Video2LoRA: Unified Semantic-Controlled Video Generation via Per-Reference-Video LoRA

Zexi Wu, Baolu Li, Jing Dai, Yiming Zhang, Yue Ma, Qinghe Wang, Xu Jia, Hongming Xu.

A lightweight HyperNetwork predicts semantic-specific LoRA weights from a reference video, enabling compact and zero-shot controllable video generation.