Papers › Diffusion-GAN: Training GANs with Diffusion

Diffusion-GAN: Training GANs with Diffusion

5 Jun 2022arXiv:2206.02262archive 2025-07-28

Zhendong Wang, Huangjie Zheng, Pengcheng He, Weizhu Chen, Mingyuan Zhou

Generative adversarial networks (GANs) are challenging to train stably, and a promising remedy of injecting instance noise into the discriminator input has not been very effective in practice. In this paper, we propose Diffusion-GAN, a novel GAN framework that leverages a forward diffusion chain to generate Gaussian-mixture distributed instance noise. Diffusion-GAN consists of three components, including an adaptive diffusion process, a diffusion timestep-dependent discriminator, and a generator. Both the observed and generated data are diffused by the same adaptive diffusion process. At each diffusion timestep, there is a different noise-to-data ratio and the timestep-dependent discriminator learns to distinguish the diffused real data from the diffused generated data. The generator learns from the discriminator's feedback by backpropagating through the forward diffusion chain, whose length is adaptively adjusted to balance the noise and data levels. We theoretically show that the discriminator's timestep-dependent strategy gives consistent and helpful guidance to the generator, enabling it to match the true data distribution. We demonstrate the advantages of Diffusion-GAN over strong GAN baselines on various datasets, showing that it can produce more realistic images with higher stability and data efficiency than state-of-the-art GANs.

PaperPDFCodeCode Syntology ranMethod as code

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.

Syntology holds a reference implementation of Diffusion-GAN, generated from the paper text (not the authors' code), at level 3 on Syntology's ladder: V2 “two implementations GENERATED from the paper's signature and spec agree numerically (1e-6) on fixture inputs” “neither of the two ever read the authors' own code, so V2 measures how unambiguously the paper specifies the method, not fidelity to the authors' implementation (measured 2026-09-11, commit 75eaa77: cross_checked_by is a second LLM on 2,628 of 2,831 served samples)”; V3 “paper-derived property tests pass on both of those same two generations.” (quoted from Syntology's server card). For this implementation, level 3 is recorded, but its report lists no property test that passed on both. No rung compares this code against the authors' implementation. For agents: get_reference_implementation(name='Diffusion-GAN') (how to connect); the free check have('2206.02262') needs no token.

For agents, on Syntology's MCP service (how to connect):

Code

No sample from the archive's official repository (Zhendong-Wang/Diffusion-GAN) is linked to this paper; the 18 samples below come from 2 community repositories. Syntology harvested code from Zhendong-Wang/Diffusion-GAN for another paper.

Zhendong-Wang/Diffusion-GAN: Syntology's graph links these samples to Exposing flaws of generative model evaluation metrics and their unfair treatment of... (arXiv:2306.04675; that paper's own run record: 53 ran (of which 0 constructed an object rather than computing a result; 30 with no instrument failure: 6 honoured, 1 violated, 23 with no contract checked; 23 where Syntology's instrument failed) · 10 unverified); nothing checks that they implement this paper's method.

Syntology 18 code samples harvested from 2 repositories linked to this paper: 15 ran (of which 1 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 1 violated, 4 with no contract checked; 9 where Syntology's instrument failed) · 3 unverified. Where Syntology's instrument failed: 6 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): 18 samples from 2 repositories, 15 ran (6 with no instrument failure; 9 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 2 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 5 of the 15 samples that ran have no recorded date.

Zhendong-Wang/Diffusion-GAN officialmentioned in papermentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Exposing flaws of generative model evaluation metrics and their unfair treatment of... (arXiv:2306.04675; that paper's own run record: 53 ran (of which 0 constructed an object rather than computing a result; 30 with no instrument failure: 6 honoured, 1 violated, 23 with no contract checked; 23 where Syntology's instrument failed) · 10 unverified); nothing checks that they implement this paper's method. report
jegzheng/truncated-diffusion-probabilistic-models mentioned on GitHubpytorchMITSyntology: 15 samples, 13 ran (9 instrument-failed) · 2 unverified report
mingyuanzhou/sid-lsg mentioned on GitHubpytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Long and Short Guidance in Score identity Distillation for One-Step Text-to-Image Generation (arXiv:2406.01561; that paper's own run record: 19 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 4 honoured, 1 violated, 4 with no contract checked; 10 where Syntology's instrument failed) · 5 unverified); nothing checks that they implement this paper's method. report
zhendong-wang/prompt-diffusion mentioned on GitHubpytorchSyntology: 3 samples, 2 ran (0 instrument-failed) · 1 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

18 samples harvested: 15 ran (of which 1 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 1 violated, 4 with no contract checked; 9 where Syntology's instrument failed) · 3 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.

1ran · honoured contract
1ran · violated contract
6ran · our draft was wrong
3ran; the contract check could not run
4ran
3unverified

Licence: 8 of the 18 samples are pointer only, meaning Syntology does not serve that copy's text. For 8 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 2 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.

jegzheng/truncated-diffusion-probabilistic-models community (archive-listed) 15 samples, 13 ran (9 instrument-failed) · 2 unverified
Normalize in 154 papers models/diffusion.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · c3a6b977022957cb · report fixture: signature in_channels:int/0/int · returned GroupNorm · level recorded, date not recorded
check_integrity in 37 papers datasets/utils.py ran · violated contract fingerprinted MIT (permissive) here; the stored copy is pointer only · 7345763c9b9300fb · report fixture: signature fpath:str/0/str, md5:str/0/str · returned bool · level recorded 2026-09-25
compute_alpha in 26 papers functions/denoising.py ran · our draft was wrong MIT (permissive) · 9215fb189fbfb9f4 · report fixture: signature beta:Tensor/1/float, t:Tensor/1/int · returned Tensor · level recorded 2026-09-22
ddpm_steps functions/denoising.py ran MIT (permissive) · 4d1f19f21237eb7d · report fixture: signature x:Tensor/4/float, seq:Tensor/1/int, model:callable/0/?, b:Tensor/1/float · returned tuple · level recorded 2026-09-25
generalized_steps in 7 papers functions/denoising.py ran; the contract check could not run (RAISES) MIT (permissive) · d47e6201b6d56d24 · report fixture: returned tuple · level recorded 2026-09-22
get_beta_schedule in 66 papers runners/diffusion.py ran · honoured contract MIT (permissive) here; the stored copy is pointer only · ca0cea1ca1eeec89 · report fixture: signature beta_schedule:str/0/str, beta_start:float/0/float, beta_end:float/0/float, num_diffusion_timesteps:int/0/int · returned ndarray · level recorded, date not recorded
get_timestep_embedding in 138 papers
census: 11 implementations from 15 papers, 5 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 1 of 2, arg 1: rank 1, kind int, dtype int64
models/diffusion.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant MIT (permissive) · cb49209c125de1b4 · report fixture: signature timesteps:Tensor/1/int, embedding_dim:int/0/int · returned Tensor · level recorded, date not recorded
list_dir in 22 papers datasets/utils.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · 915e1c6c38494be9 · report fixture: signature root:str/0/str, prefix:bool/0/bool · returned list · level recorded 2026-09-22
list_files in 33 papers datasets/utils.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · 208e196e9582a9a6 · report fixture: signature root:str/0/str, suffix:str/0/str, prefix:bool/0/bool · returned list · level recorded 2026-09-22
md5_hash in 33 papers functions/ckpt_util.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · 07d90bd6ae1be7db · report fixture: signature path:str/0/str · returned str · level recorded 2026-09-22
noise_estimation_loss in 19 papers functions/losses.py ran MIT (permissive) · 36a45cceb1209d2f · report fixture: signature model:callable/0/?, x0:Tensor/4/float, t:Tensor/1/int, e:Tensor/4/float, b:Tensor/1/float, keepdim:bool/0/bool · returned Tensor · level recorded 2026-09-24
nonlinearity in 140 papers
census: 4 implementations from 11 papers, 1 distinct output on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32
models/diffusion.py ran · our draft was wrong fingerprinted MIT (permissive) · 3137073275f8c21a · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded, date not recorded
torch2hwcuint8 in 6 papers runners/diffusion.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted MIT (permissive) here; the stored copy is pointer only · c27a10ca9f6b75f3 · report fixture: signature x:Tensor/2/float, clip:bool/0/bool · returned Tensor · level recorded, date not recorded
get_ckpt_path in 30 papers functions/ckpt_util.py unverified MIT (permissive) here; the stored copy is pointer only · c37fc656e8bb2a80 · report
zhendong-wang/prompt-diffusion community (archive-listed) 3 samples, 2 ran (0 instrument-failed) · 1 unverified
DiffusionWrapper in 5 papers ldm/models/diffusion/ddpm.py ran Apache-2.0 (permissive) · 46449d701844def0 · report fixture: signature x:Tensor/4/float, t:Tensor/1/int, c_concat:NoneType/0/?, c_crossattn:list/1/Tensor, c_adm:NoneType/0/? · returned Tensor · level recorded 2026-09-24
LitEma ldm/models/diffusion/ddpm.py ran · metamorphic tier: deterministic Apache-2.0 (permissive) · 9464846a66de7376 · report fixture: returned LitEma · level recorded 2026-09-22
DDPM in 15 papers ldm/models/diffusion/ddpm.py unverified Apache-2.0 (permissive) · af2b53bfe0d458a6 · report

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. For a generated assembly, an independent peer is a second implementation generated separately from the same paper text; neither implementation read the authors' code. At level 2 the two agreed numerically on the fixture's inputs; level 3 is recorded when property tests derived from the paper also passed on both, and each level 3 card prints how many its report lists. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it. A generated assembly's label was set when its code was generated for the method, and no model judged it; its card prints it as "by construction" or "not judged by a model". Where an assembly's phrase has no constructed figure, a brick that ran is not among the harvested samples this build reads, and whether a brick's run only constructed an object is read from that brick's harvested sample, so the figure was not counted; it does not say there were none.

2 assemblies on this paper: 1 harvested, 1 generated.

generated Assembly for Diffusion-GAN (graph method: Diffusion-GAN), generated from the paper text, not the repository's code. 1 brick; individually on a fixture: 1 ran (1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified. Ran end-to-end against an independent peer; level 3 is recorded, but its report lists no property test that passed on both.

label matches by construction: the code was generated for this method (not judged by a model)

  1. diffusion_forward_sample entry · level 3 · ran · honoured contract · 48ca655a72630e185278bab6c2c99e300719b16786eaea1d0190ba33b03020ff

harvested Assembly for Diffusion-GAN (graph method: Diffusion-GAN). 11 bricks; individually on a fixture: 9 ran (of which 1 constructed an object rather than computing a result; 6 with no instrument failure: 2 honoured, 2 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified. The assembly has not been run end-to-end.

  1. DDPM entry · level 0 · unverified · af2b53bfe0d458a6
  2. DiffusionWrapper helper · level 1 · ran · 46449d701844def0
  3. LitEma helper · level 1 · ran · 9464846a66de7376
  4. count_params helper · level 1 · ran · honoured contract · 613acd72145a95f2
  5. default helper · level 1 · ran · violated contract · fbf9ec7be545688e
  6. exists helper · level 1 · ran · violated contract · 608e364a9d2376a3
  7. extract_into_tensor helper · level 1 · ran · our draft was wrong · a15cfd7932844ef9
  8. make_beta_schedule helper · level 1 · ran · honoured contract · 3bd7e0cdbd131fdb
  9. noise_like helper · level 1 · ran; the contract check could not run · 104973640b230918
  10. instantiate_from_config helper · level 0 · unverified · ef52d142b2c30ac2
  11. get_obj_from_str helper · level 1 · ran · our draft was wrong · 221b2d116fdf1032

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2206.02262") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Image Generation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Generation AFHQ Cat Diffusion InsGen FID 2.40 #5 of 8 Archive leaderboard report
Image Generation AFHQ Dog Diffusion InsGen FID 4.83 #3 of 6 Archive leaderboard report
Image Generation AFHQ Wild Diffusion InsGen FID 1.51 #3 of 5 Archive leaderboard report
Image Generation CelebA 64x64 Diffusion StyleGAN2 FID 1.69 #4 of 39 Archive leaderboard report
Image Generation FFHQ 1024 x 1024 Diffusion StyleGAN2 FID 2.83 #6 of 20 Archive leaderboard report
Image Generation LSUN Bedroom 256 x 256 Diffusion ProjectedGAN FID 1.43 #1 of 32 Archive leaderboard report
Image Generation LSUN Bedroom 256 x 256 Diffusion StyleGAN2 FID 3.65 #8 of 32 Archive leaderboard report
Image Generation LSUN Bedroom 256 x 256 Diffusion ProjectedGAN (DINOv2) FD 547.61 #26 of 32 Archive leaderboard report
Image Generation LSUN Bedroom 256 x 256 Diffusion ProjectedGAN (DINOv2) Precision 0.79 #26 of 32 Archive leaderboard report
Image Generation LSUN Bedroom 256 x 256 Diffusion ProjectedGAN (DINOv2) Recall 0.28 #26 of 32 Archive leaderboard report
Image Generation LSUN Churches 256 x 256 Diffusion ProjectedGAN FID 1.85 #3 of 27 Archive leaderboard report
Image Generation LSUN Churches 256 x 256 Diffusion StyleGAN2 FID 3.17 #7 of 27 Archive leaderboard report
Image Generation STL-10 Diffusion ProjectedGAN FID 6.91 #1 of 31 Archive leaderboard report
Image Generation STL-10 Diffusion StyleGAN2 FID 11.53 #4 of 31 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