PeRFlow：分段整流流作为通用即插即用加速器
PeRFlow: Piecewise Rectified Flow as Universal Plug-and-Play Accelerator
AI总结：
PeRFlow 通过分段 reflow 拉直生成流轨迹，将扩散模型采样加速至少步生成，并作为通用即插即用加速器兼容多种预训练扩散模型工作流。
摘要：
我们提出分段整流流（PeRFlow），一种基于流的方法，用于加速扩散模型。PeRFlow 将生成流的采样过程划分为若干时间窗口，并通过 reflow 操作拉直每个区间内的轨迹，从而逼近分段线性流。PeRFlow 在少步生成中取得了优越的性能。此外，通过专门的参数化方式，PeRFlow 模型继承了预训练扩散模型的知识。因此，训练收敛迅速，所得模型展现出有利的迁移能力，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。训练和推理代码已公开发布。https://github.com/magic-research/piecewise-rectified-flow
英文摘要：
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
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
