EDITBRIDGE: Towards Faithful and Efficient Ultra-High-Resolution Image Editing

Hugging Face Daily Papers Papers
image-editing diffusion-bridge high-resolution sparse-attention efficient-computation

Summary

EditBridge is a diffusion bridge framework that enables efficient ultra-high-resolution image editing up to 4K by translating low-resolution edits to high-resolution outputs with sparse attention, achieving significant speed improvements and preserving source details.

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.
Original Article
View Cached Full Text

Cached at: 08/19/26, 07:56 AM

Paper page - EDITBRIDGE: Towards Faithful and Efficient Ultra-High-Resolution Image Editing

Source: https://huggingface.co/papers/2608.18063 Published on Aug 18

·

Submitted byhttps://huggingface.co/sjy92

sjyon Aug 19

Abstract

EditBridge enables efficient ultra high-resolution image editing via a diffusion bridge that translates low-resolution edits to high-resolution outputs while preserving source details through sparse attention.

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, adiffusion bridgeframework for efficient ultrahigh-resolution editing. Unlike conventional diffusion that regenerates from noise, we formulate refinement asstructured data-to-data translationfrom 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 aprior-guided block-wise sparse attentionmechanism that exploits semantic correspondence from first-stage editing to constraincross-image interactionsto 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.

View arXiv pageView PDFProject pageGitHubAdd to collection

Get this paper in your agent:

hf papers read 2608\.18063

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2608.18063 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2608.18063 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2608.18063 in a Space README.md to link it from this page.

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.

Similar Articles

Uni-Edit: Intelligent Editing Is A General Task For Unified Model Tuning

Hugging Face Daily Papers

Uni-Edit proposes using intelligent image editing as a single general task to simultaneously improve unified multimodal models' understanding, generation, and editing capabilities, with an automated data synthesis pipeline creating complex editing instructions.