Parallel Decoding Distillation for Fast Image and Video Generation

Generation in video diffusion or flow models is computationally expensive due to the slow and iterative sampling process.

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…