4K修图从半小时缩到61秒，细节还不糊
修图软件里把一张图放大到4K再改，通常要分两步：先在低分辨率上改，再单独放大。问题就出在第二步——AI会自己脑补细节，补出来的东西跟原图对不上，纹理也发虚。这篇把两步合成一步：让模型直接学「从低清改完的图，翻译回高清原图」，翻译时只盯着原图里对应的那一小块区域看，而不是全图乱扫。结果是在4K分辨率下，修一张图只要61秒，速度是原来的3.6到8.4倍，细节还保真。做电商大图、影楼精修、广告物料的人，这是你明天就能拿去省时间的那种。
📄 原文摘要(英文)
High-resolution image editing is increasingly demanded in professional workflows, yet existing diffusion-based models remain constrained to resolutions below 1K due to quadratic attention complexity and prohibitive memory requirements. A prevalent workaround employs a two-stage pipeline: editing at low resolution followed by independent super-resolution. However, this approach suffers from two critical issues: information divergence, where hallucinated details contradict the original high-resolution (HR) source, and texture degradation, manifesting as over-smoothed or over-sharpened artifacts. We propose EditBridge, a diffusion bridge framework for efficient ultra high-resolution editing. Unlike conventional diffusion that regenerates from noise, we formulate refinement as structured data-to-data translation from the low-resolution (LR) edited result to its HR counterpart, explicitly conditioned on the original HR source to preserve authentic details. To efficiently incorporate HR source guidance, we introduce a prior-guided block-wise sparse attention mechanism that exploits semantic correspondence from first-stage editing to constrain cross-image interactions to spatially aligned regions, significantly reducing computational overhead. Extensive experiments demonstrate that EditBridge achieves high-fidelity editing with superior perceptual quality at resolutions up to 4K, delivering 3.6--8.4times speedup at 2K and enabling practical 4K editing in 61 seconds.