HairCLIP: Design Your Hair by Text and Reference Image (CVPR2022)

This repository hosts the official PyTorch implementation of the paper: "HairCLIP: Design Your Hair by Text and Reference Image".

Our single framework supports hairstyle and hair color editing individually or jointly, and conditional inputs can come from either image or text domain.

Tianyi Wei¹, Dongdong Chen², Wenbo Zhou¹, Jing Liao³, Zhentao Tan¹, Lu Yuan², Weiming Zhang¹, Nenghai Yu^1
1University of Science and Technology of China, ²Microsoft Cloud AI, ³City University of Hong Kong

News

2023.10.12: We propose the more performant HairCLIPv2 that supports various interaction modalities, which is accepted by ICCV2023! 🎉
2022.03.19: Our testing code and pretrained model are released.
2022.03.09: Our training code is released.
2022.03.02: Our paper is accepted by CVPR2022 and the code will be released soon.

Web Demo

Upload your own image and try HairCLIP here with Replicate

Getting Started

Prerequisites

$ conda install --yes -c pytorch pytorch=1.7.1 torchvision cudatoolkit=11.0
$ pip install ftfy regex tqdm
$ pip install git+https://github.com/openai/CLIP.git
$ pip install tensorflow-io

Pretrained Model

If you wish to use the pretrained model for training or inference, you may do so using the flag --checkpoint_path.

Auxiliary Models and Latent Codes

By default, we assume that all auxiliary models are downloaded and saved to the directory pretrained_models.

Training

Training HairCLIP

The main training script can be found in scripts/train.py.
Intermediate training results are saved to opts.exp_dir. This includes checkpoints, train outputs, and test outputs.
Additionally, if you have tensorboard installed, you can visualize tensorboard logs in opts.exp_dir/logs.

Training the HairCLIP Mapper

cd mapper
python scripts/train.py \
--exp_dir=/path/to/experiment \
--hairstyle_description="hairstyle_list.txt" \
--color_description="purple, red, orange, yellow, green, blue, gray, brown, black, white, blond, pink" \
--latents_train_path=/path/to/train_faces.pt \
--latents_test_path=/path/to/test_faces.pt \
--hairstyle_ref_img_train_path=/path/to/celeba_hq_train \
--hairstyle_ref_img_test_path=/path/to/celeba_hq_val \
--color_ref_img_train_path=/path/to/celeba_hq_train \
--color_ref_img_test_path=/path/to/celeba_hq_val \
--color_ref_img_in_domain_path=/path/to/generated_hair_of_various colors \
--hairstyle_manipulation_prob=0.5 \
--color_manipulation_prob=0.2 \
--both_manipulation_prob=0.27 \
--hairstyle_text_manipulation_prob=0.5 \
--color_text_manipulation_prob=0.5 \
--color_in_domain_ref_manipulation_prob=0.25 \

Additional Notes

• This version only supports batch size and test batch size to be 1.
• See options/train_options.py for all training-specific flags.
• See options/test_options.py for all test-specific flags.
• You can customize your own HairCLIP by adjusting the different category probabilities. For example, if you want to train a HairCLIP that only performs hair color editing with text as the interaction mode, you can adjust the different probabilities as follows.

  --hairstyle_manipulation_prob=0 \
  --color_manipulation_prob=1 \
  --both_manipulation_prob=0 \
  --color_text_manipulation_prob=1 \

• --color_ref_img_in_domain_path is a dataset of images with diverse hair colors generated by the HairCLIP trained from the above probabilistic configuration to enhance the diversity of the dataset when editing hair colors based on the reference image, which you may not use. If you choose to use this augmentation, you need to pre-train a text-based hair color HairCLIP according to above probabilistic configuration.
• The weights of different losses in training are in the options/train_options.py, and you can adjust them to balance your needs. Empirically, the larger the loss weight, the better the corresponding effect, but it will affect the effect of other losses to some extent.

  Testing

  Inference

  The main inference script can be found in scripts/inference.py. Inference results are saved to test_opts.exp_dir.

  Example of Using Text to Edit Hairstyle

  cd mapper
  python scripts/inference.py \
  --exp_dir=/path/to/experiment \
  --checkpoint_path=../pretrained_models/hairclip.pt \
  --latents_test_path=/path/to/test_faces.pt \
  --editing_type=hairstyle \
  --input_type=text \
  --hairstyle_description="hairstyle_list.txt" \

  Example of Using Text to Edit Hairstyle Reference Image to Edit Hair Color

  cd mapper
  python scripts/inference.py \
  --exp_dir=/path/to/experiment \
  --checkpoint_path=../pretrained_models/hairclip.pt \
  --latents_test_path=/path/to/test_faces.pt \
  --editing_type=both \
  --input_type=text_image \
  --hairstyle_description="hairstyle_list.txt" \
  --color_ref_img_test_path=/path/to/celeba_hq_test \

  Additional Notes

• See options/test_options.py for all test-specific flags.
• --editing_type should be hairstyle, color, or both to indicate whether to edit only hairstyle, only hair color, or both hairstyle and hair color.
• --input_type is used to indicate the interaction mode, text for text, and image for reference image. When editing both hairstyle and hair color, the two interactions are separated by _.
• The --start_index and --end_index indicate the range of the edited test latent codes, where --start_index needs to be greater than 0 and --end_index cannot exceed the size of the whole test latent codes dataset.

Acknowledgements

This code is based on StyleCLIP.

Citation

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

@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}
}

@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}
}