Papers › Tackling the Generative Learning Trilemma with Denoising Diffusion GANs

Tackling the Generative Learning Trilemma with Denoising Diffusion GANs

15 Dec 2021ICLR 2022 4arXiv:2112.07804archive 2025-07-28

Zhisheng Xiao, Karsten Kreis, Arash Vahdat

A wide variety of deep generative models has been developed in the past decade. Yet, these models often struggle with simultaneously addressing three key requirements including: high sample quality, mode coverage, and fast sampling. We call the challenge imposed by these requirements the generative learning trilemma, as the existing models often trade some of them for others. Particularly, denoising diffusion models have shown impressive sample quality and diversity, but their expensive sampling does not yet allow them to be applied in many real-world applications. In this paper, we argue that slow sampling in these models is fundamentally attributed to the Gaussian assumption in the denoising step which is justified only for small step sizes. To enable denoising with large steps, and hence, to reduce the total number of denoising steps, we propose to model the denoising distribution using a complex multimodal distribution. We introduce denoising diffusion generative adversarial networks (denoising diffusion GANs) that model each denoising step using a multimodal conditional GAN. Through extensive evaluations, we show that denoising diffusion GANs obtain sample quality and diversity competitive with original diffusion models while being 2000× faster on the CIFAR-10 dataset. Compared to traditional GANs, our model exhibits better mode coverage and sample diversity. To the best of our knowledge, denoising diffusion GAN is the first model that reduces sampling cost in diffusion models to an extent that allows them to be applied to real-world applications inexpensively. Project page and code can be found at https://nvlabs.github.io/denoising-diffusion-gan

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 (NVlabs/denoising-diffusion-gan) is linked to this paper; the 12 samples below come from 1 community repository. Syntology harvested code from NVlabs/denoising-diffusion-gan for another paper.

NVlabs/denoising-diffusion-gan: Syntology's graph links these samples to Quantum latent distributions in deep generative models (arXiv:2508.19857; that paper's own run record: 11 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 2 honoured, 1 violated, 2 with no contract checked; 6 where Syntology's instrument failed) · 3 unverified); nothing checks that they implement this paper's method.

Syntology 12 code samples harvested from 1 repository linked to this paper: 6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 1 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 6 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: community (archive-listed): 12 samples from 1 repository, 6 ran (6 with no instrument failure; 0 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 4 of its repositories that Syntology harvested for other papers:

Levels written on 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 1 of the 6 samples that ran has no recorded date.

NVlabs/denoising-diffusion-gan officialmentioned on GitHubpytorchNOASSERTIONSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Quantum latent distributions in deep generative models (arXiv:2508.19857; that paper's own run record: 11 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 2 honoured, 1 violated, 2 with no contract checked; 6 where Syntology's instrument failed) · 3 unverified); nothing checks that they implement this paper's method. report
keonlee9420/DiffGAN-TTS mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Denoising Diffusion Probabilistic Models (arXiv:2006.11239; that paper's own run record: 186 ran (of which 81 constructed an object rather than computing a result; 142 with no instrument failure: 20 honoured, 8 violated, 114 with no contract checked; 44 where Syntology's instrument failed) · 67 unverified); nothing checks that they implement this paper's method. report
komyeongjin/specdiff-gan mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to DiffGAN-TTS: High-Fidelity and Efficient Text-to-Speech with Denoising Diffusion GANs (arXiv:2201.11972; that paper's own run record: 6 ran (of which 2 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 2 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
revsic/torch-diffusion-wavegan mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to DiffWave: A Versatile Diffusion Model for Audio Synthesis (arXiv:2009.09761; that paper's own run record: 20 ran (of which 11 constructed an object rather than computing a result; 13 with no instrument failure: 1 honoured, 0 violated, 12 with no contract checked; 7 where Syntology's instrument failed) · 13 unverified); nothing checks that they implement this paper's method. report
taki0112/denoising-diffusion-gan-Tensorflow tfMITSyntology: 12 samples, 6 ran (0 instrument-failed) · 6 unverified 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

12 samples harvested: 6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 1 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 6 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · violated contract
5ran
6unverified

Licence: 1 of the 12 samples is pointer only, meaning Syntology does not serve that copy's text. For that sample, 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 taki0112/denoising-diffusion-gan-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. 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.

taki0112/denoising-diffusion-gan-Tensorflow community (archive-listed) 12 samples, 6 ran (0 instrument-failed) · 6 unverified
adjust_dynamic_range in 7 papers src/utils.py ran MIT (permissive) · 580ee01331365cc1 · report fixture: signature images:EagerTensor/4/float, range_in:tuple/1/float, range_out:tuple/1/float, out_dtype:DType/0/? · returned EagerTensor · level recorded 2026-09-24
compute_paddings src/cuda/upfirdn_2d.py ran MIT (permissive) · 809eb892e3916de5 · report fixture: signature resample_kernel:ndarray/1/float, up:bool/0/bool, down:bool/0/bool, kernel_size:int/0/int, factor:int/0/int, gain:float/0/float · returned tuple · level recorded 2026-09-24
preprocess_fit_train_image src/utils.py ran MIT (permissive) · d1193687d98d105e · report fixture: signature images:EagerTensor/3/float · returned EagerTensor · level recorded 2026-09-24
torch_normalization src/evaluation/frechet_inception_distance.py ran MIT (permissive) · bd7cdd9c69d44405 · report fixture: signature x:EagerTensor/4/float · returned EagerTensor · level recorded 2026-09-24
var_func_geometric in 8 papers src/ops.py ran · violated contract fingerprinted MIT (permissive) here; the stored copy is pointer only · 65846ba5525a01b5 · report fixture: signature t:float/0/float, beta_min:float/0/float, beta_max:float/0/float · returned float · level recorded, date not recorded
var_func_vp in 8 papers src/ops.py ran MIT (permissive) · bfea3e00a742cd88 · report fixture: signature t:EagerTensor/0/float, beta_min:EagerTensor/0/float, beta_max:EagerTensor/0/float · returned EagerTensor · level recorded 2026-09-24
downsample_2d in 11 papers src/cuda/upfirdn_2d_ref.py unverified MIT (permissive) · 66260595985bc021 · report
get_plugin in 11 papers src/cuda/custom_ops.py unverified MIT (permissive) · 410f4fa3e787a8a1 · report
inception_processing src/evaluation/frechet_inception_distance.py unverified MIT (permissive) · 790a9397a9de1ad7 · report
random_flip_left_right src/utils.py unverified MIT (permissive) · 6fd5e92319c6c9fa · report
upsample_2d in 12 papers src/cuda/upfirdn_2d_ref.py unverified MIT (permissive) · 09f6c79e38f3a845 · report

Tasks

DiversityImage Generation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Generation CelebA-HQ 256x256 DDGAN FID 7.64 #9 of 19 Archive leaderboard report
Image Generation LSUN Churches 256 x 256 DDGAN FID 5.25 #19 of 27 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

Diffusion

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