Parallel Decoding Distillation for Fast Image and Video Generation

By Neta Shaul · Paper · cs.CV

Generation in video diffusion or flow models is computationally expensive due to the slow and iterative sampling process. Current state-of-the-art (SOTA) acceleration methods heavily rely on variational score distillation (VSD) and adversarial losses to distill diffusion models i

AI Video · Frontier · Cs.cv

View original

HomeResourceLoading…