ID-Animator: Zero-Shot Identity-Preserving Human Video Generation

arXiv:2404.15275v1 Announce Type: new
Abstract: Generating high fidelity human video with specified identities has attracted significant attention in the content generation community. However, existing techniques struggle to strike a balance between training efficiency and identity preservation, either requiring tedious case-by-case finetuning or usually missing the identity details in video generation process. In this study, we present ID-Animator, a zero-shot human-video generation approach that can perform personalized video generation given single reference facial image without further training. ID-Animator inherits existing diffusion-based …

arxiv cs.cv human identity type video video generation zero-shot