facechain

FaceChain is a deep-learning toolchain for generating your Digital-Twin.

项目简介

modelscope/facechain 是一个基于 GitHub 的开源项目，目前拥有 9,494 颗 Star。该项目的主要语言为 Jupyter Notebook。

功能特点

详情请查阅项目的 README 文档。

快速开始

安装

git clone https://github.com/modelscope/facechain.git
cd facechain

基本使用

请参考项目 README 获取详细使用方法。

README 原文

<p align="center">
    <br>
    <img src="https://modelscope.oss-cn-beijing.aliyuncs.com/modelscope.gif" width="400"/>
    <br>
    <h1>FaceChain</h1>
<p>

<p align="center">
<a href="https://trendshift.io/repositories/1185" target="_blank"><img src="https://trendshift.io/api/badge/repositories/1185" alt="modelscope%2Ffacechain | Trendshift" style="width: 250px; height: 55px;" width="250" height="55"/></a>
</p>

# News
- Our work [FaceChain-MMID](https://www.sciencedirect.com/science/article/abs/pii/S0031320325005187) got accepted to Pattern Recognition ! (May 30th, 2025 UTC)
- More Technology Details of FaceChain-FACT train-free portrait generation can be seen in [Paper](https://arxiv.org/abs/2410.12312). (October 17th, 2024 UTC)
- Our work [TopoFR](https://arxiv.org/abs/2410.10587) got accepted to NeurIPS 2024 ! (September 26th, 2024 UTC)
- We provide training scripts for new styles, offering an automatic training for new style LoRas as well as the corresponding style prompts, along with the one click call in Infinite Style Portrait generation tab! (July 3rd, 2024 UTC)
- 🚀🚀🚀 We are launching [FACT] into the main branch, offering a 10-second impressive speed and seamless integration with standard ready-to-use LoRas and ControlNets, along with improved instruction-following capabilities ! The original train-based FaceChain is moved to (https://github.com/modelscope/facechain/tree/v3.0.0 ). (May 28th, 2024 UTC)
- Our work [FaceChain-ImagineID](https://arxiv.org/abs/2403.01901) and [FaceChain-SuDe](https://arxiv.org/abs/2403.06775) got accepted to CVPR 2024 ! (February 27th, 2024 UTC)

# Introduction

如果您熟悉中文，可以阅读[中文版本的README](./README_ZH.md)。

FaceChain is a novel framework for generating identity-preserved human portraits. In the newest FaceChain FACT (Face Adapter with deCoupled Training) version, with only 1 photo and 10 seconds, you can generate personal portraits in different settings (multiple styles now supported!). FaceChain has both high controllability and authenticity in portrait generation, including text-to-image and inpainting based pipelines, and is seamlessly compatible with ControlNet and LoRAs. You may generate portraits via FaceChain's Python scripts, or via the familiar Gradio interface, or via sd webui. 
FaceChain is powered by [ModelScope](https://github.com/modelscope/modelscope).


<p align="center">
        ModelScope Studio <a href="https://modelscope.cn/studios/CVstudio/FaceChain-FACT">🤖<a></a>&nbsp ｜API <a href="https://help.aliyun.com/zh/dashscope/developer-reference/facechain-quick-start">🔥<a></a>&nbsp | SD WebUI | HuggingFace Space <a href="https://huggingface.co/spaces/modelscope/FaceChain-FACT">🤗</a>&nbsp 
</p>
<br>

<a href='https://facechain-fact.github.io/'><img src='https://img.shields.io/badge/Project-Page-Green'></a>  [![YouTube](https://badges.aleen42.com/src/youtube.svg)](https://youtu.be/DHqEl0qwi-M?si=y6VpInXdhIX0HpbI)


![image](resources/git_cover.png)


# News
- Our work [FaceChain-MMID](https://www.sciencedirect.com/science/article/abs/pii/S0031320325005187) got accepted to Pattern Recognition ! (May 30th, 2025 UTC)
- More Technology Details of FaceChain-FACT train-free portrait generation can be seen in [Paper](https://arxiv.org/abs/2410.12312). (October 17th, 2024 UTC)
- Our work [TopoFR](https://arxiv.org/abs/2410.10587) got accepted to NeurIPS 2024 ! (September 26th, 2024 UTC)
- We provide training scripts for new styles, offering an automatic training for new style LoRas as well as the corresponding style prompts, along with the one click call in Infinite Style Portrait generation tab! (July 3rd, 2024 UTC)
- 🚀🚀🚀 We are launching [FACT], offering a 10-second impressive speed and seamless integration with standard ready-to-use LoRas and ControlNets, along with improved instruction-following capabilities ! (May 28th, 2024 UTC)
- Our work [FaceChain-ImagineID](https://arxiv.org/abs/2403.01901) and [FaceChain-SuDe](https://arxiv.org/abs/2403.06775) got accepted to CVPR 2024 ! (February 27th, 2024 UTC)
- 🏆🏆🏆Alibaba Annual Outstanding Open Source Project, Alibaba Annual Open Source Pioneer (Yang Liu, Baigui Sun). (January 20th, 2024 UTC)
- Our work [InfoBatch](https://github.com/henryqin1997/InfoBatch) co-authored with NUS team got accepted to ICLR 2024(Oral)! (January 16th, 2024 UTC)
- 🏆OpenAtom's 2023 Rapidly Growing Open Source Projects Award. (December 20th, 2023 UTC)
- Add SDXL pipeline🔥🔥🔥, image detail is improved obviously. (November 22th, 2023 UTC)
- Support super resolution🔥🔥🔥, provide multiple resolution choice (512*512, 768*768, 1024*1024, 2048*2048). (November 13th, 2023 UTC)
- 🏆FaceChain has been selected in the [BenchCouncil Open100 (2022-2023)](https://www.benchcouncil.org/evaluation/opencs/annual.html#Institutions) annual ranking. (November 8th, 2023 UTC)
- Add virtual try-on module. (October 27th, 2023 UTC)
- Add wanx version [online free app](https://tongyi.aliyun.com/wanxiang/app/portrait-gallery). (October 26th, 2023 UTC)
- 🏆1024 Programmer's D

项目信息

参考链接

• GitHub 仓库