Papers › UltraEdit: Instruction-based Fine-Grained Image Editing at Scale

UltraEdit: Instruction-based Fine-Grained Image Editing at Scale

7 Jul 2024arXiv:2407.05282archive 2025-07-28

Haozhe Zhao, Xiaojian Ma, Liang Chen, Shuzheng Si, Rujie Wu, Kaikai An, Peiyu Yu, Minjia Zhang, Qing Li, Baobao Chang

This paper presents UltraEdit, a large-scale (approximately 4 million editing samples), automatically generated dataset for instruction-based image editing. Our key idea is to address the drawbacks in existing image editing datasets like InstructPix2Pix and MagicBrush, and provide a systematic approach to producing massive and high-quality image editing samples. UltraEdit offers several distinct advantages: 1) It features a broader range of editing instructions by leveraging the creativity of large language models (LLMs) alongside in-context editing examples from human raters; 2) Its data sources are based on real images, including photographs and artworks, which provide greater diversity and reduced bias compared to datasets solely generated by text-to-image models; 3) It also supports region-based editing, enhanced by high-quality, automatically produced region annotations. Our experiments show that canonical diffusion-based editing baselines trained on UltraEdit set new records on MagicBrush and Emu-Edit benchmarks. Our analysis further confirms the crucial role of real image anchors and region-based editing data. The dataset, code, and models can be found in https://ultra-editing.github.io.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also 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

Syntology 17 code samples harvested from 1 repository linked to this paper: 10 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 5 where Syntology's instrument failed) · 7 unverified. Where Syntology's instrument failed: 3 where our contract draft was wrong; 2 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 17 samples from 1 repository, 10 ran (5 with no instrument failure; 5 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written on 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 1 of the 10 samples that ran has no recorded date.

pkunlp-icler/ultraedit officialmentioned in papermentioned on GitHubjaxSyntology: 17 samples, 10 ran (5 instrument-failed) · 7 unverified 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.

Code Syntology ran Syntology

17 samples harvested: 10 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 5 where Syntology's instrument failed) · 7 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · honoured contract
3ran · our draft was wrong
2ran; the contract check could not run
4ran
7unverified

Licence: 17 of the 17 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 pkunlp-icler/ultraedit. “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. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (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 are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. 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 six 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; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. 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.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

pkunlp-icler/ultraedit official repository 17 samples, 10 ran (5 instrument-failed) · 7 unverified
check_mask_size data_generation/data_generation.py ran no licence file found · pointer only · a56d6564fd11974d · report fixture: signature mask:ndarray/2/int, min_size:float/0/float, max_size:float/0/float · returned bool · level recorded 2026-09-24
convert_to_np traning/train_sdxl_pix2pix.py ran fingerprinted no licence file found · pointer only · 629773a88a55f9e6 · report fixture: signature image:str/0/str, resolution:int/0/int · returned ndarray · level recorded 2026-09-24
download_image in 13 papers traning/train_sdxl_pix2pix.py ran · our draft was wrong no licence file found · pointer only · 1c34ef7c86b190fb · report fixture: returned Image · level recorded 2026-09-24
find_contours_number data_generation/data_generation.py ran · honoured contract no licence file found · pointer only · 56b8d77956f342de · report fixture: signature mask_image:ndarray/2/int · returned int · level recorded 2026-09-24
generate_Contours_mask data_generation/data_generation.py ran; the contract check could not run (RAISES) no licence file found · pointer only · c00e5e79dd083932 · report fixture: signature pil_img:Image/0/? · returned Image · level recorded 2026-09-24
get_time_words_attention_alpha data_generation/processors.py ran no licence file found · pointer only · 0a26bb2a52f65689 · report fixture: signature prompts:list/1/str, num_steps:int/0/int, cross_replace_steps:dict/0/?, tokenizer:MockTokenizer/0/?, max_num_words:int/0/int · returned Tensor · level recorded 2026-09-24
import_model_class_from_model_name_or_path in 64 papers traning/train_sdxl_pix2pix.py ran; the contract check could not run (RAISES) no licence file found · pointer only · dd89dacf389e9e01 · report fixture: signature pretrained_model_name_or_path:str/0/str, revision:str/0/str, subfolder:str/0/str · returned type · level recorded 2026-09-24
rescale_noise_cfg in 63 papers
census: 2 implementations from 21 papers, 1 distinct output on one shared input this sample: bucket 1 of 1, arg 1: rank 4, kind float, dtype float32 · arg 2: rank 4, kind float, dtype float32
data_generation/prompt_to_prompt_pipeline.py ran · our draft was wrong fingerprinted no licence file found · pointer only · bea2d776a332f2b0 · report fixture: signature noise_cfg:Tensor/4/float, noise_pred_text:Tensor/4/float, guidance_rescale:float/0/float · returned Tensor · level recorded, date not recorded
tokenize_prompt in 23 papers traning/train_sd3_pix2pix.py ran no licence file found · pointer only · dce9df5004a68cce · report fixture: signature tokenizer:callable/0/?, prompt:str/0/str, max_sequence_length:int/0/int · returned Tensor · level recorded 2026-09-24
update_alpha_time_word in 5 papers data_generation/processors.py ran · our draft was wrong no licence file found · pointer only · dd498a88e593fe37 · report fixture: signature alpha:Tensor/3/float, bounds:tuple/1/float, prompt_ind:int/0/int, word_inds:Tensor/1/int · returned Tensor · level recorded 2026-09-24
check_tags_chinese data_generation/Grounded-Segment-Anything/automatic_label_ram_demo.py unverified no licence file found · pointer only · be76f458330f9eec · report
create_controller data_generation/processors.py unverified no licence file found · pointer only · 93889c3f8ba8ba23 · report
create_controller data_generation/util.py unverified no licence file found · pointer only · a91b81d1e36f84e1 · report
encode_prompt in 54 papers traning/train_sd3_pix2pix.py unverified no licence file found · pointer only · 1b3f076c87d15223 · report
generate_caption in 21 papers data_generation/Grounded-Segment-Anything/automatic_label_demo.py unverified no licence file found · pointer only · d893c774b1f34088 · report
generate_tags data_generation/Grounded-Segment-Anything/automatic_label_demo.py unverified no licence file found · pointer only · c0648fc5a77afd71 · report
load_text_encoders in 12 papers traning/train_sd3_pix2pix.py unverified no licence file found · pointer only · 74ab2d24d15218ee · report

Tasks

DiversityImage Editing

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Editing ImgEdit-Data UltraEdit Action 2.98 #6 of 9 Archive leaderboard report
Image Editing ImgEdit-Data UltraEdit Add 3.44 #6 of 9 Archive leaderboard report
Image Editing ImgEdit-Data UltraEdit Adjust 2.81 #6 of 9 Archive leaderboard report
Image Editing ImgEdit-Data UltraEdit Background 2.83 #6 of 9 Archive leaderboard report
Image Editing ImgEdit-Data UltraEdit Extract 2.13 #6 of 9 Archive leaderboard report
Image Editing ImgEdit-Data UltraEdit Hybrid 1.91 #6 of 9 Archive leaderboard report
Image Editing ImgEdit-Data UltraEdit Overall 2.70 #6 of 9 Archive leaderboard report
Image Editing ImgEdit-Data UltraEdit Remove 1.45 #6 of 9 Archive leaderboard report
Image Editing ImgEdit-Data UltraEdit Replace 2.96 #6 of 9 Archive leaderboard report
Image Editing ImgEdit-Data UltraEdit Style 3.76 #6 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.

Methods

SET

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