Papers › LAFITE: Towards Language-Free Training for Text-to-Image Generation

LAFITE: Towards Language-Free Training for Text-to-Image Generation

27 Nov 2021arXiv:2111.13792archive 2025-07-28

Yufan Zhou, Ruiyi Zhang, Changyou Chen, Chunyuan Li, Chris Tensmeyer, Tong Yu, Jiuxiang Gu, Jinhui Xu, Tong Sun

One of the major challenges in training text-to-image generation models is the need of a large number of high-quality image-text pairs. While image samples are often easily accessible, the associated text descriptions typically require careful human captioning, which is particularly time- and cost-consuming. In this paper, we propose the first work to train text-to-image generation models without any text data. Our method leverages the well-aligned multi-modal semantic space of the powerful pre-trained CLIP model: the requirement of text-conditioning is seamlessly alleviated via generating text features from image features. Extensive experiments are conducted to illustrate the effectiveness of the proposed method. We obtain state-of-the-art results in the standard text-to-image generation tasks. Importantly, the proposed language-free model outperforms most existing models trained with full image-text pairs. Furthermore, our method can be applied in fine-tuning pre-trained models, which saves both training time and cost in training text-to-image generation models. Our pre-trained model obtains competitive results in zero-shot text-to-image generation on the MS-COCO dataset, yet with around only 1% of the model size and training data size relative to the recently proposed large DALL-E model.

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 18 code samples harvested from 2 repositories linked to this paper: 12 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 2 honoured, 0 violated, 8 with no contract checked; 2 where Syntology's instrument failed) · 6 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: 6 samples from 1 repository, 3 ran (2 with no instrument failure; 1 where Syntology's instrument failed); community (archive-listed): 12 samples from 1 repository, 9 ran (8 with no instrument failure; 1 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.

No sample is linked to this paper from 1 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 2 of the 12 samples that ran have no recorded date.

drboog/Lafite officialmentioned in papermentioned on GitHubpytorchMITSyntology: 6 samples, 3 ran (1 instrument-failed) · 3 unverified report
drboog/Shifted_Diffusion mentioned on GitHubjaxCC0-1.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Shifted Diffusion for Text-to-image Generation (arXiv:2211.15388; that paper's own run record: 13 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 2 honoured, 1 violated, 6 with no contract checked; 4 where Syntology's instrument failed) · 4 unverified); nothing checks that they implement this paper's method. report
oxygenlu/ratlip mentioned on GitHubpytorchMITSyntology: 12 samples, 9 ran (1 instrument-failed) · 3 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

18 samples harvested: 12 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 2 honoured, 0 violated, 8 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 has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

2ran · honoured contract
2ran · our draft was wrong
8ran
6unverified

Licence: 3 of the 18 samples are pointer only, meaning Syntology does not serve that copy's text. For 3 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.

drboog/Lafite official repository 6 samples, 3 ran (1 instrument-failed) · 3 unverified
custom_reshape dataset_tool.py ran MIT (permissive) · 080da024bbcdf7bc · report fixture: signature img:Tensor/4/float, mode:str/0/str, ratio:float/0/float · returned Tensor · level recorded 2026-09-24
file_ext in 37 papers dataset_tool.py ran · our draft was wrong fingerprinted MIT (permissive) here; the stored copy is pointer only · a2b45afa097b55b6 · report fixture: signature name:str/0/str · returned str · level recorded, date not recorded
maybe_min in 36 papers dataset_tool.py ran · honoured contract fingerprinted MIT (permissive) here; the stored copy is pointer only · dd1dc700e87f36cc · report fixture: signature a:int/0/int, b:NoneType/0/? · returned int · level recorded, date not recorded
get_imgs datasets/datasets_bird_coco.py unverified MIT (permissive) · 964f3c53ef8df7cd · report
load_filenames datasets/datasets_bird_coco.py unverified MIT (permissive) · 2c903601913a4f24 · report
prepare_data in 87 papers datasets/datasets_bird_coco.py unverified MIT (permissive) · 5123f0670f4adce1 · report
oxygenlu/ratlip community (archive-listed) 12 samples, 9 ran (1 instrument-failed) · 3 unverified
MA_GP_FP32 code/lib/modules.py ran MIT (permissive) · a2f5ae76d8f7b686 · report fixture: signature img:Tensor/2/float, sent:Tensor/2/float, out:Tensor/0/float · returned Tensor · level recorded 2026-09-24
autopad in 36 papers code/models/RATLIP.py ran · honoured contract fingerprinted MIT (permissive) here; the stored copy is pointer only · 988a3c854b1b13d0 · report fixture: signature k:int/0/int, p:NoneType/0/? · returned int · level recorded 2026-09-22
get_D_in_out_chs code/models/RATLIP.py ran MIT (permissive) · f8cd9b9545621bc0 · report fixture: signature nf:int/0/int, imsize:int/0/int · returned zip · level recorded 2026-09-24
get_G_in_out_chs code/models/RATLIP.py ran · our draft was wrong MIT (permissive) · 7b1f9c201441fa1c · report fixture: signature nf:int/0/int, imsize:int/0/int · returned zip · level recorded 2026-09-22
get_fix_data code/lib/datasets.py ran MIT (permissive) · 1b820b0f9416f8b5 · report fixture: signature train_dl:DataLoader/0/?, test_dl:DataLoader/0/?, text_encoder:callable/0/?, args:Args/0/? · returned tuple · level recorded 2026-09-24
get_one_batch_data code/lib/datasets.py ran MIT (permissive) · 7092063b4f5817fa · report fixture: signature dataloader:list/1/tuple, text_encoder:callable/0/?, args:Args/0/? · returned tuple · level recorded 2026-09-24
load_npz in 17 papers code/lib/utils.py ran MIT (permissive) · 6364051ef9e418c9 · report fixture: signature path:str/0/str · returned tuple · level recorded 2026-09-24
params_count in 6 papers code/lib/utils.py ran MIT (permissive) · edd67ef305db54ef · report fixture: signature model:callable/0/? · returned int · level recorded 2026-09-24
prepare_data in 87 papers code/lib/datasets.py ran MIT (permissive) · 31efd08e9e090d29 · report fixture: signature data:tuple/1/Tensor, text_encoder:callable/0/?, device:str/0/str · returned tuple · level recorded 2026-09-24
MA_GP_MP code/lib/modules.py unverified MIT (permissive) · e881f3aa13c1dfca · report
choose_model code/lib/utils.py unverified MIT (permissive) · 1307498a08bac630 · report
prepare_dataset in 32 papers code/lib/perpare.py unverified MIT (permissive) · d4c40e264c45657c · report

Tasks

Image GenerationText to Image GenerationText-to-Image GenerationZero-Shot Text-to-Image Generation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Text-to-Image Generation COCO (Common Objects in Context) Lafite FID 8.12 #20 of 69 Archive leaderboard report
Text-to-Image Generation COCO (Common Objects in Context) Lafite Inception score 32.34 #20 of 69 Archive leaderboard report
Text-to-Image Generation COCO (Common Objects in Context) Lafite SOA-C 61.09 #20 of 69 Archive leaderboard report
Text-to-Image Generation COCO (Common Objects in Context) Lafite (zero-shot) FID 26.94 #52 of 69 Archive leaderboard report
Text-to-Image Generation COCO (Common Objects in Context) Lafite (zero-shot) FID-1 22.97 #52 of 69 Archive leaderboard report
Text-to-Image Generation COCO (Common Objects in Context) Lafite (zero-shot) FID-2 18.70 #52 of 69 Archive leaderboard report
Text-to-Image Generation COCO (Common Objects in Context) Lafite (zero-shot) FID-4 15.72 #52 of 69 Archive leaderboard report
Text-to-Image Generation COCO (Common Objects in Context) Lafite (zero-shot) FID-8 14.79 #52 of 69 Archive leaderboard report
Text-to-Image Generation COCO (Common Objects in Context) Lafite (zero-shot) Inception score 26.02 #52 of 69 Archive leaderboard report
Text-to-Image Generation CUB Lafite FID 10.48 #7 of 20 Archive leaderboard report
Text-to-Image Generation CUB Lafite Inception score 5.97 #7 of 20 Archive leaderboard report
Text-to-Image Generation Multi-Modal-CelebA-HQ Lafite FID 12.54 #2 of 10 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

CLIP

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