Training-Free Hidden-State Refinement for Flow-Matching Image Generators

2026-08-29

AI Summary

本文通过在去噪器内部添加推理计算来改进冻结的流匹配图像生成器，提出了一种无需训练的循环框架以提高生成质量和效率。

Abstract

We aim to improve frozen flow-matching image generators by adding inference computation inside the denoiser, without changing model weights or the outer sampler. Existing generators usually spend extra test-time computation by increasing the number of sampling steps, which repeatedly evaluates the entire denoiser and couples quality gains to sampler cost. A key challenge is how to use extra computation inside a frozen transformer denoiser: the method must decide which tokens, layers, and sampling times receive repeated updates while preserving the original generation pipeline. We introduce a training-free looping framework that repeatedly applies selected transformer layers inside each denoising call. Dense and Sparse Token Loop vary the token scope; Sampling-Progress Gating and the loop layer range specify when and where looping is active; loop count and strength control the repeated updates; and Loop Guidance combines ordinary and looped vector-field predictions. Across two Scale-RAE model scales, loop variants improve primary and auxiliary quality metrics with competitive quality--efficiency trade-offs. Loop Guidance further improves both primary metrics across all three tested models; on Scale-RAE DiT2.4B, it raises GenEval from 0.4471 to 0.5691 and DPG-Bench from 0.7656 to 0.8053. Code will be released.

Problem

• flow-matching image generators
• inference computation
• frozen denoiser
• sampling steps
• quality-efficiency trade-offs

Innovation

• Training-Free Looping Framework
• Dense and Sparse Token Loop
• Sampling-Progress Gating
• Loop Guidance