Add tiny Echo modular pipeline fixture

.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 +1,25 @@
+{
+  "_class_name": "AutoencoderKLLTX2Audio",
+  "_diffusers_version": "0.41.0.dev0",
+  "attn_resolutions": null,
+  "base_channels": 4,
+  "causality_axis": "height",
+  "ch_mult": [
+    1,
+    1,
+    1
+  ],
+  "double_z": true,
+  "dropout": 0.0,
+  "in_channels": 2,
+  "is_causal": true,
+  "latent_channels": 2,
+  "mel_bins": 8,
+  "mel_hop_length": 160,
+  "mid_block_add_attention": false,
+  "norm_type": "pixel",
+  "num_res_blocks": 1,
+  "output_channels": 2,
+  "resolution": 32,
+  "sample_rate": 16000
+}

audio_vae/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b72b3c9f27b83ded97b8e121fc900165297bcc9a49a958c5d82d9bcda22f9a08
+size 26112

connectors/config.json

@@ -0,0 +1,25 @@
+{
+  "_class_name": "LTX2TextConnectors",
+  "_diffusers_version": "0.41.0.dev0",
+  "audio_connector_attention_head_dim": 4,
+  "audio_connector_num_attention_heads": 2,
+  "audio_connector_num_layers": 1,
+  "audio_connector_num_learnable_registers": null,
+  "audio_gated_attn": false,
+  "audio_hidden_dim": 8,
+  "caption_channels": 16,
+  "causal_temporal_positioning": false,
+  "connector_rope_base_seq_len": 32,
+  "per_modality_projections": true,
+  "proj_bias": false,
+  "rope_double_precision": false,
+  "rope_theta": 10000.0,
+  "rope_type": "split",
+  "text_proj_in_factor": 3,
+  "video_connector_attention_head_dim": 8,
+  "video_connector_num_attention_heads": 2,
+  "video_connector_num_layers": 1,
+  "video_connector_num_learnable_registers": null,
+  "video_gated_attn": false,
+  "video_hidden_dim": 16
+}

connectors/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c8fe14a9e80090ab4e1c44fd1af6af833590f1ace569db83963a9938e173ad9
+size 24408

modular_model_index.json

@@ -0,0 +1,103 @@
+{
+  "_blocks_class_name": "EchoBlocks",
+  "_class_name": "EchoModularPipeline",
+  "_diffusers_version": "0.41.0.dev0",
+  "audio_vae": [
+    "diffusers",
+    "AutoencoderKLLTX2Audio",
+    {
+      "pretrained_model_name_or_path": "Echo-Team/tiny-echo-modular-pipe",
+      "revision": null,
+      "subfolder": "audio_vae",
+      "type_hint": [
+        "diffusers",
+        "AutoencoderKLLTX2Audio"
+      ],
+      "variant": null
+    }
+  ],
+  "connectors": [
+    "ltx2",
+    "LTX2TextConnectors",
+    {
+      "pretrained_model_name_or_path": "Echo-Team/tiny-echo-modular-pipe",
+      "revision": null,
+      "subfolder": "connectors",
+      "type_hint": [
+        "ltx2",
+        "LTX2TextConnectors"
+      ],
+      "variant": null
+    }
+  ],
+  "text_encoder": [
+    "transformers",
+    "Gemma3ForConditionalGeneration",
+    {
+      "pretrained_model_name_or_path": "Echo-Team/tiny-echo-modular-pipe",
+      "revision": null,
+      "subfolder": "text_encoder",
+      "type_hint": [
+        "transformers",
+        "Gemma3ForConditionalGeneration"
+      ],
+      "variant": null
+    }
+  ],
+  "tokenizer": [
+    "transformers",
+    "GemmaTokenizer",
+    {
+      "pretrained_model_name_or_path": "Echo-Team/tiny-echo-modular-pipe",
+      "revision": null,
+      "subfolder": "tokenizer",
+      "type_hint": [
+        "transformers",
+        "GemmaTokenizer"
+      ],
+      "variant": null
+    }
+  ],
+  "transformer": [
+    "diffusers",
+    "LTX2VideoTransformer3DModel",
+    {
+      "pretrained_model_name_or_path": "Echo-Team/tiny-echo-modular-pipe",
+      "revision": null,
+      "subfolder": "transformer",
+      "type_hint": [
+        "diffusers",
+        "LTX2VideoTransformer3DModel"
+      ],
+      "variant": null
+    }
+  ],
+  "vae": [
+    "diffusers",
+    "AutoencoderKLLTX2Video",
+    {
+      "pretrained_model_name_or_path": "Echo-Team/tiny-echo-modular-pipe",
+      "revision": null,
+      "subfolder": "vae",
+      "type_hint": [
+        "diffusers",
+        "AutoencoderKLLTX2Video"
+      ],
+      "variant": null
+    }
+  ],
+  "vocoder": [
+    "ltx2",
+    "LTX2Vocoder",
+    {
+      "pretrained_model_name_or_path": "Echo-Team/tiny-echo-modular-pipe",
+      "revision": null,
+      "subfolder": "vocoder",
+      "type_hint": [
+        "ltx2",
+        "LTX2Vocoder"
+      ],
+      "variant": null
+    }
+  ]
+}

text_encoder/config.json

@@ -0,0 +1,68 @@
+{
+  "architectures": [
+    "Gemma3ForConditionalGeneration"
+  ],
+  "boi_token_index": 255999,
+  "dtype": "float32",
+  "eoi_token_index": 256000,
+  "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,
+    "eos_token_id": 1,
+    "final_logit_softcapping": null,
+    "head_dim": 8,
+    "hidden_activation": "gelu_pytorch_tanh",
+    "hidden_size": 16,
+    "initializer_range": 0.02,
+    "intermediate_size": 32,
+    "layer_types": [
+      "sliding_attention",
+      "full_attention"
+    ],
+    "max_position_embeddings": 128,
+    "model_type": "gemma3_text",
+    "num_attention_heads": 2,
+    "num_hidden_layers": 2,
+    "num_key_value_heads": 1,
+    "pad_token_id": 0,
+    "query_pre_attn_scalar": 256,
+    "rms_norm_eps": 1e-06,
+    "rope_parameters": {
+      "full_attention": {
+        "rope_theta": 1000000.0,
+        "rope_type": "default"
+      },
+      "sliding_attention": {
+        "rope_theta": 10000.0,
+        "rope_type": "default"
+      }
+    },
+    "sliding_window": 32,
+    "tie_word_embeddings": true,
+    "use_bidirectional_attention": false,
+    "use_cache": true,
+    "vocab_size": 262145
+  },
+  "tie_word_embeddings": true,
+  "transformers_version": "5.16.1",
+  "vision_config": {
+    "attention_dropout": 0.0,
+    "hidden_act": "gelu_pytorch_tanh",
+    "hidden_size": 16,
+    "image_size": 16,
+    "intermediate_size": 32,
+    "layer_norm_eps": 1e-06,
+    "model_type": "siglip_vision_model",
+    "num_attention_heads": 2,
+    "num_channels": 3,
+    "num_hidden_layers": 1,
+    "patch_size": 8
+  }
+}

text_encoder/generation_config.json

@@ -0,0 +1,10 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 2,
+  "eos_token_id": 1,
+  "output_attentions": false,
+  "output_hidden_states": false,
+  "pad_token_id": 0,
+  "transformers_version": "5.16.1",
+  "use_cache": true
+}

text_encoder/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1db472bab3ced27b0415be199bb108f5c489e765afb9bb6db59309825d9b4147
+size 16835184

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:daab2354f8a74e70d70b4d1f804939b68a8c9624dd06cb7858e52dd8970e9726
+size 33384567

tokenizer/tokenizer_config.json

@@ -0,0 +1,25 @@
+{
+  "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,
+  "local_files_only": 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 +1,54 @@
+{
+  "_class_name": "LTX2VideoTransformer3DModel",
+  "_diffusers_version": "0.41.0.dev0",
+  "activation_fn": "gelu-approximate",
+  "attention_bias": true,
+  "attention_head_dim": 8,
+  "attention_out_bias": true,
+  "audio_attention_head_dim": 4,
+  "audio_cross_attention_dim": 8,
+  "audio_cross_attn_mod": true,
+  "audio_ff_bias": true,
+  "audio_gated_attn": true,
+  "audio_hop_length": 160,
+  "audio_in_channels": 4,
+  "audio_num_attention_heads": 2,
+  "audio_out_channels": 4,
+  "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": 16,
+  "causal_offset": 1,
+  "cross_attention_dim": 16,
+  "cross_attn_mod": true,
+  "cross_attn_timestep_scale_multiplier": 1000,
+  "ff_bias": true,
+  "gated_attn": true,
+  "in_channels": 4,
+  "norm_elementwise_affine": false,
+  "norm_eps": 1e-06,
+  "num_attention_heads": 2,
+  "num_layers": 2,
+  "out_channels": 4,
+  "patch_size": 1,
+  "patch_size_t": 1,
+  "perturbed_attn": false,
+  "pos_embed_max_pos": 20,
+  "qk_norm": "rms_norm_across_heads",
+  "rope_double_precision": false,
+  "rope_theta": 10000.0,
+  "rope_type": "split",
+  "timestep_scale_multiplier": 1000,
+  "use_keyframes_abs_pos_embedding": false,
+  "use_prompt_adaln_single": true,
+  "use_prompt_embeddings": false,
+  "vae_scale_factors": [
+    8,
+    32,
+    32
+  ]
+}

transformer/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e636399e51c83b8a8d6706177a252a475de5c3ab85faa368777f178656336969
+size 207896

vae/config.json

@@ -0,0 +1,61 @@
+{
+  "_class_name": "AutoencoderKLLTX2Video",
+  "_diffusers_version": "0.41.0.dev0",
+  "block_out_channels": [
+    8
+  ],
+  "decoder_block_out_channels": [
+    8
+  ],
+  "decoder_causal": false,
+  "decoder_inject_noise": [
+    false,
+    false
+  ],
+  "decoder_layers_per_block": [
+    1,
+    1
+  ],
+  "decoder_spatial_padding_mode": "reflect",
+  "decoder_spatio_temporal_scaling": [
+    true
+  ],
+  "down_block_types": [
+    "LTX2VideoDownBlock3D",
+    "LTX2VideoDownBlock3D",
+    "LTX2VideoDownBlock3D",
+    "LTX2VideoDownBlock3D"
+  ],
+  "downsample_type": [
+    "spatial"
+  ],
+  "encoder_causal": true,
+  "encoder_spatial_padding_mode": "zeros",
+  "in_channels": 3,
+  "latent_channels": 4,
+  "layers_per_block": [
+    1
+  ],
+  "out_channels": 3,
+  "patch_size": 1,
+  "patch_size_t": 1,
+  "resnet_norm_eps": 1e-06,
+  "scaling_factor": 1.0,
+  "spatial_compression_ratio": null,
+  "spatio_temporal_scaling": [
+    true
+  ],
+  "temporal_compression_ratio": null,
+  "timestep_conditioning": false,
+  "upsample_factor": [
+    1
+  ],
+  "upsample_residual": [
+    false
+  ],
+  "upsample_type": [
+    "spatiotemporal",
+    "spatiotemporal",
+    "spatiotemporal"
+  ]
+}

vae/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:056241bb4b8a029713f5f71bbe3c5f904cdea378fab80ecbb2a8e7e9035140c8
+size 116464

vocoder/config.json

@@ -0,0 +1,33 @@
+{
+  "_class_name": "LTX2Vocoder",
+  "_diffusers_version": "0.41.0.dev0",
+  "act_fn": "leaky_relu",
+  "antialias": false,
+  "antialias_kernel_size": 12,
+  "antialias_ratio": 2,
+  "final_act_fn": "tanh",
+  "final_bias": true,
+  "hidden_channels": 32,
+  "in_channels": 16,
+  "leaky_relu_negative_slope": 0.1,
+  "out_channels": 2,
+  "output_sampling_rate": 16000,
+  "resnet_dilations": [
+    [
+      1,
+      3,
+      5
+    ]
+  ],
+  "resnet_kernel_sizes": [
+    3
+  ],
+  "upsample_factors": [
+    2,
+    2
+  ],
+  "upsample_kernel_sizes": [
+    4,
+    4
+  ]
+}

vocoder/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be58882aaf71ba653bb607eb160f025c3526a85b589770836a1169b513cfbb94
+size 51616