Papers › LayoutGPT: Compositional Visual Planning and Generation with Large Language Models

LayoutGPT: Compositional Visual Planning and Generation with Large Language Models

24 May 2023NeurIPS 2023 11arXiv:2305.15393archive 2025-07-28

Weixi Feng, Wanrong Zhu, Tsu-Jui Fu, Varun Jampani, Arjun Akula, Xuehai He, Sugato Basu, Xin Eric Wang, William Yang Wang

Attaining a high degree of user controllability in visual generation often requires intricate, fine-grained inputs like layouts. However, such inputs impose a substantial burden on users when compared to simple text inputs. To address the issue, we study how Large Language Models (LLMs) can serve as visual planners by generating layouts from text conditions, and thus collaborate with visual generative models. We propose LayoutGPT, a method to compose in-context visual demonstrations in style sheet language to enhance the visual planning skills of LLMs. LayoutGPT can generate plausible layouts in multiple domains, ranging from 2D images to 3D indoor scenes. LayoutGPT also shows superior performance in converting challenging language concepts like numerical and spatial relations to layout arrangements for faithful text-to-image generation. When combined with a downstream image generation model, LayoutGPT outperforms text-to-image models/systems by 20-40% and achieves comparable performance as human users in designing visual layouts for numerical and spatial correctness. Lastly, LayoutGPT achieves comparable performance to supervised methods in 3D indoor scene synthesis, demonstrating its effectiveness and potential in multiple visual domains.

PaperPDFConference PDFCodeCode 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 19 code samples harvested from 1 repository linked to this paper: 13 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 1 honoured, 0 violated, 10 with no contract checked; 2 where Syntology's instrument failed) · 6 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 19 samples from 1 repository, 13 ran (11 with no instrument failure; 2 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 13 samples that ran has no recorded date.

weixi-feng/layoutgpt officialmentioned in papermentioned on GitHubpytorchMITSyntology: 19 samples, 13 ran (2 instrument-failed) · 6 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

19 samples harvested: 13 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 1 honoured, 0 violated, 10 with no contract checked; 2 where Syntology's instrument failed) · 6 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
1ran · our draft was wrong
1ran; the contract check could not run
10ran
6unverified

Licence: 1 of the 19 samples is pointer only, meaning Syntology does not serve that copy's text. For that sample, 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 weixi-feng/layoutgpt. “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.

weixi-feng/layoutgpt official repository 19 samples, 13 ran (2 instrument-failed) · 6 unverified
all_gather in 119 papers gligen/distributed.py ran MIT (permissive) · ed03ba54397adbe4 · report fixture: signature data:dict/0/? · returned list · level recorded 2026-09-26
alpha_generator in 5 papers gligen/gligen_inference.py ran; the contract check could not run (RAISES) · metamorphic tier: well formed MIT (permissive) here; the stored copy is pointer only · b3e1f7172e4955ae · report fixture: signature length:int/0/int, type:list/1/float · returned list · level recorded, date not recorded
bb_relative_position utils.py ran fingerprinted MIT (permissive) · 0bf7957edd5ec68b · report fixture: signature boxA:ndarray/1/float, boxB:ndarray/1/float · returned tuple · level recorded 2026-09-26
create_exemplar_prompt run_layoutgpt_2d.py ran MIT (permissive) · 79259da2a67a2e86 · report fixture: signature caption:str/0/str, object_list:list/1/tuple, canvas_size:int/0/int, is_chat:bool/0/bool · returned str · level recorded 2026-09-26
list_grid eval_models/GLIP/eval_counting.py ran MIT (permissive) · 09501d1255cf3995 · report fixture: signature list1:list/1/int, list2:list/1/str · returned list · level recorded 2026-09-26
load in 392 papers eval_models/GLIP/eval_counting.py ran MIT (permissive) · 6920fbdb489405ed · report fixture: signature dir:str/0/str · returned ndarray · level recorded 2026-09-26
load_features in 14 papers run_layoutgpt_3d.py ran MIT (permissive) · 3af0b42145b07f7f · report fixture: signature meta_data:dict/0/?, floor_plan:bool/0/bool · returned dict · level recorded 2026-09-26
load_room_boxes eval_scene_layout.py ran MIT (permissive) · d7f3fdf20a8bcf2e · report fixture: signature prefix:str/0/str, id:str/0/str, stats:dict/0/? · returned tuple · level recorded 2026-09-26
parse_3D_layout parse_llm_output.py ran fingerprinted MIT (permissive) · 45aff54102d0117c · report fixture: signature string:str/0/str, unit:str/0/str · returned tuple · level recorded 2026-09-26
project in 44 papers
census: 8 implementations from 9 papers, 7 distinct outputs across 3 buckets, one shared input per bucket this sample: bucket 1 of 3, arg 1: rank 2, kind float, dtype float32 · arg 2: rank 2, kind float, dtype float32
gligen/gligen_inference.py ran · our draft was wrong fingerprinted MIT (permissive) · e49923c3510ee0bc · report fixture: signature x:Tensor/2/float, projection_matrix:Tensor/2/float · returned Tensor · level recorded 2026-09-22
reduce_loss_dict in 18 papers gligen/distributed.py ran MIT (permissive) · 5144ad456049f8ce · report fixture: signature loss_dict:dict/0/? · returned dict · level recorded 2026-09-26
reduce_sum in 34 papers
census: 4 implementations from 5 papers, 4 distinct outputs across 4 buckets, one shared input per bucket
gligen/distributed.py ran · honoured contract fingerprinted MIT (permissive) · 3f0a1105ef251d78 · report fixture: signature tensor:Tensor/2/float · returned Tensor · level recorded 2026-09-24
roty in 19 papers eval_scene_layout.py ran fingerprinted MIT (permissive) · dae708ee6dab2577 · report fixture: signature t:float/0/float · returned ndarray · level recorded 2026-09-26
eval_image eval_models/GLIP/eval_spatial.py unverified MIT (permissive) · 578380ce31db339e · report
eval_spatial_relation utils.py unverified MIT (permissive) · 3855ecf0a0c564a2 · report
load_features in 14 papers run_layoutgpt_2d.py unverified MIT (permissive) · c0b66d7eb2f18c94 · report
load_json in 344 papers utils.py unverified MIT (permissive) · a0d7fd544bf9313b · report
load_room_boxes run_layoutgpt_3d.py unverified MIT (permissive) · 5785462f2abe4ca4 · report
load_set run_layoutgpt_3d.py unverified MIT (permissive) · 32f48bb8094ef7c8 · report

Tasks

Image GenerationIndoor Scene SynthesisText to Image GenerationText-to-Image 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