RealFill is a method to personalize text2image inpainting models like stable diffusion inpainting given just a few(1~5) images of a scene. The train_realfill.py script shows how to implement the training procedure for stable diffusion inpainting.

Before running the scripts, make sure to install the library's training dependencies:

cd to the realfill folder and run

cd realfill
pip install -r requirements.txt

And initialize an 🤗Accelerate environment with:

accelerate config

Or for a default accelerate configuration without answering questions about your environment

accelerate config default

Or if your environment doesn't support an interactive shell e.g. a notebook

from accelerate.utils import write_basic_config
write_basic_config()

When running accelerate config, if we specify torch compile mode to True there can be dramatic speedups.

Now let's fill the real. For this example, we will use some images of the flower girl example from the paper.

We already provide some images for testing in data folder

You only have to launch the training using:

export MODEL_NAME="stabilityai/stable-diffusion-2-inpainting"
export TRAIN_DIR="data/flowerwoman"
export OUTPUT_DIR="flowerwoman-model"

accelerate launch train_realfill.py \
  --pretrained_model_name_or_path=$MODEL_NAME \
  --train_data_dir=$TRAIN_DIR \
  --output_dir=$OUTPUT_DIR \
  --resolution=512 \
  --train_batch_size=16 \
  --gradient_accumulation_steps=1 \
  --unet_learning_rate=2e-4 \
  --text_encoder_learning_rate=4e-5 \
  --lr_scheduler="constant" \
  --lr_warmup_steps=100 \
  --max_train_steps=2000 \
  --lora_rank=8 \
  --lora_dropout=0.1 \
  --lora_alpha=16 \

It is possible to run realfill on a low-memory GPU by using the following optimizations:

• gradient checkpointing and the 8-bit optimizer
• xformers
• setting grads to none

export MODEL_NAME="stabilityai/stable-diffusion-2-inpainting"
export TRAIN_DIR="data/flowerwoman"
export OUTPUT_DIR="flowerwoman-model"

accelerate launch train_realfill.py \
  --pretrained_model_name_or_path=$MODEL_NAME \
  --train_data_dir=$TRAIN_DIR \
  --output_dir=$OUTPUT_DIR \
  --resolution=512 \
  --train_batch_size=16 \
  --gradient_accumulation_steps=1 --gradient_checkpointing \
  --use_8bit_adam \
  --enable_xformers_memory_efficient_attention \
  --set_grads_to_none \
  --unet_learning_rate=2e-4 \
  --text_encoder_learning_rate=4e-5 \
  --lr_scheduler="constant" \
  --lr_warmup_steps=100 \
  --max_train_steps=2000 \
  --lora_rank=8 \
  --lora_dropout=0.1 \
  --lora_alpha=16 \

With the help of gradient checkpointing and the 8-bit optimizer from bitsandbytes it's possible to run train realfill on a 16GB GPU.

To install bitsandbytes please refer to this readme.

You can enable memory efficient attention by installing xFormers and padding the --enable_xformers_memory_efficient_attention argument to the script.

To save even more memory, pass the --set_grads_to_none argument to the script. This will set grads to None instead of zero. However, be aware that it changes certain behaviors, so if you start experiencing any problems, remove this argument.

More info: https://pytorch.org/docs/stable/generated/torch.optim.Optimizer.zero_grad.html

python infer.py --model_path "./dirty_sufaces_bbox_model" --validation_image ./target.png" --validation_mask "./mask.png"

This repo is built upon the code of DreamBooth from diffusers and we thank the developers for their great works and efforts to release source code. Furthermore, a special "thank you" to RealFill's authors for publishing such an amazing work.