Papers › Progressive Growing of GANs for Improved Quality, Stability, and Variation
Progressive Growing of GANs for Improved Quality, Stability, and Variation
Tero Karras, Timo Aila, Samuli Laine, Jaakko Lehtinen
We describe a new training methodology for generative adversarial networks. The key idea is to grow both the generator and discriminator progressively: starting from a low resolution, we add new layers that model increasingly fine details as training progresses. This both speeds the training up and greatly stabilizes it, allowing us to produce images of unprecedented quality, e.g., CelebA images at 1024^2. We also propose a simple way to increase the variation in generated images, and achieve a record inception score of 8.80 in unsupervised CIFAR10. Additionally, we describe several implementation details that are important for discouraging unhealthy competition between the generator and discriminator. Finally, we suggest a new metric for evaluating GAN results, both in terms of image quality and variation. As an additional contribution, we construct a higher-quality version of the CelebA dataset.
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):
get_harvested_code_for_paper(arxiv_id="1710.10196")get_code(code_sha256="…")with a sample'scode_sha256from the list belowget_citation_path(paper_1="1710.10196", paper_2="…")with another paper's arXiv id or titleget_concepts_for_paper(arxiv_id="1710.10196")
Code
The archive's official repository (tkarras/progressive_growing_of_gans) was not harvested; the 89 samples below come from 23 community repositories.
Syntology 89 code samples harvested from 23 repositories linked to this paper: 58 ran (of which 0 constructed an object rather than computing a result; 41 with no instrument failure: 6 honoured, 1 violated, 34 with no contract checked; 17 where Syntology's instrument failed) · 31 unverified. Where Syntology's instrument failed: 14 where our contract draft was wrong; 3 where the contract check could not run; failures of Syntology's instrument, not of the code.
By repository: community (archive-listed): 89 samples from 23 repositories, 58 ran (41 with no instrument failure; 17 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 29 of its repositories that Syntology harvested for other papers:
- DivJAth/DeepLearning5922, community (archive-listed): harvested for another paper, listed under the repository
- FloList/21cmGAN, community (archive-listed): harvested for another paper, listed under the repository
- RyanWu2233/Style_GAN2_FFHQ, community (archive-listed): harvested for another paper, listed under the repository
- ShenYujun/InterFaceGAN, community (archive-listed): harvested for another paper, listed under the repository
- Soldie/DeOldify-colorir-imagens-antigas, community (archive-listed): harvested for another paper, listed under the repository
- TUM-ML-Lab18/FaceSwap, community (archive-listed): harvested for another paper, listed under the repository
- a514514772/hijackgan, community (archive-listed): harvested for another paper, listed under the repository
- akanimax/T2F, community (archive-listed): harvested for another paper, listed under the repository
- alfagao/DeOldify, community (archive-listed): harvested for another paper, listed under the repository
- ariel415el/ALAE, community (archive-listed): harvested for another paper, listed under the repository
- autonomousvision/frequency_bias, community (archive-listed): harvested for another paper, listed under the repository
- axium/Blind-Image-Deconvolution-using-Deep-Generative-Priors, community (archive-listed): harvested for another paper, listed under the repository
- bit-ml/dolos, community (archive-listed): harvested for another paper, listed under the repository
- cc-hpc-itwm/DeepFakeDetection, community (archive-listed): harvested for another paper, listed under the repository
- facebookresearch/pytorch_GAN_zoo, community (archive-listed): harvested for 2 other papers, listed under the repository
- rowerliu/adbd, community (archive-listed): harvested for another paper, listed under the repository
- sergkuzn148/lol3, community (archive-listed): harvested for another paper, listed under the repository
- sergkuzn148/stg, community (archive-listed): harvested for another paper, listed under the repository
- shahbuland/basic-gans, community (archive-listed): harvested for 3 other papers, listed under the repository
- sidward14/gan-lab, community (archive-listed): harvested for another paper, listed under the repository
- sims-s/bird-gan, community (archive-listed): harvested for another paper, listed under the repository
- sobieskibj/rcsb, community (archive-listed): harvested for 2 other papers, listed under the repository
- timsainb/GAIA, community (archive-listed): harvested for another paper, listed under the repository
- valentingol/GANJax, community (archive-listed): harvested for another paper, listed under the repository
- vijishmadhavan/SkinDeep, community (archive-listed): harvested for another paper, listed under the repository
- yaxingwang/MineGAN, community (archive-listed): harvested for another paper, listed under the repository
- Ipsedo/MusicGAN, community (archive-listed): harvested for another paper, listed under the repository
- PacktPublishing/Hands-On-Image-Generation-with-TensorFlow-2.0, community (archive-listed): harvested for another paper, listed under the repository
- mindspore-ai/models, community (archive-listed): harvested for another paper, listed under the repository
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. 1 of the 58 samples that ran has no recorded date.
115 repositories listed; official and paper-mentioned ones first.
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
89 samples harvested: 58 ran (of which 0 constructed an object rather than computing a result; 41 with no instrument failure: 6 honoured, 1 violated, 34 with no contract checked; 17 where Syntology's instrument failed) · 31 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.
Licence: 23 of the 89 samples are pointer only, meaning Syntology does not serve that copy's text. For 4 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 23 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.
711d47c198722ce1 · report
fixture: signature a:list/1/list, b:list/1/list · returned tuple · level recorded 2026-09-26 3e0fd7af14f9d21f · report
fixture: signature a:list/1/float, b:list/1/float · returned float64 · level recorded 2026-09-26 c1ac6b8f2fcdbe94 · report
fixture: signature training_data:ndarray/2/float · returned ndarray · level recorded 2026-09-26 a64567ed28beff99 · report
fixture: signature step:int/0/int, batch_size:int/0/int, path:str/0/str, num_workers:int/0/int · returned DataLoader · level recorded 2026-09-22 be01ec4bcf6eb2e7 · report
fixture: returned tuple · level recorded 2026-09-22 48733b4f45e07b0c · report
fixture: returned tuple · level recorded 2026-09-22 4f3e483d37b473a8 · report
fixture: signature nin:int/0/int, nout:int/0/int, kernel_size:int/0/int, stride:int/0/int, padding:int/0/int, layer:callable/0/?, ws:bool/0/bool, bn:bool/0/bool, pn:bool/0/bool, activ:NoneType/0/?, gainWS:int/0/int · returned Sequential · level recorded 2026-09-26 b47f3e77f8afd454 · report
fixture: signature z:Tensor/2/float, radius:float/0/float · returned Tensor · level recorded 2026-09-26 90a97f8af1b8f269 · report
fixture: signature data:ndarray/2/float, drange_in:tuple/1/float, drange_out:tuple/1/float · returned ndarray · level recorded 2026-09-22 4d0511f945b207d9 · report
fixture: signature mu1:ndarray/1/float, sigma1:ndarray/2/float, mu2:ndarray/1/float, sigma2:ndarray/2/float · returned float64 · level recorded 2026-09-26 cf03a3ce8cc3695e · report
fixture: signature images:ndarray/4/float, grid_size:NoneType/0/? · returned ndarray · level recorded 2026-09-25 f7d82b02ff7c7fe1 · report
fixture: signature cur_lambda:callable/0/?, new_cond:callable/0/?, new_lambda:callable/0/? · returned function · level recorded 2026-09-22 census: 4 implementations from 7 papers, 4 distinct outputs across 4 buckets, one shared input per bucket tfutil.py ran MIT (permissive) ·
4e4ae70c11635981 · report
fixture: signature x:EagerTensor/3/float · returned EagerTensor · level recorded 2026-09-25 2cd5be47220a5bc0 · report
fixture: signature state:dict/0/? · returned dict · level recorded 2026-09-25 6e81789f8f2068c8 · report
fixture: signature a:EagerTensor/2/float, b:EagerTensor/2/float, t:EagerTensor/2/float · returned EagerTensor · level recorded 2026-09-22 e963375233fe6dbe · report
fixture: signature shape:list/1/MockDimension · returned list · level recorded 2026-09-25 38cc003d233d5e97 · report
a50999e17e91e763 · report
6d2ac42c34e9e725 · report
b919a96235b8ee68 · report
fixture: signature module:callable/0/?, name:str/0/str · returned SimpleModule · level recorded 2026-09-22 f6a1e7dfa6b60993 · report
fixture: signature data:Tensor/2/float, drange_in:tuple/1/float, drange_out:tuple/1/float · returned Tensor · level recorded 2026-09-26 70683be51b50ba38 · report
fixture: signature dataset:DummyDataset/0/?, batch_size:int/0/int, num_workers:int/0/int · returned DataLoader · level recorded 2026-09-26 52d84f33d99f9e78 · report
fixture: signature new_size:tuple/1/int, flip_horizontal:bool/0/bool · returned Compose · level recorded 2026-09-26 a370212610d1e629 · report
fixture: signature stage:int/0/int, fmap_base:int/0/int, fmap_decay:float/0/float, fmap_min:int/0/int, fmap_max:int/0/int · returned int · level recorded 2026-09-26 8047f310c6e537b8 · report
fixture: signature imgs:Tensor/4/float · returned ndarray · level recorded 2026-09-26 7c508037b40522af · report
fixture: signature v:str/0/str · returned bool · level recorded, date not recorded 5f92b1025856474c · report
521e38ac458dba5a · report
bd6383ad21a9d1b9 · report
fixture: signature data:Tensor/2/float, drange_in:tuple/1/int, drange_out:tuple/1/int · returned Tensor · level recorded 2026-09-24 bbf23ae0401556fa · report
fixture: signature data:Tensor/2/float, drange_in:tuple/1/int, drange_out:tuple/1/int · returned Tensor · level recorded 2026-09-24 155ad5e4ce841a11 · report
fixture: signature dataset:DummyImageDataset/0/?, batch_size:int/0/int, num_workers:int/0/int · returned DataLoader · level recorded 2026-09-26 e36470391de100a1 · report
fixture: signature new_size:tuple/1/int · returned Compose · level recorded 2026-09-26 3b64be721c117eb3 · report
c6b86ba24ffc7ae7 · report
fixture: signature in_channel:int/0/int, out_channel:int/0/int, kernel_size:int/0/int, pooling:callable/0/?, dropout:float/0/float · returned Sequential · level recorded 2026-09-22 fbcbe989dbb6f48f · report
fixture: signature in_channel:int/0/int, out_channel:int/0/int, kernel_size:int/0/int, upsample:callable/0/?, dropout:float/0/float · returned Sequential · level recorded 2026-09-22 census: 4 implementations from 6 papers, 2 distinct outputs on one shared input progressive_gan.py ran · our draft was wrong no licence file found · pointer only ·
6e06ab82fbd70bfe · report
fixture: signature img:Image/0/?, img_dim:tuple/1/int · returned ndarray · level recorded 2026-09-22 42c0a8e5638fc32b · report
fixture: signature latent_code:ndarray/2/float, boundary:ndarray/2/float, start_distance:float/0/float, end_distance:float/0/float, steps:int/0/int · returned ndarray · level recorded 2026-09-22 49cf0a1787e523d4 · report
fixture: signature gan_type:str/0/str, args:Args/0/? · returned str · level recorded 2026-09-22 c8ceba12b6020549 · report
fixture: signature device:str/0/str · returned Tensor · level recorded 2026-09-24 4a3a50d5b90d9dac · report
fixture: signature image:Tensor/4/float, device:str/0/str · returned Tensor · level recorded 2026-09-24 d6f847810616ed82 · report
fixture: signature image:Tensor/4/float, device:str/0/str · returned Tensor · level recorded 2026-09-24 0a2fff2788942ffb · report
fixture: signature entry:dict/0/?, as_supervised:bool/0/bool, mirror_augment:bool/0/bool, swap_channel_axes:bool/0/bool · returned EagerTensor · level recorded 2026-09-26 ae19cba8914f9449 · report
fixture: signature identifier:str/0/str · returned str · level recorded 2026-09-26 f068c2988747e1ec · report
fixture: signature kernel_shape:tuple/1/int, gain:float/0/float · returned float64 · level recorded 2026-09-26 78fab8ae54f5a5b1 · report
fixture: signature kernel_shape:tuple/1/int, gain:float/0/float, use_weight_scaling:bool/0/bool · returned tuple · level recorded 2026-09-26 a27f5e1174cca3c1 · report
fixture: signature real_output:EagerTensor/1/float, fake_output:EagerTensor/1/float · returned EagerTensor · level recorded 2026-09-26 2d4c3980af8ec4dd · report
fixture: signature fake_output:EagerTensor/1/float · returned EagerTensor · level recorded 2026-09-26 1b9cd35ececa91b8 · report
fixture: signature discriminator:callable/0/?, real_images:EagerTensor/4/float, fake_images:EagerTensor/4/float, wgan_target:float/0/float, wgan_lambda:float/0/float · returned EagerTensor · level recorded 2026-09-26 14f397e670bf892f · report
1af9892b31aabab3 · report
f9964d719c5cb8f4 · report
fixture: signature w:list/1/dict · returned dict · level recorded 2026-09-22 38cd666a74c8336f · report
fixture: signature args:Args/0/?, device:str/0/str, bs:int/0/int, label:NoneType/0/?, cxr:bool/0/bool · returned Tensor · level recorded 2026-09-26 5ef2eff36d9c9c0e · report
fixture: signature module:callable/0/?, name:str/0/str · returned SimpleModule · level recorded 2026-09-22 0ff5a15827759bd9 · report
fixture: signature module:callable/0/?, name:str/0/str · returned Linear · level recorded 2026-09-22 census: 4 implementations from 6 papers, 1 distinct output on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32 · arg 2: rank 2, kind float, dtype float32 networks.py ran · honoured contract fingerprinted licence not identified · pointer only ·
0c45399f3741921e · report
fixture: signature a:Tensor/2/float, b:Tensor/2/float, t:float/0/float · returned Tensor · level recorded 2026-09-22 5309fbd5ce19dfd1 · report
fixture: signature stage:int/0/int, fmap_base:int/0/int, fmap_decay:float/0/float, fmap_max:int/0/int · returned int · level recorded 2026-09-22 ca6835c50de9c2b5 · report
fixture: signature loss:Tensor/0/float, optimizer:MockOptimizer/0/?, mixed_precision:bool/0/bool · returned Tensor · level recorded 2026-09-22 4e921d8ccda92b1e · report
fixture: signature grads:list/1/Tensor, optimizer:StandInOptimizer/0/?, mixed_precision:bool/0/bool · returned list · level recorded 2026-09-22 71657f89e9bf3330 · report
5114afd79e51edba · report
fixture: signature pretrained:bool/0/bool · returned DCGANStandIn · level recorded 2026-09-26 65e19fe541a8b905 · report
fixture: signature pretrained:bool/0/bool, config:dict/0/?, useGPU:bool/0/bool, model_name:str/0/str · returned MockProgressiveGAN · level recorded 2026-09-26 30a4c5a03cdf07fe · report
fixture: signature x:Tensor/4/float · returned int · level recorded 2026-09-26 f321f54723433661 · report
fixture: signature path:str/0/str · returned Image · level recorded 2026-09-22 9cac19cab2d03a1a · report
fixture: signature parser:ArgumentParser/0/? · returned ArgumentParser · level recorded 2026-09-26 9a67a8a9c8decd53 · report
09407c9d23687689 · report
aa11f930df9b8195 · report
fixture: signature x:Tensor/2/float, drange_in:tuple/1/float, drange_out:tuple/1/float · returned Tensor · level recorded 2026-09-25 69c226eb82fee692 · report
fixture: signature layers:list/1/empty, c_in:int/0/int, c_out:int/0/int, k_size:int/0/int, stride:int/0/int, pad:int/0/int, leaky:bool/0/bool, bn:bool/0/bool, wn:bool/0/bool, pixel:bool/0/bool, only:bool/0/bool · returned list · level recorded 2026-09-26 b0f4358dadb23ccd · report
fixture: signature x:Tensor/4/float, ngrid:int/0/int · returned Tensor · level recorded 2026-09-25 census: 10 implementations from 14 papers, 5 distinct outputs across 2 buckets, one shared input per bucket utils.py unverified MIT (permissive) ·
01bad44f39bf9fca · report
Tasks
Datasets
Introduced by this paper, per the archive.
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Image Generation | CelebA-HQ 1024x1024 | PGGAN | FID | 7.3 | #7 of 10 | Archive leaderboard | report |
| Image Generation | LSUN Bedroom 256 x 256 | PGGAN | FID | 8.34 | #17 of 32 | Archive leaderboard | report |
| Image Generation | LSUN Cat 256 x 256 | PGGAN | Clean-FID (trainfull) | 38.35 ± 0.32 | #7 of 8 | Archive leaderboard | report |
| Image Generation | LSUN Cat 256 x 256 | PGGAN | FID | 37.52 | #7 of 8 | Archive leaderboard | report |
| Image Generation | LSUN Churches 256 x 256 | PGGAN | Clean-FID (trainfull) | 6.43 ± 0.05 | #21 of 27 | Archive leaderboard | report |
| Image Generation | LSUN Churches 256 x 256 | PGGAN | FID | 6.42 | #21 of 27 | Archive leaderboard | report |
| Image Generation | LSUN Horse 256 x 256 | PGGAN | Clean-FID (trainfull) | 14.09 ± 0.06 | #6 of 6 | 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
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