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. https://github.com/magic-research/piecewise-rectified-flow

翻译：本文提出分段整流流（PeRFlow），一种基于流的扩散模型加速方法。PeRFlow将生成流的采样过程划分为多个时间窗口，并通过回流操作在每个区间内拉直轨迹，从而逼近分段线性流。PeRFlow在少量步数生成中实现了卓越的性能。此外，通过专门的参数化设计，PeRFlow模型能够继承预训练扩散模型的知识。因此，训练收敛迅速，且获得的模型展现出优异的迁移能力，可作为通用即插即用加速器，兼容基于预训练扩散模型的各种工作流程。训练与推理代码已公开发布。https://github.com/magic-research/piecewise-rectified-flow