Fix typos in docs and comments (#11416)

* Fix typos in docs and comments

* Apply style fixes

---------
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>

src/diffusers/pipelines/controlnet_xs/pipeline_controlnet_xs.py

@@ -739,7 +739,7 @@ class StableDiffusionControlNetXSPipeline(
             callback_on_step_end_tensor_inputs (`List`, *optional*):
                 The list of tensor inputs for the `callback_on_step_end` function. The tensors specified in the list
                 will be passed as `callback_kwargs` argument. You will only be able to include variables listed in the
-                `._callback_tensor_inputs` attribute of your pipeine class.
+                `._callback_tensor_inputs` attribute of your pipeline class.
         Examples:
 
         Returns:

src/diffusers/pipelines/controlnet_xs/pipeline_controlnet_xs_sd_xl.py

@@ -880,7 +880,7 @@ class StableDiffusionXLControlNetXSPipeline(
             callback_on_step_end_tensor_inputs (`List`, *optional*):
                 The list of tensor inputs for the `callback_on_step_end` function. The tensors specified in the list
                 will be passed as `callback_kwargs` argument. You will only be able to include variables listed in the
-                `._callback_tensor_inputs` attribute of your pipeine class.
+                `._callback_tensor_inputs` attribute of your pipeline class.
 
         Examples:
 

src/diffusers/pipelines/dance_diffusion/pipeline_dance_diffusion.py

@@ -97,7 +97,7 @@ class DanceDiffusionPipeline(DiffusionPipeline):
         for i, audio in enumerate(audios):
             write(f"maestro_test_{i}.wav", pipe.unet.sample_rate, audio.transpose())
 
-        # To dislay in google colab
+        # To display in google colab
         import IPython.display as ipd
 
         for audio in audios:

src/diffusers/pipelines/deprecated/stable_diffusion_variants/pipeline_stable_diffusion_model_editing.py

@@ -509,7 +509,8 @@ class StableDiffusionModelEditingPipeline(
                 The destination prompt. Must contain all words from `source_prompt` with additional ones to specify the
                 target edit.
             lamb (`float`, *optional*, defaults to 0.1):
-                The lambda parameter specifying the regularization intesity. Smaller values increase the editing power.
+                The lambda parameter specifying the regularization intensity. Smaller values increase the editing
+                power.
             restart_params (`bool`, *optional*, defaults to True):
                 Restart the model parameters to their pre-trained version before editing. This is done to avoid edit
                 compounding. When it is `False`, edits accumulate.

src/diffusers/pipelines/deprecated/versatile_diffusion/modeling_text_unet.py

@@ -1097,7 +1097,7 @@ class UNetFlatConditionModel(ModelMixin, ConfigMixin):
             cross_attention_kwargs (`dict`, *optional*):
                 A kwargs dictionary that if specified is passed along to the [`AttnProcessor`].
             added_cond_kwargs: (`dict`, *optional*):
-                A kwargs dictionary containin additional embeddings that if specified are added to the embeddings that
+                A kwargs dictionary containing additional embeddings that if specified are added to the embeddings that
                 are passed along to the UNet blocks.
             down_block_additional_residuals (`tuple` of `torch.Tensor`, *optional*):
                 additional residuals to be added to UNet long skip connections from down blocks to up blocks for

src/diffusers/pipelines/free_noise_utils.py

@@ -478,7 +478,7 @@ class AnimateDiffFreeNoiseMixin:
                 Must be one of ["shuffle_context", "repeat_context", "random"].
                     - "shuffle_context"
                         Shuffles a fixed batch of `context_length` latents to create a final latent of size
-                        `num_frames`. This is usually the best setting for most generation scenarious. However, there
+                        `num_frames`. This is usually the best setting for most generation scenarios. However, there
                         might be visible repetition noticeable in the kinds of motion/animation generated.
                     - "repeated_context"
                         Repeats a fixed batch of `context_length` latents to create a final latent of size

src/diffusers/pipelines/i2vgen_xl/pipeline_i2vgen_xl.py

@@ -462,7 +462,7 @@ class I2VGenXLPipeline(
         image_latents = image_latents.unsqueeze(2)
 
         # Append a position mask for each subsequent frame
-        # after the intial image latent frame
+        # after the initial image latent frame
         frame_position_mask = []
         for frame_idx in range(num_frames - 1):
             scale = (frame_idx + 1) / (num_frames - 1)

src/diffusers/pipelines/kandinsky/pipeline_kandinsky_inpaint.py

@@ -496,7 +496,7 @@ class KandinskyInpaintPipeline(DiffusionPipeline):
                 "As of diffusers==0.19.0 this behavior has been inverted. Now white pixels are repainted and black pixels are preserved. "
                 "This way, Kandinsky's masking behavior is aligned with Stable Diffusion. "
                 "THIS means that you HAVE to invert the input mask to have the same behavior as before as explained in https://github.com/huggingface/diffusers/pull/4207. "
-                "This warning will be surpressed after the first inference call and will be removed in diffusers>0.23.0"
+                "This warning will be suppressed after the first inference call and will be removed in diffusers>0.23.0"
             )
             self._warn_has_been_called = True
 

src/diffusers/pipelines/kandinsky2_2/pipeline_kandinsky2_2_inpainting.py

@@ -386,7 +386,7 @@ class KandinskyV22InpaintPipeline(DiffusionPipeline):
                 "As of diffusers==0.19.0 this behavior has been inverted. Now white pixels are repainted and black pixels are preserved. "
                 "This way, Kandinsky's masking behavior is aligned with Stable Diffusion. "
                 "THIS means that you HAVE to invert the input mask to have the same behavior as before as explained in https://github.com/huggingface/diffusers/pull/4207. "
-                "This warning will be surpressed after the first inference call and will be removed in diffusers>0.23.0"
+                "This warning will be suppressed after the first inference call and will be removed in diffusers>0.23.0"
             )
             self._warn_has_been_called = True
 

src/diffusers/pipelines/kolors/text_encoder.py

@@ -668,7 +668,7 @@ class Embedding(torch.nn.Module):
         # Embeddings.
         words_embeddings = self.word_embeddings(input_ids)
         embeddings = words_embeddings
-        # Data format change to avoid explicit tranposes : [b s h] --> [s b h].
+        # Data format change to avoid explicit transposes : [b s h] --> [s b h].
         embeddings = embeddings.transpose(0, 1).contiguous()
         # If the input flag for fp32 residual connection is set, convert for float.
         if self.fp32_residual_connection:

src/diffusers/pipelines/ledits_pp/pipeline_leditspp_stable_diffusion.py

@@ -1458,7 +1458,7 @@ def compute_noise_ddim(scheduler, prev_latents, latents, timestep, noise_pred, e
     # 6. compute "direction pointing to x_t" of formula (12) from https://arxiv.org/pdf/2010.02502.pdf
     pred_sample_direction = (1 - alpha_prod_t_prev - std_dev_t**2) ** (0.5) * noise_pred
 
-    # modifed so that updated xtm1 is returned as well (to avoid error accumulation)
+    # modified so that updated xtm1 is returned as well (to avoid error accumulation)
     mu_xt = alpha_prod_t_prev ** (0.5) * pred_original_sample + pred_sample_direction
     if variance > 0.0:
         noise = (prev_latents - mu_xt) / (variance ** (0.5) * eta)

src/diffusers/pipelines/ledits_pp/pipeline_leditspp_stable_diffusion_xl.py

@@ -1742,7 +1742,7 @@ def compute_noise_ddim(scheduler, prev_latents, latents, timestep, noise_pred, e
     # 6. compute "direction pointing to x_t" of formula (12) from https://arxiv.org/pdf/2010.02502.pdf
     pred_sample_direction = (1 - alpha_prod_t_prev - std_dev_t**2) ** (0.5) * noise_pred
 
-    # modifed so that updated xtm1 is returned as well (to avoid error accumulation)
+    # modified so that updated xtm1 is returned as well (to avoid error accumulation)
     mu_xt = alpha_prod_t_prev ** (0.5) * pred_original_sample + pred_sample_direction
     if variance > 0.0:
         noise = (prev_latents - mu_xt) / (variance ** (0.5) * eta)

src/diffusers/pipelines/marigold/marigold_image_processing.py

@@ -426,7 +426,7 @@ class MarigoldImageProcessor(ConfigMixin):
                 if isinstance(img, np.ndarray):
                     img = torch.from_numpy(img)
                 if not torch.is_floating_point(img):
-                    raise ValueError(f"{prefix}: unexected dtype={img.dtype}.")
+                    raise ValueError(f"{prefix}: unexpected dtype={img.dtype}.")
             else:
                 raise ValueError(f"{prefix}: unexpected type={type(img)}.")
             if val_min != 0.0 or val_max != 1.0:
@@ -464,7 +464,7 @@ class MarigoldImageProcessor(ConfigMixin):
             if torch.is_tensor(img):
                 img = img.cpu().numpy()
             if not np.issubdtype(img.dtype, np.floating):
-                raise ValueError(f"{prefix}: unexected dtype={img.dtype}.")
+                raise ValueError(f"{prefix}: unexpected dtype={img.dtype}.")
             if val_min != 0.0 or val_max != 1.0:
                 img = (img - val_min) / (val_max - val_min)
             img = (img * (2**16 - 1)).astype(np.uint16)

src/diffusers/pipelines/omnigen/pipeline_omnigen.py

@@ -176,7 +176,7 @@ class OmniGenPipeline(
         get the continue embedding of input images by VAE
 
         Args:
-            input_pixel_values: normlized pixel of input images
+            input_pixel_values: normalized pixel of input images
             device:
         Returns: torch.Tensor
         """

src/diffusers/pipelines/pag/pipeline_pag_controlnet_sd_xl_img2img.py

@@ -115,7 +115,7 @@ EXAMPLE_DOC_STRING = """
         ...     with torch.no_grad(), torch.autocast("cuda"):
         ...         depth_map = depth_estimator(image).predicted_depth
 
-        ...     depth_map = torch.nn.fuctional.interpolate(
+        ...     depth_map = torch.nn.functional.interpolate(
         ...         depth_map.unsqueeze(1),
         ...         size=(1024, 1024),
         ...         mode="bicubic",

src/diffusers/pipelines/shap_e/renderer.py

@@ -1038,7 +1038,7 @@ class ShapERenderer(ModelMixin, ConfigMixin):
         textures = _convert_srgb_to_linear(textures)
         textures = textures.float()
 
-        # 3.3 augument the mesh with texture data
+        # 3.3 augment the mesh with texture data
         assert len(textures.shape) == 3 and textures.shape[-1] == len(texture_channels), (
             f"expected [meta_batch x inner_batch x texture_channels] field results, but got {textures.shape}"
         )

src/diffusers/pipelines/stable_cascade/pipeline_stable_cascade.py

@@ -524,9 +524,9 @@ class StableCascadeDecoderPipeline(DiffusionPipeline):
             latents = self.vqgan.config.scale_factor * latents
             images = self.vqgan.decode(latents).sample.clamp(0, 1)
             if output_type == "np":
-                images = images.permute(0, 2, 3, 1).cpu().float().numpy()  # float() as bfloat16-> numpy doesnt work
+                images = images.permute(0, 2, 3, 1).cpu().float().numpy()  # float() as bfloat16-> numpy doesn't work
             elif output_type == "pil":
-                images = images.permute(0, 2, 3, 1).cpu().float().numpy()  # float() as bfloat16-> numpy doesnt work
+                images = images.permute(0, 2, 3, 1).cpu().float().numpy()  # float() as bfloat16-> numpy doesn't work
                 images = self.numpy_to_pil(images)
         else:
             images = latents

src/diffusers/pipelines/stable_cascade/pipeline_stable_cascade_prior.py

@@ -626,11 +626,11 @@ class StableCascadePriorPipeline(DiffusionPipeline):
         self.maybe_free_model_hooks()
 
         if output_type == "np":
-            latents = latents.cpu().float().numpy()  # float() as bfloat16-> numpy doesnt work
-            prompt_embeds = prompt_embeds.cpu().float().numpy()  # float() as bfloat16-> numpy doesnt work
+            latents = latents.cpu().float().numpy()  # float() as bfloat16-> numpy doesn't work
+            prompt_embeds = prompt_embeds.cpu().float().numpy()  # float() as bfloat16-> numpy doesn't work
             negative_prompt_embeds = (
                 negative_prompt_embeds.cpu().float().numpy() if negative_prompt_embeds is not None else None
-            )  # float() as bfloat16-> numpy doesnt work
+            )  # float() as bfloat16-> numpy doesn't work
 
         if not return_dict:
             return (

src/diffusers/pipelines/stable_diffusion_attend_and_excite/pipeline_stable_diffusion_attend_and_excite.py

@@ -1047,7 +1047,7 @@ class StableDiffusionAttendAndExcitePipeline(DiffusionPipeline, StableDiffusionM
 class GaussianSmoothing(torch.nn.Module):
     """
     Arguments:
-    Apply gaussian smoothing on a 1d, 2d or 3d tensor. Filtering is performed seperately for each channel in the input
+    Apply gaussian smoothing on a 1d, 2d or 3d tensor. Filtering is performed separately for each channel in the input
     using a depthwise convolution.
         channels (int, sequence): Number of channels of the input tensors. Output will
             have this number of channels as well.

src/diffusers/pipelines/stable_diffusion_k_diffusion/pipeline_stable_diffusion_k_diffusion.py

@@ -123,7 +123,7 @@ class StableDiffusionKDiffusionPipeline(
         super().__init__()
 
         logger.info(
-            f"{self.__class__} is an experimntal pipeline and is likely to change in the future. We recommend to use"
+            f"{self.__class__} is an experimental pipeline and is likely to change in the future. We recommend to use"
             " this pipeline for fast experimentation / iteration if needed, but advice to rely on existing pipelines"
             " as defined in https://huggingface.co/docs/diffusers/api/schedulers#implemented-schedulers for"
             " production settings."