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

TL;DR

CHORDS introduces a multi-core, training-free diffusion sampling acceleration framework that significantly speeds up image and video generation without quality loss, enabling real-time high-fidelity diffusion outputs.

Contribution

This paper presents CHORDS, a novel multi-core, training-free diffusion sampling accelerator that is compatible with various models and modalities, improving speed without sacrificing quality.

Findings

Up to 2.1x speedup with four cores

50% improvement over baselines

2.9x speedup with eight cores

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.