[WIP] Add Wan Video2Video

docs/source/en/api/pipelines/wan.md

@@ -133,6 +133,46 @@ output = pipe(
 export_to_video(output, "wan-i2v.mp4", fps=16)
 ```
 
+### Video to Video Generation
+
+```python
+import torch
+from diffusers.utils import load_video, export_to_video
+from diffusers import AutoencoderKLWan, WanVideoToVideoPipeline, UniPCMultistepScheduler
+
+# Available models: Wan-AI/Wan2.1-T2V-14B-Diffusers, Wan-AI/Wan2.1-T2V-1.3B-Diffusers
+model_id = "Wan-AI/Wan2.1-T2V-1.3B-Diffusers"
+vae = AutoencoderKLWan.from_pretrained(
+    model_id, subfolder="vae", torch_dtype=torch.float32
+)
+pipe = WanVideoToVideoPipeline.from_pretrained(
+    model_id, vae=vae, torch_dtype=torch.bfloat16
+)
+flow_shift = 3.0  # 5.0 for 720P, 3.0 for 480P
+pipe.scheduler = UniPCMultistepScheduler.from_config(
+    pipe.scheduler.config, flow_shift=flow_shift
+)
+# change to pipe.to("cuda") if you have sufficient VRAM
+pipe.enable_model_cpu_offload()
+
+prompt = "A robot standing on a mountain top. The sun is setting in the background"
+negative_prompt = "Bright tones, overexposed, static, blurred details, subtitles, style, works, paintings, images, static, overall gray, worst quality, low quality, JPEG compression residue, ugly, incomplete, extra fingers, poorly drawn hands, poorly drawn faces, deformed, disfigured, misshapen limbs, fused fingers, still picture, messy background, three legs, many people in the background, walking backwards"
+video = load_video(
+    "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/hiker.mp4"
+)
+output = pipe(
+    video=video,
+    prompt=prompt,
+    negative_prompt=negative_prompt,
+    height=480,
+    width=512,
+    guidance_scale=7.0,
+    strength=0.7,
+).frames[0]
+
+export_to_video(output, "wan-v2v.mp4", fps=16)
+```
+
 ## Memory Optimizations for Wan 2.1
 
 Base inference with the large 14B Wan 2.1 models can take up to 35GB of VRAM when generating videos at 720p resolution. We'll outline a few memory optimizations we can apply to reduce the VRAM required to run the model.
@@ -323,7 +363,7 @@ import numpy as np
 from diffusers import AutoencoderKLWan, WanTransformer3DModel, WanImageToVideoPipeline
 from diffusers.hooks.group_offloading import apply_group_offloading
 from diffusers.utils import export_to_video, load_image
-from transformers import UMT5EncoderModel, CLIPVisionMode
+from transformers import UMT5EncoderModel, CLIPVisionModel
 
 model_id = "Wan-AI/Wan2.1-I2V-14B-720P-Diffusers"
 image_encoder = CLIPVisionModel.from_pretrained(
@@ -356,7 +396,7 @@ prompt = (
     "An astronaut hatching from an egg, on the surface of the moon, the darkness and depth of space realised in "
     "the background. High quality, ultrarealistic detail and breath-taking movie-like camera shot."
 )
-negative_prompt = "Bright tones, overexposed, static, blurred details, subtitles, style, works, paintings, images, static, overall gray, worst quality, low quality, JPEG compression residue, ugly, incomplete, extra fingers, poorly drawn hands, poorly drawn faces, deformed, disfigured, misshapen limbs, fused fingers, still picture, messy background, three legs, many people in the background, walking backwards
+negative_prompt = "Bright tones, overexposed, static, blurred details, subtitles, style, works, paintings, images, static, overall gray, worst quality, low quality, JPEG compression residue, ugly, incomplete, extra fingers, poorly drawn hands, poorly drawn faces, deformed, disfigured, misshapen limbs, fused fingers, still picture, messy background, three legs, many people in the background, walking backwards"
 num_frames = 33
 
 output = pipe(
@@ -372,7 +412,7 @@ output = pipe(
 export_to_video(output, "wan-i2v.mp4", fps=16)
 ```
 
-### Using a Custom Scheduler
+## Using a Custom Scheduler
 
 Wan can be used with many different schedulers, each with their own benefits regarding speed and generation quality. By default, Wan uses the `UniPCMultistepScheduler(prediction_type="flow_prediction", use_flow_sigmas=True, flow_shift=3.0)` scheduler. You can use a different scheduler as follows:
 
@@ -403,7 +443,7 @@ transformer = WanTransformer3DModel.from_single_file(ckpt_path, torch_dtype=torc
 pipe = WanPipeline.from_pretrained("Wan-AI/Wan2.1-T2V-1.3B-Diffusers", transformer=transformer)
 ```
 
-## Recommendations for Inference:
+## Recommendations for Inference
 - Keep `AutencoderKLWan` in `torch.float32` for better decoding quality.
 - `num_frames` should satisfy the following constraint: `(num_frames - 1) % 4 == 0`
 - For smaller resolution videos, try lower values of `shift` (between `2.0` to `5.0`) in the [Scheduler](https://huggingface.co/docs/diffusers/main/en/api/schedulers/flow_match_euler_discrete#diffusers.FlowMatchEulerDiscreteScheduler.shift). For larger resolution videos, try higher values (between `7.0` and `12.0`). The default value is `3.0` for Wan.

src/diffusers/__init__.py

@@ -509,6 +509,7 @@
             "VQDiffusionPipeline",
             "WanImageToVideoPipeline",
             "WanPipeline",
+            "WanVideoToVideoPipeline",
             "WuerstchenCombinedPipeline",
             "WuerstchenDecoderPipeline",
             "WuerstchenPriorPipeline",
@@ -1062,6 +1063,7 @@
             VQDiffusionPipeline,
             WanImageToVideoPipeline,
             WanPipeline,
+            WanVideoToVideoPipeline,
             WuerstchenCombinedPipeline,
             WuerstchenDecoderPipeline,
             WuerstchenPriorPipeline,

src/diffusers/pipelines/__init__.py

@@ -356,7 +356,7 @@
         "WuerstchenDecoderPipeline",
         "WuerstchenPriorPipeline",
     ]
-    _import_structure["wan"] = ["WanPipeline", "WanImageToVideoPipeline"]
+    _import_structure["wan"] = ["WanPipeline", "WanImageToVideoPipeline", "WanVideoToVideoPipeline"]
 try:
     if not is_onnx_available():
         raise OptionalDependencyNotAvailable()
@@ -709,7 +709,7 @@
             UniDiffuserPipeline,
             UniDiffuserTextDecoder,
         )
-        from .wan import WanImageToVideoPipeline, WanPipeline
+        from .wan import WanImageToVideoPipeline, WanPipeline, WanVideoToVideoPipeline
         from .wuerstchen import (
             WuerstchenCombinedPipeline,
             WuerstchenDecoderPipeline,

src/diffusers/pipelines/wan/__init__.py

@@ -24,7 +24,7 @@
 else:
     _import_structure["pipeline_wan"] = ["WanPipeline"]
     _import_structure["pipeline_wan_i2v"] = ["WanImageToVideoPipeline"]
-
+    _import_structure["pipeline_wan_video2video"] = ["WanVideoToVideoPipeline"]
 if TYPE_CHECKING or DIFFUSERS_SLOW_IMPORT:
     try:
         if not (is_transformers_available() and is_torch_available()):
@@ -35,6 +35,7 @@
     else:
         from .pipeline_wan import WanPipeline
         from .pipeline_wan_i2v import WanImageToVideoPipeline
+        from .pipeline_wan_video2video import WanVideoToVideoPipeline
 
 else:
     import sys