Papers › Elucidating the Design Space of Diffusion-Based Generative Models

Elucidating the Design Space of Diffusion-Based Generative Models

1 Jun 2022arXiv:2206.00364archive 2025-07-28

Tero Karras, Miika Aittala, Timo Aila, Samuli Laine

We argue that the theory and practice of diffusion-based generative models are currently unnecessarily convoluted and seek to remedy the situation by presenting a design space that clearly separates the concrete design choices. This lets us identify several changes to both the sampling and training processes, as well as preconditioning of the score networks. Together, our improvements yield new state-of-the-art FID of 1.79 for CIFAR-10 in a class-conditional setting and 1.97 in an unconditional setting, with much faster sampling (35 network evaluations per image) than prior designs. To further demonstrate their modular nature, we show that our design changes dramatically improve both the efficiency and quality obtainable with pre-trained score networks from previous work, including improving the FID of a previously trained ImageNet-64 model from 2.07 to near-SOTA 1.55, and after re-training with our proposed improvements to a new SOTA of 1.36.

PaperPDFCodeCode 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

Syntology 21 code samples: 18 from 7 repositories linked to this paper, 3 identical to code harvested from another paper's repository. Across all 21: 16 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 7 honoured, 0 violated, 5 with no contract checked; 4 where Syntology's instrument failed) · 5 unverified. Where Syntology's instrument failed: 3 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 4 samples from 1 repository, 2 ran (2 with no instrument failure; 0 where Syntology's instrument failed); community (archive-listed): 14 samples from 6 repositories, 12 ran (8 with no instrument failure; 4 where Syntology's instrument failed); 3 identical to code first harvested elsewhere. 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 13 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. 5 of the 16 samples that ran have no recorded date.

20 repositories listed; official and paper-mentioned ones first.

nvlabs/edm officialmentioned in papermentioned on GitHubpytorchNOASSERTIONSyntology: 4 samples, 2 ran (0 instrument-failed) · 2 unverified report
Morefre/Understanding-Generalizability-of-Diffusion-Models-Requires-Rethinking-the-Hidden-Gaussian-Structure mentioned on GitHubpytorchNOASSERTIONSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Understanding Generalizability of Diffusion Models Requires Rethinking the Hidden... (arXiv:2410.24060; that paper's own run record: 12 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; 8 where Syntology's instrument failed) · 8 unverified); nothing checks that they implement this paper's method. report
YichengDWu/tinyedm mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to ScaleLong: Towards More Stable Training of Diffusion Model via Scaling Network Long... (arXiv:2310.13545; that paper's own run record: 13 ran (of which 4 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 8 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
carzit/sd-webui-samplers-scheduler mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Restart Sampling for Improving Generative Processes (arXiv:2306.14878; that paper's own run record: 2 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; 1 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
crowsonkb/k-diffusion mentioned on GitHubpytorchSyntology: 3 samples, 2 ran (2 instrument-failed) · 1 unverified report
dopplerchase/cira-diff 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) and Guiding a Diffusion Model with a Bad Version of Itself (arXiv:2406.02507; that paper's own run record: 2 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; 1 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
friedmanroy/ctrl-shift mentioned on GitHubpytorchMITSyntology: 5 samples, 5 ran (0 instrument-failed) · 0 unverified report
intuitive-robots/beso mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Score-Based Generative Modeling through Stochastic Differential Equations (arXiv:2011.13456; that paper's own run record: 15 ran (of which 4 constructed an object rather than computing a result; 8 with no instrument failure: 2 honoured, 0 violated, 6 with no contract checked; 7 where Syntology's instrument failed) · 8 unverified); nothing checks that they implement this paper's method. report
lucidrains/imagen-pytorch mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Tell2Design: A Dataset for Language-Guided Floor Plan Generation (arXiv:2311.15941; that paper's own run record: 24 ran (of which 0 constructed an object rather than computing a result; 18 with no instrument failure: 1 honoured, 5 violated, 12 with no contract checked; 6 where Syntology's instrument failed) · 4 unverified); nothing checks that they implement this paper's method. report
milmor/diffusion-transformer mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Scalable Diffusion Models with Transformers (arXiv:2212.09748; that paper's own run record: 15 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 2 honoured, 0 violated, 10 with no contract checked; 3 where Syntology's instrument failed) · 5 unverified); nothing checks that they implement this paper's method. report
onefly123/PAS mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
p-hss/consistency-climate-downscaling mentioned on GitHubpytorchMITSyntology: not harvested report
pals-ttic/sjc mentioned on GitHubpytorchSyntology: 3 samples, 3 ran (1 instrument-failed) · 0 unverified report
pku-ml/adainf mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Do Generated Data Always Help Contrastive Learning? (arXiv:2403.12448; that paper's own run record: 6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
plai-group/vcdm mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
robbiewatt1/climatediffuse mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Generative Diffusion-based Downscaling for Climate (arXiv:2404.17752; that paper's own run record: 5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified); nothing checks that they implement this paper's method. report
sangyun884/fast-ode mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Diffusion Models Beat GANs on Image Synthesis (arXiv:2105.05233; that paper's own run record: 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), Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow (arXiv:2209.03003; that paper's own run record: 6 ran (of which 3 constructed an object rather than computing a result; 6 with no instrument failure: 3 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified) and Minimizing Trajectory Curvature of ODE-based Generative Models (arXiv:2301.12003; that paper's own run record: 1 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; 0 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
stability-ai/generative-models mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis (arXiv:2307.01952; that paper's own run record: 14 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 0 where Syntology's instrument failed) · 13 unverified); nothing checks that they implement this paper's method. report
christopher-beckham/toy-edm pytorchSyntology: 1 sample, 0 ran · 1 unverified report
probabilists/azula pytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Fast Sampling of Diffusion Models with Exponential Integrator (arXiv:2204.13902; that paper's own run record: 12 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 9 where Syntology's instrument failed) · 14 unverified) and Diffusion Posterior Sampling for General Noisy Inverse Problems (arXiv:2209.14687; that paper's own run record: 6 ran (of which 4 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 1 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 14 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

21 samples harvested: 16 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 7 honoured, 0 violated, 5 with no contract checked; 4 where Syntology's instrument failed) · 5 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.

7ran · honoured contract
3ran · our draft was wrong
1ran; the contract check could not run
5ran
5unverified

Licence: 13 of the 21 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 7 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. 5 samples whose link to this paper records no repository are listed under one of this paper's own repositories, because identical code was harvested from it for another paper. 3 samples are listed last, in a group without a repository. “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.

nvlabs/edm official repository 4 samples, 2 ran (0 instrument-failed) · 2 unverified
calculate_fid_from_inception_stats in 26 papers fid.py identical code Syntology harvested from this repository for another paper; this paper's link records no repository, path or licence of its own ran · honoured contract fingerprinted licence of this copy not recorded · 45e941764344e7f3 · report fixture: signature mu:ndarray/1/float, sigma:ndarray/2/float, mu_ref:ndarray/1/float, sigma_ref:ndarray/2/float · returned float · level recorded, date not recorded
parse_int_list in 59 papers generate.py identical code Syntology harvested from this repository for another paper; this paper's link records no repository, path or licence of its own ran · honoured contract licence of this copy not recorded · cacd4f6ec202d9b4 · report fixture: signature s:str/0/str · returned list · level recorded, date not recorded
ablation_sampler in 17 papers generate.py identical code Syntology harvested from this repository for another paper; this paper's link records no repository, path or licence of its own unverified licence of this copy not recorded · 9fbf646e18eed1db · report
edm_sampler in 34 papers generate.py identical code Syntology harvested from this repository for another paper; this paper's link records no repository, path or licence of its own unverified licence of this copy not recorded · 8b16b0674af254db · report
crowsonkb/k-diffusion community (archive-listed) 3 samples, 2 ran (2 instrument-failed) · 1 unverified
downscale_pos k_diffusion/models/image_transformer_v2.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant MIT (permissive) · ce526ffedb8faa2e · report fixture: signature pos:Tensor/4/float · returned Tensor · level recorded 2026-09-22
zero_init in 6 papers k_diffusion/models/image_transformer_v2.py ran · our draft was wrong MIT (permissive) · d63461a574db572f · report fixture: signature layer:callable/0/? · returned Linear · level recorded 2026-09-22
checkpoint in 42 papers k_diffusion/models/image_transformer_v2.py unverified MIT (permissive) · bed894f151989fee · report
friedmanroy/ctrl-shift community (archive-listed) 5 samples, 5 ran (0 instrument-failed) · 0 unverified
edm_sample sampling.py ran MIT (permissive) · 34c52bd69ff1a403 · report fixture: signature net:callable/0/?, latents:Tensor/2/float, class_labels:Tensor/1/int, num_steps:int/0/int, sigma_min:float/0/float, sigma_max:float/0/float, rho:float/0/float, verbose:bool/0/bool, invert:bool/0/bool, euler:bool/0/bool · returned tuple · level recorded 2026-09-24
edm_schedule sampling.py ran MIT (permissive) · c0c71f52be7b3680 · report fixture: signature num_steps:int/0/int, sigma_min:float/0/float, sigma_max:float/0/float, rho:float/0/float, device:str/0/str · returned Tensor · level recorded 2026-09-24
extend_coords generate_dist_shift.py ran MIT (permissive) · 206dcd48bf0f2883 · report fixture: signature shape:tuple/1/int, value:int/0/int, target:NoneType/0/? · returned Tensor · level recorded 2026-09-24
overlap_coords generate_dist_shift.py ran MIT (permissive) · 83cbd2453e3efe71 · report fixture: signature shape:tuple/1/int, value:int/0/int · returned Tensor · level recorded 2026-09-24
trunc_coords generate_dist_shift.py ran MIT (permissive) · a049710a973819ad · report fixture: signature shape:tuple/1/int, trunc:int/0/int · returned Tensor · level recorded 2026-09-24
onefly123/PAS community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
get_denoised in 5 papers pas_solvers.py identical code Syntology harvested from this repository for another paper; this paper's link records no repository, path or licence of its own ran · our draft was wrong licence of this copy not recorded · 3eed7631aeebeabc · report fixture: signature net:callable/0/?, x:Tensor/2/float, t:Tensor/1/int, class_labels:NoneType/0/?, condition:Tensor/2/float, unconditional_condition:Tensor/2/float · returned Tensor · level recorded, date not recorded
pals-ttic/sjc community (archive-listed) 3 samples, 3 ran (1 instrument-failed) · 0 unverified
karras_t_schedule adapt.py ran · honoured contract fingerprinted licence not identified · pointer only · 8285678722ad9b94 · report fixture: signature ρ:int/0/int, N:int/0/int, σ_max:int/0/int, σ_min:float/0/float · returned list · level recorded 2026-09-22
power_schedule adapt.py ran · honoured contract licence not identified · pointer only · c5ab2a66337ec866 · report fixture: signature σ_max:float/0/float, σ_min:float/0/float, num_stages:int/0/int · returned ndarray · level recorded 2026-09-22
tsr_stats run_sjc.py ran · our draft was wrong fingerprinted licence not identified · pointer only · f3cf3784fb4488db · report fixture: signature tsr:Tensor/2/float · returned dict · level recorded 2026-09-22
plai-group/vcdm community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
calculate_fid_from_inception_stats in 26 papers fid.py ran · honoured contract fingerprinted licence not identified · pointer only · 5a0fd9882013c6a5 · report fixture: signature mu:ndarray/1/float, sigma:ndarray/2/float, mu_ref:ndarray/1/float, sigma_ref:ndarray/2/float · returned float · level recorded 2026-09-22
christopher-beckham/toy-edm community (archive-listed) 1 sample, 0 ran · 1 unverified
edm_generalised_stochastic_sampler src/edm_generalised_stochastic_sampler.py unverified no licence file found · pointer only · 16450717abebe540 · report
Repository not located 3 samples, 2 ran (0 instrument-failed) · 1 unverified
3 samples are identical to code Syntology harvested from another paper's repository; this paper's own copy was not located, so no repository is named and no licence is recorded.
betas_for_alpha_bar in 123 papers repository not located ran · honoured contract licence of this copy not recorded · 2ab2316ac6fdd869 · report fixture: signature num_diffusion_timesteps:int/0/int, alpha_bar:callable/0/?, max_beta:float/0/float · returned ndarray · level recorded, date not recorded
get_named_beta_schedule in 119 papers repository not located ran · honoured contract licence of this copy not recorded · a086d6286a40b889 · report fixture: signature schedule_name:str/0/str, num_diffusion_timesteps:int/0/int · returned ndarray · level recorded, date not recorded
ablation_sampler in 17 papers repository not located unverified licence of this copy not recorded · daa5186ef7b993ca · report

Tasks

Image Generation

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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