This repository hosts the official PyTorch implementation of the paper: "HairCLIPv2: Unifying Hair Editing via Proxy Feature Blending".

HairCLIPv2 supports hairstyle and color editing individually or jointly with unprecedented user interaction mode support, including text, mask, sketch, reference image, etc.

Tianyi Wei¹, Dongdong Chen², Wenbo Zhou¹, Jing Liao³, Weiming Zhang¹, Gang Hua⁴, Nenghai Yu^1
1University of Science and Technology of China, ²Microsoft Cloud AI, ³City University of Hong Kong, ⁴Xi'an Jiaotong University

2023.12.08: The initial version of the code is released.
2023.10.12: HairCLIPv2 is accepted by ICCV2023! 🎉

$ pip install torch==1.9.0+cu111 torchvision==0.10.0+cu111 -f https://download.pytorch.org/whl/torch_stable.html
$ pip install ftfy regex tqdm matplotlib jupyter ipykernel opencv-python scikit-image kornia==0.6.7 face-alignment==1.3.5 dlib==19.22.1
$ pip install git+https://github.com/openai/CLIP.git

Download and put all the downloaded pretrained weights into the pretrained_models directory.

All inputs are in the test_images folder and all images should be made sure to be aligned to 1024x1024 according to FFHQ standards.

Open hairclip_v2_demo.ipynb to unlock your versatile hairstyles!

If you run it on a remote server, you need to run jupyter notebook --port=20367 --allow-root --ip=0.0.0.0 first. then use e.g. VS Code to select that Jupyter Server as your kernel.

• Develop an interactive interface

This code is based on Barbershop.

If you find our work useful for your research, please consider citing the following papers :)

@article{wei2023hairclipv2,
  title={HairCLIPv2: Unifying Hair Editing via Proxy Feature Blending},
  author={Wei, Tianyi and Chen, Dongdong and Zhou, Wenbo and Liao, Jing and Zhang, Weiming and Hua, Gang and Yu, Nenghai},
  journal={Proceedings of the IEEE/CVF International Conference on Computer Vision},
  year={2023}
}

@article{wei2022hairclip,
  title={Hairclip: Design your hair by text and reference image},
  author={Wei, Tianyi and Chen, Dongdong and Zhou, Wenbo and Liao, Jing and Tan, Zhentao and Yuan, Lu and Zhang, Weiming and Yu, Nenghai},
  journal={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year={2022}
}