Fix typos in strings and comments (#11476)

* Fix typos in strings and comments
Signed-off-by: co63oc <co63oc@users.noreply.github.com>

* Update src/diffusers/hooks/hooks.py
Co-authored-by: Aryan <contact.aryanvs@gmail.com>

* Update src/diffusers/hooks/hooks.py
Co-authored-by: Aryan <contact.aryanvs@gmail.com>

* Update layerwise_casting.py

* Apply style fixes

* update

---------
Signed-off-by: co63oc <co63oc@users.noreply.github.com>
Co-authored-by: Aryan <contact.aryanvs@gmail.com>
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>

examples/cogvideo/train_cogvideox_image_to_video_lora.py

@@ -555,7 +555,7 @@ class VideoDataset(Dataset):
 
         if any(not path.is_file() for path in instance_videos):
             raise ValueError(
-                "Expected '--video_column' to be a path to a file in `--instance_data_root` containing line-separated paths to video data but found atleast one path that is not a valid file."
+                "Expected '--video_column' to be a path to a file in `--instance_data_root` containing line-separated paths to video data but found at least one path that is not a valid file."
             )
 
         return instance_prompts, instance_videos

examples/cogvideo/train_cogvideox_lora.py

@@ -539,7 +539,7 @@ class VideoDataset(Dataset):
 
         if any(not path.is_file() for path in instance_videos):
             raise ValueError(
-                "Expected '--video_column' to be a path to a file in `--instance_data_root` containing line-separated paths to video data but found atleast one path that is not a valid file."
+                "Expected '--video_column' to be a path to a file in `--instance_data_root` containing line-separated paths to video data but found at least one path that is not a valid file."
             )
 
         return instance_prompts, instance_videos

examples/research_projects/multi_subject_dreambooth_inpainting/README.md

@@ -73,7 +73,7 @@ accelerate launch train_multi_subject_dreambooth_inpaint.py \
 
 ## 3. Results
 
-A [![Weights & Biases](https://img.shields.io/badge/Weights%20&%20Biases-Report-blue)](https://wandb.ai/gzguevara/uncategorized/reports/Multi-Subject-Dreambooth-for-Inpainting--Vmlldzo2MzY5NDQ4?accessToken=y0nya2d7baguhbryxaikbfr1203amvn1jsmyl07vk122mrs7tnph037u1nqgse8t) is provided showing the training progress by every 50 steps. Note, the reported  weights & baises run was performed on a A100 GPU with the following stetting:
+A [![Weights & Biases](https://img.shields.io/badge/Weights%20&%20Biases-Report-blue)](https://wandb.ai/gzguevara/uncategorized/reports/Multi-Subject-Dreambooth-for-Inpainting--Vmlldzo2MzY5NDQ4?accessToken=y0nya2d7baguhbryxaikbfr1203amvn1jsmyl07vk122mrs7tnph037u1nqgse8t) is provided showing the training progress by every 50 steps. Note, the reported weights & biases run was performed on a A100 GPU with the following stetting:
 
 ```bash
 accelerate launch train_multi_subject_dreambooth_inpaint.py \

src/diffusers/hooks/faster_cache.py

@@ -146,7 +146,7 @@ class FasterCacheConfig:
     alpha_low_frequency: float = 1.1
     alpha_high_frequency: float = 1.1
 
-    # n as described in CFG-Cache explanation in the paper - dependant on the model
+    # n as described in CFG-Cache explanation in the paper - dependent on the model
     unconditional_batch_skip_range: int = 5
     unconditional_batch_timestep_skip_range: Tuple[int, int] = (-1, 641)
 

src/diffusers/hooks/hooks.py

@@ -45,7 +45,7 @@ class ModelHook:
 
     def deinitalize_hook(self, module: torch.nn.Module) -> torch.nn.Module:
         r"""
-        Hook that is executed when a model is deinitalized.
+        Hook that is executed when a model is deinitialized.
 
         Args:
             module (`torch.nn.Module`):

src/diffusers/hooks/layerwise_casting.py

@@ -62,7 +62,7 @@ class LayerwiseCastingHook(ModelHook):
 
     def deinitalize_hook(self, module: torch.nn.Module):
         raise NotImplementedError(
-            "LayerwiseCastingHook does not support deinitalization. A model once enabled with layerwise casting will "
+            "LayerwiseCastingHook does not support deinitialization. A model once enabled with layerwise casting will "
             "have casted its weights to a lower precision dtype for storage. Casting this back to the original dtype "
             "will lead to precision loss, which might have an impact on the model's generation quality. The model should "
             "be re-initialized and loaded in the original dtype."

src/diffusers/loaders/peft.py

@@ -251,7 +251,7 @@ class PeftAdapterMixin:
 
             rank = {}
             for key, val in state_dict.items():
-                # Cannot figure out rank from lora layers that don't have atleast 2 dimensions.
+                # Cannot figure out rank from lora layers that don't have at least 2 dimensions.
                 # Bias layers in LoRA only have a single dimension
                 if "lora_B" in key and val.ndim > 1:
                     # Check out https://github.com/huggingface/peft/pull/2419 for the `^` symbol.

src/diffusers/models/autoencoders/autoencoder_kl.py

@@ -63,8 +63,8 @@ class AutoencoderKL(ModelMixin, ConfigMixin, FromOriginalModelMixin, PeftAdapter
             Synthesis with Latent Diffusion Models](https://huggingface.co/papers/2112.10752) paper.
         force_upcast (`bool`, *optional*, default to `True`):
             If enabled it will force the VAE to run in float32 for high image resolution pipelines, such as SD-XL. VAE
-            can be fine-tuned / trained to a lower range without loosing too much precision in which case
-            `force_upcast` can be set to `False` - see: https://huggingface.co/madebyollin/sdxl-vae-fp16-fix
+            can be fine-tuned / trained to a lower range without losing too much precision in which case `force_upcast`
+            can be set to `False` - see: https://huggingface.co/madebyollin/sdxl-vae-fp16-fix
         mid_block_add_attention (`bool`, *optional*, default to `True`):
             If enabled, the mid_block of the Encoder and Decoder will have attention blocks. If set to false, the
             mid_block will only have resnet blocks

src/diffusers/models/autoencoders/autoencoder_kl_allegro.py

@@ -715,8 +715,8 @@ class AutoencoderKLAllegro(ModelMixin, ConfigMixin):
             Synthesis with Latent Diffusion Models](https://huggingface.co/papers/2112.10752) paper.
         force_upcast (`bool`, default to `True`):
             If enabled it will force the VAE to run in float32 for high image resolution pipelines, such as SD-XL. VAE
-            can be fine-tuned / trained to a lower range without loosing too much precision in which case
-            `force_upcast` can be set to `False` - see: https://huggingface.co/madebyollin/sdxl-vae-fp16-fix
+            can be fine-tuned / trained to a lower range without losing too much precision in which case `force_upcast`
+            can be set to `False` - see: https://huggingface.co/madebyollin/sdxl-vae-fp16-fix
     """
 
     _supports_gradient_checkpointing = True

src/diffusers/models/autoencoders/autoencoder_kl_cogvideox.py

@@ -983,8 +983,8 @@ class AutoencoderKLCogVideoX(ModelMixin, ConfigMixin, FromOriginalModelMixin):
             Synthesis with Latent Diffusion Models](https://huggingface.co/papers/2112.10752) paper.
         force_upcast (`bool`, *optional*, default to `True`):
             If enabled it will force the VAE to run in float32 for high image resolution pipelines, such as SD-XL. VAE
-            can be fine-tuned / trained to a lower range without loosing too much precision in which case
-            `force_upcast` can be set to `False` - see: https://huggingface.co/madebyollin/sdxl-vae-fp16-fix
+            can be fine-tuned / trained to a lower range without losing too much precision in which case `force_upcast`
+            can be set to `False` - see: https://huggingface.co/madebyollin/sdxl-vae-fp16-fix
     """
 
     _supports_gradient_checkpointing = True

src/diffusers/models/autoencoders/autoencoder_kl_temporal_decoder.py

@@ -161,8 +161,8 @@ class AutoencoderKLTemporalDecoder(ModelMixin, ConfigMixin):
             Synthesis with Latent Diffusion Models](https://huggingface.co/papers/2112.10752) paper.
         force_upcast (`bool`, *optional*, default to `True`):
             If enabled it will force the VAE to run in float32 for high image resolution pipelines, such as SD-XL. VAE
-            can be fine-tuned / trained to a lower range without loosing too much precision in which case
-            `force_upcast` can be set to `False` - see: https://huggingface.co/madebyollin/sdxl-vae-fp16-fix
+            can be fine-tuned / trained to a lower range without losing too much precision in which case `force_upcast`
+            can be set to `False` - see: https://huggingface.co/madebyollin/sdxl-vae-fp16-fix
     """
 
     _supports_gradient_checkpointing = True

src/diffusers/pipelines/consisid/consisid_utils.py

@@ -166,7 +166,7 @@ def process_face_embeddings(
         raise RuntimeError("facexlib align face fail")
     align_face = face_helper_1.cropped_faces[0]  # (512, 512, 3)  # RGB
 
-    # incase insightface didn't detect face
+    # in case insightface didn't detect face
     if id_ante_embedding is None:
         logger.warning("Failed to detect face using insightface. Extracting embedding with align face")
         id_ante_embedding = face_helper_2.get_feat(align_face)

tests/lora/utils.py

@@ -1092,7 +1092,7 @@ class PeftLoraLoaderMixinTests:
     def test_simple_inference_with_text_denoiser_multi_adapter_block_lora(self):
         """
         Tests a simple inference with lora attached to text encoder and unet, attaches
-        multiple adapters and set differnt weights for different blocks (i.e. block lora)
+        multiple adapters and set different weights for different blocks (i.e. block lora)
         """
         for scheduler_cls in self.scheduler_classes:
             components, text_lora_config, denoiser_lora_config = self.get_dummy_components(scheduler_cls)
@@ -1636,7 +1636,7 @@ class PeftLoraLoaderMixinTests:
             pipe.fuse_lora(components=self.pipeline_class._lora_loadable_modules, adapter_names=["adapter-1"])
             self.assertTrue(pipe.num_fused_loras == 1, f"{pipe.num_fused_loras=}, {pipe.fused_loras=}")
 
-            # Fusing should still keep the LoRA layers so outpout should remain the same
+            # Fusing should still keep the LoRA layers so output should remain the same
             outputs_lora_1_fused = pipe(**inputs, generator=torch.manual_seed(0))[0]
 
             self.assertTrue(

tests/pipelines/cogvideo/test_cogvideox_image2video.py

@@ -270,7 +270,7 @@ class CogVideoXImageToVideoPipelineFastTests(PipelineTesterMixin, unittest.TestC
         generator_device = "cpu"
         components = self.get_dummy_components()
 
-        # The reason to modify it this way is because I2V Transformer limits the generation to resolutions used during initalization.
+        # The reason to modify it this way is because I2V Transformer limits the generation to resolutions used during initialization.
         # This limitation comes from using learned positional embeddings which cannot be generated on-the-fly like sincos or RoPE embeddings.
         # See the if-statement on "self.use_learned_positional_embeddings" in diffusers/models/embeddings.py
         components["transformer"] = CogVideoXTransformer3DModel.from_config(

tests/pipelines/consisid/test_consisid.py

@@ -280,7 +280,7 @@ class ConsisIDPipelineFastTests(PipelineTesterMixin, unittest.TestCase):
         generator_device = "cpu"
         components = self.get_dummy_components()
 
-        # The reason to modify it this way is because ConsisID Transformer limits the generation to resolutions used during initalization.
+        # The reason to modify it this way is because ConsisID Transformer limits the generation to resolutions used during initialization.
         # This limitation comes from using learned positional embeddings which cannot be generated on-the-fly like sincos or RoPE embeddings.
         # See the if-statement on "self.use_learned_positional_embeddings" in diffusers/models/embeddings.py
         components["transformer"] = ConsisIDTransformer3DModel.from_config(

tests/pipelines/kolors/test_kolors_img2img.py

@@ -155,6 +155,6 @@ class KolorsPipelineImg2ImgFastTests(PipelineTesterMixin, unittest.TestCase):
     def test_float16_inference(self):
         super().test_float16_inference(expected_max_diff=7e-2)
 
-    @unittest.skip("Test not supported because kolors img2img doesn't take pooled embeds as inputs unline kolors t2i.")
+    @unittest.skip("Test not supported because kolors img2img doesn't take pooled embeds as inputs unlike kolors t2i.")
     def test_encode_prompt_works_in_isolation(self):
         pass

tests/pipelines/pag/test_pag_pixart_sigma.py

@@ -254,7 +254,7 @@ class PixArtSigmaPAGPipelineFastTests(PipelineTesterMixin, unittest.TestCase):
             assert_mean_pixel_difference(to_np(output_with_slicing1[0]), to_np(output_without_slicing[0]))
             assert_mean_pixel_difference(to_np(output_with_slicing2[0]), to_np(output_without_slicing[0]))
 
-    # Because we have `pag_applied_layers` we cannot direcly apply
+    # Because we have `pag_applied_layers` we cannot directly apply
     # `set_default_attn_processor`
     def test_dict_tuple_outputs_equivalent(self, expected_slice=None, expected_max_difference=1e-4):
         components = self.get_dummy_components()

tests/pipelines/stable_unclip/test_stable_unclip.py

@@ -227,7 +227,7 @@ class StableUnCLIPPipelineIntegrationTests(unittest.TestCase):
         pipe.enable_sequential_cpu_offload()
 
         generator = torch.Generator(device="cpu").manual_seed(0)
-        output = pipe("anime turle", generator=generator, output_type="np")
+        output = pipe("anime turtle", generator=generator, output_type="np")
 
         image = output.images[0]
 

tests/pipelines/stable_unclip/test_stable_unclip_img2img.py

@@ -250,7 +250,7 @@ class StableUnCLIPImg2ImgPipelineIntegrationTests(unittest.TestCase):
         pipe.enable_sequential_cpu_offload()
 
         generator = torch.Generator(device="cpu").manual_seed(0)
-        output = pipe(input_image, "anime turle", generator=generator, output_type="np")
+        output = pipe(input_image, "anime turtle", generator=generator, output_type="np")
 
         image = output.images[0]
 
@@ -277,7 +277,7 @@ class StableUnCLIPImg2ImgPipelineIntegrationTests(unittest.TestCase):
         pipe.enable_sequential_cpu_offload()
 
         generator = torch.Generator(device="cpu").manual_seed(0)
-        output = pipe(input_image, "anime turle", generator=generator, output_type="np")
+        output = pipe(input_image, "anime turtle", generator=generator, output_type="np")
 
         image = output.images[0]
 

tests/pipelines/test_pipelines_common.py

@@ -2096,11 +2096,11 @@ class PipelineTesterMixin:
         with torch.no_grad():
             encoded_prompt_outputs = pipe_with_just_text_encoder.encode_prompt(**encode_prompt_inputs)
 
-        # Programatically determine the reutrn names of `encode_prompt.`
-        ast_vistor = ReturnNameVisitor()
-        encode_prompt_tree = ast_vistor.get_ast_tree(cls=self.pipeline_class)
-        ast_vistor.visit(encode_prompt_tree)
-        prompt_embed_kwargs = ast_vistor.return_names
+        # Programmatically determine the return names of `encode_prompt.`
+        ast_visitor = ReturnNameVisitor()
+        encode_prompt_tree = ast_visitor.get_ast_tree(cls=self.pipeline_class)
+        ast_visitor.visit(encode_prompt_tree)
+        prompt_embed_kwargs = ast_visitor.return_names
         prompt_embeds_kwargs = dict(zip(prompt_embed_kwargs, encoded_prompt_outputs))
 
         # Pack the outputs of `encode_prompt`.