Papers › Fast Sampling of Diffusion Models via Operator Learning

Fast Sampling of Diffusion Models via Operator Learning

24 Nov 2022arXiv:2211.13449archive 2025-07-28

Hongkai Zheng, Weili Nie, Arash Vahdat, Kamyar Azizzadenesheli, Anima Anandkumar

Diffusion models have found widespread adoption in various areas. However, their sampling process is slow because it requires hundreds to thousands of network evaluations to emulate a continuous process defined by differential equations. In this work, we use neural operators, an efficient method to solve the probability flow differential equations, to accelerate the sampling process of diffusion models. Compared to other fast sampling methods that have a sequential nature, we are the first to propose a parallel decoding method that generates images with only one model forward pass. We propose diffusion model sampling with neural operator (DSNO) that maps the initial condition, i.e., Gaussian distribution, to the continuous-time solution trajectory of the reverse diffusion process. To model the temporal correlations along the trajectory, we introduce temporal convolution layers that are parameterized in the Fourier space into the given diffusion model backbone. We show our method achieves state-of-the-art FID of 3.78 for CIFAR-10 and 7.83 for ImageNet-64 in the one-model-evaluation setting.

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 19 code samples harvested from 1 repository linked to this paper: 19 ran (of which 0 constructed an object rather than computing a result; 15 with no instrument failure: 0 honoured, 0 violated, 15 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified. Where Syntology's instrument failed: 4 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 19 samples from 1 repository, 19 ran (15 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.

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.

devzhk/dsno-pytorch officialmentioned in papermentioned on GitHubpytorchMITSyntology: 19 samples, 19 ran (4 instrument-failed) · 0 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.

Code Syntology ran Syntology

19 samples harvested: 19 ran (of which 0 constructed an object rather than computing a result; 15 with no instrument failure: 0 honoured, 0 violated, 15 with no contract checked; 4 where Syntology's instrument failed) · 0 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.

4ran · our draft was wrong
15ran

Licence: 0 of the 19 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 devzhk/dsno-pytorch. “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.

devzhk/dsno-pytorch official repository 19 samples, 19 ran (4 instrument-failed) · 0 unverified
build_state_map models/utils.py ran MIT (permissive) · 4038cee0912727be · report fixture: signature config:Config/0/? · returned dict · level recorded 2026-09-25
data_sampler in 17 papers utils/data_helper.py ran · our draft was wrong MIT (permissive) · dbb756dcd778f52f · report fixture: signature dataset:SimpleDataset/0/?, shuffle:bool/0/bool, distributed:bool/0/bool · returned RandomSampler · level recorded 2026-09-22
default_init in 38 papers models/layers.py ran · our draft was wrong MIT (permissive) · 04548c6c9fff2b3f · report fixture: signature scale:float/0/float · returned function · level recorded 2026-09-24
get_idx in 14 papers generate_imagenet.py ran MIT (permissive) · a57d49ef17dbed05 · report fixture: signature t_idx:list/1/int, t_dim:int/0/int, num_steps:int/0/int, time_step:str/0/str · returned list · level recorded 2026-09-25
get_key_map models/utils.py ran MIT (permissive) · 0e7775bc8f637675 · report fixture: signature config:MockConfig/0/? · returned dict · level recorded 2026-09-25
get_logsnr_input models/tddpmm.py ran MIT (permissive) · 3470bcd60748b7b6 · report fixture: signature logsnr:Tensor/2/float, logsnr_type:str/0/str · returned Tensor · level recorded 2026-09-25
get_logsnr_schedule models/tddpmm.py ran MIT (permissive) · 347413fbd8917c6f · report fixture: signature logsnr_max:float/0/float, logsnr_min:float/0/float · returned function · level recorded 2026-09-25
get_random_label generate_imagenet.py ran MIT (permissive) · 71c9af712b11fc4b · report fixture: signature batchsize:int/0/int, num_class:int/0/int, device:str/0/str · returned Tensor · level recorded 2026-09-25
get_timestep_embedding in 138 papers
census: 11 implementations from 15 papers, 5 distinct outputs across 2 buckets, one shared input per bucket
models/layers.py ran · our draft was wrong fingerprinted MIT (permissive) · b663f5d919fd45e0 · report fixture: signature timesteps:Tensor/1/int, embedding_dim:int/0/int, max_positions:int/0/int · returned Tensor · level recorded 2026-09-24
get_weight in 21 papers models/up_or_down_sampling.py ran MIT (permissive) · 8db300b9f1afb2d3 · report fixture: signature module:callable/0/?, shape:tuple/1/int, weight_var:str/0/str, kernel_init:callable/0/? · returned Tensor · level recorded 2026-09-25
naive_downsample_2d in 7 papers models/up_or_down_sampling.py ran fingerprinted MIT (permissive) · 9375ef0a6c4c1787 · report fixture: signature x:Tensor/4/float, factor:int/0/int · returned Tensor · level recorded 2026-09-25
naive_upsample_2d in 7 papers models/up_or_down_sampling.py ran fingerprinted MIT (permissive) · a7d9bb56776bab6d · report fixture: signature x:Tensor/4/float, factor:int/0/int · returned Tensor · level recorded 2026-09-25
percepLoss utils/loss.py ran MIT (permissive) · f28952b5b1c172f0 · report fixture: signature pred:Tensor/5/float, target:Tensor/5/float, weight:Tensor/1/float, loss_fn:callable/0/? · returned tuple · level recorded 2026-09-25
save2dir generate_imagenet.py ran MIT (permissive) · 48a5788c680cb78a · report fixture: signature images:ndarray/4/int, outdir:str/0/str, curr:int/0/int · returned int · level recorded 2026-09-25
scaled_dot_product in 9 papers models/layersmt.py ran fingerprinted MIT (permissive) · 770ce3af9e8428eb · report fixture: signature q:Tensor/4/float, k:Tensor/4/float, v:Tensor/4/float · returned Tensor · level recorded 2026-09-25
split_list in 223 papers utils/dataset.py ran fingerprinted MIT (permissive) · c393b5de24f2b4b2 · report fixture: signature arr:list/1/list, num_parts:int/0/int · returned dict · level recorded 2026-09-25
variance_scaling in 31 papers models/layers.py ran · our draft was wrong MIT (permissive) · f34882fce4b22d20 · report fixture: signature scale:float/0/float, mode:str/0/str, distribution:str/0/str, in_axis:int/0/int, out_axis:int/0/int, dtype:dtype/0/?, device:str/0/str · returned function · level recorded 2026-09-24
weightedL1 utils/loss.py ran MIT (permissive) · 2a97a27262e3dd56 · report fixture: returned tuple · level recorded 2026-09-25
weightedL2 utils/loss.py ran MIT (permissive) · 36b2614c0d8fb14d · report fixture: returned tuple · level recorded 2026-09-25

Tasks

Operator learning

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

ConvolutionDiffusion

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