18
7

Simple ReFlow: Improved Techniques for Fast Flow Models

Abstract

Diffusion and flow-matching models achieve remarkable generative performance but at the cost of many sampling steps, this slows inference and limits applicability to time-critical tasks. The ReFlow procedure can accelerate sampling by straightening generation trajectories. However, ReFlow is an iterative procedure, typically requiring training on simulated data, and results in reduced sample quality. To mitigate sample deterioration, we examine the design space of ReFlow and highlight potential pitfalls in prior heuristic practices. We then propose seven improvements for training dynamics, learning and inference, which are verified with thorough ablation studies on CIFAR10 32×3232 \times 32, AFHQv2 64×6464 \times 64, and FFHQ 64×6464 \times 64. Combining all our techniques, we achieve state-of-the-art FID scores (without / with guidance, resp.) for fast generation via neural ODEs: 2.232.23 / 1.981.98 on CIFAR10, 2.302.30 / 1.911.91 on AFHQv2, 2.842.84 / 2.672.67 on FFHQ, and 3.493.49 / 1.741.74 on ImageNet-64, all with merely 99 neural function evaluations.

View on arXiv
Comments on this paper