PeRFlow: Piecewise Rectified Flow as Universal Plug-and-Play Accelerator

13 May 2024  ·  Hanshu Yan, Xingchao Liu, Jiachun Pan, Jun Hao Liew, Qiang Liu, Jiashi Feng ·

We present Piecewise Rectified Flow (PeRFlow), a flow-based method for accelerating diffusion models. PeRFlow divides the sampling process of generative flows into several time windows and straightens the trajectories in each interval via the reflow operation, thereby approaching piecewise linear flows. PeRFlow achieves superior performance in a few-step generation. Moreover, through dedicated parameterizations, the PeRFlow models inherit knowledge from the pretrained diffusion models. Thus, the training converges fast and the obtained models show advantageous transfer ability, serving as universal plug-and-play accelerators that are compatible with various workflows based on the pre-trained diffusion models. Codes for training and inference are publicly released.

PDF Abstract


Results from the Paper

  Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.