Our TinyBeauty effectively synthesizes stunning makeup styles with consistent content, enabling seamless video application.
- [2024/06/02] 🔥 We release the source code.
- [2024/04/03] 🔥 We launch the project page.
- [2024/03/22] 🔥 We release the technical report.
Our DDA generates consistent makeup styles while retain the facial content and identity of the original image
Facial makeup results on high-resolution (1024*1024) images.Visual comparison of TineBeauty and competing methods on the FFHQ Dataset.
Visual comparison of TineBeauty and competing methods on the MT Dataset.
Visual comparison of TineBeauty and BeautyREC on challenging out-of-distribution examples
Download sample image pair and makeup style template from here, and place it in the ./data
folder.
python SD_finetune.py
-m runwayml/stable-diffusion-v1-5
-e h94/IP-Adapter
-nonmakeup data/Finetune_Data/train
-makeup data/Finetune_Data/train_purple
-o "$LORA_MODEL_SAVE_PATH"
python SD_inference.py
-m "$LORA_MODEL_SAVE_PATH"
-s data/Finetune_Data/purple.png
-d data/Finetune_Data/test
-o res/test1
If you find TinyBeauty useful for your research and applications, please cite us using this BibTeX:
@misc{jin2024tiny,
title={Toward Tiny and High-quality Facial Makeup with Data Amplify Learning},
author={Qiaoqiao Jin and Xuanhong Chen and Meiguang Jin and Ying Cheng and Rui Shi and Yucheng Zheng and Yupeng Zhu and Bingbing Ni},
year={2024},
eprint={2403.15033},
archivePrefix={arXiv},
primaryClass={cs.CV}
}