Papers › KV-Edit: Training-Free Image Editing for Precise Background Preservation
KV-Edit: Training-Free Image Editing for Precise Background Preservation
Tianrui Zhu, Shiyi Zhang, Jiawei Shao, Yansong Tang
Background consistency remains a significant challenge in image editing tasks. Despite extensive developments, existing works still face a trade-off between maintaining similarity to the original image and generating content that aligns with the target. Here, we propose KV-Edit, a training-free approach that uses KV cache in DiTs to maintain background consistency, where background tokens are preserved rather than regenerated, eliminating the need for complex mechanisms or expensive training, ultimately generating new content that seamlessly integrates with the background within user-provided regions. We further explore the memory consumption of the KV cache during editing and optimize the space complexity to O(1) using an inversion-free method. Our approach is compatible with any DiT-based generative model without additional training. Experiments demonstrate that KV-Edit significantly outperforms existing approaches in terms of both background and image quality, even surpassing training-based methods. Project webpage is available at https://xilluill.github.io/projectpages/KV-Edit
In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2502.17363")
Code
Syntology Ran 15 of 31 code samples harvested from 1 repository linked to this paper; 16 have no recorded run. Of those that ran: 1 ran · our draft was wrong; 1 ran · fixture could not drive it; 13 ran with no contract checked.
By repository: official repository: 31 samples from 1 repository, 15 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
Code Syntology ran Syntology
31 samples harvested; 15 ran; 0 honoured the contract we drafted; 16 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.
Licence: 0 of the 31 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.
Harvested from Xilluill/KV-Edit. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.
Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.
Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.
b9f8b9efb85110e4 · report
bb78f70b285fe68a · report
ed75f4c283c8cade · report
52004c455a1d9a71 · report
6b8321fc69032c6d · report
8c6dbb17f9290a46 · report
2e8de1895011c4a0 · report
8f8d9c986bd3147f · report
1a2c8d9ca3918791 · report
b4affeaaac4bcdd4 · report
0c92e50f90ae4f64 · report
a8d997e0ba042d6a · report
c46eed3b4c31dbf0 · report
3f6652da855a2ea0 · report
16c24bf237fed814 · report
bf0cff0597919d71 · report
59e8d7bc13f5d327 · report
a1f2d96d59c14287 · report
62f545ac5e999258 · report
78a0e843c3d244be · report
7b46f68f6e5e0e3d · report
5585849aeb0b2934 · report
9e0102b5544f4909 · report
e2bf41644ea4e949 · report
ddd6e35b84bfe270 · report
98151b94782828d1 · report
85080c818ceef6ea · report
c728727909e45352 · report
1b6eb944b965997b · report
63c61fe6461924ad · report
a9451ac1452e533d · report
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Text-based Image Editing | PIE-Bench | KV-Edit | Background LPIPS | 9.92 | #1 of 18 | Archive leaderboard | report |
| Text-based Image Editing | PIE-Bench | KV-Edit | Background PSNR | 35.87 | #1 of 18 | Archive leaderboard | report |
| Text-based Image Editing | PIE-Bench | KV-Edit | CLIPSIM | 25.63 | #1 of 18 | Archive leaderboard | report |
| Text-based Image Editing | PIE-Bench | KV-Edit | Structure Distance | 1.98 | #1 of 18 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections