S2DM: Sector-Shaped Diffusion Models for Video Generation

no code implementations • 20 Mar 2024 • Haoran Lang, Yuxuan Ge, Zheng Tian

For text-to-video generation tasks where temporal conditions are not explicitly given, we propose a two-stage generation strategy which can decouple the generation of temporal features from semantic-content features.

Image Generation Optical Flow Estimation +2