Add training example for DreamBooth. (#554)

* Add training example for DreamBooth.

* Fix bugs.

* Update readme and default hyperparameters.

* Reformatting code with black.

* Update for multi-gpu trianing.

* Apply suggestions from code review

* improgve sampling

* fix autocast

* improve sampling more

* fix saving

* actuallu fix saving

* fix saving

* improve dataset

* fix collate fun

* fix collate_fn

* fix collate fn

* fix key name

* fix dataset

* fix collate fn

* concat batch in collate fn

* add grad ckpt

* add option for 8bit adam

* do two forward passes for prior preservation

* Revert "do two forward passes for prior preservation"

This reverts commit 661ca4677e6dccc4ad596c2ee6ca4baad4159e95.

* add option for prior_loss_weight

* add option for clip grad norm

* add more comments

* update readme

* update readme

* Apply suggestions from code review
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

* add docstr for dataset

* update the saving logic

* Update examples/dreambooth/README.md

* remove unused imports
Co-authored-by: Suraj Patil <surajp815@gmail.com>
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

examples/dreambooth/README.md

+# DreamBooth training example
+
+[DreamBooth](https://arxiv.org/abs/2208.12242) is a method to personalize text2image models like stable diffusion given just a few(3~5) images of a subject.
+The `train_dreambooth.py` script shows how to implement the training procedure and adapt it for stable diffusion.
+
+
+## Running locally 
+### Installing the dependencies
+
+Before running the scripts, make sure to install the library's training dependencies:
+
+```bash
+pip install diffusers[training] accelerate transformers
+```
+
+And initialize an [🤗Accelerate](https://github.com/huggingface/accelerate/) environment with:
+
+```bash
+accelerate config
+```
+
+### Dog toy example
+
+You need to accept the model license before downloading or using the weights. In this example we'll use model version `v1-4`, so you'll need to visit [its card](https://huggingface.co/CompVis/stable-diffusion-v1-4), read the license and tick the checkbox if you agree. 
+
+You have to be a registered user in 🤗 Hugging Face Hub, and you'll also need to use an access token for the code to work. For more information on access tokens, please refer to [this section of the documentation](https://huggingface.co/docs/hub/security-tokens).
+
+Run the following command to authenticate your token
+
+```bash
+huggingface-cli login
+```
+
+If you have already cloned the repo, then you won't need to go through these steps. You can simple remove the `--use_auth_token` arg from the following command.
+
+<br>
+
+Now let's get our dataset. Download images from [here](https://drive.google.com/drive/folders/1BO_dyz-p65qhBRRMRA4TbZ8qW4rB99JZ) and save them in a directory. This will be our training data.
+
+And launch the training using
+
+```bash
+export MODEL_NAME="CompVis/stable-diffusion-v1-4"
+export INSTANCE_DIR="path-to-instance-images"
+export OUTPUT_DIR="path-to-save-model"
+
+accelerate launch train_dreambooth.py \
+  --pretrained_model_name_or_path=$MODEL_NAME --use_auth_token \
+  --instance_data_dir=$INSTANCE_DIR \
+  --output_dir=$OUTPUT_DIR \
+  --instance_prompt="a photo of sks dog" \
+  --resolution=512 \
+  --train_batch_size=1 \
+  --gradient_accumulation_steps=1 \
+  --learning_rate=5e-6 \
+  --lr_scheduler="constant" \
+  --lr_warmup_steps=0 \
+  --max_train_steps=400
+```
+
+### Training with prior-preservation loss
+
+Prior-preservation is used to avoid overfitting and language-drift. Refer to the paper to learn more about it. For prior-preservation we first generate images using the model with a class prompt and then use those during training along with our data.
+According to the paper, it's recommened to generate `num_epochs * num_samples` images for prior-preservation. 200-300 works well for most cases.
+
+```bash
+export MODEL_NAME="CompVis/stable-diffusion-v1-4"
+export INSTANCE_DIR="path-to-instance-images"
+export CLASS_DIR="path-to-class-images"
+export OUTPUT_DIR="path-to-save-model"
+
+accelerate launch train_dreambooth.py \
+  --pretrained_model_name_or_path=$MODEL_NAME --use_auth_token \
+  --instance_data_dir=$INSTANCE_DIR \
+  --class_data_dir=$CLASS_DIR \
+  --output_dir=$OUTPUT_DIR \
+  --with_prior_preservation --prior_loss_weight=1.0 \
+  --instance_prompt="a photo of sks dog" \
+  --class_prompt="a photo of dog" \
+  --resolution=512 \
+  --train_batch_size=1 \
+  --gradient_accumulation_steps=1 \
+  --learning_rate=5e-6 \
+  --lr_scheduler="constant" \
+  --lr_warmup_steps=0 \
+  --num_class_images=200 \
+  --max_train_steps=800
+```
+
+### Training on a 16GB GPU:
+
+With the help of gradient checkpointing and the 8-bit optimizer from bitsandbytes it's possible to run train dreambooth on a 16GB GPU.
+
+Install `bitsandbytes` with `pip install bitsandbytes`
+
+```bash
+export MODEL_NAME="CompVis/stable-diffusion-v1-4"
+export INSTANCE_DIR="path-to-instance-images"
+export CLASS_DIR="path-to-class-images"
+export OUTPUT_DIR="path-to-save-model"
+
+accelerate launch train_dreambooth.py \
+  --pretrained_model_name_or_path=$MODEL_NAME --use_auth_token \
+  --instance_data_dir=$INSTANCE_DIR \
+  --class_data_dir=$CLASS_DIR \
+  --output_dir=$OUTPUT_DIR \
+  --with_prior_preservation --prior_loss_weight=1.0 \
+  --instance_prompt="a photo of sks dog" \
+  --class_prompt="a photo of dog" \
+  --resolution=512 \
+  --train_batch_size=1 \
+  --gradient_accumulation_steps=2 --gradient_checkpointing \
+  --use_8bit_adam \
+  --learning_rate=5e-6 \
+  --lr_scheduler="constant" \
+  --lr_warmup_steps=0 \
+  --num_class_images=200 \
+  --max_train_steps=800
+```
+
+
+## Inference
+
+Once you have trained a model using above command, the inference can be done simply using the `StableDiffusionPipeline`. Make sure to include the `identifier`(e.g. sks in above example) in your prompt.
+
+```python
+
+from torch import autocast
+from diffusers import StableDiffusionPipeline
+import torch
+
+model_id = "path-to-your-trained-model"
+pipe = StableDiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.float16).to("cuda")
+
+prompt = "A photo of sks dog in a bucket"
+
+with autocast("cuda"):
+    image = pipe(prompt, num_inference_steps=50, guidance_scale=7.5).images[0]
+
+image.save("dog-bucket.png")
+```