Fix typos (#7181)

* Fix typos

* Fix typos

* Fix typos and update documentation in lora.md

docs/source/en/training/lora.md

@@ -77,7 +77,7 @@ accelerate config default
 
 Or if your environment doesn't support an interactive shell, like a notebook, you can use:
 
-```bash
+```py
 from accelerate.utils import write_basic_config
 
 write_basic_config()
@@ -170,7 +170,7 @@ Aside from setting up the LoRA layers, the training script is more or less the s
 
 Once you've made all your changes or you're okay with the default configuration, you're ready to launch the training script! 🚀
 
-Let's train on the [Pokémon BLIP captions](https://huggingface.co/datasets/lambdalabs/pokemon-blip-captions) dataset to generate our yown Pokémon. Set the environment variables `MODEL_NAME` and `DATASET_NAME` to the model and dataset respectively. You should also specify where to save the model in `OUTPUT_DIR`, and the name of the model to save to on the Hub with `HUB_MODEL_ID`. The script creates and saves the following files to your repository:
+Let's train on the [Pokémon BLIP captions](https://huggingface.co/datasets/lambdalabs/pokemon-blip-captions) dataset to generate our own Pokémon. Set the environment variables `MODEL_NAME` and `DATASET_NAME` to the model and dataset respectively. You should also specify where to save the model in `OUTPUT_DIR`, and the name of the model to save to on the Hub with `HUB_MODEL_ID`. The script creates and saves the following files to your repository:
 
 - saved model checkpoints
 - `pytorch_lora_weights.safetensors` (the trained LoRA weights)

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

@@ -128,7 +128,7 @@ seed = 2023
 # The values come from
 # https://github.com/lyn-rgb/FreeU_Diffusers#video-pipelines
 pipe.enable_freeu(b1=1.2, b2=1.4, s1=0.9, s2=0.2)
-video_frames = pipe(prompt, height=320, width=576, num_frames=30, generator=torch.manual_seed(seed)).frames
+video_frames = pipe(prompt, height=320, width=576, num_frames=30, generator=torch.manual_seed(seed)).frames[0]
 export_to_video(video_frames, "astronaut_rides_horse.mp4")
 ```
 

examples/community/README.md

@@ -3493,7 +3493,7 @@ output_frames = pipe(
     mask_end=0.8,
     mask_strength=0.5,
     negative_prompt='longbody, lowres, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality'
-).frames
+).frames[0]
 
 export_to_video(
     output_frames, "/path/to/video.mp4", 5)

src/diffusers/configuration_utils.py

@@ -127,7 +127,7 @@ class ConfigMixin:
         """The only reason we overwrite `getattr` here is to gracefully deprecate accessing
         config attributes directly. See https://github.com/huggingface/diffusers/pull/3129
 
-        Tihs funtion is mostly copied from PyTorch's __getattr__ overwrite:
+        This function is mostly copied from PyTorch's __getattr__ overwrite:
         https://pytorch.org/docs/stable/_modules/torch/nn/modules/module.html#Module
         """
 
@@ -533,7 +533,7 @@ class ConfigMixin:
                 f"{cls.config_name} configuration file."
             )
 
-        # 5. Give nice info if config attributes are initiliazed to default because they have not been passed
+        # 5. Give nice info if config attributes are initialized to default because they have not been passed
         passed_keys = set(init_dict.keys())
         if len(expected_keys - passed_keys) > 0:
             logger.info(

src/diffusers/image_processor.py

@@ -332,7 +332,7 @@ class VaeImageProcessor(ConfigMixin):
         image: Union[PIL.Image.Image, np.ndarray, torch.Tensor],
         height: int,
         width: int,
-        resize_mode: str = "default",  # "defalt", "fill", "crop"
+        resize_mode: str = "default",  # "default", "fill", "crop"
     ) -> Union[PIL.Image.Image, np.ndarray, torch.Tensor]:
         """
         Resize image.
@@ -448,7 +448,7 @@ class VaeImageProcessor(ConfigMixin):
         image: PipelineImageInput,
         height: Optional[int] = None,
         width: Optional[int] = None,
-        resize_mode: str = "default",  # "defalt", "fill", "crop"
+        resize_mode: str = "default",  # "default", "fill", "crop"
         crops_coords: Optional[Tuple[int, int, int, int]] = None,
     ) -> torch.Tensor:
         """
@@ -479,7 +479,7 @@ class VaeImageProcessor(ConfigMixin):
             if isinstance(image, torch.Tensor):
                 # if image is a pytorch tensor could have 2 possible shapes:
                 #    1. batch x height x width: we should insert the channel dimension at position 1
-                #    2. channnel x height x width: we should insert batch dimension at position 0,
+                #    2. channel x height x width: we should insert batch dimension at position 0,
                 #       however, since both channel and batch dimension has same size 1, it is same to insert at position 1
                 #    for simplicity, we insert a dimension of size 1 at position 1 for both cases
                 image = image.unsqueeze(1)

src/diffusers/pipelines/auto_pipeline.py

@@ -343,7 +343,7 @@ class AutoPipelineForText2Image(ConfigMixin):
         pipeline linked to the pipeline class using pattern matching on pipeline class name.
 
         All the modules the pipeline contains will be used to initialize the new pipeline without reallocating
-        additional memoery.
+        additional memory.
 
         The pipeline is set in evaluation mode (`model.eval()`) by default.
 
@@ -616,7 +616,7 @@ class AutoPipelineForImage2Image(ConfigMixin):
         image-to-image pipeline linked to the pipeline class using pattern matching on pipeline class name.
 
         All the modules the pipeline contains will be used to initialize the new pipeline without reallocating
-        additional memoery.
+        additional memory.
 
         The pipeline is set in evaluation mode (`model.eval()`) by default.
 
@@ -892,7 +892,7 @@ class AutoPipelineForInpainting(ConfigMixin):
         pipeline linked to the pipeline class using pattern matching on pipeline class name.
 
         All the modules the pipeline class contain will be used to initialize the new pipeline without reallocating
-        additional memoery.
+        additional memory.
 
         The pipeline is set in evaluation mode (`model.eval()`) by default.
 

src/diffusers/pipelines/text_to_video_synthesis/pipeline_text_to_video_synth.py

@@ -52,7 +52,7 @@ EXAMPLE_DOC_STRING = """
         >>> pipe.enable_model_cpu_offload()
 
         >>> prompt = "Spiderman is surfing"
-        >>> video_frames = pipe(prompt).frames
+        >>> video_frames = pipe(prompt).frames[0]
         >>> video_path = export_to_video(video_frames)
         >>> video_path
         ```

src/diffusers/pipelines/text_to_video_synthesis/pipeline_text_to_video_synth_img2img.py

@@ -52,7 +52,7 @@ EXAMPLE_DOC_STRING = """
         >>> pipe.to("cuda")
 
         >>> prompt = "spiderman running in the desert"
-        >>> video_frames = pipe(prompt, num_inference_steps=40, height=320, width=576, num_frames=24).frames
+        >>> video_frames = pipe(prompt, num_inference_steps=40, height=320, width=576, num_frames=24).frames[0]
         >>> # safe low-res video
         >>> video_path = export_to_video(video_frames, output_video_path="./video_576_spiderman.mp4")
 
@@ -73,7 +73,7 @@ EXAMPLE_DOC_STRING = """
         >>> video = [Image.fromarray(frame).resize((1024, 576)) for frame in video_frames]
 
         >>> # and denoise it
-        >>> video_frames = pipe(prompt, video=video, strength=0.6).frames
+        >>> video_frames = pipe(prompt, video=video, strength=0.6).frames[0]
         >>> video_path = export_to_video(video_frames, output_video_path="./video_1024_spiderman.mp4")
         >>> video_path
         ```