TensorX
返回文献探索

Paper · arXiv 2407.02398

Consistency Flow Matching: Defining Straight Flows with Velocity Consistency

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

17 upvotesJuly 2, 2024arXiv 预印本
AI 摘要

Consistency Flow Matching improves the efficiency and quality of sample generation by enforcing self-consistency in velocity fields and using multi-segment training for flow-based generative models.

flow matchingordinary differential equationsODEsprobability pathsnoisedata samplesfunction evaluationsiterative rectificationoptimal transportvelocity fieldself-consistencystraight flowsmulti-segment trainingsampling qualityconsistency modelsrectified flow models

Abstract

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

北京市昌平区探索星信息技术及软件开发工作室

京ICP备2026059466号
Consistency Flow Matching: Defining Straight Flows with Velocity Consistency | TensorX