Fix typos in comments and docstrings

src/diffusers/pipelines/chroma/pipeline_chroma_inpainting.py

@@ -703,7 +703,7 @@ def prepare_mask_latents(
                 )
             masked_image_latents = masked_image_latents.repeat(batch_size // masked_image_latents.shape[0], 1, 1, 1)
 
-        # aligning device to prevent device errors when concating it with the latent model input
+        # aligning device to prevent device errors when concatenating it with the latent model input
         masked_image_latents = masked_image_latents.to(device=device, dtype=dtype)
         masked_image_latents = self._pack_latents(
             masked_image_latents,

src/diffusers/pipelines/controlnet/pipeline_controlnet_inpaint.py

@@ -945,7 +945,7 @@ def prepare_mask_latents(
             torch.cat([masked_image_latents] * 2) if do_classifier_free_guidance else masked_image_latents
         )
 
-        # aligning device to prevent device errors when concating it with the latent model input
+        # aligning device to prevent device errors when concatenating it with the latent model input
         masked_image_latents = masked_image_latents.to(device=device, dtype=dtype)
         return mask, masked_image_latents
 

src/diffusers/pipelines/controlnet/pipeline_controlnet_inpaint_sd_xl.py

@@ -1035,7 +1035,7 @@ def prepare_mask_latents(
                 torch.cat([masked_image_latents] * 2) if do_classifier_free_guidance else masked_image_latents
             )
 
-            # aligning device to prevent device errors when concating it with the latent model input
+            # aligning device to prevent device errors when concatenating it with the latent model input
             masked_image_latents = masked_image_latents.to(device=device, dtype=dtype)
 
         return mask, masked_image_latents

src/diffusers/pipelines/controlnet/pipeline_controlnet_union_inpaint_sd_xl.py

@@ -1015,7 +1015,7 @@ def prepare_mask_latents(
                 torch.cat([masked_image_latents] * 2) if do_classifier_free_guidance else masked_image_latents
             )
 
-            # aligning device to prevent device errors when concating it with the latent model input
+            # aligning device to prevent device errors when concatenating it with the latent model input
             masked_image_latents = masked_image_latents.to(device=device, dtype=dtype)
 
         return mask, masked_image_latents

src/diffusers/pipelines/deprecated/paint_by_example/pipeline_paint_by_example.py

@@ -350,7 +350,7 @@ def prepare_mask_latents(
             torch.cat([masked_image_latents] * 2) if do_classifier_free_guidance else masked_image_latents
         )
 
-        # aligning device to prevent device errors when concating it with the latent model input
+        # aligning device to prevent device errors when concatenating it with the latent model input
         masked_image_latents = masked_image_latents.to(device=device, dtype=dtype)
         return mask, masked_image_latents
 

src/diffusers/pipelines/easyanimate/pipeline_easyanimate_inpaint.py

@@ -681,7 +681,7 @@ def prepare_mask_latents(
             masked_image_latents = torch.cat(new_mask_pixel_values, dim=0)
             masked_image_latents = masked_image_latents * self.vae.config.scaling_factor
 
-            # aligning device to prevent device errors when concating it with the latent model input
+            # aligning device to prevent device errors when concatenating it with the latent model input
             masked_image_latents = masked_image_latents.to(device=device, dtype=dtype)
         else:
             masked_image_latents = None

src/diffusers/pipelines/flux/pipeline_flux_control_inpaint.py

@@ -766,7 +766,7 @@ def prepare_mask_latents(
                 )
             masked_image_latents = masked_image_latents.repeat(batch_size // masked_image_latents.shape[0], 1, 1, 1)
 
-        # aligning device to prevent device errors when concating it with the latent model input
+        # aligning device to prevent device errors when concatenating it with the latent model input
         masked_image_latents = masked_image_latents.to(device=device, dtype=dtype)
         masked_image_latents = self._pack_latents(
             masked_image_latents,

src/diffusers/pipelines/flux/pipeline_flux_controlnet_inpainting.py

@@ -666,7 +666,7 @@ def prepare_mask_latents(
                 )
             masked_image_latents = masked_image_latents.repeat(batch_size // masked_image_latents.shape[0], 1, 1, 1)
 
-        # aligning device to prevent device errors when concating it with the latent model input
+        # aligning device to prevent device errors when concatenating it with the latent model input
         masked_image_latents = masked_image_latents.to(device=device, dtype=dtype)
         masked_image_latents = self._pack_latents(
             masked_image_latents,

src/diffusers/pipelines/flux/pipeline_flux_inpaint.py

@@ -737,7 +737,7 @@ def prepare_mask_latents(
                 )
             masked_image_latents = masked_image_latents.repeat(batch_size // masked_image_latents.shape[0], 1, 1, 1)
 
-        # aligning device to prevent device errors when concating it with the latent model input
+        # aligning device to prevent device errors when concatenating it with the latent model input
         masked_image_latents = masked_image_latents.to(device=device, dtype=dtype)
         masked_image_latents = self._pack_latents(
             masked_image_latents,

src/diffusers/pipelines/flux/pipeline_flux_kontext_inpaint.py

@@ -898,7 +898,7 @@ def prepare_mask_latents(
                 )
             masked_image_latents = masked_image_latents.repeat(batch_size // masked_image_latents.shape[0], 1, 1, 1)
 
-        # aligning device to prevent device errors when concating it with the latent model input
+        # aligning device to prevent device errors when concatenating it with the latent model input
         masked_image_latents = masked_image_latents.to(device=device, dtype=dtype)
         masked_image_latents = self._pack_latents(
             masked_image_latents,

src/diffusers/pipelines/ltx2/pipeline_ltx2.py

@@ -244,7 +244,7 @@ def __init__(
         self.vae_temporal_compression_ratio = (
             self.vae.temporal_compression_ratio if getattr(self, "vae", None) is not None else 8
         )
-        # TODO: check whether the MEL compression ratio logic here is corrct
+        # TODO: check whether the MEL compression ratio logic here is correct
         self.audio_vae_mel_compression_ratio = (
             self.audio_vae.mel_compression_ratio if getattr(self, "audio_vae", None) is not None else 4
         )

src/diffusers/pipelines/ltx2/pipeline_ltx2_condition.py

@@ -235,7 +235,7 @@ 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
 

src/diffusers/pipelines/ltx2/pipeline_ltx2_image2video.py

@@ -247,7 +247,7 @@ def __init__(
         self.vae_temporal_compression_ratio = (
             self.vae.temporal_compression_ratio if getattr(self, "vae", None) is not None else 8
         )
-        # TODO: check whether the MEL compression ratio logic here is corrct
+        # TODO: check whether the MEL compression ratio logic here is correct
         self.audio_vae_mel_compression_ratio = (
             self.audio_vae.mel_compression_ratio if getattr(self, "audio_vae", None) is not None else 4
         )

src/diffusers/pipelines/pag/pipeline_pag_controlnet_sd_inpaint.py

@@ -896,7 +896,7 @@ def prepare_mask_latents(
             torch.cat([masked_image_latents] * 2) if do_classifier_free_guidance else masked_image_latents
         )
 
-        # aligning device to prevent device errors when concating it with the latent model input
+        # aligning device to prevent device errors when concatenating it with the latent model input
         masked_image_latents = masked_image_latents.to(device=device, dtype=dtype)
         return mask, masked_image_latents
 

src/diffusers/pipelines/pag/pipeline_pag_sd_inpaint.py

@@ -829,7 +829,7 @@ def prepare_mask_latents(
             torch.cat([masked_image_latents] * 2) if do_classifier_free_guidance else masked_image_latents
         )
 
-        # aligning device to prevent device errors when concating it with the latent model input
+        # aligning device to prevent device errors when concatenating it with the latent model input
         masked_image_latents = masked_image_latents.to(device=device, dtype=dtype)
         return mask, masked_image_latents
 

src/diffusers/pipelines/pag/pipeline_pag_sd_xl_inpaint.py

@@ -899,7 +899,7 @@ def prepare_mask_latents(
                 torch.cat([masked_image_latents] * 2) if do_classifier_free_guidance else masked_image_latents
             )
 
-            # aligning device to prevent device errors when concating it with the latent model input
+            # aligning device to prevent device errors when concatenating it with the latent model input
             masked_image_latents = masked_image_latents.to(device=device, dtype=dtype)
 
         return mask, masked_image_latents

src/diffusers/pipelines/qwenimage/pipeline_qwenimage_edit_inpaint.py

@@ -648,7 +648,7 @@ def prepare_mask_latents(
                 )
             masked_image_latents = masked_image_latents.repeat(batch_size // masked_image_latents.shape[0], 1, 1, 1, 1)
 
-        # aligning device to prevent device errors when concating it with the latent model input
+        # aligning device to prevent device errors when concatenating it with the latent model input
         masked_image_latents = masked_image_latents.to(device=device, dtype=dtype)
 
         masked_image_latents = self._pack_latents(

src/diffusers/pipelines/qwenimage/pipeline_qwenimage_inpaint.py

@@ -603,7 +603,7 @@ def prepare_mask_latents(
                 )
             masked_image_latents = masked_image_latents.repeat(batch_size // masked_image_latents.shape[0], 1, 1, 1, 1)
 
-        # aligning device to prevent device errors when concating it with the latent model input
+        # aligning device to prevent device errors when concatenating it with the latent model input
         masked_image_latents = masked_image_latents.to(device=device, dtype=dtype)
 
         masked_image_latents = self._pack_latents(

src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_inpaint.py

@@ -803,7 +803,7 @@ def prepare_mask_latents(
             torch.cat([masked_image_latents] * 2) if do_classifier_free_guidance else masked_image_latents
         )
 
-        # aligning device to prevent device errors when concating it with the latent model input
+        # aligning device to prevent device errors when concatenating it with the latent model input
         masked_image_latents = masked_image_latents.to(device=device, dtype=dtype)
         return mask, masked_image_latents
 

src/diffusers/pipelines/stable_diffusion_3/pipeline_stable_diffusion_3_inpaint.py

@@ -809,7 +809,7 @@ def prepare_mask_latents(
             torch.cat([masked_image_latents] * 2) if do_classifier_free_guidance else masked_image_latents
         )
 
-        # aligning device to prevent device errors when concating it with the latent model input
+        # aligning device to prevent device errors when concatenating it with the latent model input
         masked_image_latents = masked_image_latents.to(device=device, dtype=dtype)
         return mask, masked_image_latents
 

src/diffusers/pipelines/stable_diffusion_xl/pipeline_stable_diffusion_xl_inpaint.py

@@ -899,7 +899,7 @@ def prepare_mask_latents(
                 torch.cat([masked_image_latents] * 2) if do_classifier_free_guidance else masked_image_latents
             )
 
-            # aligning device to prevent device errors when concating it with the latent model input
+            # aligning device to prevent device errors when concatenating it with the latent model input
             masked_image_latents = masked_image_latents.to(device=device, dtype=dtype)
 
         return mask, masked_image_latents

src/diffusers/pipelines/visualcloze/pipeline_visualcloze_combined.py

@@ -223,7 +223,7 @@ def check_inputs(
                     f"got {type(task_prompt)} and {type(content_prompt)}"
                 )
             if len(content_prompt) != len(task_prompt):
-                raise ValueError("`task_prompt` and `content_prompt` must have the same length whe they are lists.")
+                raise ValueError("`task_prompt` and `content_prompt` must have the same length when they are lists.")
 
             for sample in image:
                 if not isinstance(sample, list) or not isinstance(sample[0], list):

src/diffusers/pipelines/visualcloze/pipeline_visualcloze_generation.py

@@ -443,7 +443,7 @@ def check_inputs(
                     f"got {type(task_prompt)} and {type(content_prompt)}"
                 )
             if len(content_prompt) != len(task_prompt):
-                raise ValueError("`task_prompt` and `content_prompt` must have the same length whe they are lists.")
+                raise ValueError("`task_prompt` and `content_prompt` must have the same length when they are lists.")
 
             for sample in image:
                 if not isinstance(sample, list) or not isinstance(sample[0], list):