--- license: apache-2.0 pipeline_tag: text-to-video --- # ID-Animator This repository is the official checkpoint of [ID-Animator](https://id-animator.github.io/). It is a Zero-shot ID-Preserving Human Video Generation framework. It can generate high-quality ID-specific human video with only one ID image as reference. **[ID-Animator: Zero-Shot Identity-Preserving Human Video Generation](https://id-animator.github.io/)**
[Xuanhua He](https://scholar.google.com/citations?user=-bDAN2YAAAAJ&hl=en&oi=ao), [Quande Liu*](https://liuquande.github.io/), [Shengju Qian](https://scholar.google.com/citations?user=QNnWmasAAAAJ&hl=zh-CN), Xin Wang, Tao Hu, [Ke Cao](https://scholar.google.com/citations?user=3qMrWmgAAAAJ&hl=en&oi=ao), Keyu Yan, Jie Zhang* (*Corresponding Author) [![arXiv](https://img.shields.io/badge/arXiv-2404.15275-b31b1b.svg)](https://arxiv.org/abs/2404.15275) [![Project Page](https://img.shields.io/badge/Project-Website-green)](https://id-animator.github.io/) [![Online Demo](https://img.shields.io/badge/%F0%9F%A4%97online%20demo-yellow)](https://huggingface.co/spaces/ID-Animator/ID-Animator) ## Human Video Generation Demos ### Recontextualization
Reference Image Output Video Output Video Output Video
Reference Image Output Video Output Video Output Video
### Inference with Community Models
Reference Image Output Video Output Video Output Video
Reference Image Output Video Output Video Output Video
### Identity Mixing
Reference Image 1 Reference Image 2 Output Video Output Video
Reference Image 1 Reference Image 2 Output Video Output Video
### Combination with ControlNet
Reference Image Sketch Image Output Video Output Video
Reference Image Sketch Sequence Output Video Output Video
## Contact Us **Xuanhua He**: hexuanhua@mail.ustc.edu.cn **Quande Liu**: qdliu0226@gmail.com **Shengju Qian**: thesouthfrog@gmail.com