Flow Straighter and Faster: Efficient One-Step Generative Modeling via MeanFlow on Rectified Trajectories
By: Xinxi Zhang , Shiwei Tan , Quang Nguyen and more
Potential Business Impact:
Makes AI create images much faster and better.
Flow-based generative models have recently demonstrated strong performance, yet sampling typically relies on expensive numerical integration of ordinary differential equations (ODEs). Rectified Flow enables one-step sampling by learning nearly straight probability paths, but achieving such straightness requires multiple computationally intensive reflow iterations. MeanFlow achieves one-step generation by directly modeling the average velocity over time; however, when trained on highly curved flows, it suffers from slow convergence and noisy supervision. To address these limitations, we propose Rectified MeanFlow, a framework that models the mean velocity field along the rectified trajectory using only a single reflow step. This eliminates the need for perfectly straightened trajectories while enabling efficient training. Furthermore, we introduce a simple yet effective truncation heuristic that aims to reduce residual curvature and further improve performance. Extensive experiments on ImageNet at 64, 256, and 512 resolutions show that Re-MeanFlow consistently outperforms prior one-step flow distillation and Rectified Flow methods in both sample quality and training efficiency. Code is available at https://github.com/Xinxi-Zhang/Re-MeanFlow.
Similar Papers
Balanced conic rectified flow
CV and Pattern Recognition
Makes AI create better pictures with less data.
Rectified Flows for Fast Multiscale Fluid Flow Modeling
Machine Learning (CS)
Makes computer pictures appear much faster.
Improved Mean Flows: On the Challenges of Fastforward Generative Models
CV and Pattern Recognition
Makes AI create pictures faster and better.