Upload 22 files

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer/tokenizer.json filter=lfs diff=lfs merge=lfs -text

audio_vae/config.json

@@ -0,0 +1,26 @@
+{
+  "_class_name": "AutoencoderKLLTX2Audio",
+  "_diffusers_version": "0.37.0.dev0",
+  "_name_or_path": "OzzyGT/LTX2/audio_vae",
+  "attn_resolutions": null,
+  "base_channels": 128,
+  "causality_axis": "height",
+  "ch_mult": [
+    1,
+    2,
+    4
+  ],
+  "double_z": true,
+  "dropout": 0.0,
+  "in_channels": 2,
+  "is_causal": true,
+  "latent_channels": 8,
+  "mel_bins": 64,
+  "mel_hop_length": 160,
+  "mid_block_add_attention": false,
+  "norm_type": "pixel",
+  "num_res_blocks": 2,
+  "output_channels": 2,
+  "resolution": 256,
+  "sample_rate": 16000
+}

audio_vae/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b36ce4066065ce0aa5ff4d7cf96a3e3bc0859c6fefcf864663e3fe686c5c181c
+size 106507972

connectors/config.json

@@ -0,0 +1,20 @@
+{
+  "_class_name": "LTX2TextConnectors",
+  "_diffusers_version": "0.37.0.dev0",
+  "_name_or_path": "OzzyGT/LTX2/connectors",
+  "audio_connector_attention_head_dim": 128,
+  "audio_connector_num_attention_heads": 30,
+  "audio_connector_num_layers": 2,
+  "audio_connector_num_learnable_registers": 128,
+  "caption_channels": 3840,
+  "causal_temporal_positioning": false,
+  "connector_rope_base_seq_len": 4096,
+  "rope_double_precision": true,
+  "rope_theta": 10000.0,
+  "rope_type": "split",
+  "text_proj_in_factor": 49,
+  "video_connector_attention_head_dim": 128,
+  "video_connector_num_attention_heads": 30,
+  "video_connector_num_layers": 2,
+  "video_connector_num_learnable_registers": 128
+}

connectors/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7c0ad36c2d0706fb229193d5c698f0ef50c9b33678140b4ee84723a047b4032
+size 2862957976

model_index.json

@@ -0,0 +1,37 @@
+{
+  "_class_name": "LTX2Pipeline",
+  "_diffusers_version": "0.37.0.dev0",
+  "_name_or_path": "OzzyGT/LTX2",
+  "audio_vae": [
+    "diffusers",
+    "AutoencoderKLLTX2Audio"
+  ],
+  "connectors": [
+    "ltx2",
+    "LTX2TextConnectors"
+  ],
+  "scheduler": [
+    "diffusers",
+    "FlowMatchEulerDiscreteScheduler"
+  ],
+  "text_encoder": [
+    "transformers",
+    "Gemma3ForConditionalGeneration"
+  ],
+  "tokenizer": [
+    "transformers",
+    "GemmaTokenizer"
+  ],
+  "transformer": [
+    "diffusers",
+    "LTX2VideoTransformer3DModel"
+  ],
+  "vae": [
+    "diffusers",
+    "AutoencoderKLLTX2Video"
+  ],
+  "vocoder": [
+    "ltx2",
+    "LTX2Vocoder"
+  ]
+}

scheduler/scheduler_config.json

@@ -0,0 +1,18 @@
+{
+  "_class_name": "FlowMatchEulerDiscreteScheduler",
+  "_diffusers_version": "0.37.0.dev0",
+  "base_image_seq_len": 1024,
+  "base_shift": 0.95,
+  "invert_sigmas": false,
+  "max_image_seq_len": 4096,
+  "max_shift": 2.05,
+  "num_train_timesteps": 1000,
+  "shift": 1.0,
+  "shift_terminal": 0.1,
+  "stochastic_sampling": false,
+  "time_shift_type": "exponential",
+  "use_beta_sigmas": false,
+  "use_dynamic_shifting": true,
+  "use_exponential_sigmas": false,
+  "use_karras_sigmas": false
+}

text_encoder/config.json

@@ -0,0 +1,124 @@
+{
+  "architectures": [
+    "Gemma3ForConditionalGeneration"
+  ],
+  "boi_token_index": 255999,
+  "dtype": "bfloat16",
+  "eoi_token_index": 256000,
+  "eos_token_id": [
+    1,
+    106
+  ],
+  "image_token_index": 262144,
+  "initializer_range": 0.02,
+  "mm_tokens_per_image": 256,
+  "model_type": "gemma3",
+  "text_config": {
+    "_sliding_window_pattern": 6,
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "attn_logit_softcapping": null,
+    "bos_token_id": 2,
+    "cache_implementation": "hybrid",
+    "dtype": "bfloat16",
+    "eos_token_id": 1,
+    "final_logit_softcapping": null,
+    "head_dim": 256,
+    "hidden_activation": "gelu_pytorch_tanh",
+    "hidden_size": 3840,
+    "initializer_range": 0.02,
+    "intermediate_size": 15360,
+    "layer_types": [
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention"
+    ],
+    "max_position_embeddings": 131072,
+    "model_type": "gemma3_text",
+    "num_attention_heads": 16,
+    "num_hidden_layers": 48,
+    "num_key_value_heads": 8,
+    "pad_token_id": 0,
+    "query_pre_attn_scalar": 256,
+    "rms_norm_eps": 1e-06,
+    "rope_parameters": {
+      "full_attention": {
+        "factor": 8.0,
+        "rope_theta": 1000000,
+        "rope_type": "linear"
+      },
+      "sliding_attention": {
+        "rope_theta": 10000,
+        "rope_type": "default"
+      }
+    },
+    "sliding_window": 1024,
+    "sliding_window_pattern": 6,
+    "tie_word_embeddings": true,
+    "use_bidirectional_attention": false,
+    "use_cache": true,
+    "vocab_size": 262208
+  },
+  "tie_word_embeddings": true,
+  "transformers_version": "5.1.0",
+  "vision_config": {
+    "attention_dropout": 0.0,
+    "dtype": "bfloat16",
+    "hidden_act": "gelu_pytorch_tanh",
+    "hidden_size": 1152,
+    "image_size": 896,
+    "intermediate_size": 4304,
+    "layer_norm_eps": 1e-06,
+    "model_type": "siglip_vision_model",
+    "num_attention_heads": 16,
+    "num_channels": 3,
+    "num_hidden_layers": 27,
+    "patch_size": 14,
+    "vision_use_head": false
+  }
+}

text_encoder/generation_config.json

@@ -0,0 +1,11 @@
+{
+  "cache_implementation": "hybrid",
+  "do_sample": true,
+  "eos_token_id": [
+    1,
+    106
+  ],
+  "top_k": 64,
+  "top_p": 0.95,
+  "transformers_version": "5.1.0"
+}

text_encoder/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27b5c4675ac66237bb7f5554a0376679e55c006e30b261143ae2903cf00e846c
+size 24374794824

tokenizer/chat_template.jinja

@@ -0,0 +1,47 @@
+{{ bos_token }}
+{%- if messages[0]['role'] == 'system' -%}
+    {%- if messages[0]['content'] is string -%}
+        {%- set first_user_prefix = messages[0]['content'] + '
+
+' -%}
+    {%- else -%}
+        {%- set first_user_prefix = messages[0]['content'][0]['text'] + '
+
+' -%}
+    {%- endif -%}
+    {%- set loop_messages = messages[1:] -%}
+{%- else -%}
+    {%- set first_user_prefix = "" -%}
+    {%- set loop_messages = messages -%}
+{%- endif -%}
+{%- for message in loop_messages -%}
+    {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) -%}
+        {{ raise_exception("Conversation roles must alternate user/assistant/user/assistant/...") }}
+    {%- endif -%}
+    {%- if (message['role'] == 'assistant') -%}
+        {%- set role = "model" -%}
+    {%- else -%}
+        {%- set role = message['role'] -%}
+    {%- endif -%}
+    {{ '<start_of_turn>' + role + '
+' + (first_user_prefix if loop.first else "") }}
+    {%- if message['content'] is string -%}
+        {{ message['content'] | trim }}
+    {%- elif message['content'] is iterable -%}
+        {%- for item in message['content'] -%}
+            {%- if item['type'] == 'image' -%}
+                {{ '<start_of_image>' }}
+            {%- elif item['type'] == 'text' -%}
+                {{ item['text'] | trim }}
+            {%- endif -%}
+        {%- endfor -%}
+    {%- else -%}
+        {{ raise_exception("Invalid content type") }}
+    {%- endif -%}
+    {{ '<end_of_turn>
+' }}
+{%- endfor -%}
+{%- if add_generation_prompt -%}
+    {{'<start_of_turn>model
+'}}
+{%- endif -%}

tokenizer/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a74aefb1dc1340a25f29ab8370384b9ed24b2d921d7749ece7bbcfcfdf00d497
+size 33384443

tokenizer/tokenizer_config.json

@@ -0,0 +1,24 @@
+{
+  "backend": "tokenizers",
+  "boi_token": "<start_of_image>",
+  "bos_token": "<bos>",
+  "clean_up_tokenization_spaces": false,
+  "eoi_token": "<end_of_image>",
+  "eos_token": "<eos>",
+  "image_token": "<image_soft_token>",
+  "is_local": true,
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "model_specific_special_tokens": {
+    "boi_token": "<start_of_image>",
+    "eoi_token": "<end_of_image>",
+    "image_token": "<image_soft_token>"
+  },
+  "pad_token": "<pad>",
+  "processor_class": "Gemma3Processor",
+  "sp_model_kwargs": null,
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "GemmaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

transformer/config.json

@@ -0,0 +1,45 @@
+{
+  "_class_name": "LTX2VideoTransformer3DModel",
+  "_diffusers_version": "0.37.0.dev0",
+  "_name_or_path": "OzzyGT/LTX2/transformer",
+  "activation_fn": "gelu-approximate",
+  "attention_bias": true,
+  "attention_head_dim": 128,
+  "attention_out_bias": true,
+  "audio_attention_head_dim": 64,
+  "audio_cross_attention_dim": 2048,
+  "audio_hop_length": 160,
+  "audio_in_channels": 128,
+  "audio_num_attention_heads": 32,
+  "audio_out_channels": 128,
+  "audio_patch_size": 1,
+  "audio_patch_size_t": 1,
+  "audio_pos_embed_max_pos": 20,
+  "audio_sampling_rate": 16000,
+  "audio_scale_factor": 4,
+  "base_height": 2048,
+  "base_width": 2048,
+  "caption_channels": 3840,
+  "causal_offset": 1,
+  "cross_attention_dim": 4096,
+  "cross_attn_timestep_scale_multiplier": 1000,
+  "in_channels": 128,
+  "norm_elementwise_affine": false,
+  "norm_eps": 1e-06,
+  "num_attention_heads": 32,
+  "num_layers": 48,
+  "out_channels": 128,
+  "patch_size": 1,
+  "patch_size_t": 1,
+  "pos_embed_max_pos": 20,
+  "qk_norm": "rms_norm_across_heads",
+  "rope_double_precision": true,
+  "rope_theta": 10000.0,
+  "rope_type": "split",
+  "timestep_scale_multiplier": 1000,
+  "vae_scale_factors": [
+    8,
+    32,
+    32
+  ]
+}

transformer/diffusion_pytorch_model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f65208cd730e331e41fba0c192c75648abac829acb0ee09836b82d236cfb50c3
+size 9987228592

transformer/diffusion_pytorch_model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b36fd2d768598d0c4254df3443c98b4dc6f26aecf28d54b263e170baa1652808
+size 9970780296

transformer/diffusion_pytorch_model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0545c00e6712f63b0471d21e92173469cf579fd2f7e44bf003362f86c6c6053f
+size 9870256976

transformer/diffusion_pytorch_model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93679f2340293ef8d717b9db7a95f951da84047642ce029f386ee2b563226740
+size 7924509816

vae/config.json

@@ -0,0 +1,82 @@
+{
+  "_class_name": "AutoencoderKLLTX2Video",
+  "_diffusers_version": "0.37.0.dev0",
+  "_name_or_path": "OzzyGT/LTX2/vae",
+  "block_out_channels": [
+    256,
+    512,
+    1024,
+    2048
+  ],
+  "decoder_block_out_channels": [
+    256,
+    512,
+    1024
+  ],
+  "decoder_causal": false,
+  "decoder_inject_noise": [
+    false,
+    false,
+    false,
+    false
+  ],
+  "decoder_layers_per_block": [
+    5,
+    5,
+    5,
+    5
+  ],
+  "decoder_spatial_padding_mode": "reflect",
+  "decoder_spatio_temporal_scaling": [
+    true,
+    true,
+    true
+  ],
+  "down_block_types": [
+    "LTX2VideoDownBlock3D",
+    "LTX2VideoDownBlock3D",
+    "LTX2VideoDownBlock3D",
+    "LTX2VideoDownBlock3D"
+  ],
+  "downsample_type": [
+    "spatial",
+    "temporal",
+    "spatiotemporal",
+    "spatiotemporal"
+  ],
+  "encoder_causal": true,
+  "encoder_spatial_padding_mode": "zeros",
+  "in_channels": 3,
+  "latent_channels": 128,
+  "layers_per_block": [
+    4,
+    6,
+    6,
+    2,
+    2
+  ],
+  "out_channels": 3,
+  "patch_size": 4,
+  "patch_size_t": 1,
+  "resnet_norm_eps": 1e-06,
+  "scaling_factor": 1.0,
+  "spatial_compression_ratio": 32,
+  "spatio_temporal_scaling": [
+    true,
+    true,
+    true,
+    true
+  ],
+  "temporal_compression_ratio": 8,
+  "timestep_conditioning": false,
+  "upsample_factor": [
+    2,
+    2,
+    2
+  ],
+  "upsample_residual": [
+    true,
+    true,
+    true
+  ]
+}

vae/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:107cc359e3c4bce18c53d98686f4b3fe10c4207b6665d89b38b0741270514bfb
+size 2444982370

vocoder/config.json

@@ -0,0 +1,46 @@
+{
+  "_class_name": "LTX2Vocoder",
+  "_diffusers_version": "0.37.0.dev0",
+  "_name_or_path": "OzzyGT/LTX2/vocoder",
+  "hidden_channels": 1024,
+  "in_channels": 128,
+  "leaky_relu_negative_slope": 0.1,
+  "out_channels": 2,
+  "output_sampling_rate": 24000,
+  "resnet_dilations": [
+    [
+      1,
+      3,
+      5
+    ],
+    [
+      1,
+      3,
+      5
+    ],
+    [
+      1,
+      3,
+      5
+    ]
+  ],
+  "resnet_kernel_sizes": [
+    3,
+    7,
+    11
+  ],
+  "upsample_factors": [
+    6,
+    5,
+    2,
+    2,
+    2
+  ],
+  "upsample_kernel_sizes": [
+    16,
+    15,
+    8,
+    4,
+    4
+  ]
+}

vocoder/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15855fc59233b9cac50bdd1f0d2ccea4a5eaedbd7fd7549b16d5ebd6cc47d92a
+size 111204124