CVAIOct 31, 2025

H2-Cache: A Novel Hierarchical Dual-Stage Cache for High-Performance Acceleration of Generative Diffusion Models

arXiv:2510.27171v11 citationsh-index: 17Has CodeIEEE Open J Comput Soc
Originality Incremental advance
AI Analysis

This work addresses the speed-quality trade-off in deploying diffusion models, offering a practical solution for real-world applications, though it is incremental as it builds on existing caching techniques.

The paper tackles the computational cost of diffusion models by introducing H2-Cache, a hierarchical caching mechanism that accelerates inference up to 5.08x while maintaining near-identical image quality to the baseline.

Diffusion models have emerged as state-of-the-art in image generation, but their practical deployment is hindered by the significant computational cost of their iterative denoising process. While existing caching techniques can accelerate inference, they often create a challenging trade-off between speed and fidelity, suffering from quality degradation and high computational overhead. To address these limitations, we introduce H2-Cache, a novel hierarchical caching mechanism designed for modern generative diffusion model architectures. Our method is founded on the key insight that the denoising process can be functionally separated into a structure-defining stage and a detail-refining stage. H2-cache leverages this by employing a dual-threshold system, using independent thresholds to selectively cache each stage. To ensure the efficiency of our dual-check approach, we introduce pooled feature summarization (PFS), a lightweight technique for robust and fast similarity estimation. Extensive experiments on the Flux architecture demonstrate that H2-cache achieves significant acceleration (up to 5.08x) while maintaining image quality nearly identical to the baseline, quantitatively and qualitatively outperforming existing caching methods. Our work presents a robust and practical solution that effectively resolves the speed-quality dilemma, significantly lowering the barrier for the real-world application of high-fidelity diffusion models. Source code is available at https://github.com/Bluear7878/H2-cache-A-Hierarchical-Dual-Stage-Cache.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes