Upload Wan22VaceModularPipeline

README.md

@@ -0,0 +1,77 @@
+---
+library_name: diffusers
+tags:
+- modular-diffusers
+- diffusers
+- wan-vace
+- text-to-image
+---
+This is a modular diffusion pipeline built with 🧨 Diffusers' modular pipeline framework.
+
+**Pipeline Type**: Wan22VaceBlocks
+
+**Description**: Modular pipeline for controllable video generation using Wan2.2 VACE.
+
+This pipeline uses a 5-block architecture that can be customized and extended.
+
+## Example Usage
+
+[TODO]
+
+## Pipeline Architecture
+
+This modular pipeline is composed of the following blocks:
+
+1. **text_encoder** (`WanTextEncoderStep`)
+   - Text Encoder step that generate text_embeddings to guide the video generation
+2. **vace_encoder** (`WanVaceEncoderStep`)
+   - Vace Encoder step that preprocesses the control video, mask and reference images and encodes them into the conditioning latents used by the VACE control branch of the transformer
+3. **denoise** (`Wan22VaceCoreDenoiseStep`)
+   - denoise block that takes encoded text and vace conditioning latents and runs the denoising process.
+4. **trim_latents** (`WanVaceTrimReferenceLatentsStep`)
+   - Step that removes the prepended reference image frames from the denoised latents before decoding
+5. **decode** (`WanVaeDecoderStep`)
+   - Step that decodes the denoised latents into images 
+
+## Model Components
+
+1. text_encoder (`UMT5EncoderModel`)
+2. tokenizer (`AutoTokenizer`)
+3. guider (`ClassifierFreeGuidance`)
+4. transformer (`WanVACETransformer3DModel`)
+5. vae (`AutoencoderKLWan`)
+6. video_processor (`VideoProcessor`)
+7. scheduler (`UniPCMultistepScheduler`)
+8. guider_2 (`ClassifierFreeGuidance`)
+9. transformer_2 (`WanVACETransformer3DModel`) 
+
+## Configuration Parameters
+
+boundary_ratio (default: 0.875): The boundary ratio to divide the denoising loop into high noise and low noise stages.
+
+## Input/Output Specification
+
+**Inputs:**
+
+- `prompt` (`None`, *optional*): No description provided
+- `negative_prompt` (`None`, *optional*): No description provided
+- `max_sequence_length` (`None`, *optional*, defaults to `512`): No description provided
+- `video` (`list`, *optional*): The control video to condition the generation on. If not provided, an empty video is used.
+- `mask` (`list`, *optional*): The mask that defines which video regions to condition on (black) and which to generate (white). Can only be passed if `video` is passed as well.
+- `reference_images` (`Image | list`, *optional*): One or more reference images as extra conditioning for the generation.
+- `conditioning_scale` (`float | list | Tensor`, *optional*, defaults to `1.0`): The conditioning scale applied in each control layer of the model. If a float, it is applied uniformly to all layers; a list or tensor must have the same length as the number of control layers.
+- `height` (`None`, *optional*): No description provided
+- `width` (`None`, *optional*): No description provided
+- `num_frames` (`int`, *optional*, defaults to `81`): No description provided
+- `generator` (`None`, *optional*): No description provided
+- `num_videos_per_prompt` (`None`, *optional*, defaults to `1`): No description provided
+- `num_inference_steps` (`None`, *optional*, defaults to `50`): No description provided
+- `timesteps` (`None`, *optional*): No description provided
+- `sigmas` (`None`, *optional*): No description provided
+- `latents` (`Tensor | NoneType`, *optional*): No description provided
+- `attention_kwargs` (`None`, *optional*): No description provided
+- `output_type` (`str`, *optional*, defaults to `np`): The output type of the decoded videos
+
+**Outputs:**
+
+- `videos` (`list`): The generated videos.

modular_model_index.json

@@ -0,0 +1,90 @@
+{
+  "_blocks_class_name": "Wan22VaceBlocks",
+  "_class_name": "Wan22VaceModularPipeline",
+  "_diffusers_version": "0.40.0.dev0",
+  "boundary_ratio": 0.875,
+  "scheduler": [
+    "diffusers",
+    "UniPCMultistepScheduler",
+    {
+      "pretrained_model_name_or_path": "akshan-main/tiny-wan22-vace-modular-pipe",
+      "revision": null,
+      "subfolder": "scheduler",
+      "type_hint": [
+        "diffusers",
+        "UniPCMultistepScheduler"
+      ],
+      "variant": null
+    }
+  ],
+  "text_encoder": [
+    "transformers",
+    "T5EncoderModel",
+    {
+      "pretrained_model_name_or_path": "akshan-main/tiny-wan22-vace-modular-pipe",
+      "revision": null,
+      "subfolder": "text_encoder",
+      "type_hint": [
+        "transformers",
+        "T5EncoderModel"
+      ],
+      "variant": null
+    }
+  ],
+  "tokenizer": [
+    "transformers",
+    "T5Tokenizer",
+    {
+      "pretrained_model_name_or_path": "akshan-main/tiny-wan22-vace-modular-pipe",
+      "revision": null,
+      "subfolder": "tokenizer",
+      "type_hint": [
+        "transformers",
+        "T5Tokenizer"
+      ],
+      "variant": null
+    }
+  ],
+  "transformer": [
+    "diffusers",
+    "WanVACETransformer3DModel",
+    {
+      "pretrained_model_name_or_path": "akshan-main/tiny-wan22-vace-modular-pipe",
+      "revision": null,
+      "subfolder": "transformer",
+      "type_hint": [
+        "diffusers",
+        "WanVACETransformer3DModel"
+      ],
+      "variant": null
+    }
+  ],
+  "transformer_2": [
+    "diffusers",
+    "WanVACETransformer3DModel",
+    {
+      "pretrained_model_name_or_path": "akshan-main/tiny-wan22-vace-modular-pipe",
+      "revision": null,
+      "subfolder": "transformer_2",
+      "type_hint": [
+        "diffusers",
+        "WanVACETransformer3DModel"
+      ],
+      "variant": null
+    }
+  ],
+  "vae": [
+    "diffusers",
+    "AutoencoderKLWan",
+    {
+      "pretrained_model_name_or_path": "akshan-main/tiny-wan22-vace-modular-pipe",
+      "revision": null,
+      "subfolder": "vae",
+      "type_hint": [
+        "diffusers",
+        "AutoencoderKLWan"
+      ],
+      "variant": null
+    }
+  ]
+}

scheduler/scheduler_config.json

@@ -0,0 +1,33 @@
+{
+  "_class_name": "UniPCMultistepScheduler",
+  "_diffusers_version": "0.40.0.dev0",
+  "beta_end": 0.02,
+  "beta_schedule": "linear",
+  "beta_start": 0.0001,
+  "disable_corrector": [],
+  "dynamic_thresholding_ratio": 0.995,
+  "final_sigmas_type": "zero",
+  "flow_shift": 3.0,
+  "lower_order_final": true,
+  "num_train_timesteps": 1000,
+  "predict_x0": true,
+  "prediction_type": "flow_prediction",
+  "rescale_betas_zero_snr": false,
+  "sample_max_value": 1.0,
+  "shift_terminal": null,
+  "sigma_max": null,
+  "sigma_min": null,
+  "solver_order": 2,
+  "solver_p": null,
+  "solver_type": "bh2",
+  "steps_offset": 0,
+  "thresholding": false,
+  "time_shift_type": "exponential",
+  "timestep_spacing": "linspace",
+  "trained_betas": null,
+  "use_beta_sigmas": false,
+  "use_dynamic_shifting": false,
+  "use_exponential_sigmas": false,
+  "use_flow_sigmas": true,
+  "use_karras_sigmas": false
+}

text_encoder/config.json

@@ -0,0 +1,34 @@
+{
+  "architectures": [
+    "T5EncoderModel"
+  ],
+  "bos_token_id": 0,
+  "classifier_dropout": 0.0,
+  "d_ff": 37,
+  "d_kv": 8,
+  "d_model": 32,
+  "decoder_start_token_id": 0,
+  "dense_act_fn": "relu",
+  "dropout_rate": 0.1,
+  "dtype": "float32",
+  "eos_token_id": 1,
+  "feed_forward_proj": "relu",
+  "gradient_checkpointing": false,
+  "initializer_factor": 0.002,
+  "is_decoder": false,
+  "is_encoder_decoder": false,
+  "is_gated_act": false,
+  "layer_norm_epsilon": 1e-06,
+  "model_type": "t5",
+  "num_decoder_layers": 5,
+  "num_heads": 4,
+  "num_layers": 5,
+  "pad_token_id": 0,
+  "relative_attention_max_distance": 128,
+  "relative_attention_num_buckets": 8,
+  "scale_decoder_outputs": true,
+  "tie_word_embeddings": true,
+  "transformers_version": "5.5.3",
+  "use_cache": false,
+  "vocab_size": 1103
+}

text_encoder/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8fd206d9e0dca4134b9e51ba6041697b7838528f924726f17098f9743e2a9a39
+size 276696

tokenizer/tokenizer_config.json

@@ -0,0 +1,112 @@
+{
+  "backend": "tokenizers",
+  "eos_token": "</s>",
+  "extra_ids": 100,
+  "extra_special_tokens": [
+    "<extra_id_0>",
+    "<extra_id_1>",
+    "<extra_id_2>",
+    "<extra_id_3>",
+    "<extra_id_4>",
+    "<extra_id_5>",
+    "<extra_id_6>",
+    "<extra_id_7>",
+    "<extra_id_8>",
+    "<extra_id_9>",
+    "<extra_id_10>",
+    "<extra_id_11>",
+    "<extra_id_12>",
+    "<extra_id_13>",
+    "<extra_id_14>",
+    "<extra_id_15>",
+    "<extra_id_16>",
+    "<extra_id_17>",
+    "<extra_id_18>",
+    "<extra_id_19>",
+    "<extra_id_20>",
+    "<extra_id_21>",
+    "<extra_id_22>",
+    "<extra_id_23>",
+    "<extra_id_24>",
+    "<extra_id_25>",
+    "<extra_id_26>",
+    "<extra_id_27>",
+    "<extra_id_28>",
+    "<extra_id_29>",
+    "<extra_id_30>",
+    "<extra_id_31>",
+    "<extra_id_32>",
+    "<extra_id_33>",
+    "<extra_id_34>",
+    "<extra_id_35>",
+    "<extra_id_36>",
+    "<extra_id_37>",
+    "<extra_id_38>",
+    "<extra_id_39>",
+    "<extra_id_40>",
+    "<extra_id_41>",
+    "<extra_id_42>",
+    "<extra_id_43>",
+    "<extra_id_44>",
+    "<extra_id_45>",
+    "<extra_id_46>",
+    "<extra_id_47>",
+    "<extra_id_48>",
+    "<extra_id_49>",
+    "<extra_id_50>",
+    "<extra_id_51>",
+    "<extra_id_52>",
+    "<extra_id_53>",
+    "<extra_id_54>",
+    "<extra_id_55>",
+    "<extra_id_56>",
+    "<extra_id_57>",
+    "<extra_id_58>",
+    "<extra_id_59>",
+    "<extra_id_60>",
+    "<extra_id_61>",
+    "<extra_id_62>",
+    "<extra_id_63>",
+    "<extra_id_64>",
+    "<extra_id_65>",
+    "<extra_id_66>",
+    "<extra_id_67>",
+    "<extra_id_68>",
+    "<extra_id_69>",
+    "<extra_id_70>",
+    "<extra_id_71>",
+    "<extra_id_72>",
+    "<extra_id_73>",
+    "<extra_id_74>",
+    "<extra_id_75>",
+    "<extra_id_76>",
+    "<extra_id_77>",
+    "<extra_id_78>",
+    "<extra_id_79>",
+    "<extra_id_80>",
+    "<extra_id_81>",
+    "<extra_id_82>",
+    "<extra_id_83>",
+    "<extra_id_84>",
+    "<extra_id_85>",
+    "<extra_id_86>",
+    "<extra_id_87>",
+    "<extra_id_88>",
+    "<extra_id_89>",
+    "<extra_id_90>",
+    "<extra_id_91>",
+    "<extra_id_92>",
+    "<extra_id_93>",
+    "<extra_id_94>",
+    "<extra_id_95>",
+    "<extra_id_96>",
+    "<extra_id_97>",
+    "<extra_id_98>",
+    "<extra_id_99>"
+  ],
+  "is_local": false,
+  "model_max_length": 1024,
+  "pad_token": "<pad>",
+  "tokenizer_class": "T5Tokenizer",
+  "unk_token": "<unk>"
+}

transformer/config.json

@@ -0,0 +1,29 @@
+{
+  "_class_name": "WanVACETransformer3DModel",
+  "_diffusers_version": "0.40.0.dev0",
+  "added_kv_proj_dim": null,
+  "attention_head_dim": 12,
+  "cross_attn_norm": true,
+  "eps": 1e-06,
+  "ffn_dim": 32,
+  "freq_dim": 256,
+  "image_dim": null,
+  "in_channels": 16,
+  "num_attention_heads": 2,
+  "num_layers": 3,
+  "out_channels": 16,
+  "patch_size": [
+    1,
+    2,
+    2
+  ],
+  "pos_embed_seq_len": null,
+  "qk_norm": "rms_norm_across_heads",
+  "rope_max_seq_len": 32,
+  "text_dim": 32,
+  "vace_in_channels": 96,
+  "vace_layers": [
+    0,
+    2
+  ]
+}

transformer/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90409ac7a43a97dbaebcaad0ecb6e281a2f0edf28c0ce1c34801425b593cf61c
+size 252160

transformer_2/config.json

@@ -0,0 +1,29 @@
+{
+  "_class_name": "WanVACETransformer3DModel",
+  "_diffusers_version": "0.40.0.dev0",
+  "added_kv_proj_dim": null,
+  "attention_head_dim": 12,
+  "cross_attn_norm": true,
+  "eps": 1e-06,
+  "ffn_dim": 32,
+  "freq_dim": 256,
+  "image_dim": null,
+  "in_channels": 16,
+  "num_attention_heads": 2,
+  "num_layers": 3,
+  "out_channels": 16,
+  "patch_size": [
+    1,
+    2,
+    2
+  ],
+  "pos_embed_seq_len": null,
+  "qk_norm": "rms_norm_across_heads",
+  "rope_max_seq_len": 32,
+  "text_dim": 32,
+  "vace_in_channels": 96,
+  "vace_layers": [
+    0,
+    2
+  ]
+}

transformer_2/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24da7cda1eecb997734f1afda1e40625ee66aa99f94e32b92cdb7857870e8741
+size 252160

vae/config.json

@@ -0,0 +1,63 @@
+{
+  "_class_name": "AutoencoderKLWan",
+  "_diffusers_version": "0.40.0.dev0",
+  "attn_scales": [],
+  "base_dim": 3,
+  "decoder_base_dim": null,
+  "dim_mult": [
+    1,
+    1,
+    1,
+    1
+  ],
+  "dropout": 0.0,
+  "in_channels": 3,
+  "is_residual": false,
+  "latents_mean": [
+    -0.7571,
+    -0.7089,
+    -0.9113,
+    0.1075,
+    -0.1745,
+    0.9653,
+    -0.1517,
+    1.5508,
+    0.4134,
+    -0.0715,
+    0.5517,
+    -0.3632,
+    -0.1922,
+    -0.9497,
+    0.2503,
+    -0.2921
+  ],
+  "latents_std": [
+    2.8184,
+    1.4541,
+    2.3275,
+    2.6558,
+    1.2196,
+    1.7708,
+    2.6052,
+    2.0743,
+    3.2687,
+    2.1526,
+    2.8652,
+    1.5579,
+    1.6382,
+    1.1253,
+    2.8251,
+    1.916
+  ],
+  "num_res_blocks": 1,
+  "out_channels": 3,
+  "patch_size": null,
+  "scale_factor_spatial": 8,
+  "scale_factor_temporal": 4,
+  "temperal_downsample": [
+    false,
+    true,
+    true
+  ],
+  "z_dim": 16
+}

vae/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5972574afb9fc4993b642cb305ba81712d84e25e8969c5268d847c7164322f2f
+size 70404