FREPix: Frequency-Heterogeneous Flow Matching for Pixel-Space Image Generation

Pixel-space diffusion has re-emerged as a promising alternative to latent-space generation because it avoids the representation bottleneck introduced by VAEs. Yet most existing methods still treat image generation as a frequency-homogeneous process, overlooking the distinct roles and learning dynamics of low- and high-frequency components. To address this, we propose $\text{FREPix}$, a $\text{FRE}$quency-heterogeneous flow matching framework for $\text{Pix}$el-space image generation. $\text{FREPix}$ explicitly decomposes generation into low- and high-frequency components, assigns them separate transport paths, predicts them with a factorized network, and trains them with a frequency-aware objective. In this way, coarse-to-fine generation becomes an explicit design principle rather than an implicit behavior. On ImageNet class-to-image generation, $\text{FREPix}$ achieves competitive results among pixel-space generation models, reaching 1.91 FID at $256\times 256$ and 2.38 FID at $512\times 512$, with particularly strong behavior in the low-NFE regime.