Papers › Improved Denoising Diffusion Probabilistic Models

Improved Denoising Diffusion Probabilistic Models

18 Feb 2021arXiv:2102.09672archive 2025-07-28

Alex Nichol, Prafulla Dhariwal

Denoising diffusion probabilistic models (DDPM) are a class of generative models which have recently been shown to produce excellent samples. We show that with a few simple modifications, DDPMs can also achieve competitive log-likelihoods while maintaining high sample quality. Additionally, we find that learning variances of the reverse diffusion process allows sampling with an order of magnitude fewer forward passes with a negligible difference in sample quality, which is important for the practical deployment of these models. We additionally use precision and recall to compare how well DDPMs and GANs cover the target distribution. Finally, we show that the sample quality and likelihood of these models scale smoothly with model capacity and training compute, making them easily scalable. We release our code at https://github.com/openai/improved-diffusion

PaperPDFConference PDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2102.09672")

Code

Syntology Ran 9 of 11 code samples harvested from 4 repositories linked to this paper; 2 have no recorded run. Of those that ran: 4 ran · honoured contract; 4 ran · our draft was wrong; 1 ran · fixture could not drive it.

By repository: community (archive-listed): 11 samples from 4 repositories, 9 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

18 repositories listed; official and paper-mentioned ones first.

openai/improved-diffusion officialmentioned in papermentioned on GitHubpytorch report
Ipsedo/MusicDiffusion mentioned on GitHubpytorch report
albarji/toy-diffusion mentioned on GitHubpytorch report
astrodeepnet/diffusion4astro mentioned on GitHubpytorchMIT report
g4vrel/DDPM mentioned on GitHubpytorch report
intuitive-robots/beso mentioned on GitHubpytorch report
liaopeiyuan/pndm mentioned on GitHubpytorch report
luping-liu/PNDM mentioned on GitHubpytorch report
neonbjb/tortoise-tts mentioned on GitHubpytorch report
roselv/research_super-resolution mentioned on GitHubpytorch report
rowerliu/adbd mentioned on GitHubpytorchMIT report
rowerliu/add mentioned on GitHubpytorchMIT report
vvvm23/ddpm mentioned on GitHubpytorch report
YHL04/ddpm pytorch 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

11 samples harvested; 9 ran; 4 honoured the contract we drafted; 2 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

4ran · honoured contract
4ran · our draft was wrong
1ran · fixture could not drive it
2unverified

Licence: 0 of the 11 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 4 repositories linked to this paper, official or community; each sample names its own and says which. “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. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (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 from a repository marked official are listed first. 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 four 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; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). 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.

betas_for_alpha_bar g4vrel/DDPM/diffusion.py community (archive-listed) ran · honoured contract MIT (permissive) · 7eb19b2d745af94f · report
choose_method luping-liu/PNDM/runner/method.py community (archive-listed) ran · our draft was wrong Apache-2.0 (permissive) · 5261641d9240757c · report
compute_alpha g4vrel/DDPM/sample.py community (archive-listed) ran · our draft was wrong MIT (permissive) · 9215fb189fbfb9f4 · report
cosine_beta_schedule YHL04/ddpm/ddpm.py community (archive-listed) ran · honoured contract MIT (permissive) · 16240e26bc3e0d99 · report
ext g4vrel/DDPM/diffusion.py community (archive-listed) ran · fixture could not drive it fingerprinted MIT (permissive) · 97aabd2621b6733c · report
gen_fon luping-liu/PNDM/runner/method.py community (archive-listed) ran · our draft was wrong Apache-2.0 (permissive) · b84ad5937455cbb4 · report
gen_pflow luping-liu/PNDM/runner/method.py community (archive-listed) ran · our draft was wrong Apache-2.0 (permissive) · 5a415ade18521d1a · report
get_betas g4vrel/DDPM/diffusion.py community (archive-listed) ran · honoured contract MIT (permissive) · fab86763be9d382c · report
linear_beta_schedule YHL04/ddpm/ddpm.py community (archive-listed) ran · honoured contract MIT (permissive) · 412c5c40339e2941 · report
get_adaptive_hierarchy_n_level plai-group/flexible-video-diffusion-modeling/improved_diffusion/sampling_schemes.py community (archive-listed) unverified MIT (permissive) · 667c10845e9b4fce · report
get_hierarchy_n_level plai-group/flexible-video-diffusion-modeling/improved_diffusion/sampling_schemes.py community (archive-listed) unverified MIT (permissive) · 16222780c0751c86 · report

Tasks

DenoisingImage Generation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Generation ImageNet 256x256 Improved DDPM FID 12.3 #94 of 94 Archive leaderboard report
Image Generation ImageNet 64x64 Improved DDPM Bits per dim 3.53 #21 of 65 Archive leaderboard report
Image Generation ImageNet 64x64 Improved DDPM FID 2.92 #21 of 65 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