一致性流匹配：定义具有速度的直线流 一致性

Consistency Flow Matching: Defining Straight Flows with Velocity Consistency

July 2, 2024

作者: Ling Yang, Zixiang Zhang, Zhilong Zhang, Xingchao Liu, Minkai Xu, Wentao Zhang, Chenlin Meng, Stefano Ermon, Bin Cui

cs.AI

摘要

流匹配（FM）是通过常微分方程（ODEs）定义概率路径的一般框架，用于在噪声和数据样本之间进行转换。最近的方法尝试将这些流轨迹拉直，通过迭代校正方法或最优输运解决方案通常能够用更少的函数评估生成高质量样本。在本文中，我们介绍了一种新的FM方法，一致性流匹配（Consistency-FM），它明确在速度场中强制执行自一致性。一致性流匹配直接定义了从不同时间开始到相同终点的直线流，对其速度值施加约束。此外，我们提出了一种多段训练方法用于一致性流匹配，以增强表达能力，在采样质量和速度之间取得更好的折衷。初步实验表明，我们的一致性流匹配通过比一致性模型快4.4倍和校正流模型快1.7倍的收敛速度显著提高了训练效率，同时实现了更好的生成质量。我们的代码可在以下链接找到：https://github.com/YangLing0818/consistency_flow_matching

English

Flow matching (FM) is a general framework for defining probability paths via Ordinary Differential Equations (ODEs) to transform between noise and data samples. Recent approaches attempt to straighten these flow trajectories to generate high-quality samples with fewer function evaluations, typically through iterative rectification methods or optimal transport solutions. In this paper, we introduce Consistency Flow Matching (Consistency-FM), a novel FM method that explicitly enforces self-consistency in the velocity field. Consistency-FM directly defines straight flows starting from different times to the same endpoint, imposing constraints on their velocity values. Additionally, we propose a multi-segment training approach for Consistency-FM to enhance expressiveness, achieving a better trade-off between sampling quality and speed. Preliminary experiments demonstrate that our Consistency-FM significantly improves training efficiency by converging 4.4x faster than consistency models and 1.7x faster than rectified flow models while achieving better generation quality. Our code is available at: https://github.com/YangLing0818/consistency_flow_matching