Papers › Playground v3: Improving Text-to-Image Alignment with Deep-Fusion Large Language Models

Playground v3: Improving Text-to-Image Alignment with Deep-Fusion Large Language Models

16 Sep 2024arXiv:2409.10695archive 2025-07-28

Bingchen Liu, Ehsan Akhgari, Alexander Visheratin, Aleks Kamko, Linmiao Xu, Shivam Shrirao, Chase Lambert, Joao Souza, Suhail Doshi, Daiqing Li

We introduce Playground v3 (PGv3), our latest text-to-image model that achieves state-of-the-art (SoTA) performance across multiple testing benchmarks, excels in graphic design abilities and introduces new capabilities. Unlike traditional text-to-image generative models that rely on pre-trained language models like T5 or CLIP text encoders, our approach fully integrates Large Language Models (LLMs) with a novel structure that leverages text conditions exclusively from a decoder-only LLM. Additionally, to enhance image captioning quality-we developed an in-house captioner, capable of generating captions with varying levels of detail, enriching the diversity of text structures. We also introduce a new benchmark CapsBench to evaluate detailed image captioning performance. Experimental results demonstrate that PGv3 excels in text prompt adherence, complex reasoning, and accurate text rendering. User preference studies indicate the super-human graphic design ability of our model for common design applications, such as stickers, posters, and logo designs. Furthermore, PGv3 introduces new capabilities, including precise RGB color control and robust multilingual understanding.

PaperPDFCodeCode Syntology ran

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

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2409.10695")

Code

Syntology Ran 17 of 21 code samples harvested from 1 repository linked to this paper; 4 have no recorded run. Of those that ran: 4 ran · honoured contract; 1 ran · violated contract; 7 ran · our draft was wrong; 2 ran · fixture could not drive it; 3 ran with no contract checked.

By repository: community (archive-listed): 21 samples from 1 repository, 17 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

yuchuantian/u-dit mentioned on GitHubpytorchNOASSERTION 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

21 samples harvested; 17 ran; 4 honoured the contract we drafted; 4 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

4ran · honoured contract
1ran · violated contract
7ran · our draft was wrong
2ran · fixture could not drive it
3ran
4unverified

Licence: 21 of the 21 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 yuchuantian/u-dit. “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. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (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 from a repository marked official are listed first. 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 four 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; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). 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.

approx_standard_normal_cdf yuchuantian/u-dit/diffusion/diffusion_utils.py community (archive-listed) ran · our draft was wrong fingerprinted no licence file found · pointer only · d6a68e210556f857 · report
center_crop_arr yuchuantian/u-dit/train_accelerate.py community (archive-listed) ran · our draft was wrong no licence file found · pointer only · 1712a07966b542ee · report
continuous_gaussian_log_likelihood yuchuantian/u-dit/diffusion/diffusion_utils.py community (archive-listed) ran · our draft was wrong no licence file found · pointer only · ab1c9568b4e13899 · report
create_logger yuchuantian/u-dit/train_accelerate.py community (archive-listed) ran · our draft was wrong no licence file found · pointer only · b2cc78f4103df806 · report
create_npz_from_sample_folder yuchuantian/u-dit/sample_ddp.py community (archive-listed) ran · our draft was wrong no licence file found · pointer only · 7b21a01ae77703a3 · report
get_2d_sincos_pos_embed yuchuantian/u-dit/models.py community (archive-listed) ran · honoured contract no licence file found · pointer only · c92c27c924b517e8 · report
get_beta_schedule yuchuantian/u-dit/diffusion/gaussian_diffusion.py community (archive-listed) ran · honoured contract no licence file found · pointer only · 3e0fa4efc22272d4 · report
get_named_beta_schedule yuchuantian/u-dit/diffusion/gaussian_diffusion.py community (archive-listed) ran · honoured contract no licence file found · pointer only · 36e30c7fb679ec78 · report
mean_flat yuchuantian/u-dit/diffusion/gaussian_diffusion.py community (archive-listed) ran · our draft was wrong fingerprinted no licence file found · pointer only · f6d7c009a8efb8b7 · report
modulate yuchuantian/u-dit/models.py community (archive-listed) ran · our draft was wrong fingerprinted no licence file found · pointer only · 03310bba324ae4fb · report
normal_kl yuchuantian/u-dit/diffusion/diffusion_utils.py community (archive-listed) ran · honoured contract fingerprinted no licence file found · pointer only · 8afbfc42c6ea0448 · report
precompute_freqs_cis_2d yuchuantian/u-dit/udit_models.py community (archive-listed) ran · violated contract fingerprinted no licence file found · pointer only · f55137c53a3a4557 · report
reshape_for_broadcast yuchuantian/u-dit/udit_models.py community (archive-listed) ran · fixture could not drive it fingerprinted no licence file found · pointer only · 20ff6d11dd593018 · report
space_timesteps yuchuantian/u-dit/diffusion/respace.py community (archive-listed) ran · fixture could not drive it no licence file found · pointer only · ea9dbc131adf582e · report
trunc_normal_ yuchuantian/u-dit/udit_models.py community (archive-listed) ran licence not identified · pointer only · dc19b15524ec8454 · report
window_partition yuchuantian/u-dit/utils/udit_models_original.py community (archive-listed) ran licence not identified · pointer only · 5b36e74896cd9928 · report
window_reverse yuchuantian/u-dit/utils/udit_models_original.py community (archive-listed) ran licence not identified · pointer only · 800dfbdedee84978 · report
create_named_schedule_sampler yuchuantian/u-dit/diffusion/timestep_sampler.py community (archive-listed) unverified no licence file found · pointer only · e48218d7d73db0b3 · report
download_model yuchuantian/u-dit/download.py community (archive-listed) unverified no licence file found · pointer only · 6a0d5ecd441905cc · report
find_model yuchuantian/u-dit/download.py community (archive-listed) unverified no licence file found · pointer only · 29947a0a94157558 · report
get_2d_sincos_pos_embed_from_grid yuchuantian/u-dit/models.py community (archive-listed) unverified no licence file found · pointer only · 665d8a4e8f673a4c · report

Tasks

DecoderDiversityImage Captioning

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

AdafactorAttentionAttention DropoutBPECLIPDense ConnectionsDropoutGated Linear UnitInverse Square Root ScheduleLayer NormalizationLinear LayerMulti-Head AttentionResidual ConnectionSentencePieceSoftmaxT5

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