Papers › TR0N: Translator Networks for 0-Shot Plug-and-Play Conditional Generation

TR0N: Translator Networks for 0-Shot Plug-and-Play Conditional Generation

26 Apr 2023arXiv:2304.13742archive 2025-07-28

Zhaoyan Liu, Noel Vouitsis, Satya Krishna Gorti, Jimmy Ba, Gabriel Loaiza-Ganem

We propose TR0N, a highly general framework to turn pre-trained unconditional generative models, such as GANs and VAEs, into conditional models. The conditioning can be highly arbitrary, and requires only a pre-trained auxiliary model. For example, we show how to turn unconditional models into class-conditional ones with the help of a classifier, and also into text-to-image models by leveraging CLIP. TR0N learns a lightweight stochastic mapping which "translates" between the space of conditions and the latent space of the generative model, in such a way that the generated latent corresponds to a data sample satisfying the desired condition. The translated latent samples are then further improved upon through Langevin dynamics, enabling us to obtain higher-quality data samples. TR0N requires no training data nor fine-tuning, yet can achieve a zero-shot FID of 10.9 on MS-COCO, outperforming competing alternatives not only on this metric, but also in sampling speed -- all while retaining a much higher level of generality. Our code is available at https://github.com/layer6ai-labs/tr0n.

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="2304.13742")

Code

Syntology Ran 9 of 19 code samples harvested from 2 repositories linked to this paper; 10 have no recorded run. Of those that ran: 5 ran · our draft was wrong; 4 ran with no contract checked.

By repository: official repository: 1 sample from 1 repository, 1 ran; found in paper text by Syntology: 18 samples from 1 repository, 8 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

layer6ai-labs/tr0n officialmentioned in papermentioned on GitHubpytorch report
layer6ai-labs/fusemix mentioned on GitHubpytorch 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; 9 ran; 0 honoured the contract we drafted; 10 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.

5ran · our draft was wrong
4ran
10unverified

Licence: 1 of the 19 samples is 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 2 repositories linked to this paper, official or community; each sample names its own and says which. “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.

Translator layer6ai-labs/tr0n/tr0n/modules/models/model_biggan.py official repository ran · metamorphic tier: deterministic no licence file found · pointer only · b1552a9f45095727 · report
D_arch gnobitab/FuseDream/BigGAN_utils/BigGAN.py found in paper text by Syntology ran · our draft was wrong MIT (permissive) · 85eb95cce203dfc7 · report
G_arch gnobitab/FuseDream/BigGAN_utils/BigGAN.py found in paper text by Syntology ran · our draft was wrong MIT (permissive) · e8c308c9283407d7 · report
find_classes gnobitab/FuseDream/BigGAN_utils/datasets.py found in paper text by Syntology ran MIT (permissive) · 52d10a10fb72fb9f · report
gram_schmidt gnobitab/FuseDream/BigGAN_utils/layers.py found in paper text by Syntology ran · our draft was wrong MIT (permissive) · c41836f3e51fa8f1 · report
is_image_file gnobitab/FuseDream/BigGAN_utils/datasets.py found in paper text by Syntology ran MIT (permissive) · 4e6a8faaf8e44abe · report
make_dataset gnobitab/FuseDream/BigGAN_utils/datasets.py found in paper text by Syntology ran MIT (permissive) · 79e61b6269a450e8 · report
rand_brightness gnobitab/FuseDream/DiffAugment_pytorch.py found in paper text by Syntology ran · our draft was wrong fingerprinted MIT (permissive) · 011230b2b9b8fb6f · report
rand_saturation gnobitab/FuseDream/DiffAugment_pytorch.py found in paper text by Syntology ran · our draft was wrong fingerprinted MIT (permissive) · 5b0d8787e670fc63 · report
D_arch gnobitab/FuseDream/BigGAN_utils/BigGANdeep.py found in paper text by Syntology unverified MIT (permissive) · a99a05ac52533be9 · report
DiffAugment gnobitab/FuseDream/DiffAugment_pytorch.py found in paper text by Syntology unverified MIT (permissive) · 0be77ca193f97b78 · report
G_arch gnobitab/FuseDream/BigGAN_utils/BigGANdeep.py found in paper text by Syntology unverified MIT (permissive) · 44d6a6343f6eb182 · report
get_gaussian_mask gnobitab/FuseDream/fusedream_utils.py found in paper text by Syntology unverified MIT (permissive) · f2870dcc5a3844a1 · report
loss_dcgan_dis gnobitab/FuseDream/BigGAN_utils/losses.py found in paper text by Syntology unverified MIT (permissive) · 982a26492dc6b7fb · report
loss_dcgan_gen gnobitab/FuseDream/BigGAN_utils/losses.py found in paper text by Syntology unverified MIT (permissive) · 6c34831223553b6f · report
loss_hinge_dis gnobitab/FuseDream/BigGAN_utils/losses.py found in paper text by Syntology unverified MIT (permissive) · 290cd37ab0098d5c · report
power_iteration gnobitab/FuseDream/BigGAN_utils/layers.py found in paper text by Syntology unverified MIT (permissive) · 28d3a35157f2916d · report
proj gnobitab/FuseDream/BigGAN_utils/layers.py found in paper text by Syntology unverified MIT (permissive) · 4015ab1f3ab9b881 · report
run gnobitab/FuseDream/BigGAN_utils/inception_tf13.py found in paper text by Syntology unverified MIT (permissive) · ac122c2c1495ce94 · report

Tasks

Image GenerationText-to-Image Generation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Text-to-Image Generation COCO (Common Objects in Context) TR0N (StyleGAN-XL, LAION2BCLIP, BLIP-2, zero-shot) FID 10.9 #29 of 69 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

BigGANCLIPStyleGAN2

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