Papers › DiffiT: Diffusion Vision Transformers for Image Generation

DiffiT: Diffusion Vision Transformers for Image Generation

4 Dec 2023arXiv:2312.02139archive 2025-07-28

Ali Hatamizadeh, Jiaming Song, Guilin Liu, Jan Kautz, Arash Vahdat

Diffusion models with their powerful expressivity and high sample quality have achieved State-Of-The-Art (SOTA) performance in the generative domain. The pioneering Vision Transformer (ViT) has also demonstrated strong modeling capabilities and scalability, especially for recognition tasks. In this paper, we study the effectiveness of ViTs in diffusion-based generative learning and propose a new model denoted as Diffusion Vision Transformers (DiffiT). Specifically, we propose a methodology for finegrained control of the denoising process and introduce the Time-dependant Multihead Self Attention (TMSA) mechanism. DiffiT is surprisingly effective in generating high-fidelity images with significantly better parameter efficiency. We also propose latent and image space DiffiT models and show SOTA performance on a variety of class-conditional and unconditional synthesis tasks at different resolutions. The Latent DiffiT model achieves a new SOTA FID score of 1.73 on ImageNet256 dataset while having 19.85%, 16.88% less parameters than other Transformer-based diffusion models such as MDT and DiT,respectively. Code: https://github.com/NVlabs/DiffiT

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 25 code samples harvested from 1 repository linked to this paper: 20 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 3 honoured, 1 violated, 2 with no contract checked; 14 where Syntology's instrument failed) · 5 unverified. Where Syntology's instrument failed: 11 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: 25 samples from 1 repository, 20 ran (6 with no instrument failure; 14 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. 4 of the 20 samples that ran have no recorded date.

nvlabs/diffit officialmentioned in papermentioned on GitHubpytorchNOASSERTIONSyntology: 25 samples, 20 ran (14 instrument-failed) · 5 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

25 samples harvested: 20 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 3 honoured, 1 violated, 2 with no contract checked; 14 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 last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

3ran · honoured contract
1ran · violated contract
11ran · our draft was wrong
3ran; the contract check could not run
2ran
5unverified

Licence: 25 of the 25 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 nvlabs/diffit. “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.

nvlabs/diffit official repository 25 samples, 20 ran (14 instrument-failed) · 5 unverified
center_crop_arr in 79 papers diffit/image_datasets.py ran · our draft was wrong no licence file found · pointer only · 8ab9a97df8161f31 · report fixture: signature pil_image:Image/0/?, image_size:int/0/int · returned ndarray · level recorded, date not recorded
approx_standard_normal_cdf in 150 papers
census: 4 implementations from 14 papers, 1 distinct output on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32
diffit/diffusion_utils.py ran · our draft was wrong fingerprinted no licence file found · pointer only · d6a68e210556f857 · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded, date not recorded
args_to_dict in 8 papers diffit/script_util.py ran no licence file found · pointer only · 4e2ac192b520c457 · report fixture: signature args:Args/0/?, keys:list/1/str · returned dict · level recorded 2026-09-24
continuous_gaussian_log_likelihood in 27 papers
census: 2 implementations from 5 papers, 1 distinct output on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32 · arg 2: rank 2, kind float, dtype float32 · arg 3: rank 2, kind float, dtype float32
diffit/diffusion_utils.py ran · our draft was wrong no licence file found · pointer only · ab1c9568b4e13899 · report fixture: signature x:Tensor/2/float, means:Tensor/2/float, log_scales:Tensor/2/float · returned Tensor · level recorded 2026-09-22
create_named_schedule_sampler in 58 papers diffit/resample.py ran · our draft was wrong no licence file found · pointer only · 35572566acf61c78 · report fixture: signature name:str/0/str, diffusion:MockDiffusion/0/? · returned UniformSampler · level recorded 2026-09-22
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
diffit/diffit.py ran; the contract check could not run (RAISES) licence not identified · pointer only · aa58f30251e59c74 · report fixture: signature embed_dim:int/0/int, pos:ndarray/1/float · returned ndarray · level recorded 2026-09-24
get_2d_sincos_pos_embed in 170 papers diffit/diffit.py ran licence not identified · pointer only · d77775e45836dc1a · 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 2026-09-24
get_beta_schedule in 66 papers diffit/gaussian_diffusion.py ran · honoured contract no licence file found · pointer only · 3e0fa4efc22272d4 · 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 2026-09-22
get_named_beta_schedule in 119 papers diffit/gaussian_diffusion.py ran · honoured contract no licence file found · pointer only · 36e30c7fb679ec78 · report fixture: signature schedule_name:str/0/str, num_diffusion_timesteps:int/0/int · returned ndarray · level recorded 2026-09-22
get_param_groups_and_shapes in 73 papers diffit/fp16_util.py ran · our draft was wrong no licence file found · pointer only · e41367ad14ff58fd · report fixture: signature named_model_params:list/1/tuple · returned list · level recorded 2026-09-24
make_master_params in 90 papers diffit/fp16_util.py ran · our draft was wrong no licence file found · pointer only · e20dd5102da3b050 · report fixture: signature param_groups_and_shapes:list/1/tuple · returned list · level recorded 2026-09-24
make_output_format in 88 papers diffit/logger.py ran · our draft was wrong no licence file found · pointer only · bcd8b4acab199405 · report fixture: signature format:str/0/str, ev_dir:str/0/str, log_suffix:str/0/str · returned HumanOutputFormat · level recorded 2026-09-24
mean_flat in 53 papers
census: 9 implementations from 18 papers, 4 distinct outputs across 3 buckets, one shared input per bucket this sample: bucket 1 of 3, arg 1: rank 3, kind float, dtype float32
diffit/gaussian_diffusion.py ran · our draft was wrong fingerprinted no licence file found · pointer only · f6d7c009a8efb8b7 · report fixture: signature tensor:Tensor/3/float · returned Tensor · level recorded, date not recorded
mpi_weighted_mean in 55 papers diffit/logger.py ran · our draft was wrong no licence file found · pointer only · e515a67f7f32e76d · report fixture: signature comm:MockComm/0/?, local_name2valcount:dict/0/? · returned dict · level recorded 2026-09-26
normal_kl in 188 papers
census: 14 implementations from 24 papers, 2 distinct outputs on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32 · arg 2: rank 2, kind float, dtype float32 · arg 3: rank 2, kind float, dtype float32 · arg 4: rank 2, kind float, dtype float32
diffit/diffusion_utils.py ran · honoured contract fingerprinted no licence file found · pointer only · 8afbfc42c6ea0448 · report fixture: signature mean1:Tensor/2/float, logvar1:Tensor/2/float, mean2:Tensor/2/float, logvar2:Tensor/2/float · returned Tensor · level recorded 2026-09-22
random_crop_arr in 41 papers diffit/image_datasets.py ran · our draft was wrong no licence file found · pointer only · 53d5be4fdbcfac23 · report fixture: signature pil_image:Image/0/?, image_size:int/0/int, min_crop_frac:float/0/float, max_crop_frac:float/0/float · returned ndarray · level recorded 2026-09-26
space_timesteps in 72 papers diffit/respace.py ran; the contract check could not run (RAISES) · metamorphic tier: deterministic no licence file found · pointer only · ea9dbc131adf582e · report fixture: signature num_timesteps:int/0/int, section_counts:list/1/int · returned set · level recorded 2026-09-22
str2bool in 533 papers diffit/script_util.py ran · violated contract no licence file found · pointer only · 721eef93e7a633a1 · report fixture: signature v:str/0/str · returned bool · level recorded, date not recorded
unflatten_master_params in 90 papers diffit/fp16_util.py ran; the contract check could not run (RAISES) no licence file found · pointer only · 64fff1e30802b815 · report fixture: signature param_group:list/1/tuple, master_param:Tensor/1/float · returned tuple · level recorded 2026-09-24
zero_module in 184 papers diffit/nn.py ran · our draft was wrong no licence file found · pointer only · 129b804760b3115f · report fixture: signature module:callable/0/? · returned SimpleModule · level recorded 2026-09-22
avg_pool_nd in 83 papers diffit/nn.py unverified no licence file found · pointer only · ecd0fc28815b65ae · report
conv_nd in 94 papers diffit/nn.py unverified no licence file found · pointer only · fe4eb545bbb728e0 · report
get_2d_sincos_pos_embed_from_grid in 140 papers diffit/diffit.py unverified licence not identified · pointer only · 5f78ec79ce3ed0a3 · report
load_state_dict in 114 papers diffit/dist_util.py unverified licence not identified · pointer only · bd2d797cf36610b5 · report
profile in 89 papers diffit/logger.py unverified licence not identified · pointer only · 7065e4d5f1f47817 · report

Tasks

DenoisingImage Generation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Generation ImageNet 256x256 DiffiT FID 1.73 #36 of 94 Archive leaderboard report
Image Generation ImageNet 512x512 DiffiT FID 2.67 #35 of 52 Archive leaderboard report
Image Generation ImageNet 512x512 DiffiT Inception score 252.12 #35 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

Absolute Position EncodingsAdamAttentionBPEDense ConnectionsDiffusionDropoutLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSoftmaxTransformerVision Transformer

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