Papers › MagicBrush: A Manually Annotated Dataset for Instruction-Guided Image Editing

MagicBrush: A Manually Annotated Dataset for Instruction-Guided Image Editing

16 Jun 2023NeurIPS 2023 11arXiv:2306.10012archive 2025-07-28

Kai Zhang, Lingbo Mo, Wenhu Chen, Huan Sun, Yu Su

Text-guided image editing is widely needed in daily life, ranging from personal use to professional applications such as Photoshop. However, existing methods are either zero-shot or trained on an automatically synthesized dataset, which contains a high volume of noise. Thus, they still require lots of manual tuning to produce desirable outcomes in practice. To address this issue, we introduce MagicBrush (https://osu-nlp-group.github.io/MagicBrush/), the first large-scale, manually annotated dataset for instruction-guided real image editing that covers diverse scenarios: single-turn, multi-turn, mask-provided, and mask-free editing. MagicBrush comprises over 10K manually annotated triplets (source image, instruction, target image), which supports trainining large-scale text-guided image editing models. We fine-tune InstructPix2Pix on MagicBrush and show that the new model can produce much better images according to human evaluation. We further conduct extensive experiments to evaluate current image editing baselines from multiple dimensions including quantitative, qualitative, and human evaluations. The results reveal the challenging nature of our dataset and the gap between current baselines and real-world editing needs.

PaperPDFConference PDFCode

In Syntology View this paper on Syntology, its page in Syntology's graph. That page lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

osu-nlp-group/magicbrush officialmentioned in paperpytorchNOASSERTIONSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Learning Action and Reasoning-Centric Image Editing from Videos and Simulations (arXiv:2407.03471; that paper's own run record: 6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 2 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report

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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Image Editingtext-guided-image-editing

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Editing ImgEdit-Data MagicBrush Action 1.22 #9 of 9 Archive leaderboard report
Image Editing ImgEdit-Data MagicBrush Add 2.84 #9 of 9 Archive leaderboard report
Image Editing ImgEdit-Data MagicBrush Adjust 1.58 #9 of 9 Archive leaderboard report
Image Editing ImgEdit-Data MagicBrush Background 1.75 #9 of 9 Archive leaderboard report
Image Editing ImgEdit-Data MagicBrush Extract 1.51 #9 of 9 Archive leaderboard report
Image Editing ImgEdit-Data MagicBrush Hybrid 1.62 #9 of 9 Archive leaderboard report
Image Editing ImgEdit-Data MagicBrush Overall 1.83 #9 of 9 Archive leaderboard report
Image Editing ImgEdit-Data MagicBrush Remove 1.58 #9 of 9 Archive leaderboard report
Image Editing ImgEdit-Data MagicBrush Replace 1.97 #9 of 9 Archive leaderboard report
Image Editing ImgEdit-Data MagicBrush Style 2.38 #9 of 9 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