Papers › PixArt-Σ: Weak-to-Strong Training of Diffusion Transformer for 4K Text-to-Image Generation
PixArt-Σ: Weak-to-Strong Training of Diffusion Transformer for 4K Text-to-Image Generation
Junsong Chen, Chongjian Ge, Enze Xie, Yue Wu, Lewei Yao, Xiaozhe Ren, Zhongdao Wang, Ping Luo, Huchuan Lu, Zhenguo Li
In this paper, we introduce PixArt-Σ, a Diffusion Transformer model (DiT) capable of directly generating images at 4K resolution. PixArt-Σ represents a significant advancement over its predecessor, PixArt-α, offering images of markedly higher fidelity and improved alignment with text prompts. A key feature of PixArt-Σ is its training efficiency. Leveraging the foundational pre-training of PixArt-α, it evolves from the `weaker' baseline to a `stronger' model via incorporating higher quality data, a process we term "weak-to-strong training". The advancements in PixArt-Σ are twofold: (1) High-Quality Training Data: PixArt-Σ incorporates superior-quality image data, paired with more precise and detailed image captions. (2) Efficient Token Compression: we propose a novel attention module within the DiT framework that compresses both keys and values, significantly improving efficiency and facilitating ultra-high-resolution image generation. Thanks to these improvements, PixArt-Σ achieves superior image quality and user prompt adherence capabilities with significantly smaller model size (0.6B parameters) than existing text-to-image diffusion models, such as SDXL (2.6B parameters) and SD Cascade (5.1B parameters). Moreover, PixArt-Σ's capability to generate 4K images supports the creation of high-resolution posters and wallpapers, efficiently bolstering the production of high-quality visual content in industries such as film and gaming.
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="2403.04692")get_code(code_sha256="…")with a sample'scode_sha256from the list belowget_citation_path(paper_1="2403.04692", paper_2="…")with another paper's arXiv id or titleget_concepts_for_paper(arxiv_id="2403.04692")
Code
Syntology 9 code samples: 7 from 1 repository linked to this paper, 2 identical to code harvested from another paper's repository. Across all 9: 6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 1 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; 2 where the contract check could not run; failures of Syntology's instrument, not of the code.
By repository: official repository: 7 samples from 1 repository, 5 ran (3 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.
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 6 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
9 samples harvested: 6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 1 violated, 1 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 last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.
Licence: 6 of the 9 samples are pointer only, meaning Syntology does not serve that copy's text. For 4 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.
Harvested from PixArt-alpha/PixArt-sigma. 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.
census: 3 implementations from 6 papers, 1 distinct output on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32 train_scripts/train_pixart_lcm.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted Apache-2.0 (permissive) here; the stored copy is pointer only ·
30befb7e4327e615 · report
fixture: signature x:Tensor/2/float, target_dims:int/0/int · returned Tensor · level recorded, date not recorded 652bf9fefb65310b · report
fixture: signature style_name:str/0/str, positive:str/0/str, negative:str/0/str · returned tuple · level recorded 2026-09-24 census: 3 implementations from 5 papers, 1 distinct output on one shared input this sample: bucket 1 of 1, arg 1: rank 1, kind float, dtype float32 · arg 2: rank 1, kind int, dtype int64 train_scripts/train_pixart_lcm.py ran · our draft was wrong Apache-2.0 (permissive) here; the stored copy is pointer only ·
a15cfd7932844ef9 · report
fixture: signature a:Tensor/1/float, t:Tensor/1/int, x_shape:tuple/1/int · returned Tensor · level recorded, date not recorded 1c00f3d9c2aa103c · report
fixture: signature seed:int/0/int, randomize_seed:bool/0/bool · returned int · level recorded 2026-09-24 bf8e9418920783fb · report
fixture: signature timestep:Tensor/0/float, sigma_data:float/0/float, timestep_scaling:float/0/float · returned tuple · level recorded, date not recorded 168a4054b9fdff36 · report
b5d5cc55585820d9 · report
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.
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 repository not located ran; the contract check could not run (RAISES) · metamorphic tier: invariant licence of this copy not recorded ·
e5947aba1d10885f · report
fixture: signature embed_dim:int/0/int, pos:ndarray/1/float · returned ndarray · level recorded 2026-09-22 665d8a4e8f673a4c · report
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Image Generation | TextAtlasEval | PixArt-Sigma | StyledTextSynth Clip Score | 0.2764 | #5 of 7 | Archive leaderboard | report |
| Image Generation | TextAtlasEval | PixArt-Sigma | StyledTextSynth FID | 82.83 | #5 of 7 | Archive leaderboard | report |
| Image Generation | TextAtlasEval | PixArt-Sigma | StyledTextSynth OCR (Accuracy) | 0.42 | #5 of 7 | Archive leaderboard | report |
| Image Generation | TextAtlasEval | PixArt-Sigma | StyledTextSynth OCR (Cer) | 0.90 | #5 of 7 | Archive leaderboard | report |
| Image Generation | TextAtlasEval | PixArt-Sigma | StyledTextSynth OCR (F1 Score) | 0.62 | #5 of 7 | Archive leaderboard | report |
| Image Generation | TextAtlasEval | PixArt-Sigma | TextScenesHQ Clip Score | 0.2347 | #5 of 7 | Archive leaderboard | report |
| Image Generation | TextAtlasEval | PixArt-Sigma | TextScenesHQ FID | 72.62 | #5 of 7 | Archive leaderboard | report |
| Image Generation | TextAtlasEval | PixArt-Sigma | TextScenesHQ OCR (Accuracy) | 0.34 | #5 of 7 | Archive leaderboard | report |
| Image Generation | TextAtlasEval | PixArt-Sigma | TextScenesHQ OCR (Cer) | 0.91 | #5 of 7 | Archive leaderboard | report |
| Image Generation | TextAtlasEval | PixArt-Sigma | TextScenesHQ OCR (F1 Score) | 0.53 | #5 of 7 | Archive leaderboard | report |
| Image Generation | TextAtlasEval | PixArt-Sigma | TextVisionBlend Clip Score | 0.1891 | #5 of 7 | Archive leaderboard | report |
| Image Generation | TextAtlasEval | PixArt-Sigma | TextVisionBlend FID | 81.29 | #5 of 7 | Archive leaderboard | report |
| Image Generation | TextAtlasEval | PixArt-Sigma | TextVisionBlend OCR (Accuracy) | 2.40 | #5 of 7 | Archive leaderboard | report |
| Image Generation | TextAtlasEval | PixArt-Sigma | TextVisionBlend OCR (Cer) | 0.83 | #5 of 7 | Archive leaderboard | report |
| Image Generation | TextAtlasEval | PixArt-Sigma | TextVsionBlend OCR (F1 Score) | 1.57 | #5 of 7 | Archive leaderboard | report |
| Text-to-Image Generation | GenEval | PixArt-Σ | Overall | 0.53 | #18 of 20 | 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
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