_ff", "class": "FeedForward", "module": "diffusers.models.attention" }, { "name": "transformer_blocks.26.audio_ff.net", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.26.audio_ff.net.0", "class": "GELU", "module": "diffusers.models.activations" }, { "name": "transformer_blocks.26.audio_ff.net.0.proj", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 8192, "bias": true, "skip": false }, { "name": "transformer_blocks.26.audio_ff.net.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.26.audio_ff.net.2", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 8192, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.27", "class": "LTX2VideoTransformerBlock", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.27.norm1", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.27.attn1", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.27.attn1.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.27.attn1.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.27.attn1.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.27.attn1.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.27.attn1.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.27.attn1.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.27.attn1.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.27.attn1.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.27.attn1.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.27.audio_norm1", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.27.audio_attn1", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.27.audio_attn1.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.27.audio_attn1.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.27.audio_attn1.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.27.audio_attn1.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.27.audio_attn1.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.27.audio_attn1.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.27.audio_attn1.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.27.audio_attn1.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.27.audio_attn1.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.27.norm2", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.27.attn2", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.27.attn2.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.27.attn2.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.27.attn2.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.27.attn2.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.27.attn2.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.27.attn2.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.27.attn2.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.27.attn2.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.27.attn2.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.27.audio_norm2", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.27.audio_attn2", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.27.audio_attn2.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.27.audio_attn2.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.27.audio_attn2.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.27.audio_attn2.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.27.audio_attn2.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.27.audio_attn2.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.27.audio_attn2.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.27.audio_attn2.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.27.audio_attn2.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.27.audio_to_video_norm", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.27.audio_to_video_attn", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.27.audio_to_video_attn.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.27.audio_to_video_attn.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.27.audio_to_video_attn.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.27.audio_to_video_attn.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.27.audio_to_video_attn.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.27.audio_to_video_attn.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.27.audio_to_video_attn.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.27.audio_to_video_attn.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.27.audio_to_video_attn.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.27.video_to_audio_norm", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.27.video_to_audio_attn", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.27.video_to_audio_attn.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.27.video_to_audio_attn.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.27.video_to_audio_attn.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.27.video_to_audio_attn.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.27.video_to_audio_attn.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.27.video_to_audio_attn.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.27.video_to_audio_attn.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.27.video_to_audio_attn.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.27.video_to_audio_attn.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.27.norm3", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.27.ff", "class": "FeedForward", "module": "diffusers.models.attention" }, { "name": "transformer_blocks.27.ff.net", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.27.ff.net.0", "class": "GELU", "module": "diffusers.models.activations" }, { "name": "transformer_blocks.27.ff.net.0.proj", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 16384, "bias": true, "skip": false }, { "name": "transformer_blocks.27.ff.net.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.27.ff.net.2", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 16384, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.27.audio_norm3", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.27.audio_ff", "class": "FeedForward", "module": "diffusers.models.attention" }, { "name": "transformer_blocks.27.audio_ff.net", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.27.audio_ff.net.0", "class": "GELU", "module": "diffusers.models.activations" }, { "name": "transformer_blocks.27.audio_ff.net.0.proj", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 8192, "bias": true, "skip": false }, { "name": "transformer_blocks.27.audio_ff.net.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.27.audio_ff.net.2", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 8192, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.28", "class": "LTX2VideoTransformerBlock", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.28.norm1", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.28.attn1", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.28.attn1.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.28.attn1.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.28.attn1.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.28.attn1.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.28.attn1.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.28.attn1.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.28.attn1.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.28.attn1.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.28.attn1.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.28.audio_norm1", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.28.audio_attn1", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.28.audio_attn1.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.28.audio_attn1.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.28.audio_attn1.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.28.audio_attn1.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.28.audio_attn1.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.28.audio_attn1.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.28.audio_attn1.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.28.audio_attn1.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.28.audio_attn1.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.28.norm2", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.28.attn2", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.28.attn2.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.28.attn2.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.28.attn2.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.28.attn2.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.28.attn2.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.28.attn2.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.28.attn2.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.28.attn2.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.28.attn2.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.28.audio_norm2", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.28.audio_attn2", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.28.audio_attn2.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.28.audio_attn2.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.28.audio_attn2.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.28.audio_attn2.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.28.audio_attn2.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.28.audio_attn2.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.28.audio_attn2.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.28.audio_attn2.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.28.audio_attn2.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.28.audio_to_video_norm", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.28.audio_to_video_attn", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.28.audio_to_video_attn.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.28.audio_to_video_attn.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.28.audio_to_video_attn.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.28.audio_to_video_attn.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.28.audio_to_video_attn.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.28.audio_to_video_attn.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.28.audio_to_video_attn.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.28.audio_to_video_attn.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.28.audio_to_video_attn.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.28.video_to_audio_norm", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.28.video_to_audio_attn", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.28.video_to_audio_attn.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.28.video_to_audio_attn.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.28.video_to_audio_attn.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.28.video_to_audio_attn.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.28.video_to_audio_attn.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.28.video_to_audio_attn.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.28.video_to_audio_attn.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.28.video_to_audio_attn.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.28.video_to_audio_attn.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.28.norm3", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.28.ff", "class": "FeedForward", "module": "diffusers.models.attention" }, { "name": "transformer_blocks.28.ff.net", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.28.ff.net.0", "class": "GELU", "module": "diffusers.models.activations" }, { "name": "transformer_blocks.28.ff.net.0.proj", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 16384, "bias": true, "skip": false }, { "name": "transformer_blocks.28.ff.net.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.28.ff.net.2", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 16384, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.28.audio_norm3", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.28.audio_ff", "class": "FeedForward", "module": "diffusers.models.attention" }, { "name": "transformer_blocks.28.audio_ff.net", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.28.audio_ff.net.0", "class": "GELU", "module": "diffusers.models.activations" }, { "name": "transformer_blocks.28.audio_ff.net.0.proj", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 8192, "bias": true, "skip": false }, { "name": "transformer_blocks.28.audio_ff.net.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.28.audio_ff.net.2", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 8192, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.29", "class": "LTX2VideoTransformerBlock", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.29.norm1", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.29.attn1", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.29.attn1.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.29.attn1.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.29.attn1.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.29.attn1.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.29.attn1.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.29.attn1.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.29.attn1.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.29.attn1.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.29.attn1.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.29.audio_norm1", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.29.audio_attn1", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.29.audio_attn1.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.29.audio_attn1.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.29.audio_attn1.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.29.audio_attn1.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.29.audio_attn1.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.29.audio_attn1.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.29.audio_attn1.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.29.audio_attn1.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.29.audio_attn1.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.29.norm2", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.29.attn2", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.29.attn2.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.29.attn2.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.29.attn2.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.29.attn2.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.29.attn2.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.29.attn2.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.29.attn2.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.29.attn2.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.29.attn2.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.29.audio_norm2", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.29.audio_attn2", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.29.audio_attn2.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.29.audio_attn2.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.29.audio_attn2.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.29.audio_attn2.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.29.audio_attn2.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.29.audio_attn2.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.29.audio_attn2.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.29.audio_attn2.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.29.audio_attn2.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.29.audio_to_video_norm", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.29.audio_to_video_attn", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.29.audio_to_video_attn.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.29.audio_to_video_attn.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.29.audio_to_video_attn.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.29.audio_to_video_attn.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.29.audio_to_video_attn.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.29.audio_to_video_attn.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.29.audio_to_video_attn.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.29.audio_to_video_attn.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.29.audio_to_video_attn.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.29.video_to_audio_norm", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.29.video_to_audio_attn", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.29.video_to_audio_attn.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.29.video_to_audio_attn.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.29.video_to_audio_attn.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.29.video_to_audio_attn.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.29.video_to_audio_attn.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.29.video_to_audio_attn.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.29.video_to_audio_attn.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.29.video_to_audio_attn.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.29.video_to_audio_attn.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.29.norm3", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.29.ff", "class": "FeedForward", "module": "diffusers.models.attention" }, { "name": "transformer_blocks.29.ff.net", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.29.ff.net.0", "class": "GELU", "module": "diffusers.models.activations" }, { "name": "transformer_blocks.29.ff.net.0.proj", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 16384, "bias": true, "skip": false }, { "name": "transformer_blocks.29.ff.net.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.29.ff.net.2", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 16384, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.29.audio_norm3", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.29.audio_ff", "class": "FeedForward", "module": "diffusers.models.attention" }, { "name": "transformer_blocks.29.audio_ff.net", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.29.audio_ff.net.0", "class": "GELU", "module": "diffusers.models.activations" }, { "name": "transformer_blocks.29.audio_ff.net.0.proj", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 8192, "bias": true, "skip": false }, { "name": "transformer_blocks.29.audio_ff.net.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.29.audio_ff.net.2", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 8192, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.30", "class": "LTX2VideoTransformerBlock", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.30.norm1", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.30.attn1", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.30.attn1.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.30.attn1.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.30.attn1.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.30.attn1.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.30.attn1.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.30.attn1.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.30.attn1.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.30.attn1.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.30.attn1.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.30.audio_norm1", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.30.audio_attn1", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.30.audio_attn1.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.30.audio_attn1.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.30.audio_attn1.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.30.audio_attn1.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.30.audio_attn1.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.30.audio_attn1.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.30.audio_attn1.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.30.audio_attn1.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.30.audio_attn1.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.30.norm2", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.30.attn2", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.30.attn2.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.30.attn2.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.30.attn2.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.30.attn2.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.30.attn2.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.30.attn2.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.30.attn2.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.30.attn2.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.30.attn2.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.30.audio_norm2", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.30.audio_attn2", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.30.audio_attn2.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.30.audio_attn2.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.30.audio_attn2.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.30.audio_attn2.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.30.audio_attn2.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.30.audio_attn2.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.30.audio_attn2.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.30.audio_attn2.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.30.audio_attn2.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.30.audio_to_video_norm", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.30.audio_to_video_attn", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.30.audio_to_video_attn.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.30.audio_to_video_attn.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.30.audio_to_video_attn.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.30.audio_to_video_attn.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.30.audio_to_video_attn.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.30.audio_to_video_attn.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.30.audio_to_video_attn.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.30.audio_to_video_attn.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.30.audio_to_video_attn.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.30.video_to_audio_norm", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.30.video_to_audio_attn", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.30.video_to_audio_attn.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.30.video_to_audio_attn.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.30.video_to_audio_attn.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.30.video_to_audio_attn.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.30.video_to_audio_attn.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.30.video_to_audio_attn.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.30.video_to_audio_attn.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.30.video_to_audio_attn.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.30.video_to_audio_attn.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.30.norm3", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.30.ff", "class": "FeedForward", "module": "diffusers.models.attention" }, { "name": "transformer_blocks.30.ff.net", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.30.ff.net.0", "class": "GELU", "module": "diffusers.models.activations" }, { "name": "transformer_blocks.30.ff.net.0.proj", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 16384, "bias": true, "skip": false }, { "name": "transformer_blocks.30.ff.net.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.30.ff.net.2", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 16384, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.30.audio_norm3", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.30.audio_ff", "class": "FeedForward", "module": "diffusers.models.attention" }, { "name": "transformer_blocks.30.audio_ff.net", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.30.audio_ff.net.0", "class": "GELU", "module": "diffusers.models.activations" }, { "name": "transformer_blocks.30.audio_ff.net.0.proj", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 8192, "bias": true, "skip": false }, { "name": "transformer_blocks.30.audio_ff.net.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.30.audio_ff.net.2", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 8192, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.31", "class": "LTX2VideoTransformerBlock", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.31.norm1", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.31.attn1", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.31.attn1.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.31.attn1.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.31.attn1.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.31.attn1.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.31.attn1.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.31.attn1.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.31.attn1.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.31.attn1.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.31.attn1.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.31.audio_norm1", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.31.audio_attn1", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.31.audio_attn1.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.31.audio_attn1.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.31.audio_attn1.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.31.audio_attn1.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.31.audio_attn1.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.31.audio_attn1.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.31.audio_attn1.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.31.audio_attn1.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.31.audio_attn1.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.31.norm2", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.31.attn2", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.31.attn2.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.31.attn2.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.31.attn2.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.31.attn2.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.31.attn2.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.31.attn2.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.31.attn2.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.31.attn2.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.31.attn2.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.31.audio_norm2", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.31.audio_attn2", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.31.audio_attn2.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.31.audio_attn2.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.31.audio_attn2.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.31.audio_attn2.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.31.audio_attn2.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.31.audio_attn2.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.31.audio_attn2.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.31.audio_attn2.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.31.audio_attn2.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.31.audio_to_video_norm", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.31.audio_to_video_attn", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.31.audio_to_video_attn.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.31.audio_to_video_attn.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.31.audio_to_video_attn.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.31.audio_to_video_attn.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.31.audio_to_video_attn.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.31.audio_to_video_attn.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.31.audio_to_video_attn.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.31.audio_to_video_attn.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.31.audio_to_video_attn.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.31.video_to_audio_norm", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.31.video_to_audio_attn", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.31.video_to_audio_attn.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.31.video_to_audio_attn.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.31.video_to_audio_attn.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.31.video_to_audio_attn.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.31.video_to_audio_attn.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.31.video_to_audio_attn.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.31.video_to_audio_attn.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.31.video_to_audio_attn.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.31.video_to_audio_attn.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.31.norm3", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.31.ff", "class": "FeedForward", "module": "diffusers.models.attention" }, { "name": "transformer_blocks.31.ff.net", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.31.ff.net.0", "class": "GELU", "module": "diffusers.models.activations" }, { "name": "transformer_blocks.31.ff.net.0.proj", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 16384, "bias": true, "skip": false }, { "name": "transformer_blocks.31.ff.net.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.31.ff.net.2", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 16384, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.31.audio_norm3", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.31.audio_ff", "class": "FeedForward", "module": "diffusers.models.attention" }, { "name": "transformer_blocks.31.audio_ff.net", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.31.audio_ff.net.0", "class": "GELU", "module": "diffusers.models.activations" }, { "name": "transformer_blocks.31.audio_ff.net.0.proj", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 8192, "bias": true, "skip": false }, { "name": "transformer_blocks.31.audio_ff.net.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.31.audio_ff.net.2", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 8192, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.32", "class": "LTX2VideoTransformerBlock", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.32.norm1", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.32.attn1", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.32.attn1.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.32.attn1.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.32.attn1.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.32.attn1.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.32.attn1.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.32.attn1.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.32.attn1.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.32.attn1.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.32.attn1.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.32.audio_norm1", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.32.audio_attn1", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.32.audio_attn1.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.32.audio_attn1.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.32.audio_attn1.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.32.audio_attn1.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.32.audio_attn1.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.32.audio_attn1.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.32.audio_attn1.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.32.audio_attn1.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.32.audio_attn1.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.32.norm2", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.32.attn2", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.32.attn2.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.32.attn2.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.32.attn2.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.32.attn2.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.32.attn2.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.32.attn2.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.32.attn2.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.32.attn2.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.32.attn2.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.32.audio_norm2", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.32.audio_attn2", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.32.audio_attn2.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.32.audio_attn2.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.32.audio_attn2.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.32.audio_attn2.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.32.audio_attn2.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.32.audio_attn2.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.32.audio_attn2.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.32.audio_attn2.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.32.audio_attn2.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.32.audio_to_video_norm", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.32.audio_to_video_attn", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.32.audio_to_video_attn.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.32.audio_to_video_attn.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.32.audio_to_video_attn.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.32.audio_to_video_attn.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.32.audio_to_video_attn.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.32.audio_to_video_attn.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.32.audio_to_video_attn.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.32.audio_to_video_attn.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.32.audio_to_video_attn.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.32.video_to_audio_norm", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.32.video_to_audio_attn", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.32.video_to_audio_attn.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.32.video_to_audio_attn.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.32.video_to_audio_attn.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.32.video_to_audio_attn.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.32.video_to_audio_attn.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.32.video_to_audio_attn.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.32.video_to_audio_attn.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.32.video_to_audio_attn.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.32.video_to_audio_attn.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.32.norm3", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.32.ff", "class": "FeedForward", "module": "diffusers.models.attention" }, { "name": "transformer_blocks.32.ff.net", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.32.ff.net.0", "class": "GELU", "module": "diffusers.models.activations" }, { "name": "transformer_blocks.32.ff.net.0.proj", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 16384, "bias": true, "skip": false }, { "name": "transformer_blocks.32.ff.net.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.32.ff.net.2", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 16384, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.32.audio_norm3", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.32.audio_ff", "class": "FeedForward", "module": "diffusers.models.attention" }, { "name": "transformer_blocks.32.audio_ff.net", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.32.audio_ff.net.0", "class": "GELU", "module": "diffusers.models.activations" }, { "name": "transformer_blocks.32.audio_ff.net.0.proj", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 8192, "bias": true, "skip": false }, { "name": "transformer_blocks.32.audio_ff.net.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.32.audio_ff.net.2", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 8192, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.33", "class": "LTX2VideoTransformerBlock", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.33.norm1", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.33.attn1", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.33.attn1.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.33.attn1.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.33.attn1.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.33.attn1.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.33.attn1.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.33.attn1.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.33.attn1.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.33.attn1.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.33.attn1.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.33.audio_norm1", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.33.audio_attn1", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.33.audio_attn1.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.33.audio_attn1.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.33.audio_attn1.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.33.audio_attn1.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.33.audio_attn1.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.33.audio_attn1.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.33.audio_attn1.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.33.audio_attn1.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.33.audio_attn1.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.33.norm2", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.33.attn2", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.33.attn2.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.33.attn2.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.33.attn2.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.33.attn2.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.33.attn2.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.33.attn2.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.33.attn2.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.33.attn2.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.33.attn2.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.33.audio_norm2", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.33.audio_attn2", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.33.audio_attn2.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.33.audio_attn2.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.33.audio_attn2.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.33.audio_attn2.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.33.audio_attn2.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.33.audio_attn2.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.33.audio_attn2.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.33.audio_attn2.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.33.audio_attn2.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.33.audio_to_video_norm", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.33.audio_to_video_attn", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.33.audio_to_video_attn.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.33.audio_to_video_attn.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.33.audio_to_video_attn.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.33.audio_to_video_attn.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.33.audio_to_video_attn.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.33.audio_to_video_attn.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.33.audio_to_video_attn.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.33.audio_to_video_attn.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.33.audio_to_video_attn.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.33.video_to_audio_norm", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.33.video_to_audio_attn", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.33.video_to_audio_attn.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.33.video_to_audio_attn.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.33.video_to_audio_attn.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.33.video_to_audio_attn.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.33.video_to_audio_attn.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.33.video_to_audio_attn.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.33.video_to_audio_attn.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.33.video_to_audio_attn.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.33.video_to_audio_attn.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.33.norm3", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.33.ff", "class": "FeedForward", "module": "diffusers.models.attention" }, { "name": "transformer_blocks.33.ff.net", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.33.ff.net.0", "class": "GELU", "module": "diffusers.models.activations" }, { "name": "transformer_blocks.33.ff.net.0.proj", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 16384, "bias": true, "skip": false }, { "name": "transformer_blocks.33.ff.net.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.33.ff.net.2", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 16384, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.33.audio_norm3", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.33.audio_ff", "class": "FeedForward", "module": "diffusers.models.attention" }, { "name": "transformer_blocks.33.audio_ff.net", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.33.audio_ff.net.0", "class": "GELU", "module": "diffusers.models.activations" }, { "name": "transformer_blocks.33.audio_ff.net.0.proj", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 8192, "bias": true, "skip": false }, { "name": "transformer_blocks.33.audio_ff.net.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.33.audio_ff.net.2", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 8192, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.34", "class": "LTX2VideoTransformerBlock", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.34.norm1", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.34.attn1", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.34.attn1.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.34.attn1.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.34.attn1.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.34.attn1.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.34.attn1.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.34.attn1.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.34.attn1.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.34.attn1.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.34.attn1.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.34.audio_norm1", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.34.audio_attn1", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.34.audio_attn1.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.34.audio_attn1.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.34.audio_attn1.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.34.audio_attn1.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.34.audio_attn1.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.34.audio_attn1.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.34.audio_attn1.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.34.audio_attn1.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.34.audio_attn1.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.34.norm2", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.34.attn2", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.34.attn2.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.34.attn2.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.34.attn2.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.34.attn2.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.34.attn2.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.34.attn2.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.34.attn2.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.34.attn2.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.34.attn2.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.34.audio_norm2", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.34.audio_attn2", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.34.audio_attn2.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.34.audio_attn2.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.34.audio_attn2.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.34.audio_attn2.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.34.audio_attn2.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.34.audio_attn2.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.34.audio_attn2.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.34.audio_attn2.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.34.audio_attn2.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.34.audio_to_video_norm", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.34.audio_to_video_attn", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.34.audio_to_video_attn.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.34.audio_to_video_attn.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.34.audio_to_video_attn.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.34.audio_to_video_attn.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.34.audio_to_video_attn.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.34.audio_to_video_attn.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.34.audio_to_video_attn.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.34.audio_to_video_attn.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.34.audio_to_video_attn.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.34.video_to_audio_norm", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.34.video_to_audio_attn", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.34.video_to_audio_attn.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.34.video_to_audio_attn.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.34.video_to_audio_attn.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.34.video_to_audio_attn.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.34.video_to_audio_attn.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.34.video_to_audio_attn.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.34.video_to_audio_attn.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.34.video_to_audio_attn.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.34.video_to_audio_attn.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.34.norm3", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.34.ff", "class": "FeedForward", "module": "diffusers.models.attention" }, { "name": "transformer_blocks.34.ff.net", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.34.ff.net.0", "class": "GELU", "module": "diffusers.models.activations" }, { "name": "transformer_blocks.34.ff.net.0.proj", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 16384, "bias": true, "skip": false }, { "name": "transformer_blocks.34.ff.net.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.34.ff.net.2", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 16384, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.34.audio_norm3", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.34.audio_ff", "class": "FeedForward", "module": "diffusers.models.attention" }, { "name": "transformer_blocks.34.audio_ff.net", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.34.audio_ff.net.0", "class": "GELU", "module": "diffusers.models.activations" }, { "name": "transformer_blocks.34.audio_ff.net.0.proj", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 8192, "bias": true, "skip": false }, { "name": "transformer_blocks.34.audio_ff.net.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.34.audio_ff.net.2", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 8192, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.35", "class": "LTX2VideoTransformerBlock", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.35.norm1", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.35.attn1", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.35.attn1.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.35.attn1.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.35.attn1.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.35.attn1.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.35.attn1.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.35.attn1.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.35.attn1.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.35.attn1.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.35.attn1.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.35.audio_norm1", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.35.audio_attn1", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.35.audio_attn1.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.35.audio_attn1.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.35.audio_attn1.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.35.audio_attn1.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.35.audio_attn1.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.35.audio_attn1.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.35.audio_attn1.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.35.audio_attn1.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.35.audio_attn1.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.35.norm2", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.35.attn2", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.35.attn2.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.35.attn2.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.35.attn2.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.35.attn2.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.35.attn2.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.35.attn2.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.35.attn2.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.35.attn2.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.35.attn2.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.35.audio_norm2", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.35.audio_attn2", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.35.audio_attn2.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.35.audio_attn2.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.35.audio_attn2.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.35.audio_attn2.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.35.audio_attn2.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.35.audio_attn2.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.35.audio_attn2.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.35.audio_attn2.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.35.audio_attn2.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.35.audio_to_video_norm", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.35.audio_to_video_attn", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.35.audio_to_video_attn.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.35.audio_to_video_attn.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.35.audio_to_video_attn.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.35.audio_to_video_attn.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.35.audio_to_video_attn.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.35.audio_to_video_attn.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.35.audio_to_video_attn.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.35.audio_to_video_attn.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.35.audio_to_video_attn.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.35.video_to_audio_norm", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.35.video_to_audio_attn", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.35.video_to_audio_attn.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.35.video_to_audio_attn.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.35.video_to_audio_attn.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.35.video_to_audio_attn.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.35.video_to_audio_attn.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.35.video_to_audio_attn.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.35.video_to_audio_attn.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.35.video_to_audio_attn.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.35.video_to_audio_attn.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.35.norm3", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.35.ff", "class": "FeedForward", "module": "diffusers.models.attention" }, { "name": "transformer_blocks.35.ff.net", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.35.ff.net.0", "class": "GELU", "module": "diffusers.models.activations" }, { "name": "transformer_blocks.35.ff.net.0.proj", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 16384, "bias": true, "skip": false }, { "name": "transformer_blocks.35.ff.net.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.35.ff.net.2", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 16384, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.35.audio_norm3", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.35.audio_ff", "class": "FeedForward", "module": "diffusers.models.attention" }, { "name": "transformer_blocks.35.audio_ff.net", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.35.audio_ff.net.0", "class": "GELU", "module": "diffusers.models.activations" }, { "name": "transformer_blocks.35.audio_ff.net.0.proj", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 8192, "bias": true, "skip": false }, { "name": "transformer_blocks.35.audio_ff.net.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.35.audio_ff.net.2", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 8192, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.36", "class": "LTX2VideoTransformerBlock", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.36.norm1", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.36.attn1", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.36.attn1.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.36.attn1.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.36.attn1.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.36.attn1.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.36.attn1.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.36.attn1.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.36.attn1.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.36.attn1.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.36.attn1.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.36.audio_norm1", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.36.audio_attn1", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.36.audio_attn1.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.36.audio_attn1.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.36.audio_attn1.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.36.audio_attn1.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.36.audio_attn1.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.36.audio_attn1.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.36.audio_attn1.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.36.audio_attn1.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.36.audio_attn1.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.36.norm2", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.36.attn2", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.36.attn2.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.36.attn2.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.36.attn2.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.36.attn2.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.36.attn2.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.36.attn2.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.36.attn2.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.36.attn2.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.36.attn2.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.36.audio_norm2", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.36.audio_attn2", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.36.audio_attn2.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.36.audio_attn2.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.36.audio_attn2.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.36.audio_attn2.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.36.audio_attn2.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.36.audio_attn2.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.36.audio_attn2.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.36.audio_attn2.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.36.audio_attn2.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.36.audio_to_video_norm", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.36.audio_to_video_attn", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.36.audio_to_video_attn.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.36.audio_to_video_attn.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.36.audio_to_video_attn.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.36.audio_to_video_attn.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.36.audio_to_video_attn.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.36.audio_to_video_attn.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.36.audio_to_video_attn.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.36.audio_to_video_attn.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.36.audio_to_video_attn.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.36.video_to_audio_norm", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.36.video_to_audio_attn", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.36.video_to_audio_attn.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.36.video_to_audio_attn.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.36.video_to_audio_attn.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.36.video_to_audio_attn.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.36.video_to_audio_attn.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.36.video_to_audio_attn.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.36.video_to_audio_attn.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.36.video_to_audio_attn.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.36.video_to_audio_attn.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.36.norm3", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.36.ff", "class": "FeedForward", "module": "diffusers.models.attention" }, { "name": "transformer_blocks.36.ff.net", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.36.ff.net.0", "class": "GELU", "module": "diffusers.models.activations" }, { "name": "transformer_blocks.36.ff.net.0.proj", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 16384, "bias": true, "skip": false }, { "name": "transformer_blocks.36.ff.net.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.36.ff.net.2", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 16384, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.36.audio_norm3", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.36.audio_ff", "class": "FeedForward", "module": "diffusers.models.attention" }, { "name": "transformer_blocks.36.audio_ff.net", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.36.audio_ff.net.0", "class": "GELU", "module": "diffusers.models.activations" }, { "name": "transformer_blocks.36.audio_ff.net.0.proj", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 8192, "bias": true, "skip": false }, { "name": "transformer_blocks.36.audio_ff.net.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.36.audio_ff.net.2", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 8192, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.37", "class": "LTX2VideoTransformerBlock", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.37.norm1", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.37.attn1", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.37.attn1.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.37.attn1.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.37.attn1.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.37.attn1.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.37.attn1.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.37.attn1.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.37.attn1.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.37.attn1.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.37.attn1.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.37.audio_norm1", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.37.audio_attn1", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.37.audio_attn1.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.37.audio_attn1.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.37.audio_attn1.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.37.audio_attn1.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.37.audio_attn1.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.37.audio_attn1.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.37.audio_attn1.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.37.audio_attn1.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.37.audio_attn1.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.37.norm2", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.37.attn2", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.37.attn2.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.37.attn2.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.37.attn2.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.37.attn2.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.37.attn2.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.37.attn2.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.37.attn2.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.37.attn2.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.37.attn2.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.37.audio_norm2", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.37.audio_attn2", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.37.audio_attn2.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.37.audio_attn2.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.37.audio_attn2.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.37.audio_attn2.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.37.audio_attn2.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.37.audio_attn2.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.37.audio_attn2.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.37.audio_attn2.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.37.audio_attn2.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.37.audio_to_video_norm", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.37.audio_to_video_attn", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.37.audio_to_video_attn.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.37.audio_to_video_attn.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.37.audio_to_video_attn.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.37.audio_to_video_attn.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.37.audio_to_video_attn.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.37.audio_to_video_attn.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.37.audio_to_video_attn.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.37.audio_to_video_attn.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.37.audio_to_video_attn.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.37.video_to_audio_norm", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.37.video_to_audio_attn", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.37.video_to_audio_attn.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.37.video_to_audio_attn.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.37.video_to_audio_attn.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.37.video_to_audio_attn.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.37.video_to_audio_attn.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.37.video_to_audio_attn.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.37.video_to_audio_attn.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.37.video_to_audio_attn.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.37.video_to_audio_attn.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.37.norm3", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.37.ff", "class": "FeedForward", "module": "diffusers.models.attention" }, { "name": "transformer_blocks.37.ff.net", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.37.ff.net.0", "class": "GELU", "module": "diffusers.models.activations" }, { "name": "transformer_blocks.37.ff.net.0.proj", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 16384, "bias": true, "skip": false }, { "name": "transformer_blocks.37.ff.net.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.37.ff.net.2", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 16384, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.37.audio_norm3", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.37.audio_ff", "class": "FeedForward", "module": "diffusers.models.attention" }, { "name": "transformer_blocks.37.audio_ff.net", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.37.audio_ff.net.0", "class": "GELU", "module": "diffusers.models.activations" }, { "name": "transformer_blocks.37.audio_ff.net.0.proj", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 8192, "bias": true, "skip": false }, { "name": "transformer_blocks.37.audio_ff.net.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.37.audio_ff.net.2", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 8192, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.38", "class": "LTX2VideoTransformerBlock", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.38.norm1", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.38.attn1", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.38.attn1.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.38.attn1.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.38.attn1.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.38.attn1.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.38.attn1.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.38.attn1.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.38.attn1.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.38.attn1.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.38.attn1.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.38.audio_norm1", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.38.audio_attn1", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.38.audio_attn1.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.38.audio_attn1.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.38.audio_attn1.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.38.audio_attn1.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.38.audio_attn1.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.38.audio_attn1.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.38.audio_attn1.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.38.audio_attn1.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.38.audio_attn1.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.38.norm2", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.38.attn2", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.38.attn2.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.38.attn2.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.38.attn2.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.38.attn2.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.38.attn2.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.38.attn2.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.38.attn2.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.38.attn2.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.38.attn2.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.38.audio_norm2", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.38.audio_attn2", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.38.audio_attn2.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.38.audio_attn2.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.38.audio_attn2.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.38.audio_attn2.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.38.audio_attn2.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.38.audio_attn2.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.38.audio_attn2.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.38.audio_attn2.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.38.audio_attn2.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.38.audio_to_video_norm", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.38.audio_to_video_attn", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.38.audio_to_video_attn.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.38.audio_to_video_attn.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.38.audio_to_video_attn.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.38.audio_to_video_attn.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.38.audio_to_video_attn.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.38.audio_to_video_attn.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.38.audio_to_video_attn.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.38.audio_to_video_attn.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.38.audio_to_video_attn.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.38.video_to_audio_norm", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.38.video_to_audio_attn", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.38.video_to_audio_attn.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.38.video_to_audio_attn.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.38.video_to_audio_attn.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.38.video_to_audio_attn.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.38.video_to_audio_attn.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.38.video_to_audio_attn.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.38.video_to_audio_attn.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.38.video_to_audio_attn.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.38.video_to_audio_attn.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.38.norm3", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.38.ff", "class": "FeedForward", "module": "diffusers.models.attention" }, { "name": "transformer_blocks.38.ff.net", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.38.ff.net.0", "class": "GELU", "module": "diffusers.models.activations" }, { "name": "transformer_blocks.38.ff.net.0.proj", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 16384, "bias": true, "skip": false }, { "name": "transformer_blocks.38.ff.net.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.38.ff.net.2", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 16384, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.38.audio_norm3", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.38.audio_ff", "class": "FeedForward", "module": "diffusers.models.attention" }, { "name": "transformer_blocks.38.audio_ff.net", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.38.audio_ff.net.0", "class": "GELU", "module": "diffusers.models.activations" }, { "name": "transformer_blocks.38.audio_ff.net.0.proj", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 8192, "bias": true, "skip": false }, { "name": "transformer_blocks.38.audio_ff.net.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.38.audio_ff.net.2", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 8192, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.39", "class": "LTX2VideoTransformerBlock", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.39.norm1", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.39.attn1", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.39.attn1.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.39.attn1.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.39.attn1.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.39.attn1.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.39.attn1.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.39.attn1.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.39.attn1.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.39.attn1.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.39.attn1.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.39.audio_norm1", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.39.audio_attn1", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.39.audio_attn1.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.39.audio_attn1.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.39.audio_attn1.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.39.audio_attn1.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.39.audio_attn1.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.39.audio_attn1.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.39.audio_attn1.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.39.audio_attn1.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.39.audio_attn1.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.39.norm2", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.39.attn2", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.39.attn2.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.39.attn2.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.39.attn2.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.39.attn2.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.39.attn2.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.39.attn2.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.39.attn2.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.39.attn2.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.39.attn2.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.39.audio_norm2", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.39.audio_attn2", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.39.audio_attn2.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.39.audio_attn2.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.39.audio_attn2.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.39.audio_attn2.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.39.audio_attn2.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.39.audio_attn2.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.39.audio_attn2.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.39.audio_attn2.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.39.audio_attn2.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.39.audio_to_video_norm", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.39.audio_to_video_attn", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.39.audio_to_video_attn.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.39.audio_to_video_attn.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.39.audio_to_video_attn.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.39.audio_to_video_attn.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.39.audio_to_video_attn.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.39.audio_to_video_attn.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.39.audio_to_video_attn.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.39.audio_to_video_attn.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.39.audio_to_video_attn.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.39.video_to_audio_norm", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.39.video_to_audio_attn", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.39.video_to_audio_attn.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.39.video_to_audio_attn.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.39.video_to_audio_attn.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.39.video_to_audio_attn.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.39.video_to_audio_attn.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.39.video_to_audio_attn.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.39.video_to_audio_attn.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.39.video_to_audio_attn.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.39.video_to_audio_attn.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.39.norm3", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.39.ff", "class": "FeedForward", "module": "diffusers.models.attention" }, { "name": "transformer_blocks.39.ff.net", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.39.ff.net.0", "class": "GELU", "module": "diffusers.models.activations" }, { "name": "transformer_blocks.39.ff.net.0.proj", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 16384, "bias": true, "skip": false }, { "name": "transformer_blocks.39.ff.net.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.39.ff.net.2", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 16384, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.39.audio_norm3", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.39.audio_ff", "class": "FeedForward", "module": "diffusers.models.attention" }, { "name": "transformer_blocks.39.audio_ff.net", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.39.audio_ff.net.0", "class": "GELU", "module": "diffusers.models.activations" }, { "name": "transformer_blocks.39.audio_ff.net.0.proj", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 8192, "bias": true, "skip": false }, { "name": "transformer_blocks.39.audio_ff.net.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.39.audio_ff.net.2", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 8192, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.40", "class": "LTX2VideoTransformerBlock", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.40.norm1", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.40.attn1", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.40.attn1.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.40.attn1.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.40.attn1.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.40.attn1.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.40.attn1.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.40.attn1.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.40.attn1.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.40.attn1.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.40.attn1.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.40.audio_norm1", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.40.audio_attn1", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.40.audio_attn1.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.40.audio_attn1.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.40.audio_attn1.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.40.audio_attn1.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.40.audio_attn1.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.40.audio_attn1.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.40.audio_attn1.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.40.audio_attn1.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.40.audio_attn1.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.40.norm2", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.40.attn2", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.40.attn2.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.40.attn2.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.40.attn2.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.40.attn2.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.40.attn2.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.40.attn2.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.40.attn2.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.40.attn2.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.40.attn2.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.40.audio_norm2", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.40.audio_attn2", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.40.audio_attn2.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.40.audio_attn2.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.40.audio_attn2.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.40.audio_attn2.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.40.audio_attn2.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.40.audio_attn2.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.40.audio_attn2.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.40.audio_attn2.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.40.audio_attn2.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.40.audio_to_video_norm", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.40.audio_to_video_attn", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.40.audio_to_video_attn.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.40.audio_to_video_attn.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.40.audio_to_video_attn.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.40.audio_to_video_attn.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.40.audio_to_video_attn.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.40.audio_to_video_attn.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.40.audio_to_video_attn.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.40.audio_to_video_attn.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.40.audio_to_video_attn.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.40.video_to_audio_norm", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.40.video_to_audio_attn", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.40.video_to_audio_attn.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.40.video_to_audio_attn.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.40.video_to_audio_attn.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.40.video_to_audio_attn.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.40.video_to_audio_attn.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.40.video_to_audio_attn.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.40.video_to_audio_attn.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.40.video_to_audio_attn.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.40.video_to_audio_attn.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.40.norm3", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.40.ff", "class": "FeedForward", "module": "diffusers.models.attention" }, { "name": "transformer_blocks.40.ff.net", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.40.ff.net.0", "class": "GELU", "module": "diffusers.models.activations" }, { "name": "transformer_blocks.40.ff.net.0.proj", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 16384, "bias": true, "skip": false }, { "name": "transformer_blocks.40.ff.net.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.40.ff.net.2", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 16384, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.40.audio_norm3", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.40.audio_ff", "class": "FeedForward", "module": "diffusers.models.attention" }, { "name": "transformer_blocks.40.audio_ff.net", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.40.audio_ff.net.0", "class": "GELU", "module": "diffusers.models.activations" }, { "name": "transformer_blocks.40.audio_ff.net.0.proj", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 8192, "bias": true, "skip": false }, { "name": "transformer_blocks.40.audio_ff.net.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.40.audio_ff.net.2", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 8192, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.41", "class": "LTX2VideoTransformerBlock", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.41.norm1", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.41.attn1", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.41.attn1.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.41.attn1.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.41.attn1.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.41.attn1.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.41.attn1.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.41.attn1.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.41.attn1.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.41.attn1.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.41.attn1.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.41.audio_norm1", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.41.audio_attn1", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.41.audio_attn1.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.41.audio_attn1.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.41.audio_attn1.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.41.audio_attn1.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.41.audio_attn1.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.41.audio_attn1.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.41.audio_attn1.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.41.audio_attn1.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.41.audio_attn1.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.41.norm2", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.41.attn2", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.41.attn2.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.41.attn2.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.41.attn2.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.41.attn2.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.41.attn2.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.41.attn2.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.41.attn2.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.41.attn2.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.41.attn2.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.41.audio_norm2", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.41.audio_attn2", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.41.audio_attn2.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.41.audio_attn2.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.41.audio_attn2.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.41.audio_attn2.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.41.audio_attn2.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.41.audio_attn2.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.41.audio_attn2.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.41.audio_attn2.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.41.audio_attn2.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.41.audio_to_video_norm", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.41.audio_to_video_attn", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.41.audio_to_video_attn.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.41.audio_to_video_attn.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.41.audio_to_video_attn.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.41.audio_to_video_attn.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.41.audio_to_video_attn.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.41.audio_to_video_attn.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.41.audio_to_video_attn.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.41.audio_to_video_attn.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.41.audio_to_video_attn.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.41.video_to_audio_norm", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.41.video_to_audio_attn", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.41.video_to_audio_attn.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.41.video_to_audio_attn.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.41.video_to_audio_attn.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.41.video_to_audio_attn.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.41.video_to_audio_attn.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.41.video_to_audio_attn.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.41.video_to_audio_attn.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.41.video_to_audio_attn.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.41.video_to_audio_attn.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.41.norm3", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.41.ff", "class": "FeedForward", "module": "diffusers.models.attention" }, { "name": "transformer_blocks.41.ff.net", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.41.ff.net.0", "class": "GELU", "module": "diffusers.models.activations" }, { "name": "transformer_blocks.41.ff.net.0.proj", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 16384, "bias": true, "skip": false }, { "name": "transformer_blocks.41.ff.net.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.41.ff.net.2", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 16384, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.41.audio_norm3", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.41.audio_ff", "class": "FeedForward", "module": "diffusers.models.attention" }, { "name": "transformer_blocks.41.audio_ff.net", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.41.audio_ff.net.0", "class": "GELU", "module": "diffusers.models.activations" }, { "name": "transformer_blocks.41.audio_ff.net.0.proj", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 8192, "bias": true, "skip": false }, { "name": "transformer_blocks.41.audio_ff.net.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.41.audio_ff.net.2", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 8192, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.42", "class": "LTX2VideoTransformerBlock", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.42.norm1", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.42.attn1", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.42.attn1.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.42.attn1.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.42.attn1.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.42.attn1.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.42.attn1.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.42.attn1.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.42.attn1.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.42.attn1.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.42.attn1.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.42.audio_norm1", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.42.audio_attn1", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.42.audio_attn1.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.42.audio_attn1.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.42.audio_attn1.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.42.audio_attn1.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.42.audio_attn1.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.42.audio_attn1.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.42.audio_attn1.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.42.audio_attn1.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.42.audio_attn1.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.42.norm2", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.42.attn2", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.42.attn2.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.42.attn2.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.42.attn2.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.42.attn2.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.42.attn2.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.42.attn2.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.42.attn2.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.42.attn2.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.42.attn2.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.42.audio_norm2", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.42.audio_attn2", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.42.audio_attn2.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.42.audio_attn2.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.42.audio_attn2.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.42.audio_attn2.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.42.audio_attn2.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.42.audio_attn2.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.42.audio_attn2.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.42.audio_attn2.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.42.audio_attn2.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.42.audio_to_video_norm", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.42.audio_to_video_attn", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.42.audio_to_video_attn.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.42.audio_to_video_attn.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.42.audio_to_video_attn.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.42.audio_to_video_attn.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.42.audio_to_video_attn.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.42.audio_to_video_attn.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.42.audio_to_video_attn.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.42.audio_to_video_attn.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.42.audio_to_video_attn.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.42.video_to_audio_norm", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.42.video_to_audio_attn", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.42.video_to_audio_attn.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.42.video_to_audio_attn.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.42.video_to_audio_attn.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.42.video_to_audio_attn.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.42.video_to_audio_attn.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.42.video_to_audio_attn.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.42.video_to_audio_attn.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.42.video_to_audio_attn.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.42.video_to_audio_attn.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.42.norm3", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.42.ff", "class": "FeedForward", "module": "diffusers.models.attention" }, { "name": "transformer_blocks.42.ff.net", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.42.ff.net.0", "class": "GELU", "module": "diffusers.models.activations" }, { "name": "transformer_blocks.42.ff.net.0.proj", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 16384, "bias": true, "skip": false }, { "name": "transformer_blocks.42.ff.net.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.42.ff.net.2", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 16384, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.42.audio_norm3", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.42.audio_ff", "class": "FeedForward", "module": "diffusers.models.attention" }, { "name": "transformer_blocks.42.audio_ff.net", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.42.audio_ff.net.0", "class": "GELU", "module": "diffusers.models.activations" }, { "name": "transformer_blocks.42.audio_ff.net.0.proj", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 8192, "bias": true, "skip": false }, { "name": "transformer_blocks.42.audio_ff.net.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.42.audio_ff.net.2", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 8192, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.43", "class": "LTX2VideoTransformerBlock", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.43.norm1", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.43.attn1", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.43.attn1.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.43.attn1.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.43.attn1.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.43.attn1.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.43.attn1.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.43.attn1.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.43.attn1.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.43.attn1.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.43.attn1.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.43.audio_norm1", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.43.audio_attn1", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.43.audio_attn1.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.43.audio_attn1.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.43.audio_attn1.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.43.audio_attn1.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.43.audio_attn1.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.43.audio_attn1.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.43.audio_attn1.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.43.audio_attn1.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.43.audio_attn1.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.43.norm2", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.43.attn2", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.43.attn2.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.43.attn2.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.43.attn2.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.43.attn2.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.43.attn2.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.43.attn2.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.43.attn2.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.43.attn2.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.43.attn2.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.43.audio_norm2", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.43.audio_attn2", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.43.audio_attn2.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.43.audio_attn2.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.43.audio_attn2.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.43.audio_attn2.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.43.audio_attn2.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.43.audio_attn2.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.43.audio_attn2.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.43.audio_attn2.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.43.audio_attn2.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.43.audio_to_video_norm", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.43.audio_to_video_attn", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.43.audio_to_video_attn.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.43.audio_to_video_attn.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.43.audio_to_video_attn.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.43.audio_to_video_attn.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.43.audio_to_video_attn.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.43.audio_to_video_attn.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.43.audio_to_video_attn.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.43.audio_to_video_attn.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.43.audio_to_video_attn.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.43.video_to_audio_norm", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.43.video_to_audio_attn", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.43.video_to_audio_attn.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.43.video_to_audio_attn.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.43.video_to_audio_attn.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.43.video_to_audio_attn.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.43.video_to_audio_attn.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.43.video_to_audio_attn.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.43.video_to_audio_attn.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.43.video_to_audio_attn.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.43.video_to_audio_attn.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.43.norm3", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.43.ff", "class": "FeedForward", "module": "diffusers.models.attention" }, { "name": "transformer_blocks.43.ff.net", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.43.ff.net.0", "class": "GELU", "module": "diffusers.models.activations" }, { "name": "transformer_blocks.43.ff.net.0.proj", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 16384, "bias": true, "skip": false }, { "name": "transformer_blocks.43.ff.net.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.43.ff.net.2", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 16384, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.43.audio_norm3", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.43.audio_ff", "class": "FeedForward", "module": "diffusers.models.attention" }, { "name": "transformer_blocks.43.audio_ff.net", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.43.audio_ff.net.0", "class": "GELU", "module": "diffusers.models.activations" }, { "name": "transformer_blocks.43.audio_ff.net.0.proj", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 8192, "bias": true, "skip": false }, { "name": "transformer_blocks.43.audio_ff.net.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.43.audio_ff.net.2", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 8192, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.44", "class": "LTX2VideoTransformerBlock", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.44.norm1", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.44.attn1", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.44.attn1.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.44.attn1.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.44.attn1.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.44.attn1.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.44.attn1.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.44.attn1.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.44.attn1.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.44.attn1.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.44.attn1.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.44.audio_norm1", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.44.audio_attn1", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.44.audio_attn1.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.44.audio_attn1.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.44.audio_attn1.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.44.audio_attn1.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.44.audio_attn1.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.44.audio_attn1.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.44.audio_attn1.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.44.audio_attn1.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.44.audio_attn1.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.44.norm2", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.44.attn2", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.44.attn2.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.44.attn2.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.44.attn2.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.44.attn2.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.44.attn2.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.44.attn2.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.44.attn2.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.44.attn2.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.44.attn2.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.44.audio_norm2", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.44.audio_attn2", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.44.audio_attn2.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.44.audio_attn2.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.44.audio_attn2.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.44.audio_attn2.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.44.audio_attn2.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.44.audio_attn2.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.44.audio_attn2.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.44.audio_attn2.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.44.audio_attn2.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.44.audio_to_video_norm", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.44.audio_to_video_attn", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.44.audio_to_video_attn.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.44.audio_to_video_attn.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.44.audio_to_video_attn.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.44.audio_to_video_attn.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.44.audio_to_video_attn.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.44.audio_to_video_attn.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.44.audio_to_video_attn.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.44.audio_to_video_attn.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.44.audio_to_video_attn.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.44.video_to_audio_norm", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.44.video_to_audio_attn", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.44.video_to_audio_attn.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.44.video_to_audio_attn.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.44.video_to_audio_attn.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.44.video_to_audio_attn.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.44.video_to_audio_attn.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.44.video_to_audio_attn.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.44.video_to_audio_attn.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.44.video_to_audio_attn.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.44.video_to_audio_attn.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.44.norm3", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.44.ff", "class": "FeedForward", "module": "diffusers.models.attention" }, { "name": "transformer_blocks.44.ff.net", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.44.ff.net.0", "class": "GELU", "module": "diffusers.models.activations" }, { "name": "transformer_blocks.44.ff.net.0.proj", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 16384, "bias": true, "skip": false }, { "name": "transformer_blocks.44.ff.net.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.44.ff.net.2", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 16384, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.44.audio_norm3", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.44.audio_ff", "class": "FeedForward", "module": "diffusers.models.attention" }, { "name": "transformer_blocks.44.audio_ff.net", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.44.audio_ff.net.0", "class": "GELU", "module": "diffusers.models.activations" }, { "name": "transformer_blocks.44.audio_ff.net.0.proj", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 8192, "bias": true, "skip": false }, { "name": "transformer_blocks.44.audio_ff.net.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.44.audio_ff.net.2", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 8192, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.45", "class": "LTX2VideoTransformerBlock", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.45.norm1", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.45.attn1", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.45.attn1.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.45.attn1.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.45.attn1.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.45.attn1.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.45.attn1.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.45.attn1.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.45.attn1.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.45.attn1.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.45.attn1.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.45.audio_norm1", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.45.audio_attn1", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.45.audio_attn1.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.45.audio_attn1.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.45.audio_attn1.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.45.audio_attn1.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.45.audio_attn1.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.45.audio_attn1.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.45.audio_attn1.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.45.audio_attn1.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.45.audio_attn1.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.45.norm2", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.45.attn2", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.45.attn2.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.45.attn2.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.45.attn2.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.45.attn2.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.45.attn2.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.45.attn2.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.45.attn2.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.45.attn2.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.45.attn2.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.45.audio_norm2", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.45.audio_attn2", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.45.audio_attn2.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.45.audio_attn2.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.45.audio_attn2.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.45.audio_attn2.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.45.audio_attn2.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.45.audio_attn2.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.45.audio_attn2.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.45.audio_attn2.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.45.audio_attn2.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.45.audio_to_video_norm", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.45.audio_to_video_attn", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.45.audio_to_video_attn.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.45.audio_to_video_attn.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.45.audio_to_video_attn.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.45.audio_to_video_attn.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.45.audio_to_video_attn.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.45.audio_to_video_attn.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.45.audio_to_video_attn.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.45.audio_to_video_attn.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.45.audio_to_video_attn.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.45.video_to_audio_norm", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.45.video_to_audio_attn", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.45.video_to_audio_attn.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.45.video_to_audio_attn.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.45.video_to_audio_attn.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.45.video_to_audio_attn.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.45.video_to_audio_attn.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.45.video_to_audio_attn.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.45.video_to_audio_attn.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.45.video_to_audio_attn.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.45.video_to_audio_attn.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.45.norm3", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.45.ff", "class": "FeedForward", "module": "diffusers.models.attention" }, { "name": "transformer_blocks.45.ff.net", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.45.ff.net.0", "class": "GELU", "module": "diffusers.models.activations" }, { "name": "transformer_blocks.45.ff.net.0.proj", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 16384, "bias": true, "skip": false }, { "name": "transformer_blocks.45.ff.net.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.45.ff.net.2", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 16384, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.45.audio_norm3", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.45.audio_ff", "class": "FeedForward", "module": "diffusers.models.attention" }, { "name": "transformer_blocks.45.audio_ff.net", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.45.audio_ff.net.0", "class": "GELU", "module": "diffusers.models.activations" }, { "name": "transformer_blocks.45.audio_ff.net.0.proj", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 8192, "bias": true, "skip": false }, { "name": "transformer_blocks.45.audio_ff.net.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.45.audio_ff.net.2", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 8192, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.46", "class": "LTX2VideoTransformerBlock", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.46.norm1", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.46.attn1", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.46.attn1.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.46.attn1.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.46.attn1.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.46.attn1.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.46.attn1.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.46.attn1.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.46.attn1.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.46.attn1.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.46.attn1.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.46.audio_norm1", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.46.audio_attn1", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.46.audio_attn1.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.46.audio_attn1.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.46.audio_attn1.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.46.audio_attn1.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.46.audio_attn1.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.46.audio_attn1.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.46.audio_attn1.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.46.audio_attn1.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.46.audio_attn1.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.46.norm2", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.46.attn2", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.46.attn2.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.46.attn2.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.46.attn2.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.46.attn2.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.46.attn2.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.46.attn2.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.46.attn2.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.46.attn2.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.46.attn2.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.46.audio_norm2", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.46.audio_attn2", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.46.audio_attn2.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.46.audio_attn2.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.46.audio_attn2.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.46.audio_attn2.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.46.audio_attn2.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.46.audio_attn2.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.46.audio_attn2.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.46.audio_attn2.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.46.audio_attn2.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.46.audio_to_video_norm", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.46.audio_to_video_attn", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.46.audio_to_video_attn.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.46.audio_to_video_attn.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.46.audio_to_video_attn.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.46.audio_to_video_attn.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.46.audio_to_video_attn.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.46.audio_to_video_attn.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.46.audio_to_video_attn.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.46.audio_to_video_attn.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.46.audio_to_video_attn.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.46.video_to_audio_norm", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.46.video_to_audio_attn", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.46.video_to_audio_attn.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.46.video_to_audio_attn.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.46.video_to_audio_attn.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.46.video_to_audio_attn.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.46.video_to_audio_attn.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.46.video_to_audio_attn.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.46.video_to_audio_attn.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.46.video_to_audio_attn.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.46.video_to_audio_attn.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.46.norm3", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.46.ff", "class": "FeedForward", "module": "diffusers.models.attention" }, { "name": "transformer_blocks.46.ff.net", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.46.ff.net.0", "class": "GELU", "module": "diffusers.models.activations" }, { "name": "transformer_blocks.46.ff.net.0.proj", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 16384, "bias": true, "skip": false }, { "name": "transformer_blocks.46.ff.net.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.46.ff.net.2", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 16384, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.46.audio_norm3", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.46.audio_ff", "class": "FeedForward", "module": "diffusers.models.attention" }, { "name": "transformer_blocks.46.audio_ff.net", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.46.audio_ff.net.0", "class": "GELU", "module": "diffusers.models.activations" }, { "name": "transformer_blocks.46.audio_ff.net.0.proj", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 8192, "bias": true, "skip": false }, { "name": "transformer_blocks.46.audio_ff.net.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.46.audio_ff.net.2", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 8192, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.47", "class": "LTX2VideoTransformerBlock", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.47.norm1", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.47.attn1", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.47.attn1.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.47.attn1.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.47.attn1.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.47.attn1.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.47.attn1.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.47.attn1.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.47.attn1.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.47.attn1.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.47.attn1.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.47.audio_norm1", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.47.audio_attn1", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.47.audio_attn1.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.47.audio_attn1.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.47.audio_attn1.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.47.audio_attn1.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.47.audio_attn1.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.47.audio_attn1.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.47.audio_attn1.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.47.audio_attn1.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.47.audio_attn1.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.47.norm2", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.47.attn2", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.47.attn2.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.47.attn2.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.47.attn2.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.47.attn2.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.47.attn2.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.47.attn2.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.47.attn2.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.47.attn2.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.47.attn2.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.47.audio_norm2", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.47.audio_attn2", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.47.audio_attn2.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.47.audio_attn2.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.47.audio_attn2.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.47.audio_attn2.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.47.audio_attn2.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.47.audio_attn2.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.47.audio_attn2.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.47.audio_attn2.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.47.audio_attn2.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.47.audio_to_video_norm", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.47.audio_to_video_attn", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.47.audio_to_video_attn.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.47.audio_to_video_attn.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.47.audio_to_video_attn.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.47.audio_to_video_attn.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.47.audio_to_video_attn.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.47.audio_to_video_attn.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.47.audio_to_video_attn.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.47.audio_to_video_attn.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.47.audio_to_video_attn.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.47.video_to_audio_norm", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.47.video_to_audio_attn", "class": "LTX2Attention", "module": "diffusers.models.transformers.transformer_ltx2" }, { "name": "transformer_blocks.47.video_to_audio_attn.norm_q", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.47.video_to_audio_attn.norm_k", "class": "RMSNorm", "module": "torch.nn.modules.normalization" }, { "name": "transformer_blocks.47.video_to_audio_attn.to_q", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.47.video_to_audio_attn.to_k", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.47.video_to_audio_attn.to_v", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.47.video_to_audio_attn.to_out", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.47.video_to_audio_attn.to_out.0", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 2048, "bias": true, "skip": false }, { "name": "transformer_blocks.47.video_to_audio_attn.to_out.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.47.video_to_audio_attn.to_gate_logits", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 32, "bias": true, "skip": false }, { "name": "transformer_blocks.47.norm3", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.47.ff", "class": "FeedForward", "module": "diffusers.models.attention" }, { "name": "transformer_blocks.47.ff.net", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.47.ff.net.0", "class": "GELU", "module": "diffusers.models.activations" }, { "name": "transformer_blocks.47.ff.net.0.proj", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 16384, "bias": true, "skip": false }, { "name": "transformer_blocks.47.ff.net.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.47.ff.net.2", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 16384, "out_features": 4096, "bias": true, "skip": false }, { "name": "transformer_blocks.47.audio_norm3", "class": "RMSNorm", "module": "diffusers.models.normalization" }, { "name": "transformer_blocks.47.audio_ff", "class": "FeedForward", "module": "diffusers.models.attention" }, { "name": "transformer_blocks.47.audio_ff.net", "class": "ModuleList", "module": "torch.nn.modules.container" }, { "name": "transformer_blocks.47.audio_ff.net.0", "class": "GELU", "module": "diffusers.models.activations" }, { "name": "transformer_blocks.47.audio_ff.net.0.proj", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 8192, "bias": true, "skip": false }, { "name": "transformer_blocks.47.audio_ff.net.1", "class": "Dropout", "module": "torch.nn.modules.dropout" }, { "name": "transformer_blocks.47.audio_ff.net.2", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 8192, "out_features": 2048, "bias": true, "skip": false }, { "name": "norm_out", "class": "LayerNorm", "module": "torch.nn.modules.normalization" }, { "name": "proj_out", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 4096, "out_features": 128, "bias": true, "skip": false }, { "name": "audio_norm_out", "class": "LayerNorm", "module": "torch.nn.modules.normalization" }, { "name": "audio_proj_out", "class": "Linear", "module": "torch.nn.modules.linear", "type": "Linear", "in_features": 2048, "out_features": 128, "bias": true, "skip": false } ]