Papers › On Inference Stability for Diffusion Models

On Inference Stability for Diffusion Models

19 Dec 2023arXiv:2312.12431archive 2025-07-28

Viet Nguyen, Giang Vu, Tung Nguyen Thanh, Khoat Than, Toan Tran

Denoising Probabilistic Models (DPMs) represent an emerging domain of generative models that excel in generating diverse and high-quality images. However, most current training methods for DPMs often neglect the correlation between timesteps, limiting the model's performance in generating images effectively. Notably, we theoretically point out that this issue can be caused by the cumulative estimation gap between the predicted and the actual trajectory. To minimize that gap, we propose a novel sequence-aware loss that aims to reduce the estimation gap to enhance the sampling quality. Furthermore, we theoretically show that our proposed loss function is a tighter upper bound of the estimation loss in comparison with the conventional loss in DPMs. Experimental results on several benchmark datasets including CIFAR10, CelebA, and CelebA-HQ consistently show a remarkable improvement of our proposed method regarding the image generalization quality measured by FID and Inception Score compared to several DPM baselines. Our code and pre-trained checkpoints are available at https://github.com/VinAIResearch/SA-DPM.

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 14 code samples harvested from 1 repository linked to this paper: 11 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 2 honoured, 0 violated, 3 with no contract checked; 6 where Syntology's instrument failed) · 3 unverified. Where Syntology's instrument failed: 3 where our contract draft was wrong; 3 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, 11 ran (5 with no instrument failure; 6 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 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 5 of the 11 samples that ran have no recorded date.

vinairesearch/sa-dpm officialmentioned in papermentioned on GitHubpytorchAGPL-3.0Syntology: 14 samples, 11 ran (6 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.

Code Syntology ran Syntology

14 samples harvested: 11 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 2 honoured, 0 violated, 3 with no contract checked; 6 where Syntology's instrument failed) · 3 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.

2ran · honoured contract
3ran · our draft was wrong
3ran; the contract check could not run
3ran
3unverified

Licence: 14 of the 14 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 vinairesearch/sa-dpm. “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.

vinairesearch/sa-dpm official repository 14 samples, 11 ran (6 instrument-failed) · 3 unverified
Normalize in 154 papers models/diffusion.py ran · our draft was wrong AGPL-3.0 (copyleft) · pointer only · c3a6b977022957cb · report fixture: signature in_channels:int/0/int · returned GroupNorm · level recorded, date not recorded
calculate_alpha functions/losses.py ran · our draft was wrong AGPL-3.0 (copyleft) · pointer only · 748faa99f5d069c5 · report fixture: signature beta:Tensor/1/float · returned dict · level recorded 2026-09-24
calculate_frechet_distance in 119 papers pytorch_fid/fid_score.py ran AGPL-3.0 (copyleft) · pointer only · fcdc92d3d2e8edc1 · report fixture: signature mu1:ndarray/1/float, sigma1:ndarray/2/float, mu2:ndarray/1/float, sigma2:ndarray/2/float, eps:float/0/float · returned float64 · level recorded 2026-09-25
drop_path in 325 papers
census: 27 implementations from 61 papers, 5 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 1 of 2, arg 1: rank 4, kind float, dtype float32
models/timm.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant AGPL-3.0 (copyleft) · pointer only · 39eace7e2822504f · report fixture: signature x:Tensor/4/float, drop_prob:float/0/float, training:bool/0/bool · returned Tensor · level recorded 2026-09-22
extract_into_tensor in 33 papers
census: 3 implementations from 5 papers, 1 distinct output on one shared input
functions/losses.py ran AGPL-3.0 (copyleft) · pointer only · cc45f50a2bd93ac1 · report fixture: signature x:Tensor/1/float, t:Tensor/1/int · returned Tensor · level recorded 2026-09-24
get_beta_schedule in 66 papers generate.py ran · honoured contract AGPL-3.0 (copyleft) · pointer only · ca0cea1ca1eeec89 · report fixture: signature beta_schedule:str/0/str, beta_start:float/0/float, beta_end:float/0/float, num_diffusion_timesteps:int/0/int · returned ndarray · level recorded, date not recorded
get_timestep_embedding in 138 papers
census: 11 implementations from 15 papers, 5 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 1 of 2, arg 1: rank 1, kind int, dtype int64
models/diffusion.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant AGPL-3.0 (copyleft) · pointer only · cb49209c125de1b4 · report fixture: signature timesteps:Tensor/1/int, embedding_dim:int/0/int · returned Tensor · level recorded, date not recorded
nonlinearity in 140 papers
census: 4 implementations from 11 papers, 1 distinct output on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32
models/diffusion.py ran · our draft was wrong fingerprinted AGPL-3.0 (copyleft) · pointer only · 3137073275f8c21a · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded, date not recorded
parse_int_list in 59 papers generate.py ran · honoured contract AGPL-3.0 (copyleft) · pointer only · cacd4f6ec202d9b4 · report fixture: signature s:str/0/str · returned list · level recorded, date not recorded
sample_image in 5 papers generate.py ran AGPL-3.0 (copyleft) · pointer only · 3b27a6175d73a50b · report fixture: signature args:Args/0/?, config:Config/0/?, x:Tensor/4/float, model:callable/0/?, randn_like:callable/0/?, last:bool/0/bool · returned Tensor · level recorded 2026-09-24
trunc_normal_ in 154 papers
census: 37 implementations from 54 papers, 4 distinct outputs on one shared input
models/timm.py ran; the contract check could not run (RAISES) AGPL-3.0 (copyleft) · pointer only · 5436174f8c0e64e0 · report fixture: signature tensor:Tensor/2/float, mean:float/0/float, std:float/0/float, a:float/0/float, b:float/0/float · returned Tensor · level recorded 2026-09-26
calculate_activation_statistics in 75 papers pytorch_fid/fid_score.py unverified AGPL-3.0 (copyleft) · pointer only · bd88683e6bd4454d · report
get_activations in 100 papers pytorch_fid/fid_score.py unverified AGPL-3.0 (copyleft) · pointer only · 26edbd4467e04bec · report
sequence_aware_loss functions/losses.py unverified AGPL-3.0 (copyleft) · pointer only · 37f492692ae34358 · report

Tasks

Denoising

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