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 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

The archive's official repository (facebookresearch/DiT) was not harvested; the 18 samples below come from 5 community repositories, and 2 more are identical to code Syntology harvested from another paper's repository.

Syntology 20 code samples: 18 from 5 repositories linked to this paper, 2 identical to code harvested from another paper's repository. Across all 20: 15 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 2 honoured, 0 violated, 10 with no contract checked; 3 where Syntology's instrument failed) · 5 unverified. Where Syntology's instrument failed: 2 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 18 samples from 5 repositories, 14 ran (12 with no instrument failure; 2 where Syntology's instrument failed); 2 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.

No sample is linked to this paper from 3 of its repositories that Syntology harvested for other papers:

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. 3 of the 15 samples that ran have no recorded date.

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

facebookresearch/DiT officialmentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
FineDiffusion/FineDiffusion mentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
chuanyangjin/fast-dit mentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
hustvl/dig mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
locuslab/get mentioned on GitHubpytorchMITSyntology: 2 samples, 1 ran (0 instrument-failed) · 1 unverified report
milmor/diffusion-transformer mentioned on GitHubpytorchMITSyntology: 7 samples, 5 ran (1 instrument-failed) · 2 unverified report
milmor/diffusion-transformer-keras mentioned on GitHubtfMITSyntology: 6 samples, 6 ran (0 instrument-failed) · 0 unverified report
nyu-systems/grendel-gs mentioned on GitHubpytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to On Scaling Up 3D Gaussian Splatting Training (arXiv:2406.18533; that paper's own run record: 11 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 0 violated, 1 with no contract checked; 8 where Syntology's instrument failed) · 4 unverified); nothing checks that they implement this paper's method. report
senmaoy/RAT-Diffusion mentioned on GitHubpytorchSyntology: not harvested report
MindSpore-scientific/code-5 mindsporeSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Similarity of Neural Network Models: A Survey of Functional and Representational Measures (arXiv:2305.06329; that paper's own run record: 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
VachanVY/diffusion-transformer pytorchSyntology: 2 samples, 1 ran (0 instrument-failed) · 1 unverified report
huggingface/diffusers jaxSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to RefDecoder: Enhancing Visual Generation with Conditional Video Decoding (arXiv:2605.15196; that paper's own run record: 7 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 2 violated, 0 with no contract checked; 5 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
mindspore-lab/mindone mindsporenot reachable when probed 2026-09-17 — repositories for recent papers often appear after camera-readySyntology: not harvested 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

20 samples harvested: 15 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 2 honoured, 0 violated, 10 with no contract checked; 3 where Syntology's instrument failed) · 5 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

2ran · honoured contract
2ran · our draft was wrong
1ran; the contract check could not run
10ran
5unverified

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 5 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. 2 samples whose link to this paper records no repository are listed under one of this paper's own repositories, because identical code was harvested from it for another paper. 2 samples are listed last, in a group without a repository. “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.

hustvl/dig community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
get_1d_sincos_pos_embed_from_grid in 75 papers
census: 8 implementations from 17 papers, 2 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 1 of 2, arg 1: rank 1, kind float, dtype float64
models_dig.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant MIT (permissive) · e5947aba1d10885f · report fixture: signature embed_dim:int/0/int, pos:ndarray/1/float · returned ndarray · level recorded 2026-09-22
locuslab/get community (archive-listed) 2 samples, 1 ran (0 instrument-failed) · 1 unverified
get_2d_sincos_pos_embed in 170 papers models/get.py identical code Syntology harvested from this repository for another paper; this paper's link records no repository, path or licence of its own ran · honoured contract licence of this copy not recorded · c92c27c924b517e8 · report fixture: signature embed_dim:int/0/int, grid_size:int/0/int, cls_token:bool/0/bool, extra_tokens:int/0/int · returned ndarray · level recorded, date not recorded
get_2d_sincos_pos_embed_from_grid in 140 papers models/get.py identical code Syntology harvested from this repository for another paper; this paper's link records no repository, path or licence of its own unverified licence of this copy not recorded · 665d8a4e8f673a4c · report
milmor/diffusion-transformer community (archive-listed) 7 samples, 5 ran (1 instrument-failed) · 2 unverified
create_loader in 6 papers image_datasets.py ran MIT (permissive) · deedff7c289ab393 · report fixture: signature data_dir:str/0/str, img_size:int/0/int, batch_size:int/0/int · returned _MultiProcessingDataLoaderIter · level recorded 2026-09-25
deprocess in 13 papers utils.py ran fingerprinted MIT (permissive) · 00999b7ce52789e2 · report fixture: signature img:Tensor/2/float · returned Tensor · level recorded 2026-09-25
get_scalings diff_utils.py ran fingerprinted MIT (permissive) · 1a5424f761d38323 · report fixture: signature sig:Tensor/2/float, sig_data:Tensor/2/float · returned tuple · level recorded 2026-09-25
get_sigmas_karras in 8 papers diff_utils.py ran MIT (permissive) · fa7018efe2948b62 · report fixture: signature n:int/0/int, sigma_min:float/0/float, sigma_max:float/0/float, rho:float/0/float, device:str/0/str · returned Tensor · level recorded 2026-09-25
modulate in 137 papers
census: 3 implementations from 12 papers, 1 distinct output on one shared input
dit.py ran · our draft was wrong fingerprinted MIT (permissive) · 03310bba324ae4fb · report fixture: signature x:Tensor/2/float, shift:Tensor/1/float, scale:Tensor/1/float · returned Tensor · level recorded, date not recorded
calculate_activation_statistics in 75 papers fid.py unverified MIT (permissive) · c5a04d1cab5f16a8 · report
get_activations in 100 papers fid.py unverified MIT (permissive) · 63749a9f8d05d87c · report
milmor/diffusion-transformer-keras community (archive-listed) 6 samples, 6 ran (0 instrument-failed) · 0 unverified
calculate_activation_statistics in 75 papers fid.py ran MIT (permissive) · 55d54369eada8946 · report fixture: signature images:_BatchDataset/0/?, model:callable/0/?, batch_size:int/0/int · returned tuple · level recorded 2026-09-25
calculate_frechet_distance in 119 papers fid.py ran MIT (permissive) · ddaab4c77b3c0f3a · 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
convBlock discriminator.py ran MIT (permissive) · 03149bec2314ebce · report fixture: signature filters:int/0/int, kernel_size:int/0/int, initializer:str/0/str · returned Sequential · level recorded 2026-09-25
downBlock autoencoder.py ran MIT (permissive) · 177075a7f51b01e3 · report fixture: signature filters:int/0/int, kernel_size:int/0/int, initializer:str/0/str · returned Sequential · level recorded 2026-09-25
get_activations in 100 papers fid.py ran MIT (permissive) · b3a0c9d9b68b0ba4 · report fixture: signature dataset:_BatchDataset/0/?, inception:callable/0/?, batch_size:int/0/int · returned ndarray · level recorded 2026-09-25
upBlock in 12 papers autoencoder.py ran MIT (permissive) · dd229bfb0b49b0d5 · report fixture: signature filters:int/0/int, kernel_size:int/0/int, initializer:str/0/str · returned Sequential · level recorded 2026-09-25
VachanVY/diffusion-transformer community (archive-listed) 2 samples, 1 ran (0 instrument-failed) · 1 unverified
shift_scale torch_src/diffusion_transformer.py ran · honoured contract fingerprinted MIT (permissive) · 393c618733caf957 · report fixture: signature x:Tensor/2/float, gamma:Tensor/1/float, beta:Tensor/1/float · returned Tensor · level recorded 2026-09-22
get_diffution_transformer torch_src/diffusion_transformer.py unverified MIT (permissive) · 91f16882dada16e4 · report
Repository not located 2 samples, 1 ran (1 instrument-failed) · 1 unverified
2 samples are identical to code Syntology harvested from another paper's repository; this paper's own copy was not located, so no repository is named and no licence is recorded.
center_crop_arr in 79 papers repository not located ran · our draft was wrong licence of this copy not recorded · 1712a07966b542ee · report fixture: signature pil_image:Image/0/?, image_size:int/0/int · returned Image · level recorded, date not recorded
create_logger in 172 papers repository not located unverified licence of this copy not recorded · 8382f7e48cc8a309 · 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