HierEdit: Region-Aware Hierarchical Diffusion for Efficient High-Resolution Editing

TL;DR

HierEdit introduces a region-aware hierarchical diffusion framework that enables efficient, high-fidelity high-resolution image editing up to 4K by focusing on edited regions and reusing unaltered areas.

Contribution

The paper presents HierEdit, a novel hierarchical diffusion method that accelerates high-resolution editing without requiring high-res training data.

Findings

Achieves high-quality 4K image editing with fast inference.

Significantly reduces computational costs compared to existing methods.

Maintains consistent global semantics during editing.

Abstract

High-resolution image editing is essential for professional and creative applications, yet existing multimodal diffusion-based editors remain computationally inefficient and constrained to relatively low resolutions. Current approaches redundantly process the entire image canvas or rely on large-scale high-resolution datasets, resulting in substantial training and inference costs. We introduce HierEdit, a region-aware hierarchical diffusion framework designed for efficient and scalable high-resolution image editing. Our method first performs edits on a low-resolution proxy using an off-the-shelf editing model to generate a reference and to localize the modified regions. A hierarchical local-window diffusion model (\textbf{Local-Window MMDiT}) that refines only edited regions within the original high-res image, while reusing the unaltered regions as conditioning inputs. The low-resolution proxy further provides structural guidance and intermediate denoising supervision (\textbf{Inference Acceleration}) , ensuring consistent global semantics and stable generation without the need for full-resolution attention computation. This targeted and hierarchical design enables fast, high-fidelity editing of images up to 4K resolution without any specialized high-resolution training data. Extensive experiments demonstrate that HierEdit achieves competitive visual quality on commodity-resolution datasets while significantly accelerating inference and extending seamlessly to ultra-high-resolution 4K editing. Please check our {\href{https://peteryyzhang.github.io/HierEdit-page/}{\textbf{Project Page}}}.