Guangzhao Li

2 accepted papers

2026

FlowDirector: Training-Free Flow Steering for Precise Text-to-Video Editing

Guangzhao Li, Yanming Yang, Chenxi Song, Xiaohong Liu, Chi Zhang

CVPR 2026

Text-driven video editing aims to modify video content based on natural language instructions. While recent training-free methods have leveraged pretrained diffusion models, they often rely on an inversion-editing paradigm. This paradigm maps the video to a latent space before editing. However, the

Cited by 0 Source ↗code ↗Scholar ↗

2026

LayerT2V: A Unified Multi-Layer Video Generation Framework

Guangzhao Li, Kangrui Cen, Baixuan Zhao, Yi Xin, Siqi Luo, Guangtao Zhai +2

ICML 2026poster

Text-to-video generation has advanced rapidly, but existing methods typically output only the final composited video and lack editable layered representations, limiting their use in professional workflows. We propose \textbf{LayerT2V}, a unified multi-layer video generation framework that produces m…

Cited by 2 Source ↗Scholar ↗