SplitMeanFlow: Interval Splitting Consistency in Few-Step Generative Modeling

TL;DR

SplitMeanFlow introduces an algebraic principle called Interval Splitting Consistency for more efficient, stable, and generalizable few-step generative modeling, demonstrated by significant speedups in speech synthesis.

Contribution

It derives a novel algebraic identity for average velocity fields, generalizing differential-based methods like MeanFlow, and improves efficiency and stability in generative modeling.

Findings

Achieves 20x speedup in speech synthesis applications.

Eliminates the need for JVP computations, simplifying implementation.

Provides a more stable and hardware-compatible training framework.

Abstract

Generative models like Flow Matching have achieved state-of-the-art performance but are often hindered by a computationally expensive iterative sampling process. To address this, recent work has focused on few-step or one-step generation by learning the average velocity field, which directly maps noise to data. MeanFlow, a leading method in this area, learns this field by enforcing a differential identity that connects the average and instantaneous velocities. In this work, we argue that this differential formulation is a limiting special case of a more fundamental principle. We return to the first principles of average velocity and leverage the additivity property of definite integrals. This leads us to derive a novel, purely algebraic identity we term Interval Splitting Consistency. This identity establishes a self-referential relationship for the average velocity field across different time intervals without resorting to any differential operators. Based on this principle, we introduce SplitMeanFlow, a new training framework that enforces this algebraic consistency directly as a learning objective. We formally prove that the differential identity at the core of MeanFlow is recovered by taking the limit of our algebraic consistency as the interval split becomes infinitesimal. This establishes SplitMeanFlow as a direct and more general foundation for learning average velocity fields. From a practical standpoint, our algebraic approach is significantly more efficient, as it eliminates the need for JVP computations, resulting in simpler implementation, more stable training, and broader hardware compatibility. One-step and two-step SplitMeanFlow models have been successfully deployed in large-scale speech synthesis products (such as Doubao), achieving speedups of 20x.