Papers › Gen4Gen: Generative Data Pipeline for Generative Multi-Concept Composition

Gen4Gen: Generative Data Pipeline for Generative Multi-Concept Composition

23 Feb 2024arXiv:2402.15504archive 2025-07-28

Chun-Hsiao Yeh, Ta-Ying Cheng, He-Yen Hsieh, Chuan-En Lin, Yi Ma, Andrew Markham, Niki Trigoni, H. T. Kung, Yubei Chen

Recent text-to-image diffusion models are able to learn and synthesize images containing novel, personalized concepts (e.g., their own pets or specific items) with just a few examples for training. This paper tackles two interconnected issues within this realm of personalizing text-to-image diffusion models. First, current personalization techniques fail to reliably extend to multiple concepts -- we hypothesize this to be due to the mismatch between complex scenes and simple text descriptions in the pre-training dataset (e.g., LAION). Second, given an image containing multiple personalized concepts, there lacks a holistic metric that evaluates performance on not just the degree of resemblance of personalized concepts, but also whether all concepts are present in the image and whether the image accurately reflects the overall text description. To address these issues, we introduce Gen4Gen, a semi-automated dataset creation pipeline utilizing generative models to combine personalized concepts into complex compositions along with text-descriptions. Using this, we create a dataset called MyCanvas, that can be used to benchmark the task of multi-concept personalization. In addition, we design a comprehensive metric comprising two scores (CP-CLIP and TI-CLIP) for better quantifying the performance of multi-concept, personalized text-to-image diffusion methods. We provide a simple baseline built on top of Custom Diffusion with empirical prompting strategies for future researchers to evaluate on MyCanvas. We show that by improving data quality and prompting strategies, we can significantly increase multi-concept personalized image generation quality, without requiring any modifications to model architecture or training algorithms.

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 10 code samples harvested from 1 repository linked to this paper: 8 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified. Where Syntology's instrument failed: 2 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 10 samples from 1 repository, 8 ran (6 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 on 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

louisYen/Gen4Gen officialmentioned on GitHubpytorchMITSyntology: 10 samples, 8 ran (2 instrument-failed) · 2 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

10 samples harvested: 8 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 2 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
2ran · our draft was wrong
5ran
2unverified

Licence: 0 of the 10 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 louisYen/Gen4Gen. “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.

louisYen/Gen4Gen official repository 10 samples, 8 ran (2 instrument-failed) · 2 unverified
approximate_RDP gen4gen/saliency_models/DIS/hce_metric_main.py ran MIT (permissive) · 729599a34939c1bf · report fixture: signature boundaries:list/1/ndarray, epsilon:float/0/float · returned tuple · level recorded 2026-09-24
f1score_torch gen4gen/saliency_models/DIS/basics.py ran MIT (permissive) · ccf648472bf97751 · report fixture: signature pd:Tensor/1/float, gt:Tensor/1/float · returned tuple · level recorded 2026-09-24
filter_bdy_cond gen4gen/saliency_models/DIS/hce_metric_main.py ran MIT (permissive) · b1f805b5d053ac0d · report fixture: signature bdy_:list/1/ndarray, mask:ndarray/2/int, cond:ndarray/2/int · returned tuple · level recorded 2026-09-24
get_im_gt_name_dict gen4gen/saliency_models/DIS/data_loader_cache.py ran MIT (permissive) · c3c043344336bb0b · report fixture: signature datasets:list/1/dict, flag:str/0/str · returned list · level recorded 2026-09-24
get_objects gen4gen/s2_llm_guided_object_composition.py ran · our draft was wrong MIT (permissive) · 2ebc4e2ea773d416 · report fixture: signature d:dict/0/? · returned tuple · level recorded 2026-09-24
im_reader gen4gen/saliency_models/DIS/data_loader_cache.py ran · honoured contract MIT (permissive) · a761df1609ffb30b · report fixture: signature im_path:str/0/str · returned ndarray · level recorded 2026-09-24
mae_torch gen4gen/saliency_models/DIS/basics.py ran · our draft was wrong fingerprinted MIT (permissive) · 1ad7043f7cda3831 · report fixture: signature pred:Tensor/2/float, gt:Tensor/2/float · returned Tensor · level recorded 2026-09-24
relax_HCE gen4gen/saliency_models/DIS/hce_metric_main.py ran MIT (permissive) · de8843c32f8cfda5 · report fixture: signature gt:ndarray/3/int, rs:ndarray/3/int, gt_ske:ndarray/2/int, relax:int/0/int, epsilon:float/0/float · returned tuple · level recorded 2026-09-24
create_dataloaders in 14 papers gen4gen/saliency_models/DIS/data_loader_cache.py unverified MIT (permissive) · 5cd2aa75a7b0c6ec · report
f1_mae_torch gen4gen/saliency_models/DIS/basics.py unverified MIT (permissive) · 7d13248918a66377 · report

Tasks

Image GenerationPersonalized Image Generation

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Diffusion

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