Papers › LAION-SG: An Enhanced Large-Scale Dataset for Training Complex Image-Text Models with...

LAION-SG: An Enhanced Large-Scale Dataset for Training Complex Image-Text Models with Structural Annotations

11 Dec 2024arXiv:2412.08580archive 2025-07-28

Zejian Li, Chenye Meng, Yize Li, Ling Yang, Shengyuan Zhang, Jiarui Ma, Jiayi Li, Guang Yang, Changyuan Yang, Zhiyuan Yang, Jinxiong Chang, Lingyun Sun

Recent advances in text-to-image (T2I) generation have shown remarkable success in producing high-quality images from text. However, existing T2I models show decayed performance in compositional image generation involving multiple objects and intricate relationships. We attribute this problem to limitations in existing datasets of image-text pairs, which lack precise inter-object relationship annotations with prompts only. To address this problem, we construct LAION-SG, a large-scale dataset with high-quality structural annotations of scene graphs (SG), which precisely describe attributes and relationships of multiple objects, effectively representing the semantic structure in complex scenes. Based on LAION-SG, we train a new foundation model SDXL-SG to incorporate structural annotation information into the generation process. Extensive experiments show advanced models trained on our LAION-SG boast significant performance improvements in complex scene generation over models on existing datasets. We also introduce CompSG-Bench, a benchmark that evaluates models on compositional image generation, establishing a new standard for this domain. Our annotations with the associated processing code, the foundation model and the benchmark protocol are publicly available at https://github.com/mengcye/LAION-SG.

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 23 code samples harvested from 2 repositories linked to this paper: 12 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 4 violated, 1 with no contract checked; 7 where Syntology's instrument failed) · 11 unverified. Where Syntology's instrument failed: 7 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 11 samples from 1 repository, 5 ran (1 with no instrument failure; 4 where Syntology's instrument failed); community (archive-listed): 12 samples from 1 repository, 7 ran (4 with no instrument failure; 3 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 between 2026-09-22 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 1 of the 12 samples that ran has no recorded date.

mengcye/LAION-SG officialmentioned in papermentioned on GitHubpytorchMITSyntology: 11 samples, 5 ran (4 instrument-failed) · 6 unverified report
yangling0818/sgdiff mentioned on GitHubpytorchSyntology: 12 samples, 7 ran (3 instrument-failed) · 5 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

23 samples harvested: 12 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 4 violated, 1 with no contract checked; 7 where Syntology's instrument failed) · 11 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.

4ran · violated contract
7ran · our draft was wrong
1ran
11unverified

Licence: 13 of the 23 samples are pointer only, meaning Syntology does not serve that copy's text. For 1 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 2 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “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.

mengcye/LAION-SG official repository 11 samples, 5 ran (4 instrument-failed) · 6 unverified
build_laion_dsets sgEncoderTraining/datasets/laion_dataset.py ran · our draft was wrong MIT (permissive) · 1117cb855a81abc3 · report fixture: signature args:Args/0/? · returned tuple · level recorded 2026-09-25
build_mlp in 74 papers sgEncoderTraining/sgEncoder/module.py ran · our draft was wrong MIT (permissive) · 8692859d555c8768 · report fixture: signature dim_list:list/1/int, activation:str/0/str, batch_norm:str/0/str, dropout:float/0/float, final_nonlinearity:bool/0/bool · returned Sequential · level recorded 2026-09-25
cosine_lr in 31 papers sgEncoderTraining/training/scheduler.py ran MIT (permissive) here; the stored copy is pointer only · 932d44bbf8bd0e3f · report fixture: signature optimizer:SGD/0/?, base_lr:float/0/float, warmup_length:int/0/int, steps:int/0/int · returned function · level recorded 2026-09-26
get_autocast in 5 papers sgEncoderTraining/training/precision.py ran · our draft was wrong MIT (permissive) · f988e73e85f4ea4a · report fixture: signature precision:str/0/str · returned type · level recorded 2026-09-25
my_laion_collate_fn sgEncoderTraining/datasets/laion_dataset.py ran · our draft was wrong MIT (permissive) · 6124caed65f1c444 · report fixture: signature batch:list/1/tuple · returned tuple · level recorded 2026-09-25
boxes_to_mask sgEncoderTraining/utils.py unverified MIT (permissive) · 13f977de43dee032 · report
build_laion_loaders sgEncoderTraining/datasets/laion_dataset.py unverified MIT (permissive) · def453b3dce37100 · report
generate_box_mask sgEncoderTraining/utils.py unverified MIT (permissive) · 15167a5cc461251c · report
get_linear_feas_by_hook sgEncoderTraining/utils.py unverified MIT (permissive) · df129d4646ebbcc0 · report
import_model_class_from_model_name_or_path in 64 papers trainer_laion.py unverified MIT (permissive) · 5fc36bbf7ad81a90 · report
unwrap_model in 41 papers sgEncoderTraining/training/train_and_val_one_iter.py unverified MIT (permissive) · 2bf62c0287050bdd · report
yangling0818/sgdiff community (archive-listed) 12 samples, 7 ran (3 instrument-failed) · 5 unverified
always in 65 papers ldm/modules/x_transformer.py ran · our draft was wrong no licence file found · pointer only · fe5dd5258046898c · report fixture: signature val:int/0/int · returned function · level recorded 2026-09-22
default in 430 papers ldm/modules/attention.py ran · violated contract no licence file found · pointer only · 424012cb37b31172 · report fixture: signature val:NoneType/0/?, d:callable/0/? · returned int · level recorded 2026-09-22
exists in 528 papers
census: 5 implementations from 103 papers, 1 distinct output on one shared input this sample: bucket 1 of 1, arg 1: rank 1, kind int, dtype int64
ldm/modules/attention.py ran · violated contract no licence file found · pointer only · aa5486a3650902d8 · report fixture: signature val:Tensor/1/int · returned bool · level recorded, date not recorded
isimage in 65 papers ldm/util.py ran · violated contract fingerprinted no licence file found · pointer only · b1368330cf0f5642 · report fixture: signature x:Tensor/4/float · returned bool · level recorded 2026-09-24
ismap in 70 papers ldm/util.py ran · violated contract fingerprinted no licence file found · pointer only · d72762b700feee6f · report fixture: signature x:Tensor/4/float · returned bool · level recorded 2026-09-24
uniq in 117 papers ldm/modules/attention.py ran · our draft was wrong no licence file found · pointer only · 9a299fe5ae09e407 · report fixture: signature arr:list/1/int · returned dict_keys · level recorded 2026-09-22
vg_collate_fn testset_ddim_sampler.py ran · our draft was wrong no licence file found · pointer only · c31f6b9b1b521862 · report fixture: signature batch:list/1/tuple · returned tuple · level recorded 2026-09-25
build_model in 469 papers sg_image_pretraining/clip/model.py unverified no licence file found · pointer only · 39e6b23b55f376ea · report
draw_scene_graph testset_ddim_sampler.py unverified no licence file found · pointer only · 245ff5228caf9482 · report
draw_scene_graph sg2im/vis.py unverified no licence file found · pointer only · 08c9ee87b8be3253 · report
log_txt_as_img in 72 papers ldm/util.py unverified no licence file found · pointer only · f9bd2e83191afad1 · report
nondefault_trainer_args in 9 papers trainer.py unverified no licence file found · pointer only · 87fbedd0c27cf378 · report

Tasks

AttributeImage GenerationScene Generation

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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