Reflective Flow Sampling Enhancement
Zikai Zhou, Muyao Wang, Shitong Shao, Lichen Bai, Haoyi Xiong, Bo Han, Zeke Xie

TL;DR
Reflective Flow Sampling (RF-Sampling) is a training-free inference enhancement method designed for flow-based text-to-image models like FLUX, improving quality and prompt alignment through a theoretically grounded approach.
Contribution
RF-Sampling provides a formal, training-free inference enhancement specifically for flow models, bridging the gap with conventional diffusion model improvements.
Findings
RF-Sampling improves generation quality on multiple benchmarks.
RF-Sampling enhances prompt-text alignment in flow models.
It exhibits test-time scaling ability on FLUX.
Abstract
The growing demand for text-to-image generation has led to rapid advances in generative modeling. Recently, text-to-image diffusion models trained with flow matching algorithms, such as FLUX, have achieved remarkable progress and emerged as strong alternatives to conventional diffusion models. At the same time, inference-time enhancement strategies have been shown to improve the generation quality and text-prompt alignment of text-to-image diffusion models. However, these techniques are mainly applicable to conventional diffusion models and usually fail to perform well on flow models. To bridge this gap, we propose Reflective Flow Sampling (RF-Sampling), a theoretically-grounded and training-free inference enhancement framework explicitly designed for flow models, especially for the CFG-distilled variants (i.e., models distilled from CFG guidance techniques), like FLUX. Departing from…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
