Merge branch 'main' into doc-string

CONTRIBUTING.md

@@ -40,7 +40,7 @@ In the following, we give an overview of different ways to contribute, ranked by
 As said before, **all contributions are valuable to the community**.
 In the following, we will explain each contribution a bit more in detail.
 
-For all contributions 4.-9. you will need to open a PR. It is explained in detail how to do so in [Opening a pull requst](#how-to-open-a-pr)
+For all contributions 4.-9. you will need to open a PR. It is explained in detail how to do so in [Opening a pull request](#how-to-open-a-pr)
 
 ### 1. Asking and answering questions on the Diffusers discussion forum or on the Diffusers Discord
 
@@ -63,7 +63,7 @@ In the same spirit, you are of immense help to the community by answering such q
 
 **Please** keep in mind that the more effort you put into asking or answering a question, the higher
 the quality of the publicly documented knowledge. In the same way, well-posed and well-answered questions create a high-quality knowledge database accessible to everybody, while badly posed questions or answers reduce the overall quality of the public knowledge database.
-In short, a high quality question or answer is *precise*, *concise*, *relevant*, *easy-to-understand*, *accesible*, and *well-formated/well-posed*. For more information, please have a look through the [How to write a good issue](#how-to-write-a-good-issue) section.
+In short, a high quality question or answer is *precise*, *concise*, *relevant*, *easy-to-understand*, *accessible*, and *well-formated/well-posed*. For more information, please have a look through the [How to write a good issue](#how-to-write-a-good-issue) section.
 
 **NOTE about channels**:
 [*The forum*](https://discuss.huggingface.co/c/discussion-related-to-httpsgithubcomhuggingfacediffusers/63) is much better indexed by search engines, such as Google. Posts are ranked by popularity rather than chronologically. Hence, it's easier to look up questions and answers that we posted some time ago.
@@ -168,7 +168,7 @@ more precise, provide the link to a duplicated issue or redirect them to [the fo
 If you have verified that the issued bug report is correct and requires a correction in the source code,
 please have a look at the next sections.
 
-For all of the following contributions, you will need to open a PR. It is explained in detail how to do so in the [Opening a pull requst](#how-to-open-a-pr) section.
+For all of the following contributions, you will need to open a PR. It is explained in detail how to do so in the [Opening a pull request](#how-to-open-a-pr) section.
 
 ### 4. Fixing a "Good first issue"
 

docs/source/en/_toctree.yml

@@ -17,6 +17,8 @@
     title: AutoPipeline
   - local: tutorials/basic_training
     title: Train a diffusion model
+  - local: tutorials/using_peft_for_inference
+    title: Inference with PEFT
   title: Tutorials
 - sections:
   - sections:

docs/source/en/api/pipelines/diffedit.md

@@ -34,7 +34,7 @@ this in the generated mask, you simply have to set the embeddings related to the
 `source_prompt` and "dog" to `target_prompt`.
 * When generating partially inverted latents using `invert`, assign a caption or text embedding describing the
 overall image to the `prompt` argument to help guide the inverse latent sampling process. In most cases, the
-source concept is sufficently descriptive to yield good results, but feel free to explore alternatives.
+source concept is sufficiently descriptive to yield good results, but feel free to explore alternatives.
 * When calling the pipeline to generate the final edited image, assign the source concept to `negative_prompt`
 and the target concept to `prompt`. Taking the above example, you simply have to set the embeddings related to
 the phrases including "cat" to `negative_prompt` and "dog" to `prompt`.

docs/source/en/api/pipelines/kandinsky.md

@@ -396,7 +396,7 @@ t2i_pipe.unet.set_attn_processor(AttnAddedKVProcessor())
 ```
 
 With PyTorch >= 2.0, you can also use Kandinsky with `torch.compile` which depending 
-on your hardware can signficantly speed-up your inference time once the model is compiled.
+on your hardware can significantly speed-up your inference time once the model is compiled.
 To use Kandinsksy with `torch.compile`, you can do:
 
 ```py

docs/source/en/api/pipelines/kandinsky_v22.md

@@ -263,7 +263,7 @@ t2i_pipe.unet.set_attn_processor(AttnAddedKVProcessor())
 ```
 
 With PyTorch >= 2.0, you can also use Kandinsky with `torch.compile` which depending 
-on your hardware can signficantly speed-up your inference time once the model is compiled.
+on your hardware can significantly speed-up your inference time once the model is compiled.
 To use Kandinsksy with `torch.compile`, you can do:
 
 ```py

docs/source/en/conceptual/contribution.md

@@ -40,7 +40,7 @@ In the following, we give an overview of different ways to contribute, ranked by
 As said before, **all contributions are valuable to the community**.
 In the following, we will explain each contribution a bit more in detail.
 
-For all contributions 4.-9. you will need to open a PR. It is explained in detail how to do so in [Opening a pull requst](#how-to-open-a-pr)
+For all contributions 4.-9. you will need to open a PR. It is explained in detail how to do so in [Opening a pull request](#how-to-open-a-pr)
 
 ### 1. Asking and answering questions on the Diffusers discussion forum or on the Diffusers Discord
 
@@ -63,7 +63,7 @@ In the same spirit, you are of immense help to the community by answering such q
 
 **Please** keep in mind that the more effort you put into asking or answering a question, the higher
 the quality of the publicly documented knowledge. In the same way, well-posed and well-answered questions create a high-quality knowledge database accessible to everybody, while badly posed questions or answers reduce the overall quality of the public knowledge database.
-In short, a high quality question or answer is *precise*, *concise*, *relevant*, *easy-to-understand*, *accesible*, and *well-formated/well-posed*. For more information, please have a look through the [How to write a good issue](#how-to-write-a-good-issue) section.
+In short, a high quality question or answer is *precise*, *concise*, *relevant*, *easy-to-understand*, *accessible*, and *well-formated/well-posed*. For more information, please have a look through the [How to write a good issue](#how-to-write-a-good-issue) section.
 
 **NOTE about channels**:
 [*The forum*](https://discuss.huggingface.co/c/discussion-related-to-httpsgithubcomhuggingfacediffusers/63) is much better indexed by search engines, such as Google. Posts are ranked by popularity rather than chronologically. Hence, it's easier to look up questions and answers that we posted some time ago.
@@ -168,7 +168,7 @@ more precise, provide the link to a duplicated issue or redirect them to [the fo
 If you have verified that the issued bug report is correct and requires a correction in the source code,
 please have a look at the next sections.
 
-For all of the following contributions, you will need to open a PR. It is explained in detail how to do so in the [Opening a pull requst](#how-to-open-a-pr) section.
+For all of the following contributions, you will need to open a PR. It is explained in detail how to do so in the [Opening a pull request](#how-to-open-a-pr) section.
 
 ### 4. Fixing a `Good first issue`
 

docs/source/en/optimization/torch2.0.md

@@ -70,7 +70,7 @@ pipe.unet = torch.compile(pipe.unet, mode="reduce-overhead", fullgraph=True)
 images = pipe(prompt, num_inference_steps=steps, num_images_per_prompt=batch_size).images[0]
 ```
 
-Depending on GPU type, `torch.compile` can provide an *addtional speed-up* of **5-300x** on top of SDPA! If you're using more recent GPU architectures such as Ampere (A100, 3090), Ada (4090), and Hopper (H100), `torch.compile` is able to squeeze even more performance out of these GPUs.
+Depending on GPU type, `torch.compile` can provide an *additional speed-up* of **5-300x** on top of SDPA! If you're using more recent GPU architectures such as Ampere (A100, 3090), Ada (4090), and Hopper (H100), `torch.compile` is able to squeeze even more performance out of these GPUs.
 
 Compilation requires some time to complete, so it is best suited for situations where you prepare your pipeline once and then perform the same type of inference operations multiple times. For example, calling the compiled pipeline on a different image size triggers compilation again which can be expensive.
 

docs/source/en/training/custom_diffusion.md

@@ -69,7 +69,7 @@ write_basic_config()
 
 Now let's get our dataset. Download dataset from [here](https://www.cs.cmu.edu/~custom-diffusion/assets/data.zip) and unzip it. To use your own dataset, take a look at the [Create a dataset for training](create_dataset) guide.
 
-We also collect 200 real images using `clip-retrieval` which are combined with the target images in the training dataset as a regularization. This prevents overfitting to the the given target image. The following flags enable the regularization `with_prior_preservation`, `real_prior` with `prior_loss_weight=1.`. 
+We also collect 200 real images using `clip-retrieval` which are combined with the target images in the training dataset as a regularization. This prevents overfitting to the given target image. The following flags enable the regularization `with_prior_preservation`, `real_prior` with `prior_loss_weight=1.`. 
 The `class_prompt` should be the category name same as target image. The collected real images are with text captions similar to the `class_prompt`. The retrieved image are saved in `class_data_dir`. You can disable `real_prior` to use generated images as regularization. To collect the real images use this command first before training. 
 
 ```bash
@@ -106,7 +106,7 @@ accelerate launch train_custom_diffusion.py \
 
 **Use `--enable_xformers_memory_efficient_attention` for faster training with lower VRAM requirement (16GB per GPU). Follow [this guide](https://github.com/facebookresearch/xformers) for installation instructions.**
 
-To track your experiments using Weights and Biases (`wandb`) and to save intermediate results (whcih we HIGHLY recommend), follow these steps:
+To track your experiments using Weights and Biases (`wandb`) and to save intermediate results (which we HIGHLY recommend), follow these steps:
 
 * Install `wandb`: `pip install wandb`.
 * Authorize: `wandb login`. 

docs/source/en/training/text_inversion.md

@@ -192,7 +192,7 @@ been added to the text encoder embedding matrix and consequently been trained.
 <Tip>
 
 💡 The community has created a large library of different textual inversion embedding vectors, called [sd-concepts-library](https://huggingface.co/sd-concepts-library).
-Instead of training textual inversion embeddings from scratch you can also see whether a fitting textual inversion embedding has already been added to the libary.
+Instead of training textual inversion embeddings from scratch you can also see whether a fitting textual inversion embedding has already been added to the library.
 
 </Tip>
 

docs/source/en/tutorials/basic_training.md

@@ -284,22 +284,11 @@ Now you can wrap all these components together in a training loop with 🤗 Acce
 
 ```py
 >>> from accelerate import Accelerator
->>> from huggingface_hub import HfFolder, Repository, whoami
+>>> from huggingface_hub import create_repo, upload_folder
 >>> from tqdm.auto import tqdm
 >>> from pathlib import Path
 >>> import os
 
-
->>> def get_full_repo_name(model_id: str, organization: str = None, token: str = None):
-...     if token is None:
-...         token = HfFolder.get_token()
-...     if organization is None:
-...         username = whoami(token)["name"]
-...         return f"{username}/{model_id}"
-...     else:
-...         return f"{organization}/{model_id}"
-
-
 >>> def train_loop(config, model, noise_scheduler, optimizer, train_dataloader, lr_scheduler):
 ...     # Initialize accelerator and tensorboard logging
 ...     accelerator = Accelerator(
@@ -309,11 +298,12 @@ Now you can wrap all these components together in a training loop with 🤗 Acce
 ...         project_dir=os.path.join(config.output_dir, "logs"),
 ...     )
 ...     if accelerator.is_main_process:
-...         if config.push_to_hub:
-...             repo_name = get_full_repo_name(Path(config.output_dir).name)
-...             repo = Repository(config.output_dir, clone_from=repo_name)
-...         elif config.output_dir is not None:
+...         if config.output_dir is not None:
 ...             os.makedirs(config.output_dir, exist_ok=True)
+...         if config.push_to_hub:
+...             repo_id = create_repo(
+...                 repo_id=config.hub_model_id or Path(config.output_dir).name, exist_ok=True
+...             )
 ...         accelerator.init_trackers("train_example")
 
 ...     # Prepare everything
@@ -371,7 +361,12 @@ Now you can wrap all these components together in a training loop with 🤗 Acce
 
 ...             if (epoch + 1) % config.save_model_epochs == 0 or epoch == config.num_epochs - 1:
 ...                 if config.push_to_hub:
-...                     repo.push_to_hub(commit_message=f"Epoch {epoch}", blocking=True)
+...                     upload_folder(
+...                         repo_id=repo_id,
+...                         folder_path=config.output_dir,
+...                         commit_message=f"Epoch {epoch}",
+...                         ignore_patterns=["step_*", "epoch_*"],
+...                     )
 ...                 else:
 ...                     pipeline.save_pretrained(config.output_dir)
 ```