Fix misc typos (#4479)

Fix typos

src/diffusers/pipelines/controlnet/pipeline_controlnet_img2img.py

@@ -797,7 +797,7 @@ class StableDiffusionControlNetImg2ImgPipeline(
                 instead.
             image (`torch.FloatTensor`, `PIL.Image.Image`, `np.ndarray`, `List[torch.FloatTensor]`, `List[PIL.Image.Image]`, `List[np.ndarray]`,:
                     `List[List[torch.FloatTensor]]`, `List[List[np.ndarray]]` or `List[List[PIL.Image.Image]]`):
-                The initial image will be used as the starting point for the image generation process. Can also accpet
+                The initial image will be used as the starting point for the image generation process. Can also accept
                 image latents as `image`, if passing latents directly, it will not be encoded again.
             control_image (`torch.FloatTensor`, `PIL.Image.Image`, `np.ndarray`, `List[torch.FloatTensor]`, `List[PIL.Image.Image]`, `List[np.ndarray]`,:
                     `List[List[torch.FloatTensor]]`, `List[List[np.ndarray]]` or `List[List[PIL.Image.Image]]`):

src/diffusers/pipelines/kandinsky/pipeline_kandinsky_combined.py

@@ -474,7 +474,7 @@ class KandinskyImg2ImgCombinedPipeline(DiffusionPipeline):
                 The prompt or prompts to guide the image generation.
             image (`torch.FloatTensor`, `PIL.Image.Image`, `np.ndarray`, `List[torch.FloatTensor]`, `List[PIL.Image.Image]`, or `List[np.ndarray]`):
                 `Image`, or tensor representing an image batch, that will be used as the starting point for the
-                process. Can also accpet image latents as `image`, if passing latents directly, it will not be encoded
+                process. Can also accept image latents as `image`, if passing latents directly, it will not be encoded
                 again.
             negative_prompt (`str` or `List[str]`, *optional*):
                 The prompt or prompts not to guide the image generation. Ignored when not using guidance (i.e., ignored
@@ -720,7 +720,7 @@ class KandinskyInpaintCombinedPipeline(DiffusionPipeline):
                 The prompt or prompts to guide the image generation.
             image (`torch.FloatTensor`, `PIL.Image.Image`, `np.ndarray`, `List[torch.FloatTensor]`, `List[PIL.Image.Image]`, or `List[np.ndarray]`):
                 `Image`, or tensor representing an image batch, that will be used as the starting point for the
-                process. Can also accpet image latents as `image`, if passing latents directly, it will not be encoded
+                process. Can also accept image latents as `image`, if passing latents directly, it will not be encoded
                 again.
             mask_image (`np.array`):
                 Tensor representing an image batch, to mask `image`. White pixels in the mask will be repainted, while

src/diffusers/pipelines/kandinsky2_2/pipeline_kandinsky2_2_combined.py

@@ -455,7 +455,7 @@ class KandinskyV22Img2ImgCombinedPipeline(DiffusionPipeline):
                 The prompt or prompts to guide the image generation.
             image (`torch.FloatTensor`, `PIL.Image.Image`, `np.ndarray`, `List[torch.FloatTensor]`, `List[PIL.Image.Image]`, or `List[np.ndarray]`):
                 `Image`, or tensor representing an image batch, that will be used as the starting point for the
-                process. Can also accpet image latents as `image`, if passing latents directly, it will not be encoded
+                process. Can also accept image latents as `image`, if passing latents directly, it will not be encoded
                 again.
             negative_prompt (`str` or `List[str]`, *optional*):
                 The prompt or prompts not to guide the image generation. Ignored when not using guidance (i.e., ignored
@@ -692,7 +692,7 @@ class KandinskyV22InpaintCombinedPipeline(DiffusionPipeline):
                 The prompt or prompts to guide the image generation.
             image (`torch.FloatTensor`, `PIL.Image.Image`, `np.ndarray`, `List[torch.FloatTensor]`, `List[PIL.Image.Image]`, or `List[np.ndarray]`):
                 `Image`, or tensor representing an image batch, that will be used as the starting point for the
-                process. Can also accpet image latents as `image`, if passing latents directly, it will not be encoded
+                process. Can also accept image latents as `image`, if passing latents directly, it will not be encoded
                 again.
             mask_image (`np.array`):
                 Tensor representing an image batch, to mask `image`. White pixels in the mask will be repainted, while

src/diffusers/pipelines/kandinsky2_2/pipeline_kandinsky2_2_controlnet_img2img.py

@@ -258,7 +258,7 @@ class KandinskyV22ControlnetImg2ImgPipeline(DiffusionPipeline):
                 The clip image embeddings for text prompt, that will be used to condition the image generation.
             image (`torch.FloatTensor`, `PIL.Image.Image`, `np.ndarray`, `List[torch.FloatTensor]`, `List[PIL.Image.Image]`, or `List[np.ndarray]`):
                 `Image`, or tensor representing an image batch, that will be used as the starting point for the
-                process. Can also accpet image latents as `image`, if passing latents directly, it will not be encoded
+                process. Can also accept image latents as `image`, if passing latents directly, it will not be encoded
                 again.
             strength (`float`, *optional*, defaults to 0.8):
                 Conceptually, indicates how much to transform the reference `image`. Must be between 0 and 1. `image`

src/diffusers/pipelines/kandinsky2_2/pipeline_kandinsky2_2_img2img.py

@@ -230,7 +230,7 @@ class KandinskyV22Img2ImgPipeline(DiffusionPipeline):
                 The clip image embeddings for text prompt, that will be used to condition the image generation.
             image (`torch.FloatTensor`, `PIL.Image.Image`, `np.ndarray`, `List[torch.FloatTensor]`, `List[PIL.Image.Image]`, or `List[np.ndarray]`):
                 `Image`, or tensor representing an image batch, that will be used as the starting point for the
-                process. Can also accpet image latents as `image`, if passing latents directly, it will not be encoded
+                process. Can also accept image latents as `image`, if passing latents directly, it will not be encoded
                 again.
             strength (`float`, *optional*, defaults to 0.8):
                 Conceptually, indicates how much to transform the reference `image`. Must be between 0 and 1. `image`

src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_pix2pix_zero.py

@@ -1095,7 +1095,7 @@ class StableDiffusionPix2PixZeroPipeline(DiffusionPipeline):
                 The prompt or prompts to guide the image generation. If not defined, one has to pass `prompt_embeds`.
                 instead.
             image (`torch.FloatTensor` `np.ndarray`, `PIL.Image.Image`, `List[torch.FloatTensor]`, `List[PIL.Image.Image]`, or `List[np.ndarray]`):
-                `Image`, or tensor representing an image batch which will be used for conditioning. Can also accpet
+                `Image`, or tensor representing an image batch which will be used for conditioning. Can also accept
                 image latents as `image`, if passing latents directly, it will not be encoded again.
             num_inference_steps (`int`, *optional*, defaults to 50):
                 The number of denoising steps. More denoising steps usually lead to a higher quality image at the

src/diffusers/pipelines/text_to_video_synthesis/pipeline_text_to_video_synth_img2img.py

@@ -561,7 +561,7 @@ class VideoToVideoSDPipeline(DiffusionPipeline, TextualInversionLoaderMixin, Lor
                 The prompt or prompts to guide image generation. If not defined, you need to pass `prompt_embeds`.
             video (`List[np.ndarray]` or `torch.FloatTensor`):
                 `video` frames or tensor representing a video batch to be used as the starting point for the process.
-                Can also accpet video latents as `image`, if passing latents directly, it will not be encoded again.
+                Can also accept video latents as `image`, if passing latents directly, it will not be encoded again.
             strength (`float`, *optional*, defaults to 0.8):
                 Indicates extent to transform the reference `video`. Must be between 0 and 1. `video` is used as a
                 starting point, adding more noise to it the larger the `strength`. The number of denoising steps