Can We Change "Stroke Size" to Simplify Flow Matching?

Abstract

Deep-learning-based image generation models are useful but difficult to train. Across the different time steps along a generative path, high-noise states present distinct optimization and prediction challenges. Inspired by the varying stroke sizes used in human painting, we hypothesize that applying rough strokes early and fine strokes late can simplify flow-matching image generation. We develop MultiStroke, which progressively varies the spatial granularity of the clean-signal component in both the evolving state and velocity regression target while leaving the Gaussian component uncoarsened. A lightweight corrector aligns adjacent roughness levels during sampling. On ImageNet-1K, MultiStroke reduces FID by $22.5\%$ relative to a matched flow-matching baseline, despite the limited corrector capacity. Code is available at https://github.com/DaChengRuoQue/MultiStroke-Code. A quick video explanation is available at https://dachengruoque.github.io/MultiStroke-Web/.