Consistency Flow Matching: Defining Straight Flows with Velocity Consistency
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909239378706432 |
|---|---|
| author | Yang, Ling Zhang, Zixiang Zhang, Zhilong Liu, Xingchao Xu, Minkai Zhang, Wentao Meng, Chenlin Ermon, Stefano Cui, Bin |
| author_facet | Yang, Ling Zhang, Zixiang Zhang, Zhilong Liu, Xingchao Xu, Minkai Zhang, Wentao Meng, Chenlin Ermon, Stefano Cui, Bin |
| contents | 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 |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_02398 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Consistency Flow Matching: Defining Straight Flows with Velocity Consistency Yang, Ling Zhang, Zixiang Zhang, Zhilong Liu, Xingchao Xu, Minkai Zhang, Wentao Meng, Chenlin Ermon, Stefano Cui, Bin Computer Vision and Pattern Recognition 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 |
| title | Consistency Flow Matching: Defining Straight Flows with Velocity Consistency |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2407.02398 |