通过语义感知复用，实现多轮图像编辑的高效加速。
RegionCache: Semantic-Aware Region Reuse for Efficient Multi-Turn Image Generation
- 基于语义重叠与注意力定位，识别可复用的图像区域。
- 根据提示相似性和上下文一致性，自适应调度复用策略。
- 在保持画质前提下，提速1.43倍至2.55倍，适合多轮编辑场景。
现实中的图像生成常涉及多轮编辑，用户逐轮修改局部区域，而大部分图像内容保持不变。然而，现有基于扩散变换器（DiT）的编辑流程在每轮都重新计算整张图像，造成大量冗余计算。现有加速方法又忽视提示之间的语义对应关系，导致不必要的重算或不安全的复用，影响编辑质量。为此，本文提出RegionCache，一种面向多轮图像编辑的语义感知复用框架，可选择性复用未变化区域的扩散状态。RegionCache通过连续提示间的语义重叠和交叉注意力定位检测可复用区域，并基于提示相似性和上下文一致性采用自适应复用策略。在PixArt-alpha上的实验表明，RegionCache实现了1.43倍至2.55倍的端到端加速，同时保持相当的图像质量。代码已公开于https://github.com/hebutBryant/RegionCache。
原文摘要 · Abstract (English)
Real-world image generation often involves multi-turn editing, where users iteratively modify small regions while most image content remains unchanged. However, existing diffusion transformer (DiT)-based editing pipelines recompute the entire image at every turn, causing substantial redundant computation. Existing DiT acceleration methods further ignore semantic correspondence across prompts, leading to unnecessary recomputation or unsafe reuse that harms editing quality. To address this, we propose RegionCache, a semantic-aware reuse framework for multi-turn image editing that selectively reuses diffusion states from unchanged regions. RegionCache detects reusable regions through semantic overlap between consecutive prompts and cross-attention localization, and adopts an adaptive reuse schedule based on prompt similarity and contextual consistency. Experiments on PixArt-alpha demonstrate that RegionCache achieves 1.43x--2.55x end-to-end speedup while maintaining comparable image quality. Code is available at https://github.com/hebutBryant/RegionCache.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。