Papers › Scaling Diffusion Transformers to 16 Billion Parameters
Scaling Diffusion Transformers to 16 Billion Parameters
Zhengcong Fei, Mingyuan Fan, Changqian Yu, Debang Li, Junshi Huang
In this paper, we present DiT-MoE, a sparse version of the diffusion Transformer, that is scalable and competitive with dense networks while exhibiting highly optimized inference. The DiT-MoE includes two simple designs: shared expert routing and expert-level balance loss, thereby capturing common knowledge and reducing redundancy among the different routed experts. When applied to conditional image generation, a deep analysis of experts specialization gains some interesting observations: (i) Expert selection shows preference with spatial position and denoising time step, while insensitive with different class-conditional information; (ii) As the MoE layers go deeper, the selection of experts gradually shifts from specific spacial position to dispersion and balance. (iii) Expert specialization tends to be more concentrated at the early time step and then gradually uniform after half. We attribute it to the diffusion process that first models the low-frequency spatial information and then high-frequency complex information. Based on the above guidance, a series of DiT-MoE experimentally achieves performance on par with dense networks yet requires much less computational load during inference. More encouragingly, we demonstrate the potential of DiT-MoE with synthesized image data, scaling diffusion model at a 16.5B parameter that attains a new SoTA FID-50K score of 1.80 in 512×512 resolution settings. The project page: https://github.com/feizc/DiT-MoE.
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):
get_harvested_code_for_paper(arxiv_id="2407.11633")get_code(code_sha256="…")with a sample'scode_sha256from the list belowget_citation_path(paper_1="2407.11633", paper_2="…")with another paper's arXiv id or titleget_concepts_for_paper(arxiv_id="2407.11633")
Code
Syntology 16 code samples harvested from 1 repository linked to this paper: 12 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 4 honoured, 1 violated, 1 with no contract checked; 6 where Syntology's instrument failed) · 4 unverified. Where Syntology's instrument failed: 6 where our contract draft was wrong; failures of Syntology's instrument, not of the code.
By repository: official repository: 16 samples from 1 repository, 12 ran (6 with no instrument failure; 6 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 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 7 of the 12 samples that ran have no recorded date.
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
16 samples harvested: 12 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 4 honoured, 1 violated, 1 with no contract checked; 6 where Syntology's instrument failed) · 4 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.
Licence: 16 of the 16 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 feizc/dit-moe. “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.
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 diffusion/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 1712a07966b542ee · report
fixture: signature pil_image:Image/0/?, image_size:int/0/int · returned Image · level recorded, date not recorded 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 diffusion/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 7b21a01ae77703a3 · report
fixture: signature sample_dir:str/0/str, num:int/0/int · returned str · level recorded, date 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 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 36e30c7fb679ec78 · report
fixture: signature schedule_name:str/0/str, num_diffusion_timesteps:int/0/int · returned ndarray · level recorded 2026-09-22 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 diffusion/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 census: 3 implementations from 12 papers, 1 distinct output on one shared input models.py ran · our draft was wrong fingerprinted no licence file found · pointer only ·
03310bba324ae4fb · report
fixture: signature x:Tensor/2/float, shift:Tensor/1/float, scale:Tensor/1/float · returned Tensor · level recorded, date not recorded 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 diffusion/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 census: 4 implementations from 6 papers, 4 distinct outputs across 3 buckets, one shared input per bucket this sample: bucket 2 of 3, arg 1: rank 1, kind float, dtype float64 analysis/heatmap_class.py ran · violated contract fingerprinted no licence file found · pointer only ·
86c7147edb17dd5d · report
fixture: signature data:ndarray/1/float · returned ndarray · level recorded, date not recorded b789e06f5968456b · report
fixture: signature data:list/1/list, layer_num:int/0/int · returned ndarray · level recorded 2026-09-24 8382f7e48cc8a309 · report
6a0d5ecd441905cc · report
e8e07fe599aa424e · report
665d8a4e8f673a4c · report
Tasks
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
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