[docs] Improve LoRA docs

docs/source/en/_toctree.yml

@@ -60,6 +60,8 @@
   - sections:
     - local: training/overview
       title: Overview
+    - local: training/create_dataset
+      title: Create a dataset for training
     - local: training/unconditional_training
       title: Unconditional image generation
     - local: training/text_inversion

docs/source/en/training/controlnet.mdx

@@ -69,6 +69,8 @@ The original dataset is hosted in the ControlNet [repo](https://huggingface.co/l
 
 Our training examples use [`runwayml/stable-diffusion-v1-5`](https://huggingface.co/runwayml/stable-diffusion-v1-5) because that is what the original set of ControlNet models was trained on. However, ControlNet can be trained to augment any compatible Stable Diffusion model (such as [`CompVis/stable-diffusion-v1-4`](https://huggingface.co/CompVis/stable-diffusion-v1-4)) or [`stabilityai/stable-diffusion-2-1`](https://huggingface.co/stabilityai/stable-diffusion-2-1).
 
+To use your own dataset, take a look at the [Create a dataset for training](create_dataset) guide.
+
 ## Training
 
 Download the following images to condition our training with:
@@ -79,7 +81,9 @@ wget https://huggingface.co/datasets/huggingface/documentation-images/resolve/ma
 wget https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/controlnet_training/conditioning_image_2.png
 ```
 
-Specify the `MODEL_NAME` environment variable (either a Hub model repository id or a path to the directory containing the model weights) and pass it to the [`~diffusers.DiffusionPipeline.from_pretrained.pretrained_model_name_or_path`] argument.
+Specify the `MODEL_NAME` environment variable (either a Hub model repository id or a path to the directory containing the model weights) and pass it to the [`pretrained_model_name_or_path`](https://huggingface.co/docs/diffusers/en/api/diffusion_pipeline#diffusers.DiffusionPipeline.from_pretrained.pretrained_model_name_or_path) argument.
+
+The training script creates and saves a `diffusion_pytorch_model.bin` file in your repository.
 
 ```bash
 export MODEL_DIR="runwayml/stable-diffusion-v1-5"

docs/source/en/training/create_dataset.mdx

@@ -0,0 +1,90 @@
+# Create a dataset for training
+
+There are many datasets on the [Hub](https://huggingface.co/datasets?task_categories=task_categories:text-to-image&sort=downloads) to train a model on, but if you can't find one you're interested in or want to use your own, you can create a dataset with the 🤗 [Datasets](hf.co/docs/datasets) library. The dataset structure depends on the task you want to train your model on. The most basic dataset structure is a directory of images for tasks like unconditional image generation. Another dataset structure may be a directory of images and a text file containing their corresponding text captions for tasks like text-to-image generation.
+
+This guide will show you two ways to create a dataset to finetune on:
+
+- provide a folder of images to the `--train_data_dir` argument
+- upload a dataset to the Hub and pass the dataset repository id to the `--dataset_name` argument
+
+<Tip>
+
+💡 Learn more about how to create an image dataset for training in the [Create an image dataset](https://huggingface.co/docs/datasets/image_dataset) guide. 
+
+</Tip>
+
+## Provide a dataset as a folder
+
+For unconditional generation, you can provide your own dataset as a folder of images. The training script uses the [`ImageFolder`](https://huggingface.co/docs/datasets/en/image_dataset#imagefolder) builder from 🤗 Datasets to automatically build a dataset from the folder. Your directory structure should look like:
+
+```bash
+data_dir/xxx.png
+data_dir/xxy.png
+data_dir/[...]/xxz.png
+```
+
+Pass the path to the dataset directory to the `--train_data_dir` argument, and then you can start training:
+
+```bash
+accelerate launch train_unconditional.py \
+    --train_data_dir <path-to-train-directory> \
+    <other-arguments>
+```
+
+## Upload your data to the Hub
+
+<Tip>
+
+💡 For more details and context about creating and uploading a dataset to the Hub, take a look at the [Image search with 🤗 Datasets](https://huggingface.co/blog/image-search-datasets) post.
+
+</Tip>
+
+Start by creating a dataset with the [`ImageFolder`](https://huggingface.co/docs/datasets/image_load#imagefolder) feature, which creates an `image` column containing the PIL-encoded images. 
+
+You can use the `data_dir` or `data_files` parameters to specify the location of the dataset. The `data_files` parameter supports mapping specific files to dataset splits like `train` or `test`:
+
+```python
+from datasets import load_dataset
+
+# example 1: local folder
+dataset = load_dataset("imagefolder", data_dir="path_to_your_folder")
+
+# example 2: local files (supported formats are tar, gzip, zip, xz, rar, zstd)
+dataset = load_dataset("imagefolder", data_files="path_to_zip_file")
+
+# example 3: remote files (supported formats are tar, gzip, zip, xz, rar, zstd)
+dataset = load_dataset(
+    "imagefolder",
+    data_files="https://download.microsoft.com/download/3/E/1/3E1C3F21-ECDB-4869-8368-6DEBA77B919F/kagglecatsanddogs_3367a.zip",
+)
+
+# example 4: providing several splits
+dataset = load_dataset(
+    "imagefolder", data_files={"train": ["path/to/file1", "path/to/file2"], "test": ["path/to/file3", "path/to/file4"]}
+)
+```
+
+Then use the [`~datasets.Dataset.push_to_hub`] method to upload the dataset to the Hub:
+
+```python
+# assuming you have ran the huggingface-cli login command in a terminal
+dataset.push_to_hub("name_of_your_dataset")
+
+# if you want to push to a private repo, simply pass private=True:
+dataset.push_to_hub("name_of_your_dataset", private=True)
+```
+
+Now the dataset is available for training by passing the dataset name to the `--dataset_name` argument:
+
+```bash
+accelerate launch --mixed_precision="fp16"  train_text_to_image.py \
+  --pretrained_model_name_or_path="runwayml/stable-diffusion-v1-5" \
+  --dataset_name="name_of_your_dataset" \
+  <other-arguments>
+```
+
+## Next steps
+
+Now that you've created a dataset, you can plug it into the `train_data_dir` (if your dataset is local) or `dataset_name` (if your dataset is on the Hub) arguments of a training script.
+
+For your next steps, feel free to try and use your dataset to train a model for [unconditional generation](uncondtional_training) or [text-to-image generation](text2image)!

docs/source/en/training/custom_diffusion.mdx

@@ -67,7 +67,7 @@ write_basic_config()
 ```
 ### Cat example 😺
 
-Now let's get our dataset. Download dataset from [here](https://www.cs.cmu.edu/~custom-diffusion/assets/data.zip) and unzip it. 
+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.`. 
 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. 
@@ -79,6 +79,8 @@ python retrieve.py --class_prompt cat --class_data_dir real_reg/samples_cat --nu
 
 **___Note: Change the `resolution` to 768 if you are using the [stable-diffusion-2](https://huggingface.co/stabilityai/stable-diffusion-2) 768x768 model.___**
 
+The script creates and saves model checkpoints and a `pytorch_custom_diffusion_weights.bin` file in your repository.
+
 ```bash
 export MODEL_NAME="CompVis/stable-diffusion-v1-4"
 export OUTPUT_DIR="path-to-save-model"

docs/source/en/training/dreambooth.mdx

@@ -64,6 +64,8 @@ snapshot_download(
 )
 ```
 
+To use your own dataset, take a look at the [Create a dataset for training](create_dataset) guide.
+
 ## Finetuning
 
 <Tip warning={true}>
@@ -76,7 +78,7 @@ DreamBooth finetuning is very sensitive to hyperparameters and easy to overfit.
 <pt>
 Set the `INSTANCE_DIR` environment variable to the path of the directory containing the dog images.
 
-Specify the `MODEL_NAME` environment variable (either a Hub model repository id or a path to the directory containing the model weights) and pass it to the [`~diffusers.DiffusionPipeline.from_pretrained.pretrained_model_name_or_path`] argument.
+Specify the `MODEL_NAME` environment variable (either a Hub model repository id or a path to the directory containing the model weights) and pass it to the [`pretrained_model_name_or_path`] argument. The `instance_prompt` argument is a text prompt that contains a unique identifier, such as `sks`, and the class the image belongs to, which in this example is `a photo of a sks dog`.
 
 ```bash
 export MODEL_NAME="CompVis/stable-diffusion-v1-4"
@@ -111,7 +113,7 @@ Before running the script, make sure you have the requirements installed:
 pip install -U -r requirements.txt
 ```
 
-Specify the `MODEL_NAME` environment variable (either a Hub model repository id or a path to the directory containing the model weights) and pass it to the [`~diffusers.DiffusionPipeline.from_pretrained.pretrained_model_name_or_path`] argument.
+Specify the `MODEL_NAME` environment variable (either a Hub model repository id or a path to the directory containing the model weights) and pass it to the [`pretrained_model_name_or_path`] argument. The `instance_prompt` argument is a text prompt that contains a unique identifier, such as `sks`, and the class the image belongs to, which in this example is `a photo of a sks dog`.
 
 Now you can launch the training script with the following command:
 

docs/source/en/training/instructpix2pix.mdx

@@ -77,16 +77,16 @@ write_basic_config()
 ### Toy example
 
 As mentioned before, we'll use a [small toy dataset](https://huggingface.co/datasets/fusing/instructpix2pix-1000-samples) for training. The dataset 
-is a smaller version of the [original dataset](https://huggingface.co/datasets/timbrooks/instructpix2pix-clip-filtered) used in the InstructPix2Pix paper.
+is a smaller version of the [original dataset](https://huggingface.co/datasets/timbrooks/instructpix2pix-clip-filtered) used in the InstructPix2Pix paper. To use your own dataset, take a look at the [Create a dataset for training](create_dataset) guide.
 
-Specify the `MODEL_NAME` environment variable (either a Hub model repository id or a path to the directory containing the model weights) and pass it to the [`~diffusers.DiffusionPipeline.from_pretrained.pretrained_model_name_or_path`] argument. You'll also need to specify the dataset name in `DATASET_ID`:
+Specify the `MODEL_NAME` environment variable (either a Hub model repository id or a path to the directory containing the model weights) and pass it to the [`pretrained_model_name_or_path`](https://huggingface.co/docs/diffusers/en/api/diffusion_pipeline#diffusers.DiffusionPipeline.from_pretrained.pretrained_model_name_or_path) argument. You'll also need to specify the dataset name in `DATASET_ID`:
 
 ```bash
 export MODEL_NAME="runwayml/stable-diffusion-v1-5"
 export DATASET_ID="fusing/instructpix2pix-1000-samples"
 ```
 
-Now, we can launch training:
+Now, we can launch training. The script saves all the components (`feature_extractor`, `scheduler`, `text_encoder`, `unet`, etc) in a subfolder in your repository.
 
 ```bash
 accelerate launch --mixed_precision="fp16" train_instruct_pix2pix.py \

docs/source/en/training/lora.mdx

@@ -17,8 +17,7 @@ specific language governing permissions and limitations under the License.
 <Tip warning={true}>
 
 Currently, LoRA is only supported for the attention layers of the [`UNet2DConditionalModel`]. We also 
-support LoRA fine-tuning of the text encoder for DreamBooth in a limited capacity. For more details on how we support 
-LoRA fine-tuning of the text encoder, refer to the discussion on [this PR](https://github.com/huggingface/diffusers/pull/2918). 
+support fine-tuning the text encoder for DreamBooth with LoRA in a limited capacity. Fine-tuning the text encoder for DreamBooth generally yields better results, but it can increase compute usage.
 
 </Tip>
 
@@ -52,7 +51,7 @@ Finetuning a model like Stable Diffusion, which has billions of parameters, can
 
 Let's finetune [`stable-diffusion-v1-5`](https://huggingface.co/runwayml/stable-diffusion-v1-5) on the [Pokémon BLIP captions](https://huggingface.co/datasets/lambdalabs/pokemon-blip-captions) dataset to generate your own Pokémon.
 
-Specify the `MODEL_NAME` environment variable (either a Hub model repository id or a path to the directory containing the model weights) and pass it to the [`~diffusers.DiffusionPipeline.from_pretrained.pretrained_model_name_or_path`] argument. You'll also need to set the `DATASET_NAME` environment variable to the name of the dataset you want to train on.
+Specify the `MODEL_NAME` environment variable (either a Hub model repository id or a path to the directory containing the model weights) and pass it to the [`pretrained_model_name_or_path`](https://huggingface.co/docs/diffusers/en/api/diffusion_pipeline#diffusers.DiffusionPipeline.from_pretrained.pretrained_model_name_or_path) argument. You'll also need to set the `DATASET_NAME` environment variable to the name of the dataset you want to train on. To use your own dataset, take a look at the [Create a dataset for training](create_dataset) guide.
 
 The `OUTPUT_DIR` and `HUB_MODEL_ID` variables are optional and specify where to save the model to on the Hub:
 
@@ -69,7 +68,7 @@ There are some flags to be aware of before you start training:
 * `--report_to=wandb` reports and logs the training results to your Weights & Biases dashboard (as an example, take a look at this [report](https://wandb.ai/pcuenq/text2image-fine-tune/runs/b4k1w0tn?workspace=user-pcuenq)).
 * `--learning_rate=1e-04`, you can afford to use a higher learning rate than you normally would with LoRA.
 
-Now you're ready to launch the training (you can find the full training script [here](https://github.com/huggingface/diffusers/blob/main/examples/text_to_image/train_text_to_image_lora.py)):
+Now you're ready to launch the training (you can find the full training script [here](https://github.com/huggingface/diffusers/blob/main/examples/text_to_image/train_text_to_image_lora.py)). Training takes about 5 hours on a 2080 Ti GPU with 11GB of RAM, and it'll create and save model checkpoints and the `pytorch_lora_weights` in your repository.
 
 ```bash
 accelerate launch --mixed_precision="fp16"  train_text_to_image_lora.py \
@@ -159,9 +158,9 @@ pipe = StableDiffusionPipeline.from_pretrained(base_model_id, torch_dtype=torch.
 
 ### Training[[dreambooth-training]]
 
-Let's finetune [`stable-diffusion-v1-5`](https://huggingface.co/runwayml/stable-diffusion-v1-5) with DreamBooth and LoRA with some 🐶 [dog images](https://drive.google.com/drive/folders/1BO_dyz-p65qhBRRMRA4TbZ8qW4rB99JZ). Download and save these images to a directory.
+Let's finetune [`stable-diffusion-v1-5`](https://huggingface.co/runwayml/stable-diffusion-v1-5) with DreamBooth and LoRA with some 🐶 [dog images](https://drive.google.com/drive/folders/1BO_dyz-p65qhBRRMRA4TbZ8qW4rB99JZ). Download and save these images to a directory. To use your own dataset, take a look at the [Create a dataset for training](create_dataset) guide.
 
-To start, specify the `MODEL_NAME` environment variable (either a Hub model repository id or a path to the directory containing the model weights) and pass it to the [`~diffusers.DiffusionPipeline.from_pretrained.pretrained_model_name_or_path`] argument. You'll also need to set `INSTANCE_DIR` to the path of the directory containing the images. 
+To start, specify the `MODEL_NAME` environment variable (either a Hub model repository id or a path to the directory containing the model weights) and pass it to the [`pretrained_model_name_or_path`](https://huggingface.co/docs/diffusers/en/api/diffusion_pipeline#diffusers.DiffusionPipeline.from_pretrained.pretrained_model_name_or_path) argument. You'll also need to set `INSTANCE_DIR` to the path of the directory containing the images. 
 
 The `OUTPUT_DIR` variables is optional and specifies where to save the model to on the Hub:
 
@@ -177,7 +176,11 @@ There are some flags to be aware of before you start training:
 * `--report_to=wandb` reports and logs the training results to your Weights & Biases dashboard (as an example, take a look at this [report](https://wandb.ai/pcuenq/text2image-fine-tune/runs/b4k1w0tn?workspace=user-pcuenq)).
 * `--learning_rate=1e-04`, you can afford to use a higher learning rate than you normally would with LoRA.
 
-Now you're ready to launch the training (you can find the full training script [here](https://github.com/huggingface/diffusers/blob/main/examples/dreambooth/train_dreambooth_lora.py)):
+Now you're ready to launch the training (you can find the full training script [here](https://github.com/huggingface/diffusers/blob/main/examples/dreambooth/train_dreambooth_lora.py)). The script creates and saves model checkpoints and the `pytorch_lora_weights.bin` file in your repository.
+
+It's also possible to additionally fine-tune the text encoder with LoRA. This, in most cases, leads
+to better results with a slight increase in the compute. To allow fine-tuning the text encoder with LoRA,
+specify the `--train_text_encoder` while launching the `train_dreambooth_lora.py` script.
 
 ```bash
 accelerate launch train_dreambooth_lora.py \
@@ -198,12 +201,7 @@ accelerate launch train_dreambooth_lora.py \
   --validation_epochs=50 \
   --seed="0" \
   --push_to_hub
-```
-
-It's also possible to additionally fine-tune the text encoder with LoRA. This, in most cases, leads
-to better results with a slight increase in the compute. To allow fine-tuning the text encoder with LoRA,
-specify the `--train_text_encoder` while launching the `train_dreambooth_lora.py` script. 
-
+``` 
 
 ### Inference[[dreambooth-inference]]
 

docs/source/en/training/text2image.mdx

@@ -74,7 +74,7 @@ To load a checkpoint to resume training, pass the argument `--resume_from_checkp
 <pt>
 Launch the [PyTorch training script](https://github.com/huggingface/diffusers/blob/main/examples/text_to_image/train_text_to_image.py) for a fine-tuning run on the [Pokémon BLIP captions](https://huggingface.co/datasets/lambdalabs/pokemon-blip-captions) dataset like this.
 
-Specify the `MODEL_NAME` environment variable (either a Hub model repository id or a path to the directory containing the model weights) and pass it to the [`~diffusers.DiffusionPipeline.from_pretrained.pretrained_model_name_or_path`] argument.
+Specify the `MODEL_NAME` environment variable (either a Hub model repository id or a path to the directory containing the model weights) and pass it to the [`pretrained_model_name_or_path`](https://huggingface.co/docs/diffusers/en/api/diffusion_pipeline#diffusers.DiffusionPipeline.from_pretrained.pretrained_model_name_or_path) argument.
 
 <literalinclude>
 {"path": "../../../../examples/text_to_image/README.md",
@@ -143,7 +143,7 @@ Before running the script, make sure you have the requirements installed:
 pip install -U -r requirements_flax.txt
 ```
 
-Specify the `MODEL_NAME` environment variable (either a Hub model repository id or a path to the directory containing the model weights) and pass it to the [`~diffusers.DiffusionPipeline.from_pretrained.pretrained_model_name_or_path`] argument.
+Specify the `MODEL_NAME` environment variable (either a Hub model repository id or a path to the directory containing the model weights) and pass it to the [`pretrained_model_name_or_path`](https://huggingface.co/docs/diffusers/en/api/diffusion_pipeline#diffusers.DiffusionPipeline.from_pretrained.pretrained_model_name_or_path) argument.
 
 Now you can launch the [Flax training script](https://github.com/huggingface/diffusers/blob/main/examples/text_to_image/train_text_to_image_flax.py) like this: