Papers › Progressive Distillation for Fast Sampling of Diffusion Models

Progressive Distillation for Fast Sampling of Diffusion Models

1 Feb 2022ICLR 2022 4arXiv:2202.00512archive 2025-07-28

Tim Salimans, Jonathan Ho

Diffusion models have recently shown great promise for generative modeling, outperforming GANs on perceptual quality and autoregressive models at density estimation. A remaining downside is their slow sampling time: generating high quality samples takes many hundreds or thousands of model evaluations. Here we make two contributions to help eliminate this downside: First, we present new parameterizations of diffusion models that provide increased stability when using few sampling steps. Second, we present a method to distill a trained deterministic diffusion sampler, using many steps, into a new diffusion model that takes half as many sampling steps. We then keep progressively applying this distillation procedure to our model, halving the number of required sampling steps each time. On standard image generation benchmarks like CIFAR-10, ImageNet, and LSUN, we start out with state-of-the-art samplers taking as many as 8192 steps, and are able to distill down to models taking as few as 4 steps without losing much perceptual quality; achieving, for example, a FID of 3.0 on CIFAR-10 in 4 steps. Finally, we show that the full progressive distillation procedure does not take more time than it takes to train the original model, thus representing an efficient solution for generative modeling using diffusion at both train and test time.

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.

Syntology holds a reference implementation of Progressive Distillation, 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). No rung compares this code against the authors' implementation. For agents: get_reference_implementation(name='Progressive Distillation') (how to connect); the free check have('2202.00512') needs no token.

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

Code

Syntology 27 code samples harvested from 8 repositories linked to this paper: 10 ran (of which 4 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 0 violated, 6 with no contract checked; 3 where Syntology's instrument failed) · 17 unverified. Where Syntology's instrument failed: 3 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 7 samples from 1 repository, 1 ran (1 with no instrument failure; 0 where Syntology's instrument failed); community (archive-listed): 20 samples from 7 repositories, 9 ran (6 with no instrument failure; 3 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 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

google-research/google-research officialjaxSyntology: 7 samples, 1 ran (0 instrument-failed) · 6 unverified report
cloneofsimo/consistency_models mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
deepxuan/dn-dp mentioned on GitHubpytorchSyntology: 4 samples, 2 ran (1 instrument-failed) · 2 unverified report
ericl122333/patchdiffusion-pytorch mentioned on GitHubpytorchSyntology: 3 samples, 2 ran (0 instrument-failed) · 1 unverified report
fashn-AI/tryondiffusion mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to TryOnDiffusion: A Tale of Two UNets (arXiv:2306.08276; that paper's own run record: 14 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 1 honoured, 2 violated, 9 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
ftoralesacosta/gsgm_for_eic_calo mentioned on GitHubtfSyntology: not harvested 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
sainzerjj/sferd mentioned on GitHubpytorchMITSyntology: 5 samples, 2 ran (0 instrument-failed) · 3 unverified report
sreerajr000/consistency-models mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
viniciusmikuni/caloscorev2 mentioned on GitHubtfSyntology: not harvested report
viniciusmikuni/gsgm mentioned on GitHubtfSyntology: 2 samples, 0 ran · 2 unverified report
Hramchenko/diffusion_distiller pytorchSyntology: 4 samples, 1 ran (1 instrument-failed) · 3 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

27 samples harvested: 10 ran (of which 4 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 0 violated, 6 with no contract checked; 3 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.

1ran · honoured contract
3ran · our draft was wrong
6ran
17unverified

Licence: 10 of the 27 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 8 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.

google-research/google-research official repository 7 samples, 1 ran (0 instrument-failed) · 6 unverified
Model in 227 papers diffusion_distillation/diffusion_distillation/dpm.py ran Apache-2.0 (permissive) · e6c610e22a0b8e1f · report fixture: returned Model · level recorded 2026-09-22
diffusion_forward diffusion_distillation/diffusion_distillation/dpm.py unverified Apache-2.0 (permissive) · d37af918412dc794 · report
diffusion_reverse diffusion_distillation/diffusion_distillation/dpm.py unverified Apache-2.0 (permissive) · e6029bbacbfd72ee · report
predict_eps_from_x diffusion_distillation/diffusion_distillation/dpm.py unverified Apache-2.0 (permissive) · ecf3ebad654f83f5 · report
predict_v_from_x_and_eps diffusion_distillation/diffusion_distillation/dpm.py unverified Apache-2.0 (permissive) · 894c180fa74bdbd5 · report
predict_x_from_eps diffusion_distillation/diffusion_distillation/dpm.py unverified Apache-2.0 (permissive) · 66e7c354db444496 · report
predict_x_from_v diffusion_distillation/diffusion_distillation/dpm.py unverified Apache-2.0 (permissive) · a8cf5ffc562524b9 · report
cloneofsimo/consistency_models community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
ConsistencyModel consistency_models/unet.py ran no licence file found · pointer only · c5b3831528f9c8ce · report fixture: returned ConsistencyModel · level recorded 2026-09-22
deepxuan/dn-dp community (archive-listed) 4 samples, 2 ran (1 instrument-failed) · 2 unverified
_extract_into_tensor in 7 papers model/sr3_modules/respace.py ran · our draft was wrong no licence file found · pointer only · 7cf7aa019c5dcc57 · report fixture: signature arr:ndarray/1/float, timesteps:Tensor/1/int, broadcast_shape:tuple/1/int · returned Tensor · level recorded 2026-09-22
make_beta_schedule in 48 papers model/sr3_modules/respace.py ran · honoured contract no licence file found · pointer only · 7ef3b9728402cdd1 · report fixture: signature schedule:str/0/str, n_timestep:int/0/int, linear_start:float/0/float, linear_end:float/0/float, cosine_s:float/0/float · returned ndarray · level recorded 2026-09-22
GaussianDiffusion in 61 papers model/sr3_modules/respace.py unverified no licence file found · pointer only · 92244ba45f2a5ca4 · report
SpacedDiffusion in 12 papers model/sr3_modules/respace.py unverified no licence file found · pointer only · 0bceb8d35b696f6a · report
ericl122333/patchdiffusion-pytorch community (archive-listed) 3 samples, 2 ran (0 instrument-failed) · 1 unverified
GaussianDiffusion in 61 papers patch_diffusion/respace.py ran no licence file found · pointer only · afb6a311f3326182 · report fixture: returned GaussianDiffusion · level recorded 2026-09-22
_WrappedModel patch_diffusion/respace.py ran no licence file found · pointer only · eeb6b2016ef36e61 · report fixture: returned _WrappedModel · level recorded 2026-09-22
SpacedDiffusion in 12 papers patch_diffusion/respace.py unverified no licence file found · pointer only · 3ef0f294c952f62d · report
sainzerjj/sferd community (archive-listed) 5 samples, 2 ran (0 instrument-failed) · 3 unverified
EMA in 18 papers diffusion/train_utils.py ran · metamorphic tier: deterministic MIT (permissive) · 1baf4c2b5fd0b943 · report fixture: returned NoneType · level recorded 2026-09-22
RunningStatistics diffusion/train_utils.py ran · metamorphic tier: deterministic MIT (permissive) · 0b2e4925d1642a0b · report fixture: signature n:int/0/int, loss:float/0/float, accuracy:float/0/float, time:float/0/float · returned NoneType · level recorded 2026-09-22
DistillationTrainer diffusion/train_utils.py unverified MIT (permissive) · b13671cc03127267 · report
DummyScheduler diffusion/train_utils.py unverified MIT (permissive) · d56db955dcd1e1bb · report
save_image in 18 papers diffusion/train_utils.py unverified MIT (permissive) · d9b8534277a98f88 · report
sreerajr000/consistency-models community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
multistep_consistency_sampling sampler.py ran · our draft was wrong MIT (permissive) · 18b1cad6bd142108 · report fixture: signature net:callable/0/?, latents:Tensor/2/float, t_steps:list/1/float · returned Tensor · level recorded 2026-09-22
viniciusmikuni/gsgm community (archive-listed) 2 samples, 0 ran · 2 unverified
DeepSetsAtt demo/GSGM.py unverified no licence file found · pointer only · 9cde3092e14a7d62 · report
GSGM demo/GSGM.py unverified no licence file found · pointer only · ef2ea1d8599e8b2d · report
Hramchenko/diffusion_distiller community (archive-listed) 4 samples, 1 ran (1 instrument-failed) · 3 unverified
make_none_args train_utils.py ran · our draft was wrong MIT (permissive) · 513b57c8cf771713 · report fixture: signature img:Tensor/4/float, label:Tensor/1/int, device:str/0/str · returned dict · level recorded 2026-09-24
DiffusionDistillation train_utils.py unverified MIT (permissive) · 791b3bf86655f018 · report
default_iter_callback train_utils.py unverified MIT (permissive) · 7b619a5570fecf04 · 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". 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. 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.

9 assemblies on this paper: 8 harvested, 1 generated, listed in 2 groups (siblings lifted in one batch form one group).

generated Assembly for Progressive Distillation (graph method: Progressive Distillation), 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; 5 property tests passed on both).

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

  1. progressive_distillation_loss entry · level 3 · ran · honoured contract · e76ae70aec190dc87341aef5621ff0fa1f8e8f57e97e8a35e3015e8d097751b0

8 sibling assemblies for Progressive Distillation (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another.

harvested Assembly for Progressive Distillation (graph method: Progressive Distillation). 11 bricks; individually on a fixture: 7 ran (of which 2 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 4 where Syntology's instrument failed) · 4 unverified. The assembly has not been run end-to-end.

one of 8 siblings

  1. SpacedDiffusion entry · level 0 · unverified · 3ef0f294c952f62d
  2. GaussianDiffusion helper · level 1 · ran · afb6a311f3326182
  3. _WrappedModel helper · level 1 · ran · eeb6b2016ef36e61
  4. LossType helper · level 0 · unverified · 3dfb2574af178220
  5. ModelMeanType helper · level 0 · unverified · 8fa5f1c784de4b2d
  6. ModelVarType helper · level 0 · unverified · 9df953f617d68af1
  7. _extract_into_tensor helper · level 1 · ran; the contract check could not run · 47d10dfc019ed932
  8. discretized_gaussian_log_likelihood helper · level 1 · ran · our draft was wrong · cd33283d615fb3d7
  9. mean_flat helper · level 1 · ran · our draft was wrong · f6d7c009a8efb8b7
  10. normal_kl helper · level 1 · ran · honoured contract · cf2798b666b231ca
  11. approx_standard_normal_cdf helper · level 1 · ran · our draft was wrong · cfd76fd0d89574a4

harvested Assembly for Progressive Distillation (graph method: Progressive Distillation). 7 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) · 6 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 8 siblings

  1. Model entry · level 1 · ran · e6c610e22a0b8e1f
  2. diffusion_forward helper · level 0 · unverified · d37af918412dc794
  3. diffusion_reverse helper · level 0 · unverified · e6029bbacbfd72ee
  4. predict_eps_from_x helper · level 0 · unverified · ecf3ebad654f83f5
  5. predict_v_from_x_and_eps helper · level 0 · unverified · 894c180fa74bdbd5
  6. predict_x_from_eps helper · level 0 · unverified · 66e7c354db444496
  7. predict_x_from_v helper · level 0 · unverified · a8cf5ffc562524b9

harvested Assembly for Progressive Distillation (graph method: Progressive Distillation). 1 brick; individually on a fixture: 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. The assembly has not been run end-to-end.

one of 8 siblings

  1. multistep_consistency_sampling entry · level 1 · ran · our draft was wrong · 18b1cad6bd142108

harvested Assembly for Progressive Distillation (graph method: Progressive Distillation). 1 brick; 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) · 0 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 8 siblings

  1. ConsistencyModel entry · level 1 · ran · c5b3831528f9c8ce

harvested Assembly for Progressive Distillation (graph method: Progressive Distillation). 2 bricks; individually on a fixture: 0 ran · 2 unverified. The assembly has not been run end-to-end.

one of 8 siblings

  1. GSGM entry · level 0 · unverified · ef2ea1d8599e8b2d
  2. DeepSetsAtt helper · level 0 · unverified · 9cde3092e14a7d62

harvested Assembly for Progressive Distillation (graph method: Progressive Distillation). 5 bricks; individually on a fixture: 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified. The assembly has not been run end-to-end.

one of 8 siblings

  1. DistillationTrainer entry · level 0 · unverified · b13671cc03127267
  2. DummyScheduler helper · level 0 · unverified · d56db955dcd1e1bb
  3. EMA helper · level 1 · ran · 1baf4c2b5fd0b943
  4. RunningStatistics helper · level 1 · ran · 0b2e4925d1642a0b
  5. save_image helper · level 0 · unverified · d9b8534277a98f88

harvested Assembly for Progressive Distillation (graph method: Progressive Distillation). 8 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) · 2 unverified. The assembly has not been run end-to-end.

one of 8 siblings

  1. SpacedDiffusion entry · level 0 · unverified · 0bceb8d35b696f6a
  2. GaussianDiffusion helper · level 0 · unverified · 92244ba45f2a5ca4
  3. _WrappedModel helper · level 1 · ran · eeb6b2016ef36e61
  4. _extract_into_tensor helper · level 1 · ran · our draft was wrong · 7cf7aa019c5dcc57
  5. default helper · level 1 · ran · violated contract · fbf9ec7be545688e
  6. make_beta_schedule helper · level 1 · ran · honoured contract · 7ef3b9728402cdd1
  7. exists helper · level 1 · ran · violated contract · 608e364a9d2376a3
  8. _warmup_beta helper · level 1 · ran · honoured contract · 485e96503db83610

harvested Assembly for Progressive Distillation (graph method: Progressive Distillation). 4 bricks; individually on a fixture: 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) · 3 unverified. The assembly has not been run end-to-end.

one of 8 siblings

  1. DiffusionDistillation entry · level 0 · unverified · 791b3bf86655f018
  2. default_iter_callback helper · level 0 · unverified · 7b619a5570fecf04
  3. make_none_args helper · level 1 · ran · our draft was wrong · 513b57c8cf771713
  4. moving_average helper · level 0 · unverified · 2dae0e9618d089f2

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="2202.00512") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Density EstimationImage Generation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Generation CIFAR-10 PD (NFE=8) FID 2.57 #23 of 78 Archive leaderboard report
Image Generation CIFAR-10 PD (NFE=4) FID 3.00 #25 of 78 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