Zhejiang University, DAMO Academy (Alibaba Group), Hupan Lab, National University of Singapore · Text-to-Video

LumosX

A diffusion-based framework for personalized multi-subject video generation that enforces face-attribute alignment through Relational Self-Attention and Cross-Attention mechanisms. Achieves identity-consistent video generation with fine-grained subject-attribute control using subject-specific relational priors extracted via MLLMs.