Papers › Scalable Diffusion Models with Transformers

Scalable Diffusion Models with Transformers

19 Dec 2022ICCV 2023 1arXiv:2212.09748archive 2025-07-28

William Peebles, Saining Xie

We explore a new class of diffusion models based on the transformer architecture. We train latent diffusion models of images, replacing the commonly-used U-Net backbone with a transformer that operates on latent patches. We analyze the scalability of our Diffusion Transformers (DiTs) through the lens of forward pass complexity as measured by Gflops. We find that DiTs with higher Gflops -- through increased transformer depth/width or increased number of input tokens -- consistently have lower FID. In addition to possessing good scalability properties, our largest DiT-XL/2 models outperform all prior diffusion models on the class-conditional ImageNet 512x512 and 256x256 benchmarks, achieving a state-of-the-art FID of 2.27 on the latter.

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="2212.09748")

Code

Syntology Ran 5 of 20 code samples harvested from 4 repositories linked to this paper; 15 have no recorded run. Of those that ran: 2 ran · honoured contract; 2 ran · our draft was wrong; 1 ran · fixture could not drive it.

By repository: community (archive-listed): 16 samples from 4 repositories, 3 ran; 4 identical to code first harvested elsewhere. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

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

facebookresearch/DiT officialmentioned on GitHubpytorchNOASSERTION report
FineDiffusion/FineDiffusion mentioned on GitHubpytorchNOASSERTION report
chuanyangjin/fast-dit mentioned on GitHubpytorchNOASSERTION report
hustvl/dig mentioned on GitHubpytorch report
locuslab/get mentioned on GitHubpytorchMIT report
milmor/diffusion-transformer mentioned on GitHubpytorchMIT report
milmor/diffusion-transformer-keras mentioned on GitHubtfMIT report
nyu-systems/grendel-gs mentioned on GitHubpytorchApache-2.0 report
senmaoy/RAT-Diffusion mentioned on GitHubpytorch report
mindspore-lab/mindone mindsporenot reachable when probed 2026-09-17 — repositories for recent papers often appear after camera-ready 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

20 samples harvested; 5 ran; 2 honoured the contract we drafted; 15 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.

2ran · honoured contract
2ran · our draft was wrong
1ran · fixture could not drive it
15unverified

Licence: 4 of the 20 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. Some samples are identical code Syntology first harvested from another repository; for those, this paper's copy is not located and its licence is not recorded. “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.

get_1d_sincos_pos_embed_from_grid hustvl/dig/models_dig.py community (archive-listed) ran · fixture could not drive it fingerprinted MIT (permissive) · e5947aba1d10885f · report
modulate milmor/diffusion-transformer/dit.py community (archive-listed) ran · our draft was wrong fingerprinted MIT (permissive) · 03310bba324ae4fb · report
shift_scale VachanVY/diffusion-transformer/torch_src/diffusion_transformer.py community (archive-listed) ran · honoured contract fingerprinted MIT (permissive) · 393c618733caf957 · report
calculate_activation_statistics milmor/diffusion-transformer/fid.py community (archive-listed) unverified MIT (permissive) · c5a04d1cab5f16a8 · report
calculate_activation_statistics milmor/diffusion-transformer-keras/fid.py community (archive-listed) unverified MIT (permissive) · 55d54369eada8946 · report
calculate_frechet_distance milmor/diffusion-transformer-keras/fid.py community (archive-listed) unverified MIT (permissive) · ddaab4c77b3c0f3a · report
convBlock milmor/diffusion-transformer-keras/discriminator.py community (archive-listed) unverified MIT (permissive) · 03149bec2314ebce · report
create_loader milmor/diffusion-transformer/image_datasets.py community (archive-listed) unverified MIT (permissive) · deedff7c289ab393 · report
deprocess milmor/diffusion-transformer/utils.py community (archive-listed) unverified MIT (permissive) · 00999b7ce52789e2 · report
downBlock milmor/diffusion-transformer-keras/autoencoder.py community (archive-listed) unverified MIT (permissive) · 177075a7f51b01e3 · report
get_activations milmor/diffusion-transformer/fid.py community (archive-listed) unverified MIT (permissive) · 63749a9f8d05d87c · report
get_activations milmor/diffusion-transformer-keras/fid.py community (archive-listed) unverified MIT (permissive) · b3a0c9d9b68b0ba4 · report
get_diffution_transformer VachanVY/diffusion-transformer/torch_src/diffusion_transformer.py community (archive-listed) unverified MIT (permissive) · 91f16882dada16e4 · report
get_scalings milmor/diffusion-transformer/diff_utils.py community (archive-listed) unverified MIT (permissive) · 1a5424f761d38323 · report
get_sigmas_karras milmor/diffusion-transformer/diff_utils.py community (archive-listed) unverified MIT (permissive) · fa7018efe2948b62 · report
upBlock milmor/diffusion-transformer-keras/autoencoder.py community (archive-listed) unverified MIT (permissive) · dd229bfb0b49b0d5 · report
center_crop_arr identical code first harvested elsewhere ran · our draft was wrong licence of this copy not recorded · 1712a07966b542ee · report
get_2d_sincos_pos_embed identical code first harvested elsewhere ran · honoured contract licence of this copy not recorded · c92c27c924b517e8 · report
create_logger identical code first harvested elsewhere unverified licence of this copy not recorded · 8382f7e48cc8a309 · report
get_2d_sincos_pos_embed_from_grid identical code first harvested elsewhere unverified licence of this copy not recorded · 665d8a4e8f673a4c · report

Tasks

Image Generation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Generation ImageNet 256x256 DiT-XL/2 FID 2.27 #54 of 94 Archive leaderboard report
Image Generation ImageNet 512x512 DiT-XL/2 FID 3.04 #41 of 52 Archive leaderboard report
Image Generation ImageNet 512x512 DiT-XL/2 Inception score 240.82 #41 of 52 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

Concatenated Skip ConnectionConvolutionDiffusionMax PoolingReLUTransformerU-Net

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