{"ID":2878919,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.17356","arxiv_id":"2508.17356","title":"DiCache: Let Diffusion Model Determine Its Own Cache","abstract":"Recent years have witnessed the rapid development of acceleration techniques for diffusion models, especially caching-based acceleration methods. These studies seek to answer two fundamental questions: \"When to cache\" and \"How to use cache\", typically relying on predefined empirical laws or dataset-level priors to determine caching timings and adopting handcrafted rules for multi-step cache utilization. However, given the highly dynamic nature of the diffusion process, they often exhibit limited generalizability and fail to cope with diverse samples. In this paper, a strong sample-specific correlation is revealed between the variation patterns of the shallow-layer feature differences in the diffusion model and those of deep-layer features. Moreover, we have observed that the features from different model layers form similar trajectories. Based on these observations, we present DiCache, a novel training-free adaptive caching strategy for accelerating diffusion models at runtime, answering both when and how to cache within a unified framework. Specifically, DiCache is composed of two principal components: (1) Online Probe Profiling Scheme leverages a shallow-layer online probe to obtain an on-the-fly indicator for the caching error in real time, enabling the model to dynamically customize the caching schedule for each sample. (2) Dynamic Cache Trajectory Alignment adaptively approximates the deep-layer feature output from multi-step historical caches based on the shallow-layer feature trajectory, facilitating higher visual quality. Extensive experiments validate DiCache's capability in achieving higher efficiency and improved fidelity over state-of-the-art approaches on various leading diffusion models including WAN 2.1, HunyuanVideo and Flux.","short_abstract":"Recent years have witnessed the rapid development of acceleration techniques for diffusion models, especially caching-based acceleration methods. These studies seek to answer two fundamental questions: \"When to cache\" and \"How to use cache\", typically relying on predefined empirical laws or dataset-level priors to dete...","url_abs":"https://arxiv.org/abs/2508.17356","url_pdf":"https://arxiv.org/pdf/2508.17356v2","authors":"[\"Jiazi Bu\",\"Pengyang Ling\",\"Yujie Zhou\",\"Yibin Wang\",\"Yuhang Zang\",\"Dahua Lin\",\"Jiaqi Wang\"]","published":"2025-08-24T13:30:00Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Diffusion Model\"]","has_code":false}