Papers › StackGAN++: Realistic Image Synthesis with Stacked Generative Adversarial Networks

StackGAN++: Realistic Image Synthesis with Stacked Generative Adversarial Networks

19 Oct 2017arXiv:1710.10916archive 2025-07-28

Han Zhang, Tao Xu, Hongsheng Li, Shaoting Zhang, Xiaogang Wang, Xiaolei Huang, Dimitris Metaxas

Although Generative Adversarial Networks (GANs) have shown remarkable success in various tasks, they still face challenges in generating high quality images. In this paper, we propose Stacked Generative Adversarial Networks (StackGAN) aiming at generating high-resolution photo-realistic images. First, we propose a two-stage generative adversarial network architecture, StackGAN-v1, for text-to-image synthesis. The Stage-I GAN sketches the primitive shape and colors of the object based on given text description, yielding low-resolution images. The Stage-II GAN takes Stage-I results and text descriptions as inputs, and generates high-resolution images with photo-realistic details. Second, an advanced multi-stage generative adversarial network architecture, StackGAN-v2, is proposed for both conditional and unconditional generative tasks. Our StackGAN-v2 consists of multiple generators and discriminators in a tree-like structure; images at multiple scales corresponding to the same scene are generated from different branches of the tree. StackGAN-v2 shows more stable training behavior than StackGAN-v1 by jointly approximating multiple distributions. Extensive experiments demonstrate that the proposed stacked generative adversarial networks significantly outperform other state-of-the-art methods in generating photo-realistic images.

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="1710.10916")

Code

Syntology Ran 10 of 31 code samples harvested from 5 repositories linked to this paper; 21 have no recorded run. Of those that ran: 1 ran · violated contract; 8 ran · our draft was wrong; 1 ran with no contract checked.

By repository: official repository: 11 samples from 2 repositories, 3 ran; community (archive-listed): 20 samples from 3 repositories, 7 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

16 repositories listed; official and paper-mentioned ones first.

hanzhanggit/StackGAN officialmentioned in papermentioned on GitHubtfMIT report
hanzhanggit/StackGAN-v2 officialmentioned in papermentioned on GitHubpytorchMIT report
Maymaher/StackGANv2 mentioned on GitHubpytorch report
Vigneshthanga/stackGAN-v2 mentioned on GitHubpytorch report
akanimax/T2F mentioned on GitHubpytorchMIT report
davidstap/AttnGAN mentioned on GitHubpytorch report
hanzhanggit/StackGAN-Pytorch mentioned on GitHubpytorchMIT report
hiarsal/dae-gan mentioned on GitHubpytorch report
kkanshul/finegan mentioned on GitHubpytorchBSD-2-Clause report
komiya-m/MirrorGAN mentioned on GitHubpytorch report
pioneerAlpha/BanglaText2ImageGeneration mentioned on GitHubpytorch report
priscillalui/StackGAN-Stories mentioned on GitHubpytorch report
rightlit/StackGAN-v2-rev mentioned on GitHubpytorchMIT report
taoxugit/AttnGAN mentioned on GitHubpytorch report
tobran/DF-GAN 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

31 samples harvested; 10 ran; 0 honoured the contract we drafted; 21 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.

1ran · violated contract
8ran · our draft was wrong
1ran
21unverified

Licence: 0 of the 31 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 5 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.

KL_loss hanzhanggit/StackGAN-v2/code/trainer.py official repository ran · our draft was wrong fingerprinted MIT (permissive) · f502ac0ccf050e23 · report
is_image_file hanzhanggit/StackGAN-v2/code/datasets.py official repository ran · violated contract MIT (permissive) · ab4109634b75ef8b · report
leaky_rectify hanzhanggit/StackGAN/misc/custom_ops.py official repository ran MIT (permissive) · 0b71fdd2dc019d86 · report
KL_loss hanzhanggit/StackGAN/stageI/trainer.py official repository unverified MIT (permissive) · fd6883aef7fc0f6f · report
custom_crop hanzhanggit/StackGAN/misc/utils.py official repository unverified MIT (permissive) · fc22db7fa7e0e135 · report
drawCaption hanzhanggit/StackGAN/demo/birds_skip_thought_demo.py official repository unverified MIT (permissive) · 3e354ab43bfb020e · report
get_image hanzhanggit/StackGAN/misc/utils.py official repository unverified MIT (permissive) · 21bf8f7cea6decf5 · report
load_bbox hanzhanggit/StackGAN/misc/preprocess_birds.py official repository unverified MIT (permissive) · 386604cfa74a3d76 · report
load_filenames hanzhanggit/StackGAN/misc/preprocess_birds.py official repository unverified MIT (permissive) · 7b80aa25807d666a · report
sample_encoded_context hanzhanggit/StackGAN/demo/birds_skip_thought_demo.py official repository unverified MIT (permissive) · 549299c4575752d8 · report
transform hanzhanggit/StackGAN/misc/utils.py official repository unverified MIT (permissive) · b67362dfc6797565 · report
Block3x3_relu rightlit/StackGAN-v2-rev/code/model.py community (archive-listed) ran · our draft was wrong MIT (permissive) · 90b28e5e76aecfad · report
compute_mean_covariance rightlit/StackGAN-v2-rev/code/trainer.py community (archive-listed) ran · our draft was wrong fingerprinted MIT (permissive) · 57bbdc333d2c0749 · report
conv3x3 hanzhanggit/StackGAN-Pytorch/code/model.py community (archive-listed) ran · our draft was wrong MIT (permissive) · fac5364e2f53c6db · report
conv3x3 rightlit/StackGAN-v2-rev/code/model.py community (archive-listed) ran · our draft was wrong MIT (permissive) · ea864de5c552bc4a · report
copy_G_params rightlit/StackGAN-v2-rev/code/trainer.py community (archive-listed) ran · our draft was wrong MIT (permissive) · 2c55357aecd850cd · report
upBlock rightlit/StackGAN-v2-rev/code/model.py community (archive-listed) ran · our draft was wrong MIT (permissive) · c96308e17ab1e7ae · report
upBlock hanzhanggit/StackGAN-Pytorch/code/model.py community (archive-listed) ran · our draft was wrong MIT (permissive) · 721bc7234edf9845 · report
basic_preprocess akanimax/T2F/implementation/data_processing/TextExtractor.py community (archive-listed) unverified MIT (permissive) · 7e63b3aa4716eada · report
batcher akanimax/T2F/implementation/networks/InferSent/mutils.py community (archive-listed) unverified MIT (permissive) · b7fe5da253d02512 · report
compute_discriminator_loss hanzhanggit/StackGAN-Pytorch/code/miscc/utils.py community (archive-listed) unverified MIT (permissive) · 9183c2843448dcfe · report
compute_generator_loss hanzhanggit/StackGAN-Pytorch/code/miscc/utils.py community (archive-listed) unverified MIT (permissive) · 19689b24458da440 · report
frequency_count akanimax/T2F/implementation/data_processing/TextExtractor.py community (archive-listed) unverified MIT (permissive) · 3400d1263c6cbf9a · report
get_batch akanimax/T2F/implementation/networks/InferSent/data.py community (archive-listed) unverified MIT (permissive) · f790d98a3d6af4e5 · report
get_config akanimax/T2F/implementation/train_network.py community (archive-listed) unverified MIT (permissive) · 7b64c2c40ebe4e1d · report
get_data_loader akanimax/T2F/implementation/data_processing/DataLoader.py community (archive-listed) unverified MIT (permissive) · 4c285e4ad37fd444 · report
get_glove akanimax/T2F/implementation/networks/InferSent/data.py community (archive-listed) unverified MIT (permissive) · f1c38d138242dab0 · report
get_optimizer akanimax/T2F/implementation/networks/InferSent/mutils.py community (archive-listed) unverified MIT (permissive) · 7cdd5e14c7072483 · report
get_transform akanimax/T2F/implementation/data_processing/DataLoader.py community (archive-listed) unverified MIT (permissive) · e36470391de100a1 · report
get_word_dict akanimax/T2F/implementation/networks/InferSent/data.py community (archive-listed) unverified MIT (permissive) · 7ffb2861c51cbac6 · report
read_annotations akanimax/T2F/implementation/data_processing/TextExtractor.py community (archive-listed) unverified MIT (permissive) · dbb904b43aad3c12 · report

Tasks

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
Image Generation LSUN Bedroom 256 x 256 StackGAN-v2 FID 35.61 #19 of 32 Archive leaderboard report
Text-to-Image Generation COCO (Common Objects in Context) StackGAN-v1 FID 74.05 #66 of 69 Archive leaderboard report
Text-to-Image Generation COCO (Common Objects in Context) StackGAN-v1 Inception score 8.45 #66 of 69 Archive leaderboard report
Text-to-Image Generation CUB StackGAN-v2 FID 15.3 #11 of 20 Archive leaderboard report
Text-to-Image Generation CUB StackGAN-v2 Inception score 3.82 #11 of 20 Archive leaderboard report
Text-to-Image Generation CUB StackGAN-v1 FID 51.89 #13 of 20 Archive leaderboard report
Text-to-Image Generation CUB StackGAN-v1 Inception score 3.7 #13 of 20 Archive leaderboard report
Text-to-Image Generation Oxford 102 Flowers StackGAN-v2 FID 48.68 #6 of 8 Archive leaderboard report
Text-to-Image Generation Oxford 102 Flowers StackGAN-v2 Inception score 3.26 #6 of 8 Archive leaderboard report
Text-to-Image Generation Oxford 102 Flowers StackGAN-v1 FID 55.28 #7 of 8 Archive leaderboard report
Text-to-Image Generation Oxford 102 Flowers StackGAN-v1 Inception score 3.2 #7 of 8 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

Convolution

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