Papers › EDT: An Efficient Diffusion Transformer Framework Inspired by Human-like Sketching

EDT: An Efficient Diffusion Transformer Framework Inspired by Human-like Sketching

31 Oct 2024arXiv:2410.23788archive 2025-07-28

Xinwang Chen, Ning Liu, Yichen Zhu, Feifei Feng, Jian Tang

Transformer-based Diffusion Probabilistic Models (DPMs) have shown more potential than CNN-based DPMs, yet their extensive computational requirements hinder widespread practical applications. To reduce the computation budget of transformer-based DPMs, this work proposes the Efficient Diffusion Transformer (EDT) framework. The framework includes a lightweight-design diffusion model architecture, and a training-free Attention Modulation Matrix and its alternation arrangement in EDT inspired by human-like sketching. Additionally, we propose a token relation-enhanced masking training strategy tailored explicitly for EDT to augment its token relation learning capability. Our extensive experiments demonstrate the efficacy of EDT. The EDT framework reduces training and inference costs and surpasses existing transformer-based diffusion models in image synthesis performance, thereby achieving a significant overall enhancement. With lower FID, EDT-S, EDT-B, and EDT-XL attained speed-ups of 3.93x, 2.84x, and 1.92x respectively in the training phase, and 2.29x, 2.29x, and 2.22x respectively in inference, compared to the corresponding sizes of MDTv2. The source code is released at https://github.com/xinwangChen/EDT.

PaperPDFCodeCode Syntology ranMethod as code

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 15 code samples: 13 from 1 repository linked to this paper, 2 identical to code harvested from another paper's repository. Across all 15: 12 ran (of which 7 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 0 violated, 8 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified. Where Syntology's instrument failed: 3 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 13 samples from 1 repository, 10 ran (9 with no instrument failure; 1 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.

Levels written between 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 3 of the 12 samples that ran have no recorded date.

xinwangchen/edt officialmentioned in papermentioned on GitHubpytorchSyntology: 13 samples, 10 ran (1 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

15 samples harvested: 12 ran (of which 7 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 0 violated, 8 with no contract checked; 3 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 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.

1ran · honoured contract
3ran · our draft was wrong
8ran
3unverified

Licence: 2 of the 15 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 xinwangchen/edt. 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”. For 2 samples that ran, the graph records a signature this page does not show: for a class the fixture built without calling, the harness called the object with inputs it made up itself, so the recorded signature is the harness's probe, not the fixture's arguments. “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.

xinwangchen/edt official repository 13 samples, 10 ran (1 instrument-failed) · 3 unverified
AttentionBlock in 69 papers models_edt.py ran Apache-2.0 (permissive) · 134572c5986fe4b4 · report fixture: returned AttentionBlock · level recorded 2026-09-22
ConcatLayer models_edt.py ran Apache-2.0 (permissive) · 13a3e1751106ddb0 · report fixture: returned ConcatLayer · level recorded 2026-09-22
DownSample in 11 papers models_edt.py ran Apache-2.0 (permissive) · 8f87a045a084b3d9 · report fixture: returned DownSample · level recorded 2026-09-22
FinalLayer in 29 papers models_edt.py ran Apache-2.0 (permissive) · 413ff2ca1aeb13c7 · report fixture: returned FinalLayer · level recorded 2026-09-22
LabelEmbedder in 13 papers models_edt.py ran Apache-2.0 (permissive) · 3da76c6c6b6525e1 · report fixture: returned LabelEmbedder · level recorded 2026-09-22
RelativePositionBias models_edt.py ran Apache-2.0 (permissive) · 5f8f1f6855dddcde · report fixture: returned RelativePositionBias · level recorded 2026-09-22
TimestepEmbedder in 27 papers
census: 9 implementations from 9 papers, 5 distinct outputs across 2 buckets, one shared input per bucket
models_edt.py ran fingerprinted Apache-2.0 (permissive) · eaa37c820e8a1833 · report fixture: signature t:Tensor/1/int · returned Tensor · level recorded 2026-09-24
UpSample in 9 papers models_edt.py ran Apache-2.0 (permissive) · 60606b9b68ee5cc9 · report fixture: returned UpSample · level recorded 2026-09-22
create_logger in 172 papers train_mask_adan.py ran · our draft was wrong Apache-2.0 (permissive) · b2cc78f4103df806 · report fixture: signature logging_dir:str/0/str · returned Logger · level recorded, date not recorded
euclidean_distances models_edt.py ran · honoured contract fingerprinted Apache-2.0 (permissive) · 2862af7287c26735 · report fixture: signature row_n:int/0/int, col_n:int/0/int · returned Tensor · level recorded 2026-09-22
EDT models_edt.py unverified Apache-2.0 (permissive) · 03be0381bf318157 · report
EDTBlock models_edt.py unverified Apache-2.0 (permissive) · dc3f4c792419cf2b · report
modulation_matrix models_edt.py unverified Apache-2.0 (permissive) · f7362f7feea04ab2 · report
Repository not located 2 samples, 2 ran (2 instrument-failed) · 0 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_npz_from_sample_folder in 30 papers repository not located ran · our draft was wrong licence of this copy not recorded · 7b21a01ae77703a3 · report fixture: signature sample_dir:str/0/str, num:int/0/int · returned str · level recorded, date not recorded

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it.

1 assembly on this paper: 1 harvested, 0 generated.

harvested Assembly for EDT (graph method: EDT). 16 bricks; individually on a fixture: 12 ran (of which 7 constructed an object rather than computing a result; 10 with no instrument failure: 2 honoured, 0 violated, 8 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified. The assembly has not been run end-to-end.

  1. EDT entry · level 0 · unverified · 03be0381bf318157
  2. ConcatLayer model · level 1 · ran · 13a3e1751106ddb0
  3. DownSample model · level 1 · ran · 8f87a045a084b3d9
  4. EDTBlock model · level 0 · unverified · dc3f4c792419cf2b
  5. FinalLayer model · level 1 · ran · 413ff2ca1aeb13c7
  6. LabelEmbedder model · level 1 · ran · 3da76c6c6b6525e1
  7. TimestepEmbedder model · level 1 · ran · eaa37c820e8a1833
  8. UpSample model · level 1 · ran · 60606b9b68ee5cc9
  9. get_2d_sincos_pos_embed helper · level 1 · ran · honoured contract · 1df7f271ba4dbf2a
  10. modulate helper · level 1 · ran · our draft was wrong · 03310bba324ae4fb
  11. AttentionBlock model · level 1 · ran · 134572c5986fe4b4
  12. get_2d_sincos_pos_embed_from_grid helper · level 0 · unverified · 665d8a4e8f673a4c
  13. RelativePositionBias model · level 1 · ran · 5f8f1f6855dddcde
  14. modulation_matrix helper · level 0 · unverified · f7362f7feea04ab2
  15. get_1d_sincos_pos_embed_from_grid helper · level 1 · ran; the contract check could not run · e5947aba1d10885f
  16. euclidean_distances helper · level 1 · ran · honoured contract · 2862af7287c26735

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2410.23788") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Image Generation

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

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

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