Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,5 @@ 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
+text_encoder/gemma/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+tokenizer/tokenizer.json filter=lfs diff=lfs merge=lfs -text

audio_vae/config.json

@@ -0,0 +1,51 @@
+{
+  "audio_vae": {
+    "model": {
+      "params": {
+        "ddconfig": {
+          "double_z": true,
+          "mel_bins": 64,
+          "z_channels": 8,
+          "resolution": 256,
+          "downsample_time": false,
+          "in_channels": 2,
+          "out_ch": 2,
+          "ch": 128,
+          "ch_mult": [
+            1,
+            2,
+            4
+          ],
+          "num_res_blocks": 2,
+          "attn_resolutions": [],
+          "dropout": 0.0,
+          "mid_block_add_attention": false,
+          "norm_type": "pixel",
+          "causality_axis": "height"
+        },
+        "sampling_rate": 16000
+      }
+    },
+    "preprocessing": {
+      "audio": {
+        "sampling_rate": 16000,
+        "max_wav_value": 32768.0,
+        "duration": 5.12,
+        "stereo": true,
+        "causal_padding": 3
+      },
+      "stft": {
+        "filter_length": 1024,
+        "hop_length": 160,
+        "win_length": 1024,
+        "causal": true
+      },
+      "mel": {
+        "n_mel_channels": 64,
+        "mel_fmin": 0,
+        "mel_fmax": 8000
+      }
+    }
+  },
+  "_class_name": "LTX2AudioDecoder"
+}

audio_vae/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f86f566ac1f384e145798a609ffeebe3cf4e272c45ea915e525cde4abd10d1e
+size 106507988

model_index.json

@@ -0,0 +1,28 @@
+{
+  "_class_name": "LTX2Pipeline",
+  "_diffusers_version": "0.33.0.dev0",
+  "transformer": [
+    "diffusers",
+    "LTX2Transformer3DModel"
+  ],
+  "vae": [
+    "diffusers",
+    "CausalVideoAutoencoder"
+  ],
+  "text_encoder": [
+    "transformers",
+    "LTX2GemmaTextEncoderModel"
+  ],
+  "tokenizer": [
+    "transformers",
+    "AutoTokenizer"
+  ],
+  "audio_vae": [
+    "diffusers",
+    "LTX2AudioDecoder"
+  ],
+  "vocoder": [
+    "diffusers",
+    "LTX2Vocoder"
+  ]
+}

spatial_upscaler/config.json

@@ -0,0 +1,9 @@
+{
+  "_class_name": "LTX2LatentUpsampler",
+  "in_channels": 128,
+  "mid_channels": 1024,
+  "num_blocks_per_stage": 4,
+  "dims": 3,
+  "spatial_upsample": true,
+  "temporal_upsample": false
+}

spatial_upscaler/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c07f97ea335a2cd28402e85194227716eca760e99331d6529d160c3199a425f0
+size 995743288

spatial_upscaler_x1_5/config.json

@@ -0,0 +1,11 @@
+{
+  "_class_name": "LTX2LatentUpsampler",
+  "in_channels": 128,
+  "mid_channels": 1024,
+  "num_blocks_per_stage": 4,
+  "dims": 3,
+  "spatial_upsample": true,
+  "temporal_upsample": false,
+  "spatial_scale": 1.5,
+  "rational_resampler": true
+}

spatial_upscaler_x1_5/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a0b96bc5b4dbc5d28859896c1b8f239bb9cb186a9b71cc2106af21b7a845f28
+size 1090125530

text_embedding_projection/config.json

@@ -0,0 +1,36 @@
+{
+  "architectures": [
+    "LTX2GemmaTextEncoderModel"
+  ],
+  "hidden_size": 3840,
+  "num_hidden_layers": 48,
+  "num_attention_heads": 30,
+  "text_len": 1024,
+  "pad_token_id": 0,
+  "eos_token_id": 2,
+  "gemma_model_path": "gemma",
+  "gemma_dtype": "bfloat16",
+  "padding_side": "left",
+  "feature_extractor_in_features": 188160,
+  "feature_extractor_out_features": 3840,
+  "connector_num_attention_heads": 32,
+  "connector_attention_head_dim": 128,
+  "connector_num_layers": 8,
+  "connector_positional_embedding_theta": 10000.0,
+  "connector_positional_embedding_max_pos": [
+    4096
+  ],
+  "connector_rope_type": "split",
+  "connector_double_precision_rope": true,
+  "connector_num_learnable_registers": 128,
+  "caption_proj_before_connector": true,
+  "caption_projection_first_linear": false,
+  "caption_proj_input_norm": false,
+  "caption_projection_second_linear": false,
+  "audio_connector_num_attention_heads": 32,
+  "audio_connector_attention_head_dim": 64,
+  "audio_connector_num_layers": 8,
+  "connector_apply_gated_attention": true,
+  "video_feature_extractor_out_features": 4096,
+  "audio_feature_extractor_out_features": 2048
+}

text_embedding_projection/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6ed4ecd1b84eb8de2918724fd80fa7166c3eb5395ff06217614485d6243a096
+size 6344492152

text_encoder/config.json

@@ -0,0 +1,36 @@
+{
+  "architectures": [
+    "LTX2GemmaTextEncoderModel"
+  ],
+  "hidden_size": 3840,
+  "num_hidden_layers": 48,
+  "num_attention_heads": 30,
+  "text_len": 1024,
+  "pad_token_id": 0,
+  "eos_token_id": 2,
+  "gemma_model_path": "gemma",
+  "gemma_dtype": "bfloat16",
+  "padding_side": "left",
+  "feature_extractor_in_features": 188160,
+  "feature_extractor_out_features": 3840,
+  "connector_num_attention_heads": 32,
+  "connector_attention_head_dim": 128,
+  "connector_num_layers": 8,
+  "connector_positional_embedding_theta": 10000.0,
+  "connector_positional_embedding_max_pos": [
+    4096
+  ],
+  "connector_rope_type": "split",
+  "connector_double_precision_rope": true,
+  "connector_num_learnable_registers": 128,
+  "caption_proj_before_connector": true,
+  "caption_projection_first_linear": false,
+  "caption_proj_input_norm": false,
+  "caption_projection_second_linear": false,
+  "audio_connector_num_attention_heads": 32,
+  "audio_connector_attention_head_dim": 64,
+  "audio_connector_num_layers": 8,
+  "connector_apply_gated_attention": true,
+  "video_feature_extractor_out_features": 4096,
+  "audio_feature_extractor_out_features": 2048
+}

text_encoder/gemma/added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<image_soft_token>": 262144
+}

text_encoder/gemma/chat_template.json

@@ -0,0 +1,3 @@
+{
+  "chat_template": "{{ bos_token }}\n{%- if messages[0]['role'] == 'system' -%}\n    {%- if messages[0]['content'] is string -%}\n        {%- set first_user_prefix = messages[0]['content'] + '\n\n' -%}\n    {%- else -%}\n        {%- set first_user_prefix = messages[0]['content'][0]['text'] + '\n\n' -%}\n    {%- endif -%}\n    {%- set loop_messages = messages[1:] -%}\n{%- else -%}\n    {%- set first_user_prefix = \"\" -%}\n    {%- set loop_messages = messages -%}\n{%- endif -%}\n{%- for message in loop_messages -%}\n    {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) -%}\n        {{ raise_exception(\"Conversation roles must alternate user/assistant/user/assistant/...\") }}\n    {%- endif -%}\n    {%- if (message['role'] == 'assistant') -%}\n        {%- set role = \"model\" -%}\n    {%- else -%}\n        {%- set role = message['role'] -%}\n    {%- endif -%}\n    {{ '<start_of_turn>' + role + '\n' + (first_user_prefix if loop.first else \"\") }}\n    {%- if message['content'] is string -%}\n        {{ message['content'] | trim }}\n    {%- elif message['content'] is iterable -%}\n        {%- for item in message['content'] -%}\n            {%- if item['type'] == 'image' -%}\n                {{ '<start_of_image>' }}\n            {%- elif item['type'] == 'text' -%}\n                {{ item['text'] | trim }}\n            {%- endif -%}\n        {%- endfor -%}\n    {%- else -%}\n        {{ raise_exception(\"Invalid content type\") }}\n    {%- endif -%}\n    {{ '<end_of_turn>\n' }}\n{%- endfor -%}\n{%- if add_generation_prompt -%}\n    {{'<start_of_turn>model\n'}}\n{%- endif -%}\n"
+}

text_encoder/gemma/config.json

@@ -0,0 +1,40 @@
+{
+  "architectures": [
+    "Gemma3ForConditionalGeneration"
+  ],
+  "boi_token_index": 255999,
+  "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": {
+    "hidden_size": 3840,
+    "intermediate_size": 15360,
+    "model_type": "gemma3_text",
+    "num_attention_heads": 16,
+    "num_hidden_layers": 48,
+    "num_key_value_heads": 8,
+    "rope_scaling": {
+      "factor": 8.0,
+      "rope_type": "linear"
+    },
+    "sliding_window": 1024
+  },
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.50.0.dev0",
+  "vision_config": {
+    "hidden_size": 1152,
+    "image_size": 896,
+    "intermediate_size": 4304,
+    "model_type": "siglip_vision_model",
+    "num_attention_heads": 16,
+    "num_hidden_layers": 27,
+    "patch_size": 14,
+    "vision_use_head": false
+  }
+}

text_encoder/gemma/generation_config.json

@@ -0,0 +1,13 @@
+{
+  "bos_token_id": 2,
+  "cache_implementation": "hybrid",
+  "do_sample": true,
+  "eos_token_id": [
+    1,
+    106
+  ],
+  "pad_token_id": 0,
+  "top_k": 64,
+  "top_p": 0.95,
+  "transformers_version": "4.50.0.dev0"
+}

text_encoder/gemma/model-00001-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3303fcf94ebcf8fbf51b90169cbf88f4804b52ab4555b41745cb42f8cdca1528
+size 4979902192

text_encoder/gemma/model-00002-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d19daf93e52cc163648f0ee5cb7fde6feacf19c4fbbadce719d24fa369431e1
+size 4931296592

text_encoder/gemma/model-00003-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3016ef32217aa3c30c99151f1ae3ad255114eb89942a393b6d8f80cda9e19c3
+size 4931296656

text_encoder/gemma/model-00004-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44c051b29b34ffe0c9dfef895b205d0571f42a5783af5f1dea68c134f5a60b78
+size 4931296656

text_encoder/gemma/model-00005-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9935bbf0307208b3f925df4265d7366fb70b0d08c371a177967b74e243329350
+size 4601000928

text_encoder/gemma/preprocessor_config.json

@@ -0,0 +1,29 @@
+{
+  "do_convert_rgb": null,
+  "do_normalize": true,
+  "do_pan_and_scan": null,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "Gemma3ImageProcessor",
+  "image_seq_length": 256,
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "pan_and_scan_max_num_crops": null,
+  "pan_and_scan_min_crop_size": null,
+  "pan_and_scan_min_ratio_to_activate": null,
+  "processor_class": "Gemma3Processor",
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 896,
+    "width": 896
+  }
+}

text_encoder/gemma/processor_config.json

@@ -0,0 +1,4 @@
+{
+  "image_seq_length": 256,
+  "processor_class": "Gemma3Processor"
+}

text_encoder/gemma/special_tokens_map.json

@@ -0,0 +1,33 @@
+{
+  "boi_token": "<start_of_image>",
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eoi_token": "<end_of_image>",
+  "eos_token": {
+    "content": "<eos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "image_token": "<image_soft_token>",
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

text_encoder/gemma/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4667f2089529e8e7657cfb6d1c19910ae71ff5f28aa7ab2ff2763330affad795
+size 33384568

text_encoder/gemma/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1299c11d7cf632ef3b4e11937501358ada021bbdf7c47638d13c0ee982f2e79c
+size 4689074

text_encoder/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6ed4ecd1b84eb8de2918724fd80fa7166c3eb5395ff06217614485d6243a096
+size 6344492152

tokenizer/added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<image_soft_token>": 262144
+}

tokenizer/chat_template.json

@@ -0,0 +1,3 @@
+{
+  "chat_template": "{{ bos_token }}\n{%- if messages[0]['role'] == 'system' -%}\n    {%- if messages[0]['content'] is string -%}\n        {%- set first_user_prefix = messages[0]['content'] + '\n\n' -%}\n    {%- else -%}\n        {%- set first_user_prefix = messages[0]['content'][0]['text'] + '\n\n' -%}\n    {%- endif -%}\n    {%- set loop_messages = messages[1:] -%}\n{%- else -%}\n    {%- set first_user_prefix = \"\" -%}\n    {%- set loop_messages = messages -%}\n{%- endif -%}\n{%- for message in loop_messages -%}\n    {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) -%}\n        {{ raise_exception(\"Conversation roles must alternate user/assistant/user/assistant/...\") }}\n    {%- endif -%}\n    {%- if (message['role'] == 'assistant') -%}\n        {%- set role = \"model\" -%}\n    {%- else -%}\n        {%- set role = message['role'] -%}\n    {%- endif -%}\n    {{ '<start_of_turn>' + role + '\n' + (first_user_prefix if loop.first else \"\") }}\n    {%- if message['content'] is string -%}\n        {{ message['content'] | trim }}\n    {%- elif message['content'] is iterable -%}\n        {%- for item in message['content'] -%}\n            {%- if item['type'] == 'image' -%}\n                {{ '<start_of_image>' }}\n            {%- elif item['type'] == 'text' -%}\n                {{ item['text'] | trim }}\n            {%- endif -%}\n        {%- endfor -%}\n    {%- else -%}\n        {{ raise_exception(\"Invalid content type\") }}\n    {%- endif -%}\n    {{ '<end_of_turn>\n' }}\n{%- endfor -%}\n{%- if add_generation_prompt -%}\n    {{'<start_of_turn>model\n'}}\n{%- endif -%}\n"
+}

tokenizer/preprocessor_config.json

@@ -0,0 +1,29 @@
+{
+  "do_convert_rgb": null,
+  "do_normalize": true,
+  "do_pan_and_scan": null,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "Gemma3ImageProcessor",
+  "image_seq_length": 256,
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "pan_and_scan_max_num_crops": null,
+  "pan_and_scan_min_crop_size": null,
+  "pan_and_scan_min_ratio_to_activate": null,
+  "processor_class": "Gemma3Processor",
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 896,
+    "width": 896
+  }
+}

tokenizer/processor_config.json

@@ -0,0 +1,4 @@
+{
+  "image_seq_length": 256,
+  "processor_class": "Gemma3Processor"
+}

tokenizer/special_tokens_map.json

@@ -0,0 +1,33 @@
+{
+  "boi_token": "<start_of_image>",
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eoi_token": "<end_of_image>",
+  "eos_token": {
+    "content": "<eos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "image_token": "<image_soft_token>",
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4667f2089529e8e7657cfb6d1c19910ae71ff5f28aa7ab2ff2763330affad795
+size 33384568

tokenizer/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1299c11d7cf632ef3b4e11937501358ada021bbdf7c47638d13c0ee982f2e79c
+size 4689074

transformer/config.json

@@ -0,0 +1,41 @@
+{
+  "attention_head_dim": 128,
+  "attention_type": "default",
+  "caption_channels": 3840,
+  "cross_attention_dim": 4096,
+  "in_channels": 128,
+  "norm_eps": 1e-06,
+  "num_attention_heads": 32,
+  "num_layers": 48,
+  "out_channels": 128,
+  "positional_embedding_theta": 10000.0,
+  "positional_embedding_max_pos": [
+    20,
+    2048,
+    2048
+  ],
+  "timestep_scale_multiplier": 1000,
+  "av_ca_timestep_scale_multiplier": 1000.0,
+  "audio_num_attention_heads": 32,
+  "audio_attention_head_dim": 64,
+  "audio_out_channels": 128,
+  "audio_cross_attention_dim": 2048,
+  "audio_positional_embedding_max_pos": [
+    20
+  ],
+  "use_middle_indices_grid": true,
+  "rope_type": "split",
+  "double_precision_rope": true,
+  "_class_name": "LTX2Transformer3DModel",
+  "apply_gated_attention": true,
+  "cross_attention_adaln": true,
+  "caption_proj_before_connector": true,
+  "caption_proj_input_norm": false,
+  "caption_projection_first_linear": false,
+  "caption_projection_second_linear": false,
+  "connector_num_attention_heads": 32,
+  "connector_attention_head_dim": 128,
+  "connector_num_layers": 8,
+  "audio_connector_num_attention_heads": 32,
+  "audio_connector_attention_head_dim": 64
+}

transformer/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d67605a9a547994c7fcb04aa3fc1edcd1d23062b1c1e13dcd17ce156257d1f7
+size 37978195728

vae/config.json

@@ -0,0 +1,133 @@
+{
+  "vae": {
+    "_class_name": "CausalVideoAutoencoder",
+    "dims": 3,
+    "in_channels": 3,
+    "out_channels": 3,
+    "latent_channels": 128,
+    "encoder_blocks": [
+      [
+        "res_x",
+        {
+          "num_layers": 4
+        }
+      ],
+      [
+        "compress_space_res",
+        {
+          "multiplier": 2
+        }
+      ],
+      [
+        "res_x",
+        {
+          "num_layers": 6
+        }
+      ],
+      [
+        "compress_time_res",
+        {
+          "multiplier": 2
+        }
+      ],
+      [
+        "res_x",
+        {
+          "num_layers": 4
+        }
+      ],
+      [
+        "compress_all_res",
+        {
+          "multiplier": 2
+        }
+      ],
+      [
+        "res_x",
+        {
+          "num_layers": 2
+        }
+      ],
+      [
+        "compress_all_res",
+        {
+          "multiplier": 1
+        }
+      ],
+      [
+        "res_x",
+        {
+          "num_layers": 2
+        }
+      ]
+    ],
+    "decoder_blocks": [
+      [
+        "res_x",
+        {
+          "num_layers": 4
+        }
+      ],
+      [
+        "compress_space",
+        {
+          "multiplier": 2
+        }
+      ],
+      [
+        "res_x",
+        {
+          "num_layers": 6
+        }
+      ],
+      [
+        "compress_time",
+        {
+          "multiplier": 2
+        }
+      ],
+      [
+        "res_x",
+        {
+          "num_layers": 4
+        }
+      ],
+      [
+        "compress_all",
+        {
+          "multiplier": 1
+        }
+      ],
+      [
+        "res_x",
+        {
+          "num_layers": 2
+        }
+      ],
+      [
+        "compress_all",
+        {
+          "multiplier": 2
+        }
+      ],
+      [
+        "res_x",
+        {
+          "num_layers": 2
+        }
+      ]
+    ],
+    "scaling_factor": 1.0,
+    "norm_layer": "pixel_norm",
+    "patch_size": 4,
+    "latent_log_var": "uniform",
+    "use_quant_conv": false,
+    "causal_decoder": false,
+    "timestep_conditioning": false,
+    "normalize_latent_channels": false,
+    "encoder_base_channels": 128,
+    "decoder_base_channels": 128,
+    "spatial_padding_mode": "zeros"
+  },
+  "_class_name": "CausalVideoAutoencoder"
+}

vae/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bff48897fbad8eb5bb63db42f4e70f8a0cfa6491805947c2927eaaf13217d548
+size 1452233474

vocoder/config.json

@@ -0,0 +1,102 @@
+{
+  "vocoder": {
+    "vocoder": {
+      "upsample_initial_channel": 1536,
+      "resblock": "AMP1",
+      "upsample_rates": [
+        5,
+        2,
+        2,
+        2,
+        2,
+        2
+      ],
+      "resblock_kernel_sizes": [
+        3,
+        7,
+        11
+      ],
+      "upsample_kernel_sizes": [
+        11,
+        4,
+        4,
+        4,
+        4,
+        4
+      ],
+      "resblock_dilation_sizes": [
+        [
+          1,
+          3,
+          5
+        ],
+        [
+          1,
+          3,
+          5
+        ],
+        [
+          1,
+          3,
+          5
+        ]
+      ],
+      "stereo": true,
+      "use_tanh_at_final": false,
+      "activation": "snakebeta",
+      "use_bias_at_final": false
+    },
+    "bwe": {
+      "upsample_initial_channel": 512,
+      "resblock": "AMP1",
+      "upsample_rates": [
+        6,
+        5,
+        2,
+        2,
+        2
+      ],
+      "resblock_kernel_sizes": [
+        3,
+        7,
+        11
+      ],
+      "upsample_kernel_sizes": [
+        12,
+        11,
+        4,
+        4,
+        4
+      ],
+      "resblock_dilation_sizes": [
+        [
+          1,
+          3,
+          5
+        ],
+        [
+          1,
+          3,
+          5
+        ],
+        [
+          1,
+          3,
+          5
+        ]
+      ],
+      "stereo": true,
+      "use_tanh_at_final": false,
+      "activation": "snakebeta",
+      "use_bias_at_final": false,
+      "apply_final_activation": false,
+      "input_sampling_rate": 16000,
+      "output_sampling_rate": 48000,
+      "hop_length": 80,
+      "n_fft": 512,
+      "win_size": 512,
+      "num_mels": 64
+    }
+  },
+  "_class_name": "LTX2Vocoder"
+}

vocoder/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b64c7e94f0744ec68d04df6616bf5a8369bc20c41addb82f8ad5086fea2386f2
+size 258308856