Mean Flows for One-step Generative Modeling

We propose a principled and effective framework for one-step generative modeling. We introduce the notion of average velocity to characterize flow fields, in contrast to instantaneous velocity modeled by Flow Matching methods. A well-defined identity between average and instantaneous velocities is derived and used to guide neural network training. Our method, termed the MeanFlow model, is self-contained and requires no pre-training, distillation, or curriculum learning. MeanFlow demonstrates strong empirical performance: it achieves an FID of 3.43 with a single function evaluation (1-NFE) on ImageNet 256x256 trained from scratch, significantly outperforming previous state-of-the-art one-step diffusion/flow models. Our study substantially narrows the gap between one-step diffusion/flow models and their multi-step predecessors, and we hope it will motivate future research to revisit the foundations of these powerful models.

@article{geng2025_2505.13447,
  title={ Mean Flows for One-step Generative Modeling },
  author={ Zhengyang Geng and Mingyang Deng and Xingjian Bai and J. Zico Kolter and Kaiming He },
  journal={arXiv preprint arXiv:2505.13447},
  year={ 2025 }
}