EditBridge enables faithful and efficient ultra-high-resolution image editing by reformulating refinement as a structured data-to-data diffusion bridge, explicitly guided by the original high-resolution source. Our prior-guided block-wise sparse attention preserves aligned details while substantially reducing computational cost. EditBridge supports editing at resolutions up to 4K, achieves a 3.6–8.4× speedup at 2K, and completes practical 4K editing in 61 seconds.</p>\n","updatedAt":"2026-08-19T07:26:54.816Z","author":{"_id":"67051ad602b48c3fce373fe7","avatarUrl":"/avatars/ebf10382f7c34f41b77f30eb1eea784e.svg","fullname":"sjy","name":"sjy92","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"isUserFollowing":false}},"numEdits":1,"identifiedLanguage":{"language":"en","probability":0.8847184181213379},"editors":["sjy92"],"editorAvatarUrls":["/avatars/ebf10382f7c34f41b77f30eb1eea784e.svg"],"reactions":[],"isReport":false}}],"primaryEmailConfirmed":false,"paper":{"id":"2608.18063","authors":[{"_id":"6a855a3c536bdd3bdd48f918","name":"Jiayi Song","hidden":false},{"_id":"6a855a3c536bdd3bdd48f919","name":"Shijie Huang","hidden":false},{"_id":"6a855a3c536bdd3bdd48f91a","user":{"_id":"6a855cdad5d32b83525c7142","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/no-auth/hrBPKYtt7WApy52ku-tr5.png","isPro":false,"fullname":"Fangtai Wu","user":"FangtaiWu","type":"user","name":"FangtaiWu"},"name":"Fangtai Wu","status":"claimed_verified","statusLastChangedAt":"2026-08-19T08:45:04.493Z","hidden":false},{"_id":"6a855a3c536bdd3bdd48f91b","name":"Yubo Huang","hidden":false},{"_id":"6a855a3c536bdd3bdd48f91c","name":"Zhenxiong Tan","hidden":false},{"_id":"6a855a3c536bdd3bdd48f91d","name":"Songhua Liu","hidden":false},{"_id":"6a855a3c536bdd3bdd48f91e","name":"Jiaming Liu","hidden":false},{"_id":"6a855a3c536bdd3bdd48f91f","name":"Ruihua Huang","hidden":false}],"publishedAt":"2026-08-18T00:00:00.000Z","submittedOnDailyAt":"2026-08-19T00:00:00.000Z","title":"EDITBRIDGE: Towards Faithful and Efficient Ultra-High-Resolution Image Editing","submittedOnDailyBy":{"_id":"67051ad602b48c3fce373fe7","avatarUrl":"/avatars/ebf10382f7c34f41b77f30eb1eea784e.svg","isPro":false,"fullname":"sjy","user":"sjy92","type":"user","name":"sjy92"},"summary":"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.","upvotes":17,"discussionId":"6a855a3c536bdd3bdd48f920","projectPage":"https://editbridge.github.io/","githubRepo":"https://github.com/songyangyifei/editbridge","githubRepoAddedBy":"user","ai_summary":"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.","ai_keywords":["diffusion bridge","structured data-to-data translation","prior-guided block-wise sparse attention","cross-image interactions","high-resolution editing"],"ai_summary_model":"thinkingmachines/Inkling-Small","githubStars":2},"canReadDatabase":false,"canManagePapers":false,"canSubmit":false,"hasHfLevelAccess":false,"upvoted":false,"upvoters":[{"_id":"67051ad602b48c3fce373fe7","avatarUrl":"/avatars/ebf10382f7c34f41b77f30eb1eea784e.svg","isPro":false,"fullname":"sjy","user":"sjy92","type":"user"},{"_id":"64b929308b53fb5dbd059ce3","avatarUrl":"/avatars/564c44cf45db794747a96f79f30ecd91.svg","isPro":false,"fullname":"Liu Songhua","user":"Huage001","type":"user"},{"_id":"66dbe9343b6063ac837a0aa5","avatarUrl":"/avatars/b44e04e00ea863efc133eaab545962d5.svg","isPro":false,"fullname":"oooooo","user":"kzfkzf","type":"user"},{"_id":"6715164c7dfe714b42ba178d","avatarUrl":"/avatars/7a77bfe3aebec2c5e94e890b0b960f49.svg","isPro":false,"fullname":"akko","user":"hyb1124","type":"user"},{"_id":"637c941588699fba70e29f70","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/637c941588699fba70e29f70/b6G_QZkT-MhE47dx87i0d.png","isPro":false,"fullname":"LIU JIAMING","user":"jamesliu1217","type":"user"},{"_id":"67b3f529d21021f9eb29fa36","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/67b3f529d21021f9eb29fa36/2bJpoGozgLCUs6VmhZqXv.jpeg","isPro":false,"fullname":"Zixuan Jiang","user":"Andrew0425","type":"user"},{"_id":"66b32a0f03ab4e54bbca6df8","avatarUrl":"/avatars/ca907771f37c4d50fb99cefcdd7e10f0.svg","isPro":false,"fullname":"BoWen Fu","user":"HappyBug","type":"user"},{"_id":"66cd4cb53f233bf2c7953c12","avatarUrl":"/avatars/c2e4d5a32e7967253cba7c72b0323d4d.svg","isPro":false,"fullname":"Ruixun Liu","user":"lrx123","type":"user"},{"_id":"66112fe17b5851bad341be51","avatarUrl":"/avatars/3b7c2081290fa1c8cb85b79214446bbe.svg","isPro":false,"fullname":"huangshijie","user":"nicolaus-huang","type":"user"},{"_id":"660a645d5814b3dfc3a95e83","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/660a645d5814b3dfc3a95e83/S-yLw7-QFXg7fX94bfbtn.jpeg","isPro":false,"fullname":"Bingnan Li","user":"Cuttle-fish-my","type":"user"},{"_id":"695237218e29e42bf4904795","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/695237218e29e42bf4904795/11EUdiWVNqH3D0aIj75tw.jpeg","isPro":false,"fullname":"Haozhong Xiong","user":"xhznju","type":"user"},{"_id":"6a855cdad5d32b83525c7142","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/no-auth/hrBPKYtt7WApy52ku-tr5.png","isPro":false,"fullname":"Fangtai Wu","user":"FangtaiWu","type":"user"}],"acceptLanguages":["en"],"dailyPaperRank":0,"markdownContentUrl":"https://huggingface.co/buckets/huggingchat/papers-content/resolve/2608/2608.18063.md","query":{}}">
EDITBRIDGE: Towards Faithful and Efficient Ultra-High-Resolution Image Editing
Published on Aug 18
· Submitted by sjy on 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, 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.
Community
EditBridge enables faithful and efficient ultra-high-resolution image editing by reformulating refinement as a structured data-to-data diffusion bridge, explicitly guided by the original high-resolution source. Our prior-guided block-wise sparse attention preserves aligned details while substantially reducing computational cost. EditBridge supports editing at resolutions up to 4K, achieves a 3.6–8.4× speedup at 2K, and completes practical 4K editing in 61 seconds.
Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.
Tap or paste here to upload images
Cite arxiv.org/abs/2608.18063 in a model README.md to link it from this page.
Cite arxiv.org/abs/2608.18063 in a dataset README.md to link it from this page.
Cite arxiv.org/abs/2608.18063 in a Space README.md to link it from this page.
Discussion (0)
Sign in to join the discussion. Free account, 30 seconds — email code or GitHub.
Sign in →No comments yet. Sign in and be the first to say something.