SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2204.13902 · ICLR · 2023

Fast Sampling of Diffusion Models with Exponential Integrator

Qinsheng Zhang, Yongxin Chen

arXiv · PDF · Open in the Atlas

Code that ran

12 of 26 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 2 honoured the contract we drafted, 0 violated it and 1 has no contract verdict; 9 failures of our instrument; 14 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2204.13902.json · badge: /api/ran/2204.13902.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
qsh-zh/deis canonical (classifier label)
classifier basis: classifier_2025
5 ran · 9 no recorded run
hankpipi/diffusers-hetu community (classifier label)
classifier basis not recorded on the link
6 ran · 0 no recorded run
probabilists/azula community
Papers with Code archive
1 ran · 5 no recorded run
FunctionStatusWhere it lives
ab_step Ran
ran; our contract draft was wrong, not the code
qsh-zh/deis/jax_deis/sampler.py
pointer only (licence: NONE) · get_code("8c6face91c6b2d6c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, qsh-zh/deis when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

betas_for_alpha_bar Ran
ran, honoured the contract we drafted
hankpipi/diffusers-hetu/src/diffusers/schedulers/scheduling_ddim_hetu.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from hanshuyan/adjointdpm, is pointer only (licence: NONE) · get_code("e6293358fb50e129")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from hanshuyan/adjointdpm, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

betas_for_alpha_bar Ran
ran, honoured the contract we drafted
hankpipi/diffusers-hetu/src/diffusers/schedulers/scheduling_dpmsolver_multistep_hetu.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from gulucaptain/videoassembler, is pointer only (licence: NONE) · get_code("c3d321eafd7ea5fc")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from gulucaptain/videoassembler, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

calculate_diff Ran
ran on a synthesized input
hankpipi/diffusers-hetu/src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_edit_hetu.py
code served (permissive licence) · get_code("f404b70c8fa44c93")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned ndarray, ndim 1, dtype family float, shape (4,) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np

# Create two small latent arrays with distinct shapes for clarity
# Shape (2, 4) - batch size 2, latent dimension 4
latents1 = np.array([
    [1.0, 2.0, 3.0, 4.0],
    [5.0, 6.0, 7.0, 8.0]
], dtype=np.float32)

latents2 = np.array([
    [1.5, 2.5, 3.5, 4.5],
    [5.5, 6.5, 7.5, 8.5]
], dtype=np.float32)

ARGS = {
    "latents1": latents1,
    "latents2": latents2,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 1, dtype family float, shape (4,) — shape (4,) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
get_ab_eps_coef_order0 Ran
ran; our contract draft was wrong, not the code
qsh-zh/deis/jax_deis/sampler.py
pointer only (licence: NONE) · get_code("9fc74482f90852db")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, qsh-zh/deis when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_coef_per_step_fn Ran
ran; our contract draft was wrong, not the code
qsh-zh/deis/jax_deis/sampler.py
pointer only (licence: NONE) · get_code("047a63bd314f76e5")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, qsh-zh/deis when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_constant_schedule Ran
ran; our contract draft was wrong, not the code
hankpipi/diffusers-hetu/src/diffusers/optimization.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from Feng-Hong/WINO-DLLM, is pointer only (licence: NONE) · get_code("a8366f238618edad")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from Feng-Hong/WINO-DLLM, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_constant_schedule_with_warmup Ran
ran; our contract draft was wrong, not the code
hankpipi/diffusers-hetu/src/diffusers/optimization.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from Feng-Hong/WINO-DLLM, is pointer only (licence: NONE) · get_code("11f07821d1b2286b")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from Feng-Hong/WINO-DLLM, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_integrator_basis_fn Ran
ran; our contract draft was wrong, not the code
qsh-zh/deis/jax_deis/sampler.py
pointer only (licence: NONE) · get_code("86a2d8ec186ea23a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, qsh-zh/deis when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_linear_schedule_with_warmup Ran
ran; our contract draft was wrong, not the code
hankpipi/diffusers-hetu/src/diffusers/optimization.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from Feng-Hong/WINO-DLLM, is pointer only (licence: NONE) · get_code("1975e0c51e6f5753")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from Feng-Hong/WINO-DLLM, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

promote_dtype Ran
ran; our contract draft was wrong, not the code
probabilists/azula/azula/sample.py
code served (permissive licence) · get_code("270aef5509e49841")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned function. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
from collections.abc import Callable

torch.manual_seed(0)

# Create a simple function that takes tensors and returns a tensor
def sample_function(a, b):
    """A simple function that takes two tensors and returns their sum."""
    return a + b

# Create tensor arguments with different dtypes to test promotion
arg1 = torch.tensor([[1.0, 2.0, 3.0, 4.0], [5.0, 6.0, 7.0, 8.0]], dtype=torch.float32)
arg2 = torch.tensor([[1.0, 2.0, 3.0, 4.0], [5.0, 6.0, 7.0, 8.0]], dtype=torch.float32)

ARGS = {
    'f': sample_function,
    'min_dtype': torch.float32,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type function — a function output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a function output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
single_poly_coef Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
qsh-zh/deis/jax_deis/sampler.py
pointer only (licence: NONE) · get_code("42c8364b75e3eed2")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, qsh-zh/deis when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

Denoiser Not yet run
unverified (harvested, no recorded run)
probabilists/azula/azula/sample.py
code served (permissive licence) · get_code("1ccb2a7000e28ccf")
How it ran

no invocation recorded.

ExpSDE Not yet run
unverified (harvested, no recorded run)
qsh-zh/deis/jax_deis/sampler.py
pointer only (licence: NONE) · get_code("826614d74a92d36a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, qsh-zh/deis when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

MultiStepSDE Not yet run
unverified (harvested, no recorded run)
qsh-zh/deis/jax_deis/sampler.py
pointer only (licence: NONE) · get_code("e63e074a97bdbba7")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, qsh-zh/deis when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Posterior Not yet run
unverified (harvested, no recorded run)
probabilists/azula/azula/sample.py
code served (permissive licence) · get_code("15ce8315808e4f16")
How it ran

no invocation recorded.

Sampler Not yet run
unverified (harvested, no recorded run)
probabilists/azula/azula/sample.py
code served (permissive licence) · get_code("2604445654b63d20")
How it ran

no invocation recorded.

Schedule Not yet run
unverified (harvested, no recorded run)
probabilists/azula/azula/sample.py
code served (permissive licence) · get_code("9f9e8449e6838182")
How it ran

no invocation recorded.

get_ab_eps_coef Not yet run
unverified (harvested, no recorded run)
qsh-zh/deis/jax_deis/sampler.py
pointer only (licence: NONE) · get_code("9d7c174fb487814f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, qsh-zh/deis when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

get_one_coef_per_step_fn Not yet run
unverified (harvested, no recorded run)
qsh-zh/deis/jax_deis/sampler.py
pointer only (licence: NONE) · get_code("8050aa9c471e9994")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, qsh-zh/deis when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

get_rev_ts Not yet run
unverified (harvested, no recorded run)
qsh-zh/deis/jax_deis/sampler.py
pointer only (licence: NONE) · get_code("5ee03a5f9d65d37d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, qsh-zh/deis when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

get_sampler Not yet run
unverified (harvested, no recorded run)
qsh-zh/deis/jax_deis/sampler.py
pointer only (licence: NONE) · get_code("e04b6fa68b802212")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, qsh-zh/deis when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

get_sampler_ipndm Not yet run
unverified (harvested, no recorded run)
qsh-zh/deis/jax_deis/sampler.py
pointer only (licence: NONE) · get_code("20e88ff233a7d48a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, qsh-zh/deis when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

get_sampler_rho_ab Not yet run
unverified (harvested, no recorded run)
qsh-zh/deis/jax_deis/sampler.py
pointer only (licence: NONE) · get_code("f389d4f5884dab3d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, qsh-zh/deis when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

get_sampler_t_ab Not yet run
unverified (harvested, no recorded run)
qsh-zh/deis/jax_deis/sampler.py
pointer only (licence: NONE) · get_code("325d6d95af681572")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, qsh-zh/deis when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

zEABSampler Not yet run
unverified (harvested, no recorded run)
probabilists/azula/azula/sample.py
code served (permissive licence) · get_code("c376b63ed485cb0c")
How it ran

no invocation recorded.

Also present in other papers' code

Of 26 samples lifted from this paper's linked repositories, 26 carry a function identity and 0 do not. Of the 26 distinct functions with an identity, 9 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 0 the same month, 9 later) and 17 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
get_linear_schedule_with_warmup 21 other papers
4 dated earlier, 17 later
2004.10964 (2020-04)
Don't Stop Pretraining: Adapt Language Models to Domains and Tasks
2011.07430 (2020-11)
Audio-Visual Event Recognition through the lens of Adversary
2109.04912 (2021-09)
ReasonBERT: Pre-trained to Reason with Distant Supervision
and 18 more not named here
get_constant_schedule 13 other papers
1 dated earlier, 12 later
2004.10964 (2020-04)
Don't Stop Pretraining: Adapt Language Models to Domains and Tasks
2305.15328 (2023-05)
Visual Programming for Text-to-Image Generation and Evaluation
2306.08553 (2023-06)
Noise Stability Optimization for Finding Flat Minima: A Hessian-based Regularization Approach
and 10 more not named here
get_constant_schedule_with_warmup 13 other papers
1 dated earlier, 12 later
2004.10964 (2020-04)
Don't Stop Pretraining: Adapt Language Models to Domains and Tasks
2305.15328 (2023-05)
Visual Programming for Text-to-Image Generation and Evaluation
2306.08276 (2023-06)
TryOnDiffusion: A Tale of Two UNets
and 10 more not named here
betas_for_alpha_bar 3 other papers
3 later
2307.14352 (2023-07)
General Image-to-Image Translation with One-Shot Image Guidance
2311.16711 (2023-11)
LEDITS++: Limitless Image Editing using Text-to-Image Models
2311.17338 (2023-11)
MagDiff: Multi-Alignment Diffusion for High-Fidelity Video Generation and Editing
betas_for_alpha_bar 2 other papers
2 later
2312.12030 (2023-12)
Towards Accurate Guided Diffusion Sampling through Symplectic Adjoint Method
2605.11414 (2026-05)
Generative Diffusion Prior Distillation for Long-Context Knowledge Transfer
Denoiser
brick of this paper's assembly: helper
1 other paper
1 later
2209.14687 (2022-09)
Diffusion Posterior Sampling for General Noisy Inverse Problems
Posterior
brick of this paper's assembly: helper
1 other paper
1 later
2209.14687 (2022-09)
Diffusion Posterior Sampling for General Noisy Inverse Problems
Sampler
brick of this paper's assembly: helper
1 other paper
1 later
2209.14687 (2022-09)
Diffusion Posterior Sampling for General Noisy Inverse Problems
Schedule
brick of this paper's assembly: helper
1 other paper
1 later
2209.14687 (2022-09)
Diffusion Posterior Sampling for General Noisy Inverse Problems

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

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 fewer 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 highfidelity samples in as few as 10 steps. Moreover, by directly using pre-trained DMs, we achieve state-of-art sampling performance when the number of score function evaluation (NFE) is limited, e.g., 4.17 FID with 10 NFEs, 2.86 FID with only 20 NFEs on CIFAR10. Project page and code: https://qsh-zh.github.io/deis.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2204.13902")
get_code_for_paper("2204.13902")
have("2204.13902")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2204.13902.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2204.13902.svg)](https://syntology.ai/paper/2204.13902)

Connect an agent — have() is free.