Papers › FasterDiT: Towards Faster Diffusion Transformers Training without Architecture Modification

FasterDiT: Towards Faster Diffusion Transformers Training without Architecture Modification

14 Oct 2024arXiv:2410.10356archive 2025-07-28

Jingfeng Yao, Wang Cheng, Wenyu Liu, Xinggang Wang

Diffusion Transformers (DiT) have attracted significant attention in research. However, they suffer from a slow convergence rate. In this paper, we aim to accelerate DiT training without any architectural modification. We identify the following issues in the training process: firstly, certain training strategies do not consistently perform well across different data. Secondly, the effectiveness of supervision at specific timesteps is limited. In response, we propose the following contributions: (1) We introduce a new perspective for interpreting the failure of the strategies. Specifically, we slightly extend the definition of Signal-to-Noise Ratio (SNR) and suggest observing the Probability Density Function (PDF) of SNR to understand the essence of the data robustness of the strategy. (2) We conduct numerous experiments and report over one hundred experimental results to empirically summarize a unified accelerating strategy from the perspective of PDF. (3) We develop a new supervision method that further accelerates the training process of DiT. Based on them, we propose FasterDiT, an exceedingly simple and practicable design strategy. With few lines of code modifications, it achieves 2.30 FID on ImageNet 256 resolution at 1000k iterations, which is comparable to DiT (2.27 FID) but 7 times faster in training.

PaperPDFCodeCode 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="2410.10356")

Code

Syntology Ran 6 of 10 code samples harvested from 1 repository linked to this paper; 4 have no recorded run. Of those that ran: 6 ran with no contract checked.

By repository: community (archive-listed): 10 samples from 1 repository, 6 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

hustvl/LightningDiT mentioned on GitHubpytorch 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

10 samples harvested; 6 ran; 0 honoured the contract we drafted; 4 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.

6ran
4unverified

Licence: 0 of the 10 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 hustvl/LightningDiT. “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.

Attention hustvl/LightningDiT/models/lightningdit.py community (archive-listed) ran MIT (permissive) · 10d58a623eb5beb1 · report
FinalLayer hustvl/LightningDiT/models/lightningdit.py community (archive-listed) ran MIT (permissive) · 044b0ed1c2fd2514 · report
LabelEmbedder hustvl/LightningDiT/models/lightningdit.py community (archive-listed) ran MIT (permissive) · 908133c58e4b4a36 · report
RMSNorm hustvl/LightningDiT/models/lightningdit.py community (archive-listed) ran MIT (permissive) · 3777a235d6ea1491 · report
SwiGLUFFN hustvl/LightningDiT/models/lightningdit.py community (archive-listed) ran MIT (permissive) · 39fbca475083b37f · report
VisionRotaryEmbeddingFast hustvl/LightningDiT/models/lightningdit.py community (archive-listed) ran MIT (permissive) · 64a16f9548e5d293 · report
LightningDiT hustvl/LightningDiT/models/lightningdit.py community (archive-listed) unverified MIT (permissive) · 4f92bf659324e8f1 · report
LightningDiTBlock hustvl/LightningDiT/models/lightningdit.py community (archive-listed) unverified MIT (permissive) · 3df6325a7d960bdc · report
TimestepEmbedder hustvl/LightningDiT/models/lightningdit.py community (archive-listed) unverified MIT (permissive) · 8f2712b9234f6ba0 · report
modulate hustvl/LightningDiT/models/lightningdit.py community (archive-listed) unverified MIT (permissive) · 5ea6b9bd142d4069 · report

Tasks

Image Generation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Generation ImageNet 256x256 FasterDiT-XL/2 FID 2.03 #49 of 94 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

AttentionSoftmax

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