English

CHORDS: Diffusion Sampling Accelerator with Multi-core Hierarchical ODE Solvers

Machine Learning 2025-07-22 v1

Abstract

Diffusion-based generative models have become dominant generators of high-fidelity images and videos but remain limited by their computationally expensive inference procedures. Existing acceleration techniques either require extensive model retraining or compromise significantly on sample quality. This paper explores a general, training-free, and model-agnostic acceleration strategy via multi-core parallelism. Our framework views multi-core diffusion sampling as an ODE solver pipeline, where slower yet accurate solvers progressively rectify faster solvers through a theoretically justified inter-core communication mechanism. This motivates our multi-core training-free diffusion sampling accelerator, CHORDS, which is compatible with various diffusion samplers, model architectures, and modalities. Through extensive experiments, CHORDS significantly accelerates sampling across diverse large-scale image and video diffusion models, yielding up to 2.1x speedup with four cores, improving by 50% over baselines, and 2.9x speedup with eight cores, all without quality degradation. This advancement enables CHORDS to establish a solid foundation for real-time, high-fidelity diffusion generation.

Keywords

Cite

@article{arxiv.2507.15260,
  title  = {CHORDS: Diffusion Sampling Accelerator with Multi-core Hierarchical ODE Solvers},
  author = {Jiaqi Han and Haotian Ye and Puheng Li and Minkai Xu and James Zou and Stefano Ermon},
  journal= {arXiv preprint arXiv:2507.15260},
  year   = {2025}
}

Comments

ICCV 2025

R2 v1 2026-07-01T04:10:33.114Z