Fix typos (#7411)

* Fix typos

* Fix typo in SVD.md

docs/source/en/using-diffusers/svd.md

@@ -21,7 +21,7 @@ This guide will show you how to use SVD to generate short videos from images.
 Before you begin, make sure you have the following libraries installed:
 
 ```py
-!pip install -q -U diffusers transformers accelerate 
+!pip install -q -U diffusers transformers accelerate
 ```
 
 The are two variants of this model, [SVD](https://huggingface.co/stabilityai/stable-video-diffusion-img2vid) and [SVD-XT](https://huggingface.co/stabilityai/stable-video-diffusion-img2vid-xt). The SVD checkpoint is trained to generate 14 frames and the SVD-XT checkpoint is further finetuned to generate 25 frames.
@@ -86,7 +86,7 @@ Video generation is very memory intensive because you're essentially generating
 + frames = pipe(image, decode_chunk_size=2, generator=generator, num_frames=25).frames[0]
 ```
 
-Using all these tricks togethere should lower the memory requirement to less than 8GB VRAM.
+Using all these tricks together should lower the memory requirement to less than 8GB VRAM.
 
 ## Micro-conditioning
 

examples/community/unclip_text_interpolation.py

@@ -48,7 +48,7 @@ class UnCLIPTextInterpolationPipeline(DiffusionPipeline):
             Tokenizer of class
             [CLIPTokenizer](https://huggingface.co/docs/transformers/v4.21.0/en/model_doc/clip#transformers.CLIPTokenizer).
         prior ([`PriorTransformer`]):
-            The canonincal unCLIP prior to approximate the image embedding from the text embedding.
+            The canonical unCLIP prior to approximate the image embedding from the text embedding.
         text_proj ([`UnCLIPTextProjModel`]):
             Utility class to prepare and combine the embeddings before they are passed to the decoder.
         decoder ([`UNet2DConditionModel`]):

src/diffusers/pipelines/kandinsky/pipeline_kandinsky_combined.py

@@ -129,7 +129,7 @@ class KandinskyCombinedPipeline(DiffusionPipeline):
         movq ([`VQModel`]):
             MoVQ Decoder to generate the image from the latents.
         prior_prior ([`PriorTransformer`]):
-            The canonincal unCLIP prior to approximate the image embedding from the text embedding.
+            The canonical unCLIP prior to approximate the image embedding from the text embedding.
         prior_image_encoder ([`CLIPVisionModelWithProjection`]):
             Frozen image-encoder.
         prior_text_encoder ([`CLIPTextModelWithProjection`]):
@@ -346,7 +346,7 @@ class KandinskyImg2ImgCombinedPipeline(DiffusionPipeline):
         movq ([`VQModel`]):
             MoVQ Decoder to generate the image from the latents.
         prior_prior ([`PriorTransformer`]):
-            The canonincal unCLIP prior to approximate the image embedding from the text embedding.
+            The canonical unCLIP prior to approximate the image embedding from the text embedding.
         prior_image_encoder ([`CLIPVisionModelWithProjection`]):
             Frozen image-encoder.
         prior_text_encoder ([`CLIPTextModelWithProjection`]):
@@ -586,7 +586,7 @@ class KandinskyInpaintCombinedPipeline(DiffusionPipeline):
         movq ([`VQModel`]):
             MoVQ Decoder to generate the image from the latents.
         prior_prior ([`PriorTransformer`]):
-            The canonincal unCLIP prior to approximate the image embedding from the text embedding.
+            The canonical unCLIP prior to approximate the image embedding from the text embedding.
         prior_image_encoder ([`CLIPVisionModelWithProjection`]):
             Frozen image-encoder.
         prior_text_encoder ([`CLIPTextModelWithProjection`]):

src/diffusers/pipelines/kandinsky/pipeline_kandinsky_prior.py

@@ -134,7 +134,7 @@ class KandinskyPriorPipeline(DiffusionPipeline):
 
     Args:
         prior ([`PriorTransformer`]):
-            The canonincal unCLIP prior to approximate the image embedding from the text embedding.
+            The canonical unCLIP prior to approximate the image embedding from the text embedding.
         image_encoder ([`CLIPVisionModelWithProjection`]):
             Frozen image-encoder.
         text_encoder ([`CLIPTextModelWithProjection`]):

src/diffusers/pipelines/kandinsky2_2/pipeline_kandinsky2_2_combined.py

@@ -119,7 +119,7 @@ class KandinskyV22CombinedPipeline(DiffusionPipeline):
         movq ([`VQModel`]):
             MoVQ Decoder to generate the image from the latents.
         prior_prior ([`PriorTransformer`]):
-            The canonincal unCLIP prior to approximate the image embedding from the text embedding.
+            The canonical unCLIP prior to approximate the image embedding from the text embedding.
         prior_image_encoder ([`CLIPVisionModelWithProjection`]):
             Frozen image-encoder.
         prior_text_encoder ([`CLIPTextModelWithProjection`]):
@@ -346,7 +346,7 @@ class KandinskyV22Img2ImgCombinedPipeline(DiffusionPipeline):
         movq ([`VQModel`]):
             MoVQ Decoder to generate the image from the latents.
         prior_prior ([`PriorTransformer`]):
-            The canonincal unCLIP prior to approximate the image embedding from the text embedding.
+            The canonical unCLIP prior to approximate the image embedding from the text embedding.
         prior_image_encoder ([`CLIPVisionModelWithProjection`]):
             Frozen image-encoder.
         prior_text_encoder ([`CLIPTextModelWithProjection`]):
@@ -594,7 +594,7 @@ class KandinskyV22InpaintCombinedPipeline(DiffusionPipeline):
         movq ([`VQModel`]):
             MoVQ Decoder to generate the image from the latents.
         prior_prior ([`PriorTransformer`]):
-            The canonincal unCLIP prior to approximate the image embedding from the text embedding.
+            The canonical unCLIP prior to approximate the image embedding from the text embedding.
         prior_image_encoder ([`CLIPVisionModelWithProjection`]):
             Frozen image-encoder.
         prior_text_encoder ([`CLIPTextModelWithProjection`]):

src/diffusers/pipelines/kandinsky2_2/pipeline_kandinsky2_2_prior.py

@@ -90,7 +90,7 @@ class KandinskyV22PriorPipeline(DiffusionPipeline):
 
     Args:
         prior ([`PriorTransformer`]):
-            The canonincal unCLIP prior to approximate the image embedding from the text embedding.
+            The canonical unCLIP prior to approximate the image embedding from the text embedding.
         image_encoder ([`CLIPVisionModelWithProjection`]):
             Frozen image-encoder.
         text_encoder ([`CLIPTextModelWithProjection`]):

src/diffusers/pipelines/kandinsky2_2/pipeline_kandinsky2_2_prior_emb2emb.py

@@ -108,7 +108,7 @@ class KandinskyV22PriorEmb2EmbPipeline(DiffusionPipeline):
 
     Args:
         prior ([`PriorTransformer`]):
-            The canonincal unCLIP prior to approximate the image embedding from the text embedding.
+            The canonical unCLIP prior to approximate the image embedding from the text embedding.
         image_encoder ([`CLIPVisionModelWithProjection`]):
             Frozen image-encoder.
         text_encoder ([`CLIPTextModelWithProjection`]):

src/diffusers/pipelines/shap_e/pipeline_shap_e_img2img.py

@@ -86,7 +86,7 @@ class ShapEImg2ImgPipeline(DiffusionPipeline):
 
     Args:
         prior ([`PriorTransformer`]):
-            The canonincal unCLIP prior to approximate the image embedding from the text embedding.
+            The canonical unCLIP prior to approximate the image embedding from the text embedding.
         image_encoder ([`~transformers.CLIPVisionModel`]):
             Frozen image-encoder.
         image_processor ([`~transformers.CLIPImageProcessor`]):

src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_depth2img.py

@@ -700,8 +700,8 @@ class StableDiffusionDepth2ImgPipeline(DiffusionPipeline, TextualInversionLoader
         >>> url = "http://images.cocodataset.org/val2017/000000039769.jpg"
         >>> init_image = Image.open(requests.get(url, stream=True).raw)
         >>> prompt = "two tigers"
-        >>> n_propmt = "bad, deformed, ugly, bad anotomy"
-        >>> image = pipe(prompt=prompt, image=init_image, negative_prompt=n_propmt, strength=0.7).images[0]
+        >>> n_prompt = "bad, deformed, ugly, bad anotomy"
+        >>> image = pipe(prompt=prompt, image=init_image, negative_prompt=n_prompt, strength=0.7).images[0]
         ```
 
         Returns:

src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_instruct_pix2pix.py

@@ -194,7 +194,7 @@ class StableDiffusionInstructPix2PixPipeline(
                 A higher guidance scale value encourages the model to generate images closely linked to the text
                 `prompt` at the expense of lower image quality. Guidance scale is enabled when `guidance_scale > 1`.
             image_guidance_scale (`float`, *optional*, defaults to 1.5):
-                Push the generated image towards the inital `image`. Image guidance scale is enabled by setting
+                Push the generated image towards the initial `image`. Image guidance scale is enabled by setting
                 `image_guidance_scale > 1`. Higher image guidance scale encourages generated images that are closely
                 linked to the source `image`, usually at the expense of lower image quality. This pipeline requires a
                 value of at least `1`.

src/diffusers/pipelines/stable_diffusion/pipeline_stable_unclip.py

@@ -76,7 +76,7 @@ class StableUnCLIPPipeline(DiffusionPipeline, StableDiffusionMixin, TextualInver
         prior_text_encoder ([`CLIPTextModelWithProjection`]):
             Frozen [`CLIPTextModelWithProjection`] text-encoder.
         prior ([`PriorTransformer`]):
-            The canonincal unCLIP prior to approximate the image embedding from the text embedding.
+            The canonical unCLIP prior to approximate the image embedding from the text embedding.
         prior_scheduler ([`KarrasDiffusionSchedulers`]):
             Scheduler used in the prior denoising process.
         image_normalizer ([`StableUnCLIPImageNormalizer`]):

src/diffusers/pipelines/stable_diffusion_xl/pipeline_stable_diffusion_xl_instruct_pix2pix.py

@@ -659,7 +659,7 @@ class StableDiffusionXLInstructPix2PixPipeline(
                 1`. Higher guidance scale encourages to generate images that are closely linked to the text `prompt`,
                 usually at the expense of lower image quality.
             image_guidance_scale (`float`, *optional*, defaults to 1.5):
-                Image guidance scale is to push the generated image towards the inital image `image`. Image guidance
+                Image guidance scale is to push the generated image towards the initial image `image`. Image guidance
                 scale is enabled by setting `image_guidance_scale > 1`. Higher image guidance scale encourages to
                 generate images that are closely linked to the source image `image`, usually at the expense of lower
                 image quality. This pipeline requires a value of at least `1`.

src/diffusers/schedulers/scheduling_consistency_models.py

@@ -438,7 +438,7 @@ class CMStochasticIterativeScheduler(SchedulerMixin, ConfigMixin):
             # add_noise is called after first denoising step (for inpainting)
             step_indices = [self.step_index] * timesteps.shape[0]
         else:
-            # add noise is called bevore first denoising step to create inital latent(img2img)
+            # add noise is called before first denoising step to create initial latent(img2img)
             step_indices = [self.begin_index] * timesteps.shape[0]
 
         sigma = sigmas[step_indices].flatten()

src/diffusers/schedulers/scheduling_deis_multistep.py

@@ -775,7 +775,7 @@ class DEISMultistepScheduler(SchedulerMixin, ConfigMixin):
             # add_noise is called after first denoising step (for inpainting)
             step_indices = [self.step_index] * timesteps.shape[0]
         else:
-            # add noise is called bevore first denoising step to create inital latent(img2img)
+            # add noise is called before first denoising step to create initial latent(img2img)
             step_indices = [self.begin_index] * timesteps.shape[0]
 
         sigma = sigmas[step_indices].flatten()

src/diffusers/schedulers/scheduling_dpmsolver_multistep.py

@@ -1018,7 +1018,7 @@ class DPMSolverMultistepScheduler(SchedulerMixin, ConfigMixin):
             # add_noise is called after first denoising step (for inpainting)
             step_indices = [self.step_index] * timesteps.shape[0]
         else:
-            # add noise is called bevore first denoising step to create inital latent(img2img)
+            # add noise is called before first denoising step to create initial latent(img2img)
             step_indices = [self.begin_index] * timesteps.shape[0]
 
         sigma = sigmas[step_indices].flatten()

src/diffusers/schedulers/scheduling_dpmsolver_sde.py

@@ -547,7 +547,7 @@ class DPMSolverSDEScheduler(SchedulerMixin, ConfigMixin):
             # add_noise is called after first denoising step (for inpainting)
             step_indices = [self.step_index] * timesteps.shape[0]
         else:
-            # add noise is called bevore first denoising step to create inital latent(img2img)
+            # add noise is called before first denoising step to create initial latent(img2img)
             step_indices = [self.begin_index] * timesteps.shape[0]
 
         sigma = sigmas[step_indices].flatten()

src/diffusers/schedulers/scheduling_dpmsolver_singlestep.py

@@ -968,7 +968,7 @@ class DPMSolverSinglestepScheduler(SchedulerMixin, ConfigMixin):
             # add_noise is called after first denoising step (for inpainting)
             step_indices = [self.step_index] * timesteps.shape[0]
         else:
-            # add noise is called bevore first denoising step to create inital latent(img2img)
+            # add noise is called before first denoising step to create initial latent(img2img)
             step_indices = [self.begin_index] * timesteps.shape[0]
 
         sigma = sigmas[step_indices].flatten()

src/diffusers/schedulers/scheduling_edm_dpmsolver_multistep.py

@@ -673,7 +673,7 @@ class EDMDPMSolverMultistepScheduler(SchedulerMixin, ConfigMixin):
             # add_noise is called after first denoising step (for inpainting)
             step_indices = [self.step_index] * timesteps.shape[0]
         else:
-            # add noise is called bevore first denoising step to create inital latent(img2img)
+            # add noise is called before first denoising step to create initial latent(img2img)
             step_indices = [self.begin_index] * timesteps.shape[0]
 
         sigma = sigmas[step_indices].flatten()

src/diffusers/schedulers/scheduling_edm_euler.py

@@ -371,7 +371,7 @@ class EDMEulerScheduler(SchedulerMixin, ConfigMixin):
             # add_noise is called after first denoising step (for inpainting)
             step_indices = [self.step_index] * timesteps.shape[0]
         else:
-            # add noise is called bevore first denoising step to create inital latent(img2img)
+            # add noise is called before first denoising step to create initial latent(img2img)
             step_indices = [self.begin_index] * timesteps.shape[0]
 
         sigma = sigmas[step_indices].flatten()

src/diffusers/schedulers/scheduling_euler_ancestral_discrete.py

@@ -471,7 +471,7 @@ class EulerAncestralDiscreteScheduler(SchedulerMixin, ConfigMixin):
             # add_noise is called after first denoising step (for inpainting)
             step_indices = [self.step_index] * timesteps.shape[0]
         else:
-            # add noise is called bevore first denoising step to create inital latent(img2img)
+            # add noise is called before first denoising step to create initial latent(img2img)
             step_indices = [self.begin_index] * timesteps.shape[0]
 
         sigma = sigmas[step_indices].flatten()