Papers › Fast Sampling of Diffusion Models with Exponential Integrator

Fast Sampling of Diffusion Models with Exponential Integrator

29 Apr 2022arXiv:2204.13902archive 2025-07-28

Qinsheng Zhang, Yongxin Chen

The past few years have witnessed the great success of Diffusion models (DMs) in generating high-fidelity samples in generative modeling tasks. A major limitation of the DM is its notoriously slow sampling procedure which normally requires hundreds to thousands of time discretization steps of the learned diffusion process to reach the desired accuracy. Our goal is to develop a fast sampling method for DMs with a much less number of steps while retaining high sample quality. To this end, we systematically analyze the sampling procedure in DMs and identify key factors that affect the sample quality, among which the method of discretization is most crucial. By carefully examining the learned diffusion process, we propose Diffusion Exponential Integrator Sampler (DEIS). It is based on the Exponential Integrator designed for discretizing ordinary differential equations (ODEs) and leverages a semilinear structure of the learned diffusion process to reduce the discretization error. The proposed method can be applied to any DMs and can generate high-fidelity samples in as few as 10 steps. In our experiments, it takes about 3 minutes on one A6000 GPU to generate 50k images from CIFAR10. Moreover, by directly using pre-trained DMs, we achieve the state-of-art sampling performance when the number of score function evaluation (NFE) is limited, e.g., 4.17 FID with 10 NFEs, 3.37 FID, and 9.74 IS with only 15 NFEs on CIFAR10. Code is available at https://github.com/qsh-zh/deis

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 Exponential Integrator Sampler (DEIS), generated from the paper text (not the authors' code), at level 2 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)” (quoted from Syntology's server card). No rung compares this code against the authors' implementation. For agents: get_reference_implementation(name='Diffusion Exponential Integrator Sampler (DEIS)') (how to connect); the free check have('2204.13902') needs no token.

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

Code

Syntology 26 code samples harvested from 3 repositories linked to this paper: 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. Where Syntology's instrument failed: 8 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: 14 samples from 1 repository, 5 ran (0 with no instrument failure; 5 where Syntology's instrument failed); community (archive-listed): 12 samples from 2 repositories, 7 ran (3 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 1 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.

qsh-zh/deis officialmentioned in papermentioned on GitHubjaxSyntology: 14 samples, 5 ran (5 instrument-failed) · 9 unverified report
hankpipi/diffusers-hetu mentioned on GitHubjaxApache-2.0Syntology: 6 samples, 6 ran (3 instrument-failed) · 0 unverified report
huggingface/diffusers mentioned on GitHubjaxSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to RefDecoder: Enhancing Visual Generation with Conditional Video Decoding (arXiv:2605.15196; that paper's own run record: 7 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 2 violated, 0 with no contract checked; 5 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
shivamshrirao/diffusers mentioned on GitHubjaxApache-2.0Syntology: not harvested report
probabilists/azula pytorchSyntology: 6 samples, 1 ran (1 instrument-failed) · 5 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

26 samples harvested: 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. “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
8ran · our draft was wrong
1ran; the contract check could not run
2ran
14unverified

Licence: 19 of the 26 samples are pointer only, meaning Syntology does not serve that copy's text. For 5 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 3 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.

qsh-zh/deis official repository 14 samples, 5 ran (5 instrument-failed) · 9 unverified
ab_step jax_deis/sampler.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 8c6face91c6b2d6c · report fixture: signature x:ArrayImpl/2/float, ei_coef:ArrayImpl/1/float, new_eps:ArrayImpl/2/float, eps_pred:ArrayImpl/3/float · returned tuple · level recorded 2026-09-22
get_ab_eps_coef_order0 jax_deis/sampler.py ran · our draft was wrong no licence file found · pointer only · 9fc74482f90852db · report fixture: signature sde:MinimalSDE/0/?, highest_order:int/0/int, timesteps:ArrayImpl/1/float · returned ArrayImpl · level recorded 2026-09-22
get_coef_per_step_fn jax_deis/sampler.py ran · our draft was wrong no licence file found · pointer only · 047a63bd314f76e5 · report fixture: signature sde:MockSDE/0/?, highest_order:int/0/int, order:int/0/int · returned function · level recorded 2026-09-22
get_integrator_basis_fn jax_deis/sampler.py ran · our draft was wrong no licence file found · pointer only · 86a2d8ec186ea23a · report fixture: signature sde:MockSDE/0/? · returned function · level recorded 2026-09-22
single_poly_coef jax_deis/sampler.py ran; the contract check could not run (RAISES) fingerprinted no licence file found · pointer only · 42c8364b75e3eed2 · report fixture: signature t_val:ArrayImpl/0/float, ts_poly:ArrayImpl/1/float, coef_idx:int/0/int · returned ArrayImpl · level recorded 2026-09-22
ExpSDE jax_deis/sampler.py unverified no licence file found · pointer only · 826614d74a92d36a · report
MultiStepSDE jax_deis/sampler.py unverified no licence file found · pointer only · e63e074a97bdbba7 · report
get_ab_eps_coef jax_deis/sampler.py unverified no licence file found · pointer only · 9d7c174fb487814f · report
get_one_coef_per_step_fn jax_deis/sampler.py unverified no licence file found · pointer only · 8050aa9c471e9994 · report
get_rev_ts jax_deis/sampler.py unverified no licence file found · pointer only · 5ee03a5f9d65d37d · report
get_sampler in 20 papers jax_deis/sampler.py unverified no licence file found · pointer only · e04b6fa68b802212 · report
get_sampler_ipndm jax_deis/sampler.py unverified no licence file found · pointer only · 20e88ff233a7d48a · report
get_sampler_rho_ab jax_deis/sampler.py unverified no licence file found · pointer only · f389d4f5884dab3d · report
get_sampler_t_ab jax_deis/sampler.py unverified no licence file found · pointer only · 325d6d95af681572 · report
hankpipi/diffusers-hetu community (archive-listed) 6 samples, 6 ran (3 instrument-failed) · 0 unverified
betas_for_alpha_bar in 123 papers src/diffusers/schedulers/scheduling_ddim_hetu.py ran · honoured contract fingerprinted Apache-2.0 (permissive) here; the stored copy is pointer only · e6293358fb50e129 · report fixture: signature num_diffusion_timesteps:int/0/int, max_beta:float/0/float · returned Tensor · level recorded 2026-09-24
betas_for_alpha_bar in 123 papers src/diffusers/schedulers/scheduling_dpmsolver_multistep_hetu.py ran fingerprinted Apache-2.0 (permissive) here; the stored copy is pointer only · c3d321eafd7ea5fc · report fixture: signature num_diffusion_timesteps:int/0/int, max_beta:float/0/float · returned Tensor · level recorded 2026-09-24
calculate_diff src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_edit_hetu.py ran fingerprinted Apache-2.0 (permissive) · f404b70c8fa44c93 · report fixture: signature latents1:ndarray/2/float, latents2:ndarray/2/float · returned ndarray · level recorded 2026-09-25
get_constant_schedule in 21 papers src/diffusers/optimization.py ran · our draft was wrong Apache-2.0 (permissive) here; the stored copy is pointer only · a8366f238618edad · report fixture: signature optimizer:SGD/0/?, last_epoch:int/0/int · returned LambdaLR · level recorded 2026-09-24
get_constant_schedule_with_warmup in 25 papers src/diffusers/optimization.py ran · our draft was wrong Apache-2.0 (permissive) here; the stored copy is pointer only · 11f07821d1b2286b · report fixture: signature optimizer:SGD/0/?, num_warmup_steps:int/0/int, last_epoch:int/0/int · returned LambdaLR · level recorded 2026-09-24
get_linear_schedule_with_warmup in 39 papers src/diffusers/optimization.py ran · our draft was wrong Apache-2.0 (permissive) here; the stored copy is pointer only · 1975e0c51e6f5753 · report fixture: signature optimizer:SGD/0/?, num_warmup_steps:int/0/int, num_training_steps:int/0/int, last_epoch:int/0/int · returned LambdaLR · level recorded 2026-09-24
probabilists/azula community (archive-listed) 6 samples, 1 ran (1 instrument-failed) · 5 unverified
promote_dtype azula/sample.py ran · our draft was wrong MIT (permissive) · 270aef5509e49841 · report fixture: signature f:callable/0/?, min_dtype:dtype/0/? · returned function · level recorded 2026-09-22
Denoiser in 7 papers azula/sample.py unverified MIT (permissive) · 1ccb2a7000e28ccf · report
Posterior azula/sample.py unverified MIT (permissive) · 15ce8315808e4f16 · report
Sampler in 21 papers azula/sample.py unverified MIT (permissive) · 2604445654b63d20 · report
Schedule azula/sample.py unverified MIT (permissive) · 9f9e8449e6838182 · report
zEABSampler azula/sample.py unverified MIT (permissive) · c376b63ed485cb0c · 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.

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

generated Assembly for Diffusion Exponential Integrator Sampler (DEIS) (graph method: Diffusion Exponential Integrator Sampler (DEIS)), generated from the paper text, not the repository's code. 1 brick; individually on a fixture: 1 ran (1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified. Ran end-to-end against an independent peer (level 2).

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

  1. deis_rho_rk_midpoint_step entry · level 2 · ran · ab727adc0dd708db6030357d694e85a104ca2eacb18e917593d8600d7995dabc

2 sibling assemblies for Diffusion Exponential Integrator Sampler (DEIS) (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another.

harvested Assembly for Diffusion Exponential Integrator Sampler (DEIS) (graph method: Diffusion Exponential Integrator Sampler (DEIS)). 6 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) · 5 unverified. The assembly has not been run end-to-end.

one of 2 siblings

  1. zEABSampler entry · level 0 · unverified · c376b63ed485cb0c
  2. Denoiser helper · level 0 · unverified · 1ccb2a7000e28ccf
  3. Sampler helper · level 0 · unverified · 2604445654b63d20
  4. promote_dtype helper · level 1 · ran · our draft was wrong · 270aef5509e49841
  5. Posterior helper · level 0 · unverified · 15ce8315808e4f16
  6. Schedule helper · level 0 · unverified · 9f9e8449e6838182

harvested Assembly for Diffusion Exponential Integrator Sampler (DEIS) (graph method: Diffusion Exponential Integrator Sampler (DEIS)). 11 bricks; individually on a fixture: 5 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; 5 where Syntology's instrument failed) · 6 unverified. The assembly has not been run end-to-end.

one of 2 siblings

  1. get_sampler_rho_ab entry · level 0 · unverified · f389d4f5884dab3d
  2. MultiStepSDE helper · level 0 · unverified · e63e074a97bdbba7
  3. ab_step helper · level 1 · ran · our draft was wrong · 8c6face91c6b2d6c
  4. get_ab_eps_coef scheduler · level 0 · unverified · 9d7c174fb487814f
  5. get_rev_ts helper · level 0 · unverified · 5ee03a5f9d65d37d
  6. get_ab_eps_coef_order0 helper · level 1 · ran · our draft was wrong · 9fc74482f90852db
  7. get_coef_per_step_fn helper · level 1 · ran · our draft was wrong · 047a63bd314f76e5
  8. ExpSDE helper · level 0 · unverified · 826614d74a92d36a
  9. get_one_coef_per_step_fn helper · level 0 · unverified · 8050aa9c471e9994
  10. get_integrator_basis_fn helper · level 1 · ran · our draft was wrong · 86a2d8ec186ea23a
  11. single_poly_coef helper · level 1 · ran; the contract check could not run (RAISES) · 42c8364b75e3eed2

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="2204.13902") returns these assemblies with each brick's role and wiring (how to connect).

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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