提出高效加速框架，让流模型生成速度提升6倍以上。
StreamFlow: Theory, Algorithm, and Implementation for High-Efficiency Rectified Flow Generation
- 设计新速度场与向量化时间步处理，优化生成流程
- 实测512×512图像生成速度提升6.11倍（611%）
- 适合追求生成效率的扩散模型研究者与工程应用
近年来，修正流（Rectified Flow）与流匹配（Flow Matching）技术显著提升了生成模型在控制精度、生成质量与效率方面的表现。然而，由于理论与现有扩散模型的差异，传统加速方法无法直接应用于修正流模型。本文从理论、设计与推理策略出发，构建了完整的加速流水线，引入批量处理新速度场、异构时间步向量化及动态TensorRT编译等新方法，全面加速基于流模型的生成任务。现有公开方法平均加速仅18%，而实验表明本方法可将512×512图像生成速度提升至611%，远超当前非通用加速方案。
原文摘要 · Abstract (English)
New technologies such as Rectified Flow and Flow Matching have significantly improved the performance of generative models in the past two years, especially in terms of control accuracy, generation quality, and generation efficiency. However, due to some differences in its theory, design, and existing diffusion models, the existing acceleration methods cannot be directly applied to the Rectified Flow model. In this article, we have comprehensively implemented an overall acceleration pipeline from the aspects of theory, design, and reasoning strategies. This pipeline uses new methods such as batch processing with a new velocity field, vectorization of heterogeneous time-step batch processing, and dynamic TensorRT compilation for the new methods to comprehensively accelerate related models based on flow models. Currently, the existing public methods usually achieve an acceleration of 18%, while experiments have proved that our new method can accelerate the 512*512 image generation speed to up to 611%, which is far beyond the current non-generalized acceleration methods.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。