Papers › StackGAN: Text to Photo-realistic Image Synthesis with Stacked Generative Adversarial Networks

StackGAN: Text to Photo-realistic Image Synthesis with Stacked Generative Adversarial Networks

10 Dec 2016ICCV 2017 10arXiv:1612.03242archive 2025-07-28

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

Synthesizing high-quality images from text descriptions is a challenging problem in computer vision and has many practical applications. Samples generated by existing text-to-image approaches can roughly reflect the meaning of the given descriptions, but they fail to contain necessary details and vivid object parts. In this paper, we propose Stacked Generative Adversarial Networks (StackGAN) to generate 256x256 photo-realistic images conditioned on text descriptions. We decompose the hard problem into more manageable sub-problems through a sketch-refinement process. The Stage-I GAN sketches the primitive shape and colors of the object based on the given text description, yielding Stage-I 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. It is able to rectify defects in Stage-I results and add compelling details with the refinement process. To improve the diversity of the synthesized images and stabilize the training of the conditional-GAN, we introduce a novel Conditioning Augmentation technique that encourages smoothness in the latent conditioning manifold. Extensive experiments and comparisons with state-of-the-arts on benchmark datasets demonstrate that the proposed method achieves significant improvements on generating photo-realistic images conditioned on text descriptions.

PaperPDFConference PDFCodeCode 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

No sample from the archive's official repository (hanzhanggit/StackGAN) is linked to this paper; the 31 samples below come from 5 community repositories. Syntology harvested code from hanzhanggit/StackGAN for another paper.

hanzhanggit/StackGAN: Syntology's graph links these samples to StackGAN++: Realistic Image Synthesis with Stacked Generative Adversarial Networks (arXiv:1710.10916; that paper's own run record: 22 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 1 violated, 12 with no contract checked; 9 where Syntology's instrument failed) · 9 unverified); nothing checks that they implement this paper's method.

Syntology 31 code samples harvested from 5 repositories linked to this paper: 22 ran (of which 0 constructed an object rather than computing a result; 15 with no instrument failure: 2 honoured, 1 violated, 12 with no contract checked; 7 where Syntology's instrument failed) · 9 unverified. Where Syntology's instrument failed: 5 where our contract draft was wrong; 2 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 31 samples from 5 repositories, 22 ran (15 with no instrument failure; 7 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 3 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

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

hanzhanggit/StackGAN officialmentioned in papermentioned on GitHubtfMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to StackGAN++: Realistic Image Synthesis with Stacked Generative Adversarial Networks (arXiv:1710.10916; that paper's own run record: 22 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 1 violated, 12 with no contract checked; 9 where Syntology's instrument failed) · 9 unverified); nothing checks that they implement this paper's method. report
123972/Deep-Learning-Final-Project mentioned on GitHubMITSyntology: not harvested report
CorneliusHsiao/FoodMethodGAN mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Deep Residual Learning for Image Recognition (arXiv:1512.03385; that paper's own run record: 254 ran (of which 108 constructed an object rather than computing a result; 163 with no instrument failure: 3 honoured, 1 violated, 159 with no contract checked; 91 where Syntology's instrument failed) · 123 unverified); nothing checks that they implement this paper's method. report
FIT4003StackGAN/FIT4003-StackGAN-v2-Metamorphic-Testing mentioned on GitHubpytorchSyntology: 3 samples, 3 ran (3 instrument-failed) · 0 unverified report
Vishal-V/GSoC mentioned on GitHubtfApache-2.0Syntology: 17 samples, 15 ran (3 instrument-failed) · 2 unverified report
Vishal-V/GSoC-TensorFlow mentioned on GitHubtfApache-2.0Syntology: not harvested report
Vishal-V/StackGAN mentioned on GitHubtfMITSyntology: 1 sample, 0 ran · 1 unverified report
alinstein/Modify-image-by-text mentioned on GitHubpytorchSyntology: not harvested report
charchit7/QuickDraw-App mentioned on GitHubpytorchSyntology: not harvested report
dhirajpatnaik16297/IMG-TXT-Generative-Adversarial-Network mentioned on GitHubtfSyntology: not harvested report
hanzhanggit/StackGAN-Pytorch mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to StackGAN++: Realistic Image Synthesis with Stacked Generative Adversarial Networks (arXiv:1710.10916; that paper's own run record: 22 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 1 violated, 12 with no contract checked; 9 where Syntology's instrument failed) · 9 unverified); nothing checks that they implement this paper's method. report
hanzhanggit/StackGAN-inception-model mentioned on GitHubtfSyntology: 1 sample, 0 ran · 1 unverified report
hg1722/fashionista mentioned on GitHubtfSyntology: not harvested report
rafaelortegar/Deep-Learning-Final-Project mentioned on GitHubMITSyntology: not harvested report
rafiahmed40/stack-adverserial-network mentioned on GitHubtfMITSyntology: 9 samples, 4 ran (1 instrument-failed) · 5 unverified report
savya08/Text-to-Image mentioned on GitHubSyntology: not harvested report
sdai654416/Joint-GAN mentioned on GitHubtfSyntology: not harvested report
suryar510/StackGAN mentioned on GitHubtfSyntology: not harvested report
uditss03/txt2img mentioned on GitHubSyntology: not harvested report
vdopp234/Text2Image mentioned on GitHubtfSyntology: not harvested report
r-khanna/stackGAN-text-to-image-synthesis- pytorchSyntology: not harvested 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

31 samples harvested: 22 ran (of which 0 constructed an object rather than computing a result; 15 with no instrument failure: 2 honoured, 1 violated, 12 with no contract checked; 7 where Syntology's instrument failed) · 9 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

2ran · honoured contract
1ran · violated contract
5ran · our draft was wrong
2ran; the contract check could not run
12ran
9unverified

Licence: 3 of the 31 samples are pointer only, meaning Syntology does not serve that copy's text. For 2 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 5 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. 1 sample whose link to this paper records no repository is listed under one of this paper's own repositories, because identical code was harvested from it for another 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. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

FIT4003StackGAN/FIT4003-StackGAN-v2-Metamorphic-Testing community (archive-listed) 3 samples, 3 ran (3 instrument-failed) · 0 unverified
KL_loss in 5 papers code/trainer.py ran · our draft was wrong fingerprinted MIT (permissive) · f502ac0ccf050e23 · report fixture: signature mu:Tensor/2/float, logvar:Tensor/2/float · returned Tensor · level recorded 2026-09-22
compute_mean_covariance code/trainer.py ran · our draft was wrong fingerprinted MIT (permissive) · 57bbdc333d2c0749 · report fixture: signature img:Tensor/4/float · returned tuple · level recorded 2026-09-22
copy_G_params code/trainer.py ran · our draft was wrong MIT (permissive) · 2c55357aecd850cd · report fixture: signature model:callable/0/? · returned list · level recorded 2026-09-22
Vishal-V/GSoC community (archive-listed) 17 samples, 15 ran (3 instrument-failed) · 2 unverified
ConvBlock in 61 papers
census: 8 implementations from 8 papers, 6 distinct outputs across 2 buckets, one shared input per bucket
stack_gan/model.py ran Apache-2.0 (permissive) · 13cff2847daf7634 · report fixture: signature x:KerasTensor/0/float, num_kernels:int/0/int, kernel_size:tuple/1/int, strides:int/0/int, activation:bool/0/bool · returned KerasTensor · level recorded 2026-09-26
UpSamplingBlock stack_gan/model.py ran fingerprinted Apache-2.0 (permissive) · 6fc80b91caf67336 · report fixture: signature x:EagerTensor/4/float, num_kernels:int/0/int · returned EagerTensor · level recorded 2026-09-26
apply_mask in 25 papers mask_rcnn/visualize.py ran Apache-2.0 (permissive) · cdda836085a5b1af · report fixture: signature image:ndarray/3/float, mask:ndarray/2/int, color:ndarray/1/float, alpha:float/0/float · returned ndarray · level recorded 2026-09-24
compute_backbone_shapes in 12 papers mask_rcnn/model.py ran · our draft was wrong Apache-2.0 (permissive) here; the stored copy is pointer only · ae91aee49740c295 · report fixture: signature config:StandInConfig/0/?, image_shape:tuple/1/int · returned ndarray · level recorded 2026-09-22
compute_iou in 68 papers mask_rcnn/utils.py ran · violated contract Apache-2.0 (permissive) · ae0c5e015d8cf734 · report fixture: signature box:ndarray/1/float, boxes:ndarray/2/float, box_area:float/0/float, boxes_area:ndarray/1/float · returned ndarray · level recorded 2026-09-24
compute_overlaps in 11 papers mask_rcnn/utils.py ran · honoured contract fingerprinted Apache-2.0 (permissive) · 9f81af6c8a2344a3 · report fixture: signature boxes1:ndarray/2/float, boxes2:ndarray/2/float · returned ndarray · level recorded 2026-09-24
conditioning_augmentation stack_gan/model.py ran Apache-2.0 (permissive) · 1adac96a64c536f7 · report fixture: signature x:EagerTensor/2/float · returned EagerTensor · level recorded 2026-09-26
conv_block in 95 papers mask_rcnn/model.py ran Apache-2.0 (permissive) · 4a91e0c12a4df0bc · report fixture: signature input_tensor:EagerTensor/4/float, kernel_size:int/0/int, filters:list/1/int, stage:int/0/int, block:str/0/str, strides:tuple/1/int, use_bias:bool/0/bool, train_bn:bool/0/bool · returned EagerTensor · level recorded 2026-09-26
draw_box in 16 papers mask_rcnn/visualize.py ran · our draft was wrong Apache-2.0 (permissive) · dc05d22f3d39bea6 · report fixture: signature image:ndarray/3/int, box:tuple/1/int, color:list/1/int · returned ndarray · level recorded 2026-09-24
extract_bboxes in 14 papers mask_rcnn/utils.py ran; the contract check could not run (RAISES) fingerprinted Apache-2.0 (permissive) · d2c9b72e23d9588a · report fixture: signature mask:ndarray/3/int · returned ndarray · level recorded 2026-09-24
get_random_block_from_data autoencoder/model/AutoencoderRunner.py ran fingerprinted Apache-2.0 (permissive) · 74e5099c2cbb3e49 · report fixture: signature data:ndarray/1/int, batch_size:int/0/int · returned ndarray · level recorded 2026-09-26
make_eval_inputs_from_np_arrays boosted_trees/train_higgs.py ran Apache-2.0 (permissive) · c353c26b5c082459 · report fixture: signature features_np:ndarray/2/float, label_np:ndarray/1/float · returned function · level recorded 2026-09-26
make_inputs_from_np_arrays boosted_trees/train_higgs.py ran Apache-2.0 (permissive) · f5b233a3ce3e8fb9 · report fixture: signature features_np:ndarray/2/float, label_np:ndarray/2/float · returned tuple · level recorded 2026-09-26
random_colors in 12 papers mask_rcnn/visualize.py ran · honoured contract Apache-2.0 (permissive) · a9d0cf3b71fefa32 · report fixture: signature N:int/0/int, bright:bool/0/bool · returned list · level recorded 2026-09-24
read_higgs_data boosted_trees/train_higgs.py ran Apache-2.0 (permissive) · ade723634de3da01 · report fixture: signature data_dir:str/0/str, train_start:int/0/int, train_count:int/0/int, eval_start:int/0/int, eval_count:int/0/int · returned tuple · level recorded 2026-09-26
download_data in 6 papers face_app/data_download.py unverified Apache-2.0 (permissive) · c8dea6dd84ed3e6b · report
identity_block in 32 papers mask_rcnn/model.py unverified Apache-2.0 (permissive) · ebaf5ac773912a84 · report
Vishal-V/StackGAN community (archive-listed) 1 sample, 0 ran · 1 unverified
download_data in 6 papers data_download.py unverified MIT (permissive) · ff2c5c521817cf06 · report
hanzhanggit/StackGAN-inception-model community (archive-listed) 1 sample, 0 ran · 1 unverified
preprocess in 284 papers
census: 11 implementations from 13 papers, 10 distinct outputs across 5 buckets, one shared input per bucket
inception_score.py identical code Syntology harvested from this repository for another paper; this paper's link records no repository, path or licence of its own unverified licence of this copy not recorded · b85a728ed7aaaade · report
rafiahmed40/stack-adverserial-network community (archive-listed) 9 samples, 4 ran (1 instrument-failed) · 5 unverified
KL_loss in 5 papers stageI/trainer.py ran MIT (permissive) · fd6883aef7fc0f6f · report fixture: signature mu:EagerTensor/2/float, log_sigma:EagerTensor/2/float · returned EagerTensor · level recorded 2026-09-25
custom_crop in 5 papers misc/utils.py ran MIT (permissive) · fc22db7fa7e0e135 · report fixture: signature img:ndarray/3/int, bbox:list/1/int · returned ndarray · level recorded 2026-09-25
leaky_rectify misc/custom_ops.py ran; the contract check could not run (RAISES) MIT (permissive) here; the stored copy is pointer only · 0b71fdd2dc019d86 · report fixture: returned EagerTensor · level recorded 2026-09-24
load_filenames misc/preprocess_birds.py ran MIT (permissive) · 7b80aa25807d666a · report fixture: signature data_dir:str/0/str · returned list · level recorded 2026-09-25
drawCaption demo/birds_skip_thought_demo.py unverified MIT (permissive) · 3e354ab43bfb020e · report
get_image in 52 papers misc/utils.py unverified MIT (permissive) · 21bf8f7cea6decf5 · report
load_bbox misc/preprocess_birds.py unverified MIT (permissive) · 386604cfa74a3d76 · report
sample_encoded_context demo/birds_skip_thought_demo.py unverified MIT (permissive) · 549299c4575752d8 · report

Tasks

Image GenerationText-to-Image Generation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Text-to-Image Generation CUB StackGAN Inception score 3.7 #20 of 20 Archive leaderboard report
Text-to-Image Generation Oxford 102 Flowers StackGAN Inception score 3.2 #8 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