让图像编辑快过眨眼，且精准不乱改。
FlashEdit: Decoupling Speed, Structure, and Semantics for Precise Image Editing
- 一步逆推+循环一致，快速还原图像初始状态。
- 0.2秒内完成编辑，速度比传统方法快150倍以上。
- 适合需要实时修改、保持细节的设计师或开发者。
基于扩散模型的文本引导图像编辑虽质量优异，但延迟过高。本文提出FlashEdit，一种面向标准逆推编辑场景的实时局部编辑框架。其高效与精准源于三大创新：(1) 周期一致的一步逆推（COSI）管道，通过循环一致性促进流形对齐的一步逆推；(2) 背景防护（BG-Shield）技术，利用结构自注意力干预提升未编辑区域的保真度；(3) 稀疏空间交叉注意力（SSCA）机制，通过抑制语义泄露实现精确编辑。在PIE-Bench上的实验表明，该方法实现了显著的保真度-效率权衡，编辑耗时低于0.2秒，相比基于DDIM的多步编辑提速超过150倍。代码将公开于https://github.com/JunyiWuCode/FlashEdit。
原文摘要 · Abstract (English)
Text-guided image editing with diffusion models has achieved remarkable quality but often suffers from prohibitive latency. We introduce \textbf{FlashEdit}, a real-time localized image editing framework for the standard inversion-based editing setting. Its efficiency and precision stem from three key innovations: (1) a \textbf{Cycle-Consistent One-Step Inversion (COSI)} pipeline that encourages manifold-aligned one-step inversion through cycle consistency; (2) a \textbf{Background Shield (BG-Shield)} technique that improves preservation of non-edited regions via structural self-attention intervention; and (3) a \textbf{Sparsified Spatial Cross-Attention (SSCA)} mechanism that promotes precise edits by suppressing semantic leakage. Experiments on PIE-Bench demonstrate a strong preservation-efficiency trade-off, with edits completed in under 0.2 seconds and an over 150$\times$ speedup over DDIM-based multi-step editing. Our code will be made publicly available at \url{https://github.com/JunyiWuCode/FlashEdit}.
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。