LapFlow: Laplacian Multi-scale Flow Matching for Generative Modeling

Zelin Zhao, Petr Molodyk, Haotian Xue, Yongxin Chen

Keywords: flow matching, multi-scale, generative modeling, image generation

TL;DR: In this paper, we present a multi-scale framework for flow matching, aiming to improve the scalability of image generative modeling.

Abstract: In this paper, we present Laplacian multiscale flow matching (LapFlow), a novel framework that enhances flow matching by leveraging multi-scale representations for image generative modeling. Our approach decomposes images into Laplacian pyramid residuals and processes different scales in parallel through a mixture-of-transformers (MoT) architecture with causal attention mechanisms. Unlike previous cascaded approaches that require explicit renoising between scales, our model generates multi-scale representations in parallel, eliminating the need for bridging processes. The proposed multi-scale architecture not only improves generation quality but also accelerates the sampling process and promotes scaling flow matching methods. Through extensive experimentation on CelebA-HQ and ImageNet, we demonstrate that our method achieves superior sample quality with fewer GFLOPs and faster inference compared to single-scale and multi-scale flow matching baselines. The proposed model scales effectively to high-resolution generation (up to 1024×1024) while maintaining lower computational overhead.

Primary Area: generative models

Submission Number: 11716