SOURCE-LINKED INTELLIGENCE

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

arXiv · AI, language, vision and robotics · article · Aug 29, 2026 · UTC

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 downstrea

Read original source ↗ Open in workspace

recordType

paper

region

Global