Merge branch 'main' into feat-taylorseer

Author: toilaluan

docs/source/en/_toctree.yml

@@ -22,6 +22,8 @@
     title: Reproducibility
   - local: using-diffusers/schedulers
     title: Schedulers
+  - local: using-diffusers/automodel
+    title: AutoModel
   - local: using-diffusers/other-formats
     title: Model formats
   - local: using-diffusers/push_to_hub
@@ -119,6 +121,8 @@
     title: ComponentsManager
   - local: modular_diffusers/guiders
     title: Guiders
+  - local: modular_diffusers/custom_blocks
+    title: Building Custom Blocks
   title: Modular Diffusers
 - isExpanded: false
   sections:
@@ -450,6 +454,8 @@
   - sections:
     - local: api/pipelines/overview
       title: Overview
+    - local: api/pipelines/auto_pipeline
+      title: AutoPipeline
     - sections:
       - local: api/pipelines/audioldm
         title: AudioLDM
@@ -462,8 +468,6 @@
       - local: api/pipelines/stable_audio
         title: Stable Audio
       title: Audio
-    - local: api/pipelines/auto_pipeline
-      title: AutoPipeline
     - sections:
       - local: api/pipelines/amused
         title: aMUSEd
@@ -527,6 +531,8 @@
         title: HiDream-I1
       - local: api/pipelines/hunyuandit
         title: Hunyuan-DiT
+      - local: api/pipelines/hunyuanimage21
+        title: HunyuanImage2.1
       - local: api/pipelines/pix2pix
         title: InstructPix2Pix
       - local: api/pipelines/kandinsky
@@ -640,8 +646,6 @@
         title: ConsisID
       - local: api/pipelines/framepack
         title: Framepack
-      - local: api/pipelines/hunyuanimage21
-        title: HunyuanImage2.1
       - local: api/pipelines/hunyuan_video
         title: HunyuanVideo
       - local: api/pipelines/i2vgenxl

docs/source/en/api/models/auto_model.md

@@ -12,15 +12,7 @@ specific language governing permissions and limitations under the License.
 
 # AutoModel
 
-The `AutoModel` is designed to make it easy to load a checkpoint without needing to know the specific model class. `AutoModel` automatically retrieves the correct model class from the checkpoint `config.json` file.
-
-```python
-from diffusers import AutoModel, AutoPipelineForText2Image
-
-unet = AutoModel.from_pretrained("stable-diffusion-v1-5/stable-diffusion-v1-5", subfolder="unet")
-pipe = AutoPipelineForText2Image.from_pretrained("stable-diffusion-v1-5/stable-diffusion-v1-5", unet=unet)
-```
-
+[`AutoModel`] automatically retrieves the correct model class from the checkpoint `config.json` file.
 
 ## AutoModel
 

docs/source/en/api/models/wan_animate_transformer_3d.md

@@ -18,7 +18,7 @@ The model can be loaded with the following code snippet.
 ```python
 from diffusers import WanAnimateTransformer3DModel
 
-transformer = WanAnimateTransformer3DModel.from_pretrained("Wan-AI/Wan2.2-Animate-14B-720P-Diffusers", subfolder="transformer", torch_dtype=torch.bfloat16)
+transformer = WanAnimateTransformer3DModel.from_pretrained("Wan-AI/Wan2.2-Animate-14B-Diffusers", subfolder="transformer", torch_dtype=torch.bfloat16)
 ```
 
 ## WanAnimateTransformer3DModel

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

@@ -281,7 +281,7 @@ For replacement mode, you additionally need:
 - **Mask video**: A mask indicating where to generate content (white) vs. preserve original (black)
 
 > [!NOTE]
-> The preprocessing tools are available in the original Wan-Animate repository. Integration of these preprocessing steps into Diffusers is planned for a future release.
+> Raw videos should not be used for inputs such as `pose_video`, which the pipeline expects to be preprocessed to extract the proper information. Preprocessing scripts to prepare these inputs are available in the [original Wan-Animate repository](https://github.com/Wan-Video/Wan2.2?tab=readme-ov-file#1-preprocessing). Integration of these preprocessing steps into Diffusers is planned for a future release.
 
 The example below demonstrates how to use the Wan-Animate pipeline:
 
@@ -293,13 +293,10 @@ import numpy as np
 import torch
 from diffusers import AutoencoderKLWan, WanAnimatePipeline
 from diffusers.utils import export_to_video, load_image, load_video
-from transformers import CLIPVisionModel
 
 model_id = "Wan-AI/Wan2.2-Animate-14B-Diffusers"
 vae = AutoencoderKLWan.from_pretrained(model_id, subfolder="vae", torch_dtype=torch.float32)
-pipe = WanAnimatePipeline.from_pretrained(
-    model_id, vae=vae, torch_dtype=torch.bfloat16
-)
+pipe = WanAnimatePipeline.from_pretrained(model_id, vae=vae, torch_dtype=torch.bfloat16)
 pipe.to("cuda")
 
 # Load character image and preprocessed videos
@@ -330,11 +327,11 @@ output = pipe(
     negative_prompt=negative_prompt,
     height=height,
     width=width,
-    num_frames=81,
-    guidance_scale=5.0,
-    mode="animation",  # Animation mode (default)
+    segment_frame_length=77,
+    guidance_scale=1.0,
+    mode="animate",  # Animation mode (default)
 ).frames[0]
-export_to_video(output, "animated_character.mp4", fps=16)
+export_to_video(output, "animated_character.mp4", fps=30)
 ```
 
 </hfoption>
@@ -345,14 +342,10 @@ import numpy as np
 import torch
 from diffusers import AutoencoderKLWan, WanAnimatePipeline
 from diffusers.utils import export_to_video, load_image, load_video
-from transformers import CLIPVisionModel
 
 model_id = "Wan-AI/Wan2.2-Animate-14B-Diffusers"
-image_encoder = CLIPVisionModel.from_pretrained(model_id, subfolder="image_encoder", torch_dtype=torch.float16)
 vae = AutoencoderKLWan.from_pretrained(model_id, subfolder="vae", torch_dtype=torch.float32)
-pipe = WanAnimatePipeline.from_pretrained(
-    model_id, vae=vae, image_encoder=image_encoder, torch_dtype=torch.bfloat16
-)
+pipe = WanAnimatePipeline.from_pretrained(model_id, vae=vae, torch_dtype=torch.bfloat16)
 pipe.to("cuda")
 
 # Load all required inputs for replacement mode
@@ -387,11 +380,11 @@ output = pipe(
     negative_prompt=negative_prompt,
     height=height,
     width=width,
-    num_frames=81,
-    guidance_scale=5.0,
-    mode="replacement",  # Replacement mode
+    segment_frame_lengths=77,
+    guidance_scale=1.0,
+    mode="replace",  # Replacement mode
 ).frames[0]
-export_to_video(output, "character_replaced.mp4", fps=16)
+export_to_video(output, "character_replaced.mp4", fps=30)
 ```
 
 </hfoption>
@@ -402,14 +395,10 @@ import numpy as np
 import torch
 from diffusers import AutoencoderKLWan, WanAnimatePipeline
 from diffusers.utils import export_to_video, load_image, load_video
-from transformers import CLIPVisionModel
 
 model_id = "Wan-AI/Wan2.2-Animate-14B-Diffusers"
-image_encoder = CLIPVisionModel.from_pretrained(model_id, subfolder="image_encoder", torch_dtype=torch.float16)
 vae = AutoencoderKLWan.from_pretrained(model_id, subfolder="vae", torch_dtype=torch.float32)
-pipe = WanAnimatePipeline.from_pretrained(
-    model_id, vae=vae, image_encoder=image_encoder, torch_dtype=torch.bfloat16
-)
+pipe = WanAnimatePipeline.from_pretrained(model_id, vae=vae, torch_dtype=torch.bfloat16)
 pipe.to("cuda")
 
 image = load_image("path/to/character.jpg")
@@ -443,25 +432,24 @@ output = pipe(
     negative_prompt=negative_prompt,
     height=height,
     width=width,
-    num_frames=81,
+    segment_frame_length=77,
     num_inference_steps=50,
     guidance_scale=5.0,
-    num_frames_for_temporal_guidance=5,  # Use 5 frames for temporal guidance (1 or 5 recommended)
+    prev_segment_conditioning_frames=5,  # Use 5 frames for temporal guidance (1 or 5 recommended)
     callback_on_step_end=callback_fn,
     callback_on_step_end_tensor_inputs=["latents"],
 ).frames[0]
-export_to_video(output, "animated_advanced.mp4", fps=16)
+export_to_video(output, "animated_advanced.mp4", fps=30)
 ```
 
 </hfoption>
 </hfoptions>
 
 #### Key Parameters
 
-- **mode**: Choose between `"animation"` (default) or `"replacement"`
-- **num_frames_for_temporal_guidance**: Number of frames for temporal guidance (1 or 5 recommended). Using 5 provides better temporal consistency but requires more memory
-- **guidance_scale**: Controls how closely the output follows the text prompt. Higher values (5-7) produce results more aligned with the prompt
-- **num_frames**: Total number of frames to generate. Should be divisible by `vae_scale_factor_temporal` (default: 4)
+- **mode**: Choose between `"animate"` (default) or `"replace"`
+- **prev_segment_conditioning_frames**: Number of frames for temporal guidance (1 or 5 recommended). Using 5 provides better temporal consistency but requires more memory
+- **guidance_scale**: Controls how closely the output follows the text prompt. Higher values (5-7) produce results more aligned with the prompt. For Wan-Animate, CFG is disabled by default (`guidance_scale=1.0`) but can be enabled to support negative prompts and finer control over facial expressions. (Note that CFG will only target the text prompt and face conditioning.)
 
 
 ## Notes