Follow the steps below to set up the environment and run the inference demo.

Clone the repository:

git clone git@github.com:rayray9999/Genfocus.git
cd Genfocus

Environment setup:

conda create -n Genfocus python=3.12
conda activate Genfocus

Install requirements:

pip install -r requirements.txt

You can download the pre-trained models using the following commands. Ensure you are in the Genfocus root directory.

# 1. Download main models to the root directory
wget https://huggingface.co/nycu-cplab/Genfocus-Model/resolve/main/bokehNet.safetensors
wget https://huggingface.co/nycu-cplab/Genfocus-Model/resolve/main/deblurNet.safetensors
# 2. Setup checkpoints directory and download auxiliary model
mkdir -p checkpoints
cd checkpoints
wget https://huggingface.co/nycu-cplab/Genfocus-Model/resolve/main/checkpoints/depth_pro.pt
cd ..

Launch the interactive web interface locally:

Note: The project uses FLUX.1-dev. You must request access and authenticate locally before running the demo.

python demo.py

The demo will be accessible at https://127.0.0.1:7860 in your browser.

We are actively working on improving this project. Current progress:

• Upload Model Weights
• Release HF Demo & Gradio Code (with tiling tricks for high-res images)
• Release Benchmark data
• Release Inference Code (Support for adjustable parameters/settings)
• Release Training Code and Data

If you find this project useful for your research, please consider citing:

@article{Genfocus2025,
  title={Generative Refocusing: Flexible Defocus Control from a Single Image},
  author={Tuan Mu, Chun-Wei and Huang, Jia-Bin and Liu, Yu-Lun},
  journal={arXiv preprint arXiv:2512.16923},
  year={2025}
}

For any questions or suggestions, please open an issue or contact me at raytm9999.cs09@nycu.edu.tw.