{"ID":5439487,"CreatedAt":"2026-07-01T01:17:58.482524686Z","UpdatedAt":"2026-07-02T19:06:01.127452785Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2606.30849","arxiv_id":"2606.30849","title":"SyncCache: Exploiting Asymmetric Dynamics for Fast Audio-Driven Portrait Animation","abstract":"Diffusion Transformers (DiTs) have significantly advanced audio-driven portrait animation, but their high computational cost leads to substantial inference latency. Although training-free diffusion caching accelerates inference significant, existing methods are primarily developed for text-conditioned generation and overlook the spatial and modality imbalances inherent in audio-driven portrait animation. In this paper, we propose SyncCache, a training-free caching acceleration method tailored for DiT-based portrait animation that explicitly exploits asymmetric dynamics. Specifically, high-frequency dynamics driven by audio conditions and concentrated in human regions are more challenging and critical to cache and reuse than the low-frequency visual background in portrait animation. First, we introduce Spatially-Asymmetric Probing to prioritize error sensitivity in dynamic human region. Second, through Modality-Decoupled Caching, we bypass heavy DiT block by reusing stable inter-block residuals, while continuously recomputing lightweight audio blocks to preserve precise lip synchronization. Furthermore, we introduce a cache ratio to control cache capacity and formulate memory-adaptive cache selection as an offline dynamic programming problem without online overhead. Extensive experiments demonstrate that SyncCache achieves superior speed-quality trade-offs, delivering up to 4.12x acceleration on HunyuanVideo-Avatar and 3.75x on Wan-S2V with near-lossless visual fidelity and precise audio alignment.","short_abstract":"Diffusion Transformers (DiTs) have significantly advanced audio-driven portrait animation, but their high computational cost leads to substantial inference latency. Although training-free diffusion caching accelerates inference significant, existing methods are primarily developed for text-conditioned generation and ov...","url_abs":"https://arxiv.org/abs/2606.30849","url_pdf":"https://arxiv.org/pdf/2606.30849v1","authors":"[\"Juncheng Ma\",\"Yuxuan Du\",\"Yanan Sun\",\"Zhening Xing\",\"Changlin Li\",\"Zhenyu Tang\",\"Bo Li\",\"Peng-Tao Jiang\",\"Li Yuan\",\"Daquan Zhou\",\"Yonghong Tian\"]","published":"2026-06-29T19:26:13Z","proceeding":"cs.CV","tasks":"[\"cs.CV\",\"cs.SD\",\"eess.AS\"]","methods":"[\"Diffusion Model\",\"Transformer\"]","has_code":false}