Fix typos and add Typo check GitHub Action (#483)

* Fix typos

* Add a typo check action

* Fix a bug

* Changed to manual typo check currently

Ref: https://github.com/huggingface/diffusers/pull/483#pullrequestreview-1104468010

Co-authored-by: Anton Lozhkov <aglozhkov@gmail.com>

* Removed a confusing message

* Renamed "nin_shortcut" to "in_shortcut"

* Add memo about NIN
Co-authored-by: Anton Lozhkov <aglozhkov@gmail.com>

src/diffusers/pipelines/latent_diffusion/pipeline_latent_diffusion.py

@@ -85,7 +85,7 @@ class LDMTextToImagePipeline(DiffusionPipeline):
                 deterministic.
             output_type (`str`, *optional*, defaults to `"pil"`):
                 The output format of the generate image. Choose between
-                [PIL](https://pillow.readthedocs.io/en/stable/): `PIL.Image.Image` or `nd.array`.
+                [PIL](https://pillow.readthedocs.io/en/stable/): `PIL.Image.Image` or `np.array`.
             return_dict (`bool`, *optional*):
                 Whether or not to return a [`~pipeline_utils.ImagePipelineOutput`] instead of a plain tuple.
 

src/diffusers/pipelines/latent_diffusion_uncond/pipeline_latent_diffusion_uncond.py

@@ -50,7 +50,7 @@ class LDMPipeline(DiffusionPipeline):
                 expense of slower inference.
             output_type (`str`, *optional*, defaults to `"pil"`):
                 The output format of the generate image. Choose between
-                [PIL](https://pillow.readthedocs.io/en/stable/): `PIL.Image.Image` or `nd.array`.
+                [PIL](https://pillow.readthedocs.io/en/stable/): `PIL.Image.Image` or `np.array`.
             return_dict (`bool`, *optional*, defaults to `True`):
                 Whether or not to return a [`~pipeline_utils.ImagePipelineOutput`] instead of a plain tuple.
 

src/diffusers/pipelines/pndm/pipeline_pndm.py

@@ -63,7 +63,7 @@ class PNDMPipeline(DiffusionPipeline):
                 generator](https://pytorch.org/docs/stable/generated/torch.Generator.html) to make generation
                 deterministic.
             output_type (`str`, `optional`, defaults to `"pil"`): The output format of the generate image. Choose
-                between [PIL](https://pillow.readthedocs.io/en/stable/): `PIL.Image.Image` or `nd.array`.
+                between [PIL](https://pillow.readthedocs.io/en/stable/): `PIL.Image.Image` or `np.array`.
             return_dict (`bool`, `optional`, defaults to `True`): Whether or not to return a
                 [`~pipeline_utils.ImagePipelineOutput`] instead of a plain tuple.
 

src/diffusers/pipelines/score_sde_ve/pipeline_score_sde_ve.py

@@ -43,7 +43,7 @@ class ScoreSdeVePipeline(DiffusionPipeline):
                 deterministic.
             output_type (`str`, *optional*, defaults to `"pil"`):
                 The output format of the generate image. Choose between
-                [PIL](https://pillow.readthedocs.io/en/stable/): `PIL.Image.Image` or `nd.array`.
+                [PIL](https://pillow.readthedocs.io/en/stable/): `PIL.Image.Image` or `np.array`.
             return_dict (`bool`, *optional*, defaults to `True`):
                 Whether or not to return a [`~pipeline_utils.ImagePipelineOutput`] instead of a plain tuple.
 

src/diffusers/pipelines/stable_diffusion/README.md

@@ -12,7 +12,7 @@ The summary of the model is the following:
 
 - Stable Diffusion has the same architecture as [Latent Diffusion](https://arxiv.org/abs/2112.10752) but uses a frozen CLIP Text Encoder instead of training the text encoder jointly with the diffusion model.
 - An in-detail explanation of the Stable Diffusion model can be found under [Stable Diffusion with 🧨 Diffusers](https://huggingface.co/blog/stable_diffusion).
-- If you don't want to rely on the Hugging Face Hub and having to pass a authentification token, you can 
+- If you don't want to rely on the Hugging Face Hub and having to pass a authentication token, you can 
 download the weights with `git lfs install; git clone https://huggingface.co/CompVis/stable-diffusion-v1-4` and instead pass the local path to the cloned folder to `from_pretrained` as shown below.
 - Stable Diffusion can work with a variety of different samplers as is shown below.
 

src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion.py

@@ -136,7 +136,7 @@ class StableDiffusionPipeline(DiffusionPipeline):
                 tensor will ge generated by sampling using the supplied random `generator`.
             output_type (`str`, *optional*, defaults to `"pil"`):
                 The output format of the generate image. Choose between
-                [PIL](https://pillow.readthedocs.io/en/stable/): `PIL.Image.Image` or `nd.array`.
+                [PIL](https://pillow.readthedocs.io/en/stable/): `PIL.Image.Image` or `np.array`.
             return_dict (`bool`, *optional*, defaults to `True`):
                 Whether or not to return a [`~pipelines.stable_diffusion.StableDiffusionPipelineOutput`] instead of a
                 plain tuple.
@@ -224,7 +224,7 @@ class StableDiffusionPipeline(DiffusionPipeline):
 
         self.scheduler.set_timesteps(num_inference_steps, **extra_set_kwargs)
 
-        # if we use LMSDiscreteScheduler, let's make sure latents are mulitplied by sigmas
+        # if we use LMSDiscreteScheduler, let's make sure latents are multiplied by sigmas
         if isinstance(self.scheduler, LMSDiscreteScheduler):
             latents = latents * self.scheduler.sigmas[0]
 

src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_img2img.py

@@ -146,7 +146,7 @@ class StableDiffusionImg2ImgPipeline(DiffusionPipeline):
                 deterministic.
             output_type (`str`, *optional*, defaults to `"pil"`):
                 The output format of the generate image. Choose between
-                [PIL](https://pillow.readthedocs.io/en/stable/): `PIL.Image.Image` or `nd.array`.
+                [PIL](https://pillow.readthedocs.io/en/stable/): `PIL.Image.Image` or `np.array`.
             return_dict (`bool`, *optional*, defaults to `True`):
                 Whether or not to return a [`~pipelines.stable_diffusion.StableDiffusionPipelineOutput`] instead of a
                 plain tuple.
@@ -249,7 +249,7 @@ class StableDiffusionImg2ImgPipeline(DiffusionPipeline):
             # expand the latents if we are doing classifier free guidance
             latent_model_input = torch.cat([latents] * 2) if do_classifier_free_guidance else latents
 
-            # if we use LMSDiscreteScheduler, let's make sure latents are mulitplied by sigmas
+            # if we use LMSDiscreteScheduler, let's make sure latents are multiplied by sigmas
             if isinstance(self.scheduler, LMSDiscreteScheduler):
                 sigma = self.scheduler.sigmas[t_index]
                 # the model input needs to be scaled to match the continuous ODE formulation in K-LMS

src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_inpaint.py

@@ -169,7 +169,7 @@ class StableDiffusionInpaintPipeline(DiffusionPipeline):
                 deterministic.
             output_type (`str`, *optional*, defaults to `"pil"`):
                 The output format of the generate image. Choose between
-                [PIL](https://pillow.readthedocs.io/en/stable/): `PIL.Image.Image` or `nd.array`.
+                [PIL](https://pillow.readthedocs.io/en/stable/): `PIL.Image.Image` or `np.array`.
             return_dict (`bool`, *optional*, defaults to `True`):
                 Whether or not to return a [`~pipelines.stable_diffusion.StableDiffusionPipelineOutput`] instead of a
                 plain tuple.

src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_onnx.py

@@ -107,7 +107,7 @@ class StableDiffusionOnnxPipeline(DiffusionPipeline):
 
         self.scheduler.set_timesteps(num_inference_steps, **extra_set_kwargs)
 
-        # if we use LMSDiscreteScheduler, let's make sure latents are mulitplied by sigmas
+        # if we use LMSDiscreteScheduler, let's make sure latents are multiplied by sigmas
         if isinstance(self.scheduler, LMSDiscreteScheduler):
             latents = latents * self.scheduler.sigmas[0]
 

src/diffusers/pipelines/stochastic_karras_ve/pipeline_stochastic_karras_ve.py

@@ -55,7 +55,7 @@ class KarrasVePipeline(DiffusionPipeline):
                 expense of slower inference.
             output_type (`str`, *optional*, defaults to `"pil"`):
                 The output format of the generate image. Choose between
-                [PIL](https://pillow.readthedocs.io/en/stable/): `PIL.Image.Image` or `nd.array`.
+                [PIL](https://pillow.readthedocs.io/en/stable/): `PIL.Image.Image` or `np.array`.
             return_dict (`bool`, *optional*, defaults to `True`):
                 Whether or not to return a [`~pipeline_utils.ImagePipelineOutput`] instead of a plain tuple.
 

src/diffusers/schedulers/README.md

 # Schedulers
 
 - Schedulers are the algorithms to use diffusion models in inference as well as for training. They include the noise schedules and define algorithm-specific diffusion steps.
-- Schedulers can be used interchangable between diffusion models in inference to find the preferred trade-off between speed and generation quality.
+- Schedulers can be used interchangeable between diffusion models in inference to find the preferred trade-off between speed and generation quality.
 - Schedulers are available in numpy, but can easily be transformed into PyTorch.
 
 ## API

src/diffusers/schedulers/scheduling_karras_ve.py

@@ -34,7 +34,7 @@ class KarrasVeOutput(BaseOutput):
             Computed sample (x_{t-1}) of previous timestep. `prev_sample` should be used as next model input in the
             denoising loop.
         derivative (`torch.FloatTensor` of shape `(batch_size, num_channels, height, width)` for images):
-            Derivate of predicted original image sample (x_0).
+            Derivative of predicted original image sample (x_0).
     """
 
     prev_sample: torch.FloatTensor

src/diffusers/schedulers/scheduling_sde_vp.py

@@ -14,7 +14,7 @@
 
 # DISCLAIMER: This file is strongly influenced by https://github.com/yang-song/score_sde_pytorch
 
-# TODO(Patrick, Anton, Suraj) - make scheduler framework indepedent and clean-up a bit
+# TODO(Patrick, Anton, Suraj) - make scheduler framework independent and clean-up a bit
 
 import numpy as np
 import torch

tests/test_modeling_common.py

@@ -145,7 +145,7 @@ class ModelTesterMixin:
             new_model.to(torch_device)
             new_model.eval()
 
-        # check if all paramters shape are the same
+        # check if all parameters shape are the same
         for param_name in model.state_dict().keys():
             param_1 = model.state_dict()[param_name]
             param_2 = new_model.state_dict()[param_name]

utils/check_inits.py

@@ -288,7 +288,7 @@ def check_submodules():
     if len(module_not_registered) > 0:
         list_of_modules = "\n".join(f"- {module}" for module in module_not_registered)
         raise ValueError(
-            "The following submodules are not properly registed in the main init of Transformers:\n"
+            "The following submodules are not properly registered in the main init of Transformers:\n"
             f"{list_of_modules}\n"
             "Make sure they appear somewhere in the keys of `_import_structure` with an empty list as value."
         )

utils/check_table.py

@@ -53,7 +53,7 @@ def _find_text_in_file(filename, start_prompt, end_prompt):
     return "".join(lines[start_index:end_index]), start_index, end_index, lines
 
 
-# Add here suffixes that are used to identify models, seperated by |
+# Add here suffixes that are used to identify models, separated by |
 ALLOWED_MODEL_SUFFIXES = "Model|Encoder|Decoder|ForConditionalGeneration"
 # Regexes that match TF/Flax/PT model names.
 _re_tf_models = re.compile(r"TF(.*)(?:Model|Encoder|Decoder|ForConditionalGeneration)")
@@ -88,11 +88,11 @@ def _center_text(text, width):
 def get_model_table_from_auto_modules():
     """Generates an up-to-date model table from the content of the auto modules."""
     # Dictionary model names to config.
-    config_maping_names = diffusers_module.models.auto.configuration_auto.CONFIG_MAPPING_NAMES
+    config_mapping_names = diffusers_module.models.auto.configuration_auto.CONFIG_MAPPING_NAMES
     model_name_to_config = {
-        name: config_maping_names[code]
+        name: config_mapping_names[code]
         for code, name in diffusers_module.MODEL_NAMES_MAPPING.items()
-        if code in config_maping_names
+        if code in config_mapping_names
     }
     model_name_to_prefix = {name: config.replace("ConfigMixin", "") for name, config in model_name_to_config.items()}
 

utils/check_tf_ops.py

@@ -41,7 +41,7 @@ INTERNAL_OPS = [
 ]
 
 
-def onnx_compliancy(saved_model_path, strict, opset):
+def onnx_compliance(saved_model_path, strict, opset):
     saved_model = SavedModel()
     onnx_ops = []
 
@@ -98,4 +98,4 @@ if __name__ == "__main__":
     args = parser.parse_args()
 
     if args.framework == "onnx":
-        onnx_compliancy(args.saved_model_path, args.strict, args.opset)
+        onnx_compliance(args.saved_model_path, args.strict, args.opset)

utils/custom_init_isort.py

@@ -178,7 +178,7 @@ def sort_imports(file, check_only=True):
         code, start_prompt="_import_structure = {", end_prompt="if TYPE_CHECKING:"
     )
 
-    # We ignore block 0 (everything untils start_prompt) and the last block (everything after end_prompt).
+    # We ignore block 0 (everything until start_prompt) and the last block (everything after end_prompt).
     for block_idx in range(1, len(main_blocks) - 1):
         # Check if the block contains some `_import_structure`s thingy to sort.
         block = main_blocks[block_idx]
@@ -202,7 +202,7 @@ def sort_imports(file, check_only=True):
         internal_blocks = split_code_in_indented_blocks(internal_block_code, indent_level=indent)
         # We have two categories of import key: list or _import_structu[key].append/extend
         pattern = _re_direct_key if "_import_structure" in block_lines[0] else _re_indirect_key
-        # Grab the keys, but there is a trap: some lines are empty or jsut comments.
+        # Grab the keys, but there is a trap: some lines are empty or just comments.
         keys = [(pattern.search(b).groups()[0] if pattern.search(b) is not None else None) for b in internal_blocks]
         # We only sort the lines with a key.
         keys_to_sort = [(i, key) for i, key in enumerate(keys) if key is not None]