{ "transformer": { "_class_name": "AVTransformer3DModel", "activation_fn": "gelu-approximate", "attention_bias": true, "attention_head_dim": 128, "attention_type": "default", "caption_channels": 3840, "cross_attention_dim": 4096, "double_self_attention": false, "dropout": 0.0, "in_channels": 128, "norm_elementwise_affine": false, "norm_eps": 1e-06, "norm_num_groups": 32, "num_attention_heads": 32, "num_embeds_ada_norm": 1000, "num_layers": 48, "num_vector_embeds": null, "only_cross_attention": false, "cross_attention_norm": true, "out_channels": 128, "upcast_attention": false, "use_linear_projection": false, "qk_norm": "rms_norm", "standardization_norm": "rms_norm", "positional_embedding_type": "rope", "positional_embedding_theta": 10000.0, "positional_embedding_max_pos": [ 20, 2048, 2048 ], "timestep_scale_multiplier": 1000, "av_ca_timestep_scale_multiplier": 1000.0, "causal_temporal_positioning": true, "audio_num_attention_heads": 32, "audio_attention_head_dim": 64, "use_audio_video_cross_attention": true, "ff_bias": false, "share_ff": false, "audio_out_channels": 128, "audio_cross_attention_dim": 2048, "audio_positional_embedding_max_pos": [ 20 ], "av_cross_ada_norm": true, "use_embeddings_connector": true, "connector_attention_head_dim": 128, "connector_num_attention_heads": 32, "connector_num_layers": 8, "connector_positional_embedding_max_pos": [ 4096 ], "connector_num_learnable_registers": 128, "connector_norm_output": true, "use_middle_indices_grid": true, "apply_gated_attention": true, "connector_apply_gated_attention": true, "caption_projection_first_linear": false, "caption_projection_second_linear": false, "caption_proj_input_norm": false, "connector_learnable_registers_std": 1, "caption_proj_before_connector": true, "audio_connector_attention_head_dim": 64, "audio_connector_num_attention_heads": 32, "cross_attention_adaln": true, "rope_type": "split", "frequencies_precision": "float64", "text_encoder_norm_type": "PER_TOKEN_RMS", "use_keyframes_abs_pos_embedding": true }, "scheduler": { "_class_name": "RectifiedFlowScheduler", "_diffusers_version": "0.25.1", "num_train_timesteps": 1000, "shifting": null, "base_resolution": null, "sampler": "LinearQuadratic" } }