Spatial-Temporal Decoupled Reference Conditioning for Identity-Preserving Text-to-Video Generation 文章

ArXiv CS.CV2026-06-02NEWSen作者: Yuheng Chen, Teng Hu, Yuji Wang, Qingdong He, Lizhuang Ma, Jiangning Zhang
查看原文 →
关系图谱

Spatial-Temporal Decoupled Reference Conditioning for Identity-Preserving Text-to-Video Generation · 相关技术

相关技术

Identity-preserving video generationvideo VAEST-DRCIPVG