Papers › Controllable Text-to-Image Generation

Controllable Text-to-Image Generation

16 Sep 2019NeurIPS 2019 12arXiv:1909.07083archive 2025-07-28

Bowen Li, Xiaojuan Qi, Thomas Lukasiewicz, Philip H. S. Torr

In this paper, we propose a novel controllable text-to-image generative adversarial network (ControlGAN), which can effectively synthesise high-quality images and also control parts of the image generation according to natural language descriptions. To achieve this, we introduce a word-level spatial and channel-wise attention-driven generator that can disentangle different visual attributes, and allow the model to focus on generating and manipulating subregions corresponding to the most relevant words. Also, a word-level discriminator is proposed to provide fine-grained supervisory feedback by correlating words with image regions, facilitating training an effective generator which is able to manipulate specific visual attributes without affecting the generation of other content. Furthermore, perceptual loss is adopted to reduce the randomness involved in the image generation, and to encourage the generator to manipulate specific attributes required in the modified text. Extensive experiments on benchmark datasets demonstrate that our method outperforms existing state of the art, and is able to effectively manipulate synthetic images using natural language descriptions. Code is available at https://github.com/mrlibw/ControlGAN.

PaperPDFConference PDFCodeCode 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="1909.07083")

Code

Syntology Ran 0 of 10 code samples harvested from 1 repository linked to this paper; 10 have no recorded run.

By repository: community (archive-listed): 10 samples from 1 repository, 0 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

mrlibw/ControlGAN officialmentioned in paperpytorch report
taki0112/ControlGAN-Tensorflow mentioned on GitHubtfMIT 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; 0 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.

10unverified

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 taki0112/ControlGAN-Tensorflow. “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.

L2_loss taki0112/ControlGAN-Tensorflow/legacy_code/perceptual_class.py community (archive-listed) unverified MIT (permissive) · 71a7228a4a0450ec · report
Leaky_Relu taki0112/ControlGAN-Tensorflow/ops.py community (archive-listed) unverified MIT (permissive) · 6b120cf9b5aa7582 · report
Relu taki0112/ControlGAN-Tensorflow/ops.py community (archive-listed) unverified MIT (permissive) · 865bf88a67a374a7 · report
Tanh taki0112/ControlGAN-Tensorflow/ops.py community (archive-listed) unverified MIT (permissive) · 2635ec7408c505b8 · report
adjust_dynamic_range taki0112/ControlGAN-Tensorflow/utils.py community (archive-listed) unverified MIT (permissive) · a991a23f7dd903f5 · report
conv taki0112/ControlGAN-Tensorflow/legacy_code/ops.py community (archive-listed) unverified MIT (permissive) · 91310f5fb45d94c4 · report
flatten taki0112/ControlGAN-Tensorflow/legacy_code/ops.py community (archive-listed) unverified MIT (permissive) · d29bc3068b3eae3f · report
fully_connected taki0112/ControlGAN-Tensorflow/legacy_code/ops.py community (archive-listed) unverified MIT (permissive) · 68cf33f32693ba2e · report
load_test_image taki0112/ControlGAN-Tensorflow/utils.py community (archive-listed) unverified MIT (permissive) · 562021bdb7164a5d · report
preprocess_fit_train_image taki0112/ControlGAN-Tensorflow/utils.py community (archive-listed) unverified MIT (permissive) · 98df0e20c34bd849 · report

Tasks

Image GenerationText to Image GenerationText-to-Image Generation

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Text-to-Image Generation CUB Attention-driven Generator (perceptual loss) Inception score 4.58 #17 of 20 Archive leaderboard report
Text-to-Image Generation Multi-Modal-CelebA-HQ ControlGAN Acc 14.6 #7 of 10 Archive leaderboard report
Text-to-Image Generation Multi-Modal-CelebA-HQ ControlGAN FID 116.32 #7 of 10 Archive leaderboard report
Text-to-Image Generation Multi-Modal-CelebA-HQ ControlGAN LPIPS 0.522 #7 of 10 Archive leaderboard report
Text-to-Image Generation Multi-Modal-CelebA-HQ ControlGAN Real 13.1 #7 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.

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