CurveFlow: Curvature-Guided Flow Matching for Image Generation

TL;DR

CurveFlow introduces a curvature-guided flow matching approach that learns smooth, non-linear trajectories for image generation, significantly improving semantic alignment and image quality in text-to-image tasks.

Contribution

We propose a novel curvature regularization technique for flow models, enabling non-linear trajectories that enhance semantic consistency in image generation.

Findings

Achieves state-of-the-art results on MS COCO datasets.

Significantly improves semantic metrics like BLEU, METEOR, ROUGE, and CLAIR.

Outperforms standard rectified flow and other non-linear baselines.

Abstract

Existing rectified flow models are based on linear trajectories between data and noise distributions. This linearity enforces zero curvature, which can inadvertently force the image generation process through low-probability regions of the data manifold. A key question remains underexplored: how does the curvature of these trajectories correlate with the semantic alignment between generated images and their corresponding captions, i.e., instructional compliance? To address this, we introduce CurveFlow, a novel flow matching framework designed to learn smooth, non-linear trajectories by directly incorporating curvature guidance into the flow path. Our method features a robust curvature regularization technique that penalizes abrupt changes in the trajectory's intrinsic dynamics.Extensive experiments on MS COCO 2014 and 2017 demonstrate that CurveFlow achieves state-of-the-art performance in text-to-image generation, significantly outperforming both standard rectified flow variants and other non-linear baselines like Rectified Diffusion. The improvements are especially evident in semantic consistency metrics such as BLEU, METEOR, ROUGE, and CLAIR. This confirms that our curvature-aware modeling substantially enhances the model's ability to faithfully follow complex instructions while simultaneously maintaining high image quality. The code is made publicly available at https://github.com/Harvard-AI-and-Robotics-Lab/CurveFlow.