Year: 2025
Type: conference-paper
Abstract: 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 welldefined 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 256×256 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.Our code is available at https://github.com/gsunshine/meanflow.
DOI: 10.52202/085713-2534
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
OpenAlex ID: W4417298370