cs.LGMay 18, 2026

Dual-Rate Diffusion: Accelerating diffusion models with an interleaved heavy-light network

Authors: Grigory BartoshDavid RuheEmiel HoogeboomJonathan HeekThomas MensinkTim Salimans

Organizations: *Work done while interning at Google DeepMind Amsterdam, 1University of Amsterdam, 2Google DeepMind Amsterdam · 2Google DeepMind Amsterdam

Abstract

Diffusion models achieve state-of-the-art generative performance but suffer from high computational costs during inference due to the repeated evaluation of a heavy neural network. In this work, we propose Dual-Rate Diffusion, a method to accelerate sampling by interleaving the execution of a heavy high-capacity context encoder and a light efficient denoising model. The context encoder is evaluated sparsely to extract high-dimensional features, which are effectively reused by the light denoising model at every step to refine the sample efficiently. This approach significantly accelerates inference without compromising sample quality. On ImageNet benchmarks, Dual-Rate Diffusion matches the performance of standard baselines while reducing computational cost by a factor of 22-44. Furthermore, we demonstrate that our method is compatible with distillation techniques, such as Moment Matching Distillation, enabling further efficiency gains in few-step generation.

Explore similar work

CardsList
  1. General and Efficient Steering of Diffusion Models

    Feb 11, 2026Qingsong Wang, Mikhail Belkin, Yusu WangActivation Steering