Jul 2026
Vera: Identity-Faithful Human Subject-to-Video Generation
Vera is proposed, a unified human-centric S2V framework for single- and multi- person generation that improves human identity consistency, multi-person subject binding, and motion naturalness, while reducing identity confusion and excessive reference-image copying.
Yulong Xu, Xinyue Liu, Shujuan Li et al.
· arXiv.org · 0 citations