reformat code

Author: Trgtuan10

src/diffusers/pipelines/qwenimage/pipeline_qwenimage_img2img.py

@@ -42,6 +42,7 @@
         ```
 """
 
+
 # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion_img2img.retrieve_latents
 def retrieve_latents(
     encoder_output: torch.Tensor, generator: Optional[torch.Generator] = None, sample_mode: str = "sample"
@@ -55,6 +56,7 @@ def retrieve_latents(
     else:
         raise AttributeError("Could not access latents of provided encoder_output")
 
+
 # Copied from diffusers.pipelines.qwenimage.pipeline_qwenimage.calculate_shift
 def calculate_shift(
     image_seq_len,
@@ -469,7 +471,7 @@ def prepare_latents(
 
         image = image.to(device=device, dtype=dtype)
         if image.shape[1] != self.latent_channels:
-            image_latents = self._encode_vae_image(image=image, generator=generator)   # [B,z,1,H',W']
+            image_latents = self._encode_vae_image(image=image, generator=generator)  # [B,z,1,H',W']
         else:
             image_latents = image
         if batch_size > image_latents.shape[0] and batch_size % image_latents.shape[0] == 0:

src/diffusers/pipelines/qwenimage/pipeline_qwenimage_inpaint.py

@@ -45,6 +45,7 @@
         ```
 """
 
+
 # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion_img2img.retrieve_latents
 def retrieve_latents(
     encoder_output: torch.Tensor, generator: Optional[torch.Generator] = None, sample_mode: str = "sample"
@@ -58,6 +59,7 @@ def retrieve_latents(
     else:
         raise AttributeError("Could not access latents of provided encoder_output")
 
+
 # Copied from diffusers.pipelines.qwenimage.pipeline_qwenimage.calculate_shift
 def calculate_shift(
     image_seq_len,
@@ -490,14 +492,13 @@ def prepare_latents(
         elif image.dim() != 5:
             raise ValueError(f"Expected image dims 4 or 5, got {image.dim()}.")
 
-
         if latents is not None:
             latent_image_ids = self._prepare_latent_image_ids(batch_size, height // 2, width // 2, device, dtype)
             return latents.to(device=device, dtype=dtype), latent_image_ids
 
         image = image.to(device=device, dtype=dtype)
         if image.shape[1] != self.latent_channels:
-            image_latents = self._encode_vae_image(image=image, generator=generator)   # [B,z,1,H',W']
+            image_latents = self._encode_vae_image(image=image, generator=generator)  # [B,z,1,H',W']
         else:
             image_latents = image
         if batch_size > image_latents.shape[0] and batch_size % image_latents.shape[0] == 0:
@@ -971,7 +972,6 @@ def __call__(
 
                 latents = (1 - init_mask) * init_latents_proper + init_mask * latents
 
-
                 if latents.dtype != latents_dtype:
                     if torch.backends.mps.is_available():
                         # some platforms (eg. apple mps) misbehave due to a pytorch bug: https://github.com/pytorch/pytorch/pull/99272

src/diffusers/utils/dummy_torch_and_transformers_objects.py

@@ -1756,6 +1756,7 @@ def from_config(cls, *args, **kwargs):
     def from_pretrained(cls, *args, **kwargs):
         requires_backends(cls, ["torch", "transformers"])
 
+
 class QwenImageImg2ImgPipeline(metaclass=DummyObject):
     _backends = ["torch", "transformers"]
 
@@ -1770,6 +1771,7 @@ def from_config(cls, *args, **kwargs):
     def from_pretrained(cls, *args, **kwargs):
         requires_backends(cls, ["torch", "transformers"])
 
+
 class QwenImageInpaintPipeline(metaclass=DummyObject):
     _backends = ["torch", "transformers"]