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× speedup over DDIM-based multi-step editing. Our code will be made publicly available at \url{https://github.com/JunyiWuCode/FlashEdit}.
@article{arxiv.2509.22244,
title = {FlashEdit: Decoupling Speed, Structure, and Semantics for Precise Image Editing},
author = {Junyi Wu and Zhiteng Li and Haotong Qin and Yulun Zhang and Xiaokang Yang},
journal= {arXiv preprint arXiv:2509.22244},
year = {2026}
}
Comments
Our code will be made publicly available at https://github.com/JunyiWuCode/FlashEdit