--- 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 |
Reference Image | Output Video | Output Video | Output Video |
Reference Image | Output Video | Output Video | Output Video |
Reference Image 1 | Reference Image 2 | Output Video | Output Video |
Reference Image 1 | Reference Image 2 | Output Video | Output Video |
Reference Image | Sketch Image | Output Video | Output Video |
Reference Image | Sketch Sequence | Output Video | Output Video |