Jul 2026
Flex-Forcing: Towards a Unified Autoregressive and Bidirectional Video Diffusion Model
Flex-Forcing is introduced, a unified training and inference framework that enables a video diffusion model to seamlessly operate under both bidirectional and autoregressive generation regimes, and achieves consistently better video quality, long-video stability than strong baselines with a rigid inference schedule.
Xinyin Ma, Julius Berner, Chao Liu et al.
· arXiv.org · 1 citation