LIU Yaofang

Pusa-VidGen. Pusa: Thousands Timesteps Video Diffusion Model

FVDM. Code for Paper 'Redefining Temporal Modeling in Video Diffusion: The Vectorized Timestep Approach'

Mochi-Full-Finetuner. Code for full fintuing Mochi model with FSDP (and CP)

Super-Resolving. Code for Paper Super-resolving Real-world Image Illumination Enhancement: A New Dataset and A Conditional Diffusion Model

DynamiCrafter. DynamiCrafter: Animating Open-domain Images with Video Diffusion Priors