EpaCache: Error-Propagation-Aware Caching for Accelerating Diffusion-Based Visual Generation

arXiv:2608.29264v1 Announce Type: new Abstract: Diffusion-based visual generative models deliver strong image and video synthesis quality but incur high inference costs because sequential samplers repeatedly evaluate large networks. Caching-based methods reduce inference latency by reusing intermediate computations across adjacent timesteps. However, existing cache controllers rely primarily on local temporal variation and overlook the trajectory-level consequences of cache reuse. We introduce Error-Propagation-Aware Cache (EpaCache), a training-free caching policy that adaptively allocates the reuse budget on timesteps with lower downstream impact. Experiments on image and video synthesis models demonstrate that EpaCache consistently improves the latency--fidelity trade-off over existing caching methods. On FLUX.1-dev, EpaCache outperforms the prior state-of-the-art caching method in both latency and fidelity, reducing inference time from 11.7 s to 11.3 s while improving PSNR from 21.4 to 22.8. On HunyuanVideo, EpaCache achieves a 2.63imes speedup over uncached inference and improves SSIM from 0.891 to 0.905 over the prior state-of-the-art method at matched latency.

Related

• From Local Mismatch to Global Impact: Optimizing Cache Reuse Policy for Efficient Diffusion
• OnlineCache: Learning Dynamic Caching Policies with Error Correction for Efficient Diffusion Inference

Source: arXiv cs.AI | 2026-09-01