Papers › Diffusion Models Beat GANs on Image Synthesis

Diffusion Models Beat GANs on Image Synthesis

11 May 2021NeurIPS 2021 12arXiv:2105.05233archive 2025-07-28

Prafulla Dhariwal, Alex Nichol

We show that diffusion models can achieve image sample quality superior to the current state-of-the-art generative models. We achieve this on unconditional image synthesis by finding a better architecture through a series of ablations. For conditional image synthesis, we further improve sample quality with classifier guidance: a simple, compute-efficient method for trading off diversity for fidelity using gradients from a classifier. We achieve an FID of 2.97 on ImageNet 128×128, 4.59 on ImageNet 256×256, and 7.72 on ImageNet 512×512, and we match BigGAN-deep even with as few as 25 forward passes per sample, all while maintaining better coverage of the distribution. Finally, we find that classifier guidance combines well with upsampling diffusion models, further improving FID to 3.94 on ImageNet 256×256 and 3.85 on ImageNet 512×512. We release our code at https://github.com/openai/guided-diffusion

PaperPDFConference PDFCodeCode 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.

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

Code

No sample from the archive's official repository (openai/guided-diffusion) is linked to this paper; the 50 samples below come from 15 community repositories. Syntology harvested code from openai/guided-diffusion for another paper.

openai/guided-diffusion: Syntology's graph links these samples to Label-Efficient Hyperspectral Image Classification via Spectral FiLM Modulation of... (arXiv:2512.03430; that paper's own run record: 16 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 4 honoured, 0 violated, 0 with no contract checked; 12 where Syntology's instrument failed) · 6 unverified); nothing checks that they implement this paper's method.

Syntology 50 code samples harvested from 15 repositories linked to this paper: 33 ran (of which 13 constructed an object rather than computing a result; 29 with no instrument failure: 4 honoured, 0 violated, 25 with no contract checked; 4 where Syntology's instrument failed) · 17 unverified. Where Syntology's instrument failed: 4 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 50 samples from 15 repositories, 33 ran (29 with no instrument failure; 4 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 between 2026-09-22 and 2026-09-24 (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.

openai/guided-diffusion officialmentioned in papermentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Label-Efficient Hyperspectral Image Classification via Spectral FiLM Modulation of... (arXiv:2512.03430; that paper's own run record: 16 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 4 honoured, 0 violated, 0 with no contract checked; 12 where Syntology's instrument failed) · 6 unverified); nothing checks that they implement this paper's method. report
Janspiry/Palette-Image-to-Image-Diffusion-Models mentioned on GitHubpytorchSyntology: 12 samples, 7 ran (1 instrument-failed) · 5 unverified report
LouisRouss/Diffusion-Based-Model-for-Colorization mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
ML-GSAI/EGSDE mentioned on GitHubpytorchSyntology: not harvested report
afiaka87/clip-guided-diffusion mentioned on GitHubpytorchMITSyntology: 11 samples, 7 ran (0 instrument-failed) · 4 unverified report
alexmaols/elucd mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
clu0/unet.cu mentioned on GitHubpytorchSyntology: 8 samples, 5 ran (1 instrument-failed) · 3 unverified report
crosszamirski/guided-i2i mentioned on GitHubpytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Class-Guided Image-to-Image Diffusion: Cell Painting from Brightfield Images with Class Labels (arXiv:2303.08863; that paper's own run record: 14 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 4 honoured, 0 violated, 1 with no contract checked; 9 where Syntology's instrument failed) · 3 unverified); nothing checks that they implement this paper's method. report
crowsonkb/guided-diffusion mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
deepfake-study/guided-diffusion mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
facebookresearch/rcdm mentioned on GitHubpytorchSyntology: 1 sample, 0 ran · 1 unverified report
filipbasara0/simple-diffusion mentioned on GitHubpytorchSyntology: 2 samples, 2 ran (0 instrument-failed) · 0 unverified report
forever208/adm-es mentioned on GitHubpytorchMITSyntology: 1 sample, 0 ran · 1 unverified report
forever208/ddpm-ip mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Input Perturbation Reduces Exposure Bias in Diffusion Models (arXiv:2301.11706; that paper's own run record: 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
jerryyann/dpi mentioned on GitHubpytorchSyntology: 1 sample, 0 ran · 1 unverified report
jogo175/treediffusion mentioned on GitHubpytorchSyntology: 2 samples, 2 ran (1 instrument-failed) · 0 unverified report
jychoi118/p2-weighting mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
lucidrains/ddpm-proteins mentioned on GitHubpytorchSyntology: 3 samples, 3 ran (0 instrument-failed) · 0 unverified report
royg27/BIGRoC mentioned on GitHubpytorchSyntology: not harvested report
sangyun884/fast-ode mentioned on GitHubpytorchSyntology: 4 samples, 2 ran (1 instrument-failed) · 2 unverified report
soobin-um/minority-guidance mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Don't Play Favorites: Minority Guidance for Diffusion Models (arXiv:2301.12334; that paper's own run record: 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. 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

50 samples harvested: 33 ran (of which 13 constructed an object rather than computing a result; 29 with no instrument failure: 4 honoured, 0 violated, 25 with no contract checked; 4 where Syntology's instrument failed) · 17 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.

4ran · honoured contract
4ran · our draft was wrong
25ran
17unverified

Licence: 19 of the 50 samples are pointer only, meaning Syntology does not serve that copy's text. For 3 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 15 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”. For 6 samples that ran, the graph records a signature this page does not show: for a class the fixture built without calling, the harness called the object with inputs it made up itself, so the recorded signature is the harness's probe, not the fixture's arguments. “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.

Janspiry/Palette-Image-to-Image-Diffusion-Models community (archive-listed) 12 samples, 7 ran (1 instrument-failed) · 5 unverified
AttentionBlock in 69 papers models/guided_diffusion_modules/unet.py ran MIT (permissive) · 8ad49f3a007cc16c · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-24
Downsample in 58 papers models/guided_diffusion_modules/unet.py ran fingerprinted MIT (permissive) · 98fe2137d5940de7 · report fixture: returned Downsample · level recorded 2026-09-22
QKVAttention in 25 papers models/guided_diffusion_modules/unet.py ran MIT (permissive) · 8a4eb07344b8d7b7 · report fixture: signature qkv:Tensor/3/float · returned Tensor · level recorded 2026-09-24
QKVAttentionLegacy in 20 papers models/guided_diffusion_modules/unet.py ran MIT (permissive) · 9fd7822b33474816 · report fixture: signature qkv:Tensor/3/float · returned Tensor · level recorded 2026-09-24
SiLU in 8 papers
census: 5 implementations from 5 papers, 1 distinct output on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32
models/guided_diffusion_modules/unet.py ran · metamorphic tier: invariant fingerprinted MIT (permissive) · 1da15c720fdd1b92 · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-22
Upsample in 77 papers models/guided_diffusion_modules/unet.py ran fingerprinted MIT (permissive) · 5740a56d8f8c2afb · report fixture: returned Upsample · level recorded 2026-09-22
gamma_embedding models/guided_diffusion_modules/unet.py ran · our draft was wrong fingerprinted MIT (permissive) · c13200b52f85fb0b · report fixture: signature gammas:Tensor/1/float, dim:int/0/int, max_period:int/0/int · returned Tensor · level recorded 2026-09-22
EmbedBlock models/guided_diffusion_modules/unet.py unverified MIT (permissive) · 783b16025841a763 · report
EmbedSequential models/guided_diffusion_modules/unet.py unverified MIT (permissive) · d34634a4460e18ca · report
UNet in 40 papers models/guided_diffusion_modules/unet.py unverified MIT (permissive) · a21b0ea52f83ee5b · report
count_flops_attn models/guided_diffusion_modules/unet.py unverified MIT (permissive) · c19cbce17b969d76 · report
LouisRouss/Diffusion-Based-Model-for-Colorization community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
GaussianDiffusion in 61 papers src/diffusion.py ran · metamorphic tier: deterministic no licence file found · pointer only · d985629e3d6b71c4 · report fixture: returned GaussianDiffusion · level recorded 2026-09-22
afiaka87/clip-guided-diffusion community (archive-listed) 11 samples, 7 ran (0 instrument-failed) · 4 unverified
alphanumeric_filter cgd/script_util.py ran fingerprinted MIT (permissive) · 8caf32fce73095ab · report fixture: signature s:str/0/str · returned str · level recorded 2026-09-24
fetch in 11 papers cgd/script_util.py ran MIT (permissive) · 9f95b3f3132f00a1 · report fixture: signature url_or_path:str/0/str · returned BufferedReader · level recorded 2026-09-24
parse_prompt in 9 papers cgd/script_util.py ran fingerprinted MIT (permissive) · 0a8c631b651f4813 · report fixture: signature prompt:str/0/str · returned tuple · level recorded 2026-09-24
range_loss cgd/losses.py ran fingerprinted MIT (permissive) · 4284713ef6b7ead5 · report fixture: signature input:Tensor/4/float · returned Tensor · level recorded 2026-09-24
spherical_dist_loss in 6 papers cgd/losses.py ran fingerprinted MIT (permissive) · 5bd6891b5cc4506d · report fixture: signature x:Tensor/2/float, y:Tensor/2/float · returned Tensor · level recorded 2026-09-24
support_sz cgd/ResizeRight/interp_methods.py ran MIT (permissive) here; the stored copy is pointer only · eb3584d528a35911 · report fixture: signature sz:int/0/int · returned function · level recorded 2026-09-24
tv_loss in 17 papers cgd/losses.py ran fingerprinted MIT (permissive) · 4d1cb7924c3fd431 · report fixture: signature input:Tensor/4/float · returned Tensor · level recorded 2026-09-24
cubic in 19 papers cgd/ResizeRight/interp_methods.py unverified MIT (permissive) here; the stored copy is pointer only · 69f91d76e488739d · report
get_field_of_view cgd/ResizeRight/resize_right.py unverified MIT (permissive) · 1353cd3aa1bf5207 · report
get_projected_grid cgd/ResizeRight/resize_right.py unverified MIT (permissive) · 9aa17993a0cc9ce7 · report
set_framework_dependencies cgd/ResizeRight/interp_methods.py unverified MIT (permissive) here; the stored copy is pointer only · ae962b80c12bc789 · report
alexmaols/elucd community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
GaussianDiffusion in 61 papers DDPM/guided_diffusion/gaussian_diffusion.py ran MIT (permissive) · 2461ad8a60086135 · report fixture: returned GaussianDiffusion · level recorded 2026-09-22
clu0/unet.cu community (archive-listed) 8 samples, 5 ran (1 instrument-failed) · 3 unverified
AttentionBlock in 69 papers dev/unet.py ran · metamorphic tier: deterministic fingerprinted no licence file found · pointer only · 26bd849e8995e2a1 · report fixture: returned AttentionBlock · level recorded 2026-09-22
Downsample in 58 papers dev/unet.py ran · metamorphic tier: deterministic fingerprinted no licence file found · pointer only · 2b4dc2218b2a8487 · report fixture: returned Downsample · level recorded 2026-09-22
QKVAttention in 25 papers dev/unet.py ran no licence file found · pointer only · 2384e76ad3ea9835 · report fixture: signature qkv:Tensor/3/float · returned Tensor · level recorded 2026-09-24
Upsample in 77 papers dev/unet.py ran · metamorphic tier: deterministic fingerprinted no licence file found · pointer only · bd5e9f697bbd1762 · report fixture: returned Upsample · level recorded 2026-09-22
timestep_embedding in 79 papers
census: 22 implementations from 27 papers, 6 distinct outputs across 2 buckets, one shared input per bucket
dev/unet.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 5cf36092e6ff1604 · report fixture: signature timesteps:Tensor/1/float, dim:int/0/int, max_period:int/0/int · returned Tensor · level recorded 2026-09-22
ResBlock in 127 papers
census: 6 implementations from 5 papers, 6 distinct outputs across 2 buckets, one shared input per bucket
dev/unet.py unverified no licence file found · pointer only · 4a5965fce1c935c5 · report
TimestepEmbedSequential in 28 papers dev/unet.py unverified no licence file found · pointer only · d9ce54d68567e11c · report
UNetModel in 23 papers dev/unet.py unverified no licence file found · pointer only · 0e94d8645e22f0f0 · report
crowsonkb/guided-diffusion community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
GaussianDiffusion in 61 papers guided_diffusion/gaussian_diffusion.py ran MIT (permissive) · 45a6c1579d9a484c · report fixture: returned GaussianDiffusion · level recorded 2026-09-22
deepfake-study/guided-diffusion community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
GaussianDiffusion in 61 papers guided_diffusion/gaussian_diffusion.py ran MIT (permissive) · 7ee620bcf78b28ac · report fixture: returned GaussianDiffusion · level recorded 2026-09-22
facebookresearch/rcdm community (archive-listed) 1 sample, 0 ran · 1 unverified
GaussianDiffusion in 61 papers guided_diffusion_rcdm/gaussian_diffusion.py unverified MIT (permissive) · 292ca31b16848f08 · report
filipbasara0/simple-diffusion community (archive-listed) 2 samples, 2 ran (0 instrument-failed) · 0 unverified
DDIMScheduler simple_diffusion/scheduler/ddim.py ran MIT (permissive) · 13e6972b5fc13010 · report fixture: returned DDIMScheduler · level recorded 2026-09-22
cosine_beta_schedule in 76 papers simple_diffusion/scheduler/ddim.py ran · honoured contract fingerprinted MIT (permissive) · b236cc9fdeeb2655 · report fixture: signature timesteps:int/0/int, beta_start:float/0/float, beta_end:float/0/float, s:float/0/float · returned Tensor · level recorded 2026-09-22
forever208/adm-es community (archive-listed) 1 sample, 0 ran · 1 unverified
GaussianDiffusion in 61 papers guided_diffusion/gaussian_diffusion.py unverified MIT (permissive) · feb8aaa0fa488906 · report
jerryyann/dpi community (archive-listed) 1 sample, 0 ran · 1 unverified
GaussianDiffusion in 61 papers guided_diffusion/gaussian_diffusion.py unverified no licence file found · pointer only · 784cb6f7dc2a2b74 · report
jogo175/treediffusion community (archive-listed) 2 samples, 2 ran (1 instrument-failed) · 0 unverified
SpacedDiffusion in 12 papers models/diffusion/spaced_diff.py ran · metamorphic tier: deterministic fingerprinted no licence file found · pointer only · 9193321e03a428a0 · report fixture: returned SpacedDiffusion · level recorded 2026-09-22
extract in 149 papers
census: 9 implementations from 12 papers, 4 distinct outputs across 3 buckets, one shared input per bucket this sample: bucket 1 of 3, arg 1: rank 1, kind float, dtype float32 · arg 2: rank 1, kind int, dtype int64
models/diffusion/spaced_diff.py ran · our draft was wrong no licence file found · pointer only · 803681ed62fd000a · report fixture: signature a:Tensor/1/float, t:Tensor/1/int, x_shape:tuple/1/int · returned Tensor · level recorded 2026-09-22
jychoi118/p2-weighting community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
GaussianDiffusion in 61 papers guided_diffusion/gaussian_diffusion.py ran MIT (permissive) · 87e380d90fe4bb73 · report fixture: returned GaussianDiffusion · level recorded 2026-09-22
lucidrains/ddpm-proteins community (archive-listed) 3 samples, 3 ran (0 instrument-failed) · 0 unverified
GaussianDiffusion in 61 papers ddpm_proteins/ddpm_proteins.py ran · metamorphic tier: deterministic MIT (permissive) · 48680835112f36e1 · report fixture: returned GaussianDiffusion · level recorded 2026-09-22
broadcat in 21 papers ddpm_proteins/ddpm_proteins.py ran · honoured contract MIT (permissive) · f50a8d20efb35c68 · report fixture: signature tensors:list/1/Tensor, dim:int/0/int · returned Tensor · level recorded 2026-09-22
cosine_beta_schedule in 76 papers ddpm_proteins/ddpm_proteins.py ran · honoured contract fingerprinted MIT (permissive) · d069cafc41670adf · report fixture: signature timesteps:int/0/int, s:float/0/float · returned ndarray · level recorded 2026-09-22
sangyun884/fast-ode community (archive-listed) 4 samples, 2 ran (1 instrument-failed) · 2 unverified
check_folder in 7 papers guided_diffusion/gaussian_diffusion.py ran · our draft was wrong no licence file found · pointer only · e21cebaf03604f02 · report fixture: signature log_dir:str/0/str · returned str · level recorded 2026-09-22
denorm in 23 papers guided_diffusion/gaussian_diffusion.py ran · honoured contract fingerprinted no licence file found · pointer only · f1c35d187bd5b161 · report fixture: signature t:Tensor/2/float · returned Tensor · level recorded 2026-09-22
GaussianDiffusion in 61 papers guided_diffusion/gaussian_diffusion.py unverified no licence file found · pointer only · 11af4361b4a2cb72 · report
tensor_imsave guided_diffusion/gaussian_diffusion.py unverified no licence file found · pointer only · 3f4c6747dee50c0b · 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. 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. Siblings are assemblies lifted from this paper in the same batch for the same method: alternative readings kept side by side; none replaces or supersedes another.

14 assemblies on this paper: 14 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).

14 sibling assemblies for classifier guidance (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another. Bricks printed for 12 of 14 sibling assemblies; the other 2 are listed with their counts; every brick is in this page's JSON twin.

harvested Assembly for classifier guidance (graph method: classifier guidance). 2 bricks; individually on a fixture: 1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; the one sample that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

one of 14 siblings

  1. GaussianDiffusion entry · level 1 · ran · d985629e3d6b71c4
  2. extract helper · level 0 · unverified · 09c8479d9a5b3e06

harvested Assembly for classifier guidance (graph method: classifier guidance). 9 bricks; individually on a fixture: 5 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 4 unverified. The assembly has not been run end-to-end.

one of 14 siblings

  1. GaussianDiffusion entry · level 0 · unverified · 784cb6f7dc2a2b74
  2. LossType helper · level 0 · unverified · 3dfb2574af178220
  3. ModelMeanType helper · level 0 · unverified · f1e863a92ff43943
  4. ModelVarType helper · level 0 · unverified · 9df953f617d68af1
  5. _extract_into_tensor helper · level 1 · ran; the contract check could not run · 47d10dfc019ed932
  6. discretized_gaussian_log_likelihood loss · level 1 · ran · our draft was wrong · cd33283d615fb3d7
  7. mean_flat helper · level 1 · ran · our draft was wrong · f6d7c009a8efb8b7
  8. normal_kl loss · level 1 · ran · honoured contract · cf2798b666b231ca
  9. approx_standard_normal_cdf helper · level 1 · ran · our draft was wrong · cfd76fd0d89574a4

harvested Assembly for classifier guidance (graph method: classifier guidance). 2 bricks; individually on a fixture: 2 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

one of 14 siblings

  1. SpacedDiffusion entry · level 1 · ran · 9193321e03a428a0
  2. extract helper · level 1 · ran · our draft was wrong · 803681ed62fd000a

harvested Assembly for classifier guidance (graph method: classifier guidance). 7 bricks; individually on a fixture: 6 ran (of which 1 constructed an object rather than computing a result; 5 with no instrument failure: 2 honoured, 2 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified. The assembly has not been run end-to-end.

one of 14 siblings

  1. GaussianDiffusion entry · level 1 · ran · 48680835112f36e1
  2. broadcat helper · level 1 · ran · honoured contract · f50a8d20efb35c68
  3. cosine_beta_schedule scheduler · level 1 · ran · honoured contract · d069cafc41670adf
  4. default helper · level 1 · ran · violated contract · fbf9ec7be545688e
  5. exists helper · level 1 · ran · violated contract · 608e364a9d2376a3
  6. extract helper · level 0 · unverified · 09c8479d9a5b3e06
  7. noise_like helper · level 1 · ran; the contract check could not run · 104973640b230918

harvested Assembly for classifier guidance (graph method: classifier guidance). 9 bricks; individually on a fixture: 5 ran (of which 3 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified. The assembly has not been run end-to-end.

one of 14 siblings

  1. UNetModel entry · level 0 · unverified · 0e94d8645e22f0f0
  2. AttentionBlock model · level 1 · ran · 26bd849e8995e2a1
  3. Downsample helper · level 1 · ran · 2b4dc2218b2a8487
  4. ResBlock model · level 0 · unverified · 4a5965fce1c935c5
  5. TimestepEmbedSequential model · level 0 · unverified · d9ce54d68567e11c
  6. Upsample helper · level 1 · ran · bd5e9f697bbd1762
  7. timestep_embedding helper · level 1 · ran · our draft was wrong · 5cf36092e6ff1604
  8. QKVAttention model · level 1 · ran · 2384e76ad3ea9835
  9. TimestepBlock helper · level 0 · unverified · 7958a01675377ce4

harvested Assembly for classifier guidance (graph method: classifier guidance). 3 bricks; individually on a fixture: 3 ran (of which 1 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

one of 14 siblings

  1. DDIMScheduler entry · level 1 · ran · 13e6972b5fc13010
  2. cosine_beta_schedule scheduler · level 1 · ran · honoured contract · b236cc9fdeeb2655
  3. unnormalize_to_zero_to_one helper · level 1 · ran · honoured contract · 97e1bbd232dfe092

harvested Assembly for classifier guidance (graph method: classifier guidance). 9 bricks; individually on a fixture: 6 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 4 where Syntology's instrument failed) · 3 unverified. The assembly has not been run end-to-end.

one of 14 siblings

  1. GaussianDiffusion entry · level 1 · ran · 7ee620bcf78b28ac
  2. LossType helper · level 0 · unverified · 3dfb2574af178220
  3. ModelMeanType helper · level 0 · unverified · f1e863a92ff43943
  4. ModelVarType helper · level 0 · unverified · 9df953f617d68af1
  5. _extract_into_tensor helper · level 1 · ran; the contract check could not run · 47d10dfc019ed932
  6. discretized_gaussian_log_likelihood helper · level 1 · ran · our draft was wrong · cd33283d615fb3d7
  7. mean_flat helper · level 1 · ran · our draft was wrong · f6d7c009a8efb8b7
  8. normal_kl helper · level 1 · ran · honoured contract · cf2798b666b231ca
  9. approx_standard_normal_cdf helper · level 1 · ran · our draft was wrong · cfd76fd0d89574a4

harvested Assembly for classifier guidance (graph method: classifier guidance). 9 bricks; individually on a fixture: 6 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 4 where Syntology's instrument failed) · 3 unverified. The assembly has not been run end-to-end.

one of 14 siblings

  1. GaussianDiffusion entry · level 1 · ran · 45a6c1579d9a484c
  2. LossType loss · level 0 · unverified · 3dfb2574af178220
  3. ModelMeanType helper · level 0 · unverified · f1e863a92ff43943
  4. ModelVarType helper · level 0 · unverified · 9df953f617d68af1
  5. _extract_into_tensor helper · level 1 · ran; the contract check could not run · 47d10dfc019ed932
  6. discretized_gaussian_log_likelihood helper · level 1 · ran · our draft was wrong · cd33283d615fb3d7
  7. mean_flat helper · level 1 · ran · our draft was wrong · f6d7c009a8efb8b7
  8. normal_kl helper · level 1 · ran · honoured contract · cf2798b666b231ca
  9. approx_standard_normal_cdf helper · level 1 · ran · our draft was wrong · cfd76fd0d89574a4

harvested Assembly for classifier guidance (graph method: classifier guidance). 9 bricks; individually on a fixture: 6 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 4 where Syntology's instrument failed) · 3 unverified. The assembly has not been run end-to-end.

one of 14 siblings

  1. GaussianDiffusion entry · level 1 · ran · 87e380d90fe4bb73
  2. LossType loss · level 0 · unverified · 3dfb2574af178220
  3. ModelMeanType helper · level 0 · unverified · f1e863a92ff43943
  4. ModelVarType helper · level 0 · unverified · 9df953f617d68af1
  5. _extract_into_tensor helper · level 1 · ran; the contract check could not run · 47d10dfc019ed932
  6. discretized_gaussian_log_likelihood helper · level 1 · ran · our draft was wrong · cd33283d615fb3d7
  7. mean_flat helper · level 1 · ran · our draft was wrong · f6d7c009a8efb8b7
  8. normal_kl helper · level 1 · ran · honoured contract · cf2798b666b231ca
  9. approx_standard_normal_cdf helper · level 1 · ran · our draft was wrong · cfd76fd0d89574a4

harvested Assembly for classifier guidance (graph method: classifier guidance). 9 bricks; individually on a fixture: 6 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 4 where Syntology's instrument failed) · 3 unverified. The assembly has not been run end-to-end.

one of 14 siblings

  1. GaussianDiffusion entry · level 1 · ran · 2461ad8a60086135
  2. LossType helper · level 0 · unverified · 3dfb2574af178220
  3. ModelMeanType helper · level 0 · unverified · f1e863a92ff43943
  4. ModelVarType helper · level 0 · unverified · 9df953f617d68af1
  5. _extract_into_tensor helper · level 1 · ran; the contract check could not run · 47d10dfc019ed932
  6. discretized_gaussian_log_likelihood helper · level 1 · ran · our draft was wrong · cd33283d615fb3d7
  7. mean_flat helper · level 1 · ran · our draft was wrong · f6d7c009a8efb8b7
  8. normal_kl helper · level 1 · ran · honoured contract · cf2798b666b231ca
  9. approx_standard_normal_cdf helper · level 1 · ran · our draft was wrong · cfd76fd0d89574a4

harvested Assembly for classifier guidance (graph method: classifier guidance). 17 bricks; individually on a fixture: 12 ran (of which 4 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 0 violated, 8 with no contract checked; 3 where Syntology's instrument failed) · 5 unverified. The assembly has not been run end-to-end.

one of 14 siblings

  1. UNet entry · level 0 · unverified · a21b0ea52f83ee5b
  2. AttentionBlock model · level 1 · ran · 8ad49f3a007cc16c
  3. Downsample helper · level 1 · ran · 98fe2137d5940de7
  4. EmbedSequential helper · level 0 · unverified · d34634a4460e18ca
  5. ResBlock model · level 0 · unverified · 694e1cddc1c9b050
  6. SiLU helper · level 1 · ran · 1da15c720fdd1b92
  7. Upsample helper · level 1 · ran · 5740a56d8f8c2afb
  8. gamma_embedding helper · level 1 · ran · our draft was wrong · c13200b52f85fb0b
  9. normalization helper · level 1 · ran · our draft was wrong · 5b31715a9b105926
  10. zero_module helper · level 1 · ran · our draft was wrong · 129b804760b3115f
  11. QKVAttention model · level 1 · ran · 8a4eb07344b8d7b7
  12. QKVAttentionLegacy model · level 1 · ran · 9fd7822b33474816
  13. checkpoint helper · level 1 · ran · honoured contract · aafea5a6cd6d98ab
  14. EmbedBlock helper · level 0 · unverified · 783b16025841a763
  15. GroupNorm32 helper · level 1 · ran · 426c2385fa431d9a
  16. count_flops_attn helper · level 0 · unverified · c19cbce17b969d76
  17. CheckpointFunction helper · level 1 · ran · 69360f5b0cc8f069

harvested Assembly for classifier guidance (graph method: classifier guidance). 9 bricks; individually on a fixture: 5 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 4 unverified. The assembly has not been run end-to-end.

one of 14 siblings

  1. GaussianDiffusion entry · level 0 · unverified · feb8aaa0fa488906
  2. LossType helper · level 0 · unverified · 3dfb2574af178220
  3. ModelMeanType helper · level 0 · unverified · f1e863a92ff43943
  4. ModelVarType helper · level 0 · unverified · 9df953f617d68af1
  5. _extract_into_tensor helper · level 1 · ran; the contract check could not run · 47d10dfc019ed932
  6. discretized_gaussian_log_likelihood helper · level 1 · ran · our draft was wrong · cd33283d615fb3d7
  7. mean_flat helper · level 1 · ran · our draft was wrong · f6d7c009a8efb8b7
  8. normal_kl helper · level 1 · ran · honoured contract · cf2798b666b231ca
  9. approx_standard_normal_cdf helper · level 1 · ran · our draft was wrong · cfd76fd0d89574a4
  1. GaussianDiffusion · c8f7b7b6786ef999 · 12 bricks; individually on a fixture: 7 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 5 where Syntology's instrument failed) · 5 unverified · The assembly has not been run end-to-end · assemblies[12] in the JSON twin
  2. GaussianDiffusion · f88ef9c506e3054c · 9 bricks; individually on a fixture: 5 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 4 unverified · The assembly has not been run end-to-end · assemblies[13] in the JSON twin

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="2105.05233") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Conditional Image GenerationDiversityImage Generation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Conditional Image Generation ImageNet 128x128 ADM-G (classifier_scale=0.5) FID 2.97 #5 of 22 Archive leaderboard report
Conditional Image Generation ImageNet 256x256 ADM-G FID 4.59 #3 of 5 Archive leaderboard report
Conditional Image Generation ImageNet 256x256 ADM-G Inception score 186.7 #3 of 5 Archive leaderboard report
Image Generation ImageNet 128x128 ADM-G FID 2.97 #10 of 23 Archive leaderboard report
Image Generation ImageNet 256x256 ADM-G, ADM-U FID 3.94 #78 of 94 Archive leaderboard report
Image Generation ImageNet 256x256 ADM-G FID 4.59 #86 of 94 Archive leaderboard report
Image Generation ImageNet 512x512 ADM-G, ADM-U FID 3.85 #47 of 52 Archive leaderboard report
Image Generation ImageNet 512x512 ADM-G, ADM-U Inception score 221.72 #47 of 52 Archive leaderboard report
Image Generation ImageNet 512x512 ADM-G FID 7.72 #52 of 52 Archive leaderboard report
Image Generation ImageNet 512x512 ADM-G Inception score 172.71 #52 of 52 Archive leaderboard report
Image Generation ImageNet 64x64 ADM (dropout) FID 2.07 #18 of 65 Archive leaderboard report
Image Generation LSUN Bedroom 256 x 256 ADM (dropout) FID 1.90 #4 of 32 Archive leaderboard report
Image Generation LSUN Bedroom 256 x 256 ADM (dropout, DINOv2) FD 59.64 #20 of 32 Archive leaderboard report
Image Generation LSUN Bedroom 256 x 256 ADM (dropout, DINOv2) Precision 0.85 #20 of 32 Archive leaderboard report
Image Generation LSUN Bedroom 256 x 256 ADM (dropout, DINOv2) Recall 0.75 #20 of 32 Archive leaderboard report
Image Generation LSUN Cat 256 x 256 ADM (dropout) FID 5.57 #3 of 8 Archive leaderboard report
Image Generation LSUN Horse 256 x 256 ADM (dropout) FID 2.57 #3 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

Introduced by this paper: classifier-guidance

AdamBatch NormalizationConvolutionDiffusionResidual Connectionclassifier-guidance

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