stevhliu · Aug 24, 2026 · Jul 24, 2026
diff --git a/src/diffusers/models/unets/unet_spatio_temporal_condition.py b/src/diffusers/models/unets/unet_spatio_temporal_condition.py
@@ -50,7 +50,7 @@ class UNetSpatioTemporalConditionModel(ModelMixin, AttentionMixin, ConfigMixin,
         block_out_channels (`tuple[int]`, *optional*, defaults to `(320, 640, 1280, 1280)`):
             The tuple of output channels for each block.
         addition_time_embed_dim: (`int`, defaults to 256):
-            Dimension to to encode the additional time ids.
+            Dimension to encode the additional time ids.
         projection_class_embeddings_input_dim (`int`, defaults to 768):
             The dimension of the projection of encoded `added_time_ids`.
         layers_per_block (`int`, *optional*, defaults to 2): The number of layers per block.

diff --git a/src/diffusers/modular_pipelines/anima/before_denoise.py b/src/diffusers/modular_pipelines/anima/before_denoise.py
@@ -108,9 +108,7 @@ def repeat_tensor_to_batch_size(
     elif input_tensor.shape[0] == batch_size:
         repeat_by = num_images_per_prompt
     else:
-        raise ValueError(
-            f"`{input_name}` must have have batch size 1 or {batch_size}, but got {input_tensor.shape[0]}"
-        )
+        raise ValueError(f"`{input_name}` must have batch size 1 or {batch_size}, but got {input_tensor.shape[0]}")
 
     # expand the tensor to match the batch_size * num_images_per_prompt
     input_tensor = input_tensor.repeat_interleave(repeat_by, dim=0)

diff --git a/src/diffusers/modular_pipelines/flux/before_denoise.py b/src/diffusers/modular_pipelines/flux/before_denoise.py
@@ -470,7 +470,7 @@ def intermediate_outputs(self) -> list[OutputParam]:
     def check_inputs(image_latents, latents):
         if image_latents.shape[0] != latents.shape[0]:
             raise ValueError(
-                f"`image_latents` must have have same batch size as `latents`, but got {image_latents.shape[0]} and {latents.shape[0]}"
+                f"`image_latents` must have same batch size as `latents`, but got {image_latents.shape[0]} and {latents.shape[0]}"
             )
 
         if image_latents.ndim != 3:

diff --git a/src/diffusers/modular_pipelines/helios/before_denoise.py b/src/diffusers/modular_pipelines/helios/before_denoise.py
@@ -167,9 +167,7 @@ def repeat_tensor_to_batch_size(
     elif input_tensor.shape[0] == batch_size:
         repeat_by = num_videos_per_prompt
     else:
-        raise ValueError(
-            f"`{input_name}` must have have batch size 1 or {batch_size}, but got {input_tensor.shape[0]}"
-        )
+        raise ValueError(f"`{input_name}` must have batch size 1 or {batch_size}, but got {input_tensor.shape[0]}")
 
     # expand the tensor to match the batch_size * num_videos_per_prompt
     input_tensor = input_tensor.repeat_interleave(repeat_by, dim=0)

diff --git a/src/diffusers/modular_pipelines/qwenimage/before_denoise.py b/src/diffusers/modular_pipelines/qwenimage/before_denoise.py
@@ -426,7 +426,7 @@ def intermediate_outputs(self) -> list[OutputParam]:
     def check_inputs(image_latents, latents):
         if image_latents.shape[0] != latents.shape[0]:
             raise ValueError(
-                f"`image_latents` must have have same batch size as `latents`, but got {image_latents.shape[0]} and {latents.shape[0]}"
+                f"`image_latents` must have same batch size as `latents`, but got {image_latents.shape[0]} and {latents.shape[0]}"
             )
 
         if image_latents.ndim != 3:

diff --git a/src/diffusers/modular_pipelines/qwenimage/inputs.py b/src/diffusers/modular_pipelines/qwenimage/inputs.py
@@ -67,9 +67,7 @@ def repeat_tensor_to_batch_size(
     elif input_tensor.shape[0] == batch_size:
         repeat_by = num_images_per_prompt
     else:
-        raise ValueError(
-            f"`{input_name}` must have have batch size 1 or {batch_size}, but got {input_tensor.shape[0]}"
-        )
+        raise ValueError(f"`{input_name}` must have batch size 1 or {batch_size}, but got {input_tensor.shape[0]}")
 
     # expand the tensor to match the batch_size * num_images_per_prompt
     input_tensor = input_tensor.repeat_interleave(repeat_by, dim=0)

diff --git a/src/diffusers/modular_pipelines/stable_diffusion_3/inputs.py b/src/diffusers/modular_pipelines/stable_diffusion_3/inputs.py
@@ -70,9 +70,7 @@ def repeat_tensor_to_batch_size(
     elif input_tensor.shape[0] == batch_size:
         repeat_by = num_images_per_prompt
     else:
-        raise ValueError(
-            f"`{input_name}` must have have batch size 1 or {batch_size}, but got {input_tensor.shape[0]}"
-        )
+        raise ValueError(f"`{input_name}` must have batch size 1 or {batch_size}, but got {input_tensor.shape[0]}")
 
     # expand the tensor to match the batch_size * num_images_per_prompt
     input_tensor = input_tensor.repeat_interleave(repeat_by, dim=0)

diff --git a/src/diffusers/modular_pipelines/wan/before_denoise.py b/src/diffusers/modular_pipelines/wan/before_denoise.py
@@ -80,9 +80,7 @@ def repeat_tensor_to_batch_size(
     elif input_tensor.shape[0] == batch_size:
         repeat_by = num_videos_per_prompt
     else:
-        raise ValueError(
-            f"`{input_name}` must have have batch size 1 or {batch_size}, but got {input_tensor.shape[0]}"
-        )
+        raise ValueError(f"`{input_name}` must have batch size 1 or {batch_size}, but got {input_tensor.shape[0]}")
 
     # expand the tensor to match the batch_size * num_videos_per_prompt
     input_tensor = input_tensor.repeat_interleave(repeat_by, dim=0)

diff --git a/src/diffusers/modular_pipelines/z_image/before_denoise.py b/src/diffusers/modular_pipelines/z_image/before_denoise.py
@@ -80,9 +80,7 @@ def repeat_tensor_to_batch_size(
     elif input_tensor.shape[0] == batch_size:
         repeat_by = num_images_per_prompt
     else:
-        raise ValueError(
-            f"`{input_name}` must have have batch size 1 or {batch_size}, but got {input_tensor.shape[0]}"
-        )
+        raise ValueError(f"`{input_name}` must have batch size 1 or {batch_size}, but got {input_tensor.shape[0]}")
 
     # expand the tensor to match the batch_size * num_images_per_prompt
     input_tensor = input_tensor.repeat_interleave(repeat_by, dim=0)

diff --git a/src/diffusers/pipelines/flux/pipeline_flux_kontext_inpaint.py b/src/diffusers/pipelines/flux/pipeline_flux_kontext_inpaint.py
@@ -923,8 +923,8 @@ def __call__(
 
         Args:
             image (`torch.Tensor`, `PIL.Image.Image`, `np.ndarray`, `list[torch.Tensor]`, `list[PIL.Image.Image]`, or `list[np.ndarray]`):
-                `Image`, numpy array or tensor representing an image batch to be be inpainted (which parts of the image
-                to be masked out with `mask_image` and repainted according to `prompt` and `image_reference`). For both
+                `Image`, numpy array or tensor representing an image batch to be inpainted (which parts of the image to
+                be masked out with `mask_image` and repainted according to `prompt` and `image_reference`). For both
                 numpy array and pytorch tensor, the expected value range is between `[0, 1]` If it's a tensor or a list
                 or tensors, the expected shape should be `(B, C, H, W)` or `(C, H, W)`. If it is a numpy array or a
                 list of arrays, the expected shape should be `(B, H, W, C)` or `(H, W, C)` It can also accept image

diff --git a/src/diffusers/pipelines/ltx2/pipeline_ltx2_condition.py b/src/diffusers/pipelines/ltx2/pipeline_ltx2_condition.py
@@ -262,7 +262,7 @@ def rescale_noise_cfg(noise_cfg, noise_pred_text, guidance_rescale=0.0):
 
 class LTX2ConditionPipeline(DiffusionPipeline, FromSingleFileMixin, LTX2LoraLoaderMixin):
     r"""
-    Pipeline for video generation which allows image conditions to be inserted at arbitary parts of the video.
+    Pipeline for video generation which allows image conditions to be inserted at arbitrary parts of the video.
 
     Reference: https://github.com/Lightricks/LTX-Video