Papers › Analyzing and Improving the Image Quality of StyleGAN
Analyzing and Improving the Image Quality of StyleGAN
Tero Karras, Samuli Laine, Miika Aittala, Janne Hellsten, Jaakko Lehtinen, Timo Aila
The style-based GAN architecture (StyleGAN) yields state-of-the-art results in data-driven unconditional generative image modeling. We expose and analyze several of its characteristic artifacts, and propose changes in both model architecture and training methods to address them. In particular, we redesign the generator normalization, revisit progressive growing, and regularize the generator to encourage good conditioning in the mapping from latent codes to images. In addition to improving image quality, this path length regularizer yields the additional benefit that the generator becomes significantly easier to invert. This makes it possible to reliably attribute a generated image to a particular network. We furthermore visualize how well the generator utilizes its output resolution, and identify a capacity problem, motivating us to train larger models for additional quality improvements. Overall, our improved model redefines the state of the art in unconditional image modeling, both in terms of existing distribution quality metrics as well as perceived image quality.
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="1912.04958")get_code(code_sha256="…")with a sample'scode_sha256from the list belowget_citation_path(paper_1="1912.04958", paper_2="…")with another paper's arXiv id or titleget_concepts_for_paper(arxiv_id="1912.04958")
Code
Syntology 92 code samples harvested from 27 repositories linked to this paper: 68 ran (of which 0 constructed an object rather than computing a result; 48 with no instrument failure: 4 honoured, 6 violated, 38 with no contract checked; 20 where Syntology's instrument failed) · 24 unverified. Where Syntology's instrument failed: 16 where our contract draft was wrong; 4 where the contract check could not run; failures of Syntology's instrument, not of the code.
By repository: official repository: 1 sample from 1 repository, 0 ran (0 with no instrument failure; 0 where Syntology's instrument failed); community (archive-listed): 91 samples from 26 repositories, 68 ran (48 with no instrument failure; 20 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 12 of its repositories that Syntology harvested for other papers:
- RyanWu2233/Style_GAN2_FFHQ, community (archive-listed): harvested for another paper, listed under the repository
- akashgit/stylegan2_wt, 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
- e4s2022/e4s, community (archive-listed): harvested for another paper, listed under the repository
- eps696/stylegan2, community (archive-listed): harvested for another paper, listed under the repository
- kunheek/style-aware-discriminator, community (archive-listed): harvested for another paper, listed under the repository
- lukemelas/unsupervised-image-segmentation, community (archive-listed): harvested for another paper, listed under the repository
- minyoungg/pix2latent, community (archive-listed): harvested for another paper, listed under the repository
- sidward14/gan-lab, community (archive-listed): harvested for another paper, listed under the repository
- yuzq97/starter_project, community (archive-listed): harvested for 2 other papers, listed under the repository
- labmlai/annotated_deep_learning_paper_implementations, community (archive-listed): harvested for 15 other papers, listed under the repository
- toshas/torch-fidelity, 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. 5 of the 68 samples that ran have no recorded date.
126 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
92 samples harvested: 68 ran (of which 0 constructed an object rather than computing a result; 48 with no instrument failure: 4 honoured, 6 violated, 38 with no contract checked; 20 where Syntology's instrument failed) · 24 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: 25 of the 92 samples are pointer only, meaning Syntology does not serve that copy's text. For 7 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 27 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. “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.
fc6991cc46411667 · report
56dc57ef0acb82be · report
cbe94318d8c3dd02 · report
fixture: signature el:int/0/int · returned list · level recorded 2026-09-22 d4a98e207f6dc8d9 · report
fixture: signature value:NoneType/0/?, d:int/0/int · returned int · level recorded 2026-09-22 78d64d6c6d3e642a · report
fixture: signature t:Tensor/2/float · returned bool · level recorded 2026-09-22 28ef046211377170 · report
census: 7 implementations from 5 papers, 5 distinct outputs across 2 buckets, one shared input per bucket stylegan2_pytorch/diff_augment.py ran MIT (permissive) ·
737fe4ff1cef5f47 · report
fixture: signature x:Tensor/4/float, types:list/1/str · returned Tensor · level recorded 2026-09-24 85f67e8fb251251f · report
fixture: signature contexts:list/1/callable · returned function · level recorded, date not recorded census: 5 implementations from 103 papers, 1 distinct output on one shared input this sample: bucket 1 of 1, arg 1: rank 1, kind int, dtype int64 stylegan2_pytorch/stylegan2_pytorch.py ran · violated contract MIT (permissive) here; the stored copy is pointer only ·
aa5486a3650902d8 · report
fixture: signature val:Tensor/1/int · returned bool · level recorded, date not recorded census: 7 implementations from 9 papers, 5 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 1 of 2, arg 1: rank 4, kind float, dtype float32 stylegan2_pytorch/diff_augment.py ran · our draft was wrong fingerprinted MIT (permissive) here; the stored copy is pointer only ·
011230b2b9b8fb6f · report
fixture: signature x:Tensor/4/float · returned Tensor · level recorded, date not recorded census: 6 implementations from 9 papers, 3 distinct outputs on one shared input this sample: bucket 1 of 1, arg 1: rank 4, kind float, dtype float32 stylegan2_pytorch/diff_augment.py ran · our draft was wrong fingerprinted MIT (permissive) here; the stored copy is pointer only ·
5b0d8787e670fc63 · report
fixture: signature x:Tensor/4/float · returned Tensor · level recorded, date not recorded 3a70fcd4a1ef51b5 · report
fixture: signature s:str/0/str · returned float · level recorded 2026-09-24 3e85674588130c34 · report
fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-24 bb4f3ee04b54c9cd · report
fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-24 1fe64d4f2b0f6e34 · report
fixture: signature name:str/0/str · returned ndarray · level recorded 2026-09-25 0564ba38597daf7c · report
fixture: signature file:str/0/str · returned tuple · level recorded 2026-09-25 fb54de042a2c0cee · report
fixture: signature tensors:list/1/Tensor · returned Tensor · level recorded 2026-09-24 f7c472870e1621ff · report
fixture: signature out_size:int/0/int, generator_resolution:int/0/int, is_stylegan1:bool/0/bool · returned tuple · level recorded 2026-09-22 31857d2f579c1600 · report
ed03ba54397adbe4 · report
fixture: signature data:dict/0/? · returned list · level recorded 2026-09-26 e6c1de4697e7ed81 · report
fixture: signature sample_mean:ndarray/1/float, sample_cov:ndarray/2/float, real_mean:ndarray/1/float, real_cov:ndarray/2/float, eps:float/0/float · returned float32 · level recorded 2026-09-22 826a4bfd8b5cb2fc · report
fixture: signature loader:list/1/Tensor, inception:callable/0/?, device:str/0/str · returned Tensor · level recorded 2026-09-25 6f65e378a4313f87 · report
fixture: signature k:list/1/float · returned Tensor · level recorded, date not recorded 5144ad456049f8ce · report
fixture: signature loss_dict:dict/0/? · returned dict · level recorded 2026-09-26 census: 4 implementations from 5 papers, 4 distinct outputs across 4 buckets, one shared input per bucket distributed.py ran · honoured contract fingerprinted MIT (permissive) ·
3f0a1105ef251d78 · report
fixture: signature tensor:Tensor/2/float · returned Tensor · level recorded 2026-09-24 514dd3c0eee3691c · report
fixture: signature data_loader:CustomDatasetDataLoader/0/?, func:callable/0/?, name:str/0/str · returned tuple · level recorded 2026-09-25 581c80d602289d6d · report
fixture: signature data_loader:MockDataLoader/0/?, func:callable/0/?, name:str/0/str · returned tuple · level recorded 2026-09-25 29e5e72bcd006dcd · report
fixture: signature in_tens:Tensor/4/float, keepdim:bool/0/bool · returned Tensor · level recorded 2026-09-22 census: 11 implementations from 16 papers, 9 distinct outputs across 3 buckets, one shared input per bucket lpips/networks_basic.py ran; the contract check could not run (RAISES) fingerprinted MIT (permissive) here; the stored copy is pointer only ·
351677a36e1961df · report
fixture: signature in_tens:Tensor/4/float, out_H:int/0/int · returned Tensor · level recorded 2026-09-24 805a0a55a20dd455 · report
842b4512e2f900b8 · report
fixture: signature image:ndarray/3/float · returned ndarray · level recorded 2026-09-24 0b6b64ce27b6f5d8 · report
fixture: signature fake_scores:EagerTensor/1/float, real_scores:EagerTensor/1/float, cfg:Config/0/?, disc_real_score_gradients:EagerTensor/4/float · returned EagerTensor · level recorded 2026-09-24 86c7a1518eea5484 · report
fixture: signature fake_scores:EagerTensor/1/float · returned EagerTensor · level recorded 2026-09-24 3009b511634a89fb · report
fixture: signature inputs:EagerTensor/4/float, filters:EagerTensor/4/float, data_format:str/0/str · returned EagerTensor · level recorded 2026-09-24 071ebfa6782a24ce · report
fixture: signature feature_maps_base:int/0/int, feature_maps_decay:float/0/float, feature_maps_min:int/0/int, feature_maps_max:int/0/int · returned function · level recorded 2026-09-24 e84a59c738a25e4f · report
fixture: signature mnist_dir:str/0/str · returned tuple · level recorded 2026-09-24 b1c1b03d103b2827 · report
fixture: signature shape:tuple/1/int, gain:float/0/float, lr_multiplier:float/0/float · returned float64 · level recorded 2026-09-24 b83c9dfb41ea1c2a · report
fixture: signature eval_dist:ndarray/1/float, ref_dist:ndarray/1/float, num_angles:int/0/int, epsilon:float/0/float · returned tuple · level recorded 2026-09-22 feab88ece44cfb43 · report
fixture: signature value:NoneType/0/?, d:str/0/str · returned str · level recorded 2026-09-22 census: 6 implementations from 6 papers, 6 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 1 of 2, arg 1: rank 2, kind float, dtype float32 · arg 2: rank 2, kind float, dtype float32 CoW_generator.py ran · our draft was wrong licence not identified · pointer only ·
6d7397331b84d54f · report
fixture: signature val:float/0/float, low:Tensor/2/float, high:Tensor/2/float · returned Tensor · level recorded 2026-09-22 5bdcd58a1b1c3547 · report
b80de22ba51da829 · report
fixture: signature radius:float/0/float, latents_persistent:tuple/1/ndarray, latents_interpolate:float/0/float · returned ndarray · level recorded 2026-09-22 e08f316a9dc1f50e · report
a691acff20d5a466 · report
fixture: signature n:int/0/int · returned bool · level recorded 2026-09-24 47ffad5aa9bb9c7d · report
fixture: signature src_path:str/0/str · returned str · level recorded 2026-09-22 7284618ab4d5847d · report
census: 7 implementations from 5 papers, 5 distinct outputs across 2 buckets, one shared input per bucket stylegan2_pytorch/diff_augment.py ran MIT (permissive) ·
688410c911dd9bc7 · report
fixture: signature x:Tensor/4/float, types:list/1/str · returned Tensor · level recorded 2026-09-24 census: 7 implementations from 9 papers, 5 distinct outputs across 2 buckets, one shared input per bucket stylegan2_pytorch/diff_augment.py ran fingerprinted MIT (permissive) ·
8d3c9a8fec68ec10 · report
fixture: signature x:Tensor/4/float, scale:float/0/float · returned Tensor · level recorded 2026-09-24 census: 6 implementations from 9 papers, 3 distinct outputs on one shared input stylegan2_pytorch/diff_augment.py ran fingerprinted MIT (permissive) ·
31f2e654bb2eb0a1 · report
fixture: signature x:Tensor/4/float, scale:float/0/float · returned Tensor · level recorded 2026-09-24 beb915a3206ef2b0 · report
fixture: signature n:int/0/int · returned list · level recorded 2026-09-24 8af2f60798b76e8c · report
fixture: signature n:int/0/int · returned ndarray · level recorded 2026-09-22 44a45d3c0dd7f84f · report
fixture: signature n:int/0/int · returned list · level recorded 2026-09-24 ea6c82ed6a138df9 · report
fixture: signature t:float/0/float, initial_lr:float/0/float, rampdown:float/0/float, rampup:float/0/float · returned float · level recorded 2026-09-22 a73e1d557a70850c · report
fixture: signature latent:Tensor/2/float, strength:float/0/float · returned Tensor · level recorded 2026-09-22 d4a7743c226cbee2 · report
fixture: signature noises:list/1/Tensor · returned Tensor · level recorded 2026-09-22 93402ab39ef7bf7f · report
fixture: signature seeds:list/1/int, Gs:MockGs/0/? · returned list · level recorded 2026-09-22 03bf478c960a67ca · report
f11bcd77ae7e45cd · report
fixture: signature ndims:int/0/int, nlayers:int/0/int · returned Functional · level recorded 2026-09-24 census: 2 implementations from 7 papers, 1 distinct output on one shared input this sample: bucket 1 of 1, arg 1: rank 1, kind float, dtype float32 · arg 2: rank 1, kind float, dtype float32 train_aegan.py ran · our draft was wrong fingerprinted MIT (permissive) ·
3651db4e5ae8d189 · report
fixture: signature real_pred:Tensor/1/float, fake_pred:Tensor/1/float · returned Tensor · level recorded 2026-09-22 dbb756dcd778f52f · report
fixture: signature dataset:SimpleDataset/0/?, shuffle:bool/0/bool, distributed:bool/0/bool · returned RandomSampler · level recorded 2026-09-22 7fe245a7216ae67b · report
fixture: signature vars:MockVarsDict/0/?, source_name:str/0/str, target_name:str/0/str, bias:bool/0/bool, start:int/0/int · returned dict · level recorded 2026-09-22 1c7cd5abc48bcf75 · report
fixture: signature vars:dict/0/?, source_name:str/0/str, target_name:str/0/str, flip:bool/0/bool · returned dict · level recorded 2026-09-22 96b279b9ef818d94 · report
fixture: signature vars:dict/0/?, source_name:str/0/str, target_name:str/0/str · returned dict · level recorded 2026-09-22 8bacd060ce9aa706 · report
fixture: signature real_logits:Tensor/2/float, fake_logits:Tensor/2/float · returned Tensor · level recorded 2026-09-24 3ad4567c3a15de09 · report
fixture: signature fake_logits:Tensor/2/float · returned Tensor · level recorded 2026-09-24 fa6245afd0bd3943 · report
fixture: signature array:ndarray/4/float, ncols:int/0/int · returned ndarray · level recorded 2026-09-24 d4bb2865508c3d4b · report
fixture: signature obj:Tensor/4/float · returned ndarray · level recorded 2026-09-24 census: 8 implementations from 8 papers, 3 distinct outputs across 3 buckets, one shared input per bucket misc.py ran MIT (permissive) ·
181e050b9236c790 · report
fixture: signature obj:ndarray/3/float, device:str/0/str · returned Tensor · level recorded 2026-09-24 98e99278bbc2d9fc · 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 887196edb544b380 · report
1f61e80b10011e25 · report
fixture: signature path:str/0/str · returned str · level recorded 2026-09-26 5a6569d11eafa188 · report
d4a53739e4974d00 · report
9d5002fbab594877 · report
06c39cfa6fb83ec9 · report
3afef538049c0b44 · report
fixture: signature real_img:Tensor/4/float, D:callable/0/?, gamma:float/0/float · returned Tensor · level recorded 2026-09-24 b8884c80b0981815 · report
fixture: signature fake_img:Tensor/4/float, real_img:Tensor/4/float, D:callable/0/?, gamma:float/0/float · returned Tensor · level recorded 2026-09-24 854f44ea3c707948 · report
fixture: signature obj_name:str/0/str · returned tuple · level recorded 2026-09-24 8d54fc5b205e0566 · report
fixture: signature module:module/0/?, obj_name:str/0/str · returned int · level recorded 2026-09-24 1feff8453d5e0cc4 · report
fixture: signature file_name:str/0/str · returned list · level recorded 2026-09-24 13cb2d0d9cc08f48 · report
fixture: signature folder_name:str/0/str · returned list · level recorded 2026-09-24 948b0cb2873fdc0c · report
fixture: signature item_name:str/0/str · returned ndarray · level recorded 2026-09-24 44593202a560da74 · report
Tasks
Results from the paper archive 2025-07-28
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
Introduced by this paper: StyleGAN2
1 archive method tag without a method page not shown.
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