make style and make quality

Author: dg845

src/diffusers/image_processor.py

@@ -1471,4 +1471,4 @@ def resize_and_crop_tensor(samples: torch.Tensor, new_width: int, new_height: in
             end_y = start_y + new_height
             samples = samples[:, :, start_y:end_y, start_x:end_x]
 
-        return samples
+        return samples

src/diffusers/pipelines/wan/image_processor.py

@@ -43,8 +43,8 @@ class WanAnimateImageProcessor(VaeImageProcessor):
             Whether to convert the images to grayscale format.
         fill_color (`str` or `float` or `Tuple[float, ...]`, *optional*, defaults to `None`):
             An optional fill color when `resize_mode` is set to `"fill"`. This will fill the empty space with that
-            color instead of filling with data from the image. Any valid `color` argument to `PIL.Image.new` is
-            valid; if `None`, will default to filling with data from `image`.
+            color instead of filling with data from the image. Any valid `color` argument to `PIL.Image.new` is valid;
+            if `None`, will default to filling with data from `image`.
     """
 
     @register_to_config

src/diffusers/pipelines/wan/pipeline_wan_animate.py

@@ -23,7 +23,7 @@
 from transformers import AutoTokenizer, CLIPImageProcessor, CLIPVisionModel, UMT5EncoderModel
 
 from ...callbacks import MultiPipelineCallbacks, PipelineCallback
-from ...image_processor import PipelineImageInput, VaeImageProcessor
+from ...image_processor import PipelineImageInput
 from ...loaders import WanLoraLoaderMixin
 from ...models import AutoencoderKLWan, WanAnimateTransformer3DModel
 from ...schedulers import UniPCMultistepScheduler
@@ -978,9 +978,9 @@ def __call__(
         image_height, image_width = self.video_processor.get_default_height_width(image)
         if image_height != height or image_width != width:
             logger.warning(f"Reshaping reference image from ({image_width}, {image_height}) to ({width}, {height})")
-        image_pixels = self.vae_image_processor.preprocess(
-            image, height=height, width=width, resize_mode="fill"
-        ).to(device, dtype=torch.float32)
+        image_pixels = self.vae_image_processor.preprocess(image, height=height, width=width, resize_mode="fill").to(
+            device, dtype=torch.float32
+        )
 
         # Get CLIP features from the reference image
         if image_embeds is None:
@@ -1174,9 +1174,9 @@ def __call__(
                 .view(1, self.vae.config.z_dim, 1, 1, 1)
                 .to(latents.device, latents.dtype)
             )
-            latents_recip_std = 1.0 / torch.tensor(self.vae.config.latents_std).view(1, self.vae.config.z_dim, 1, 1, 1).to(
-                latents.device, latents.dtype
-            )
+            latents_recip_std = 1.0 / torch.tensor(self.vae.config.latents_std).view(
+                1, self.vae.config.z_dim, 1, 1, 1
+            ).to(latents.device, latents.dtype)
             latents = latents / latents_recip_std + latents_mean
             # Skip the first latent frame (used for conditioning)
             out_frames = self.vae.decode(latents[:, :, 1:], return_dict=False)[0]