SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2403.04692 · 2024

PixArt-Σ: Weak-to-Strong Training of Diffusion Transformer for 4K Text-to-Image Generation

arXiv · PDF · Open in the Atlas

Code that ran

6 of 9 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 1 honoured the contract we drafted, 1 violated it and 0 have no contract verdict; 4 failures of our instrument; 3 no recorded run); 1 of them was also run on the host, not in the jail, by the peer-agreement lane that set its level, measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2403.04692.json · badge: /api/ran/2403.04692.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
PixArt-alpha/PixArt-sigma canonical (classifier label)
classifier basis: census
5 ran · 2 no recorded run
copy not recorded community
not in the paper's declared repositories
1 ran · 1 no recorded run
FunctionStatusWhere it lives
append_dims Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
PixArt-alpha/PixArt-sigma/train_scripts/train_pixart_lcm.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from layer6ai-labs/direct-cms, is pointer only (licence: NONE) · get_code("30befb7e4327e615")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from layer6ai-labs/direct-cms, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

apply_style Ran
ran; our contract draft was wrong, not the code
PixArt-alpha/PixArt-sigma/app/app_pixart_sigma.py
code served (permissive licence) · get_code("652bf9fefb65310b")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned tuple, ndim 1, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import numpy as np

# The function apply_style takes three parameters:
# 1. style_name: str - name of the style to apply
# 2. positive: str - positive prompt text
# 3. negative: str - negative prompt text (optional, defaults to '')

# Looking at the function body:
# - It uses styles.get(style_name, styles[DEFAULT_STYLE_NAME]) to get a tuple of (prompt, negative_prompt)
# - It checks if negative is falsy
# - It replaces '{prompt}' in the prompt template with the positive text
# - It concatenates negative_prompt from style with the negative parameter
# - Returns a tuple of two strings

ARGS = {
    'style_name': 'Cinematic',
    'positive': 'a beautiful landscape with mountains',
    'negative': 'blurry, out of focus'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple, ndim 1, dtype family float — a tuple output has no array shape of its own; none is stated
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
extract_into_tensor Ran
ran; our contract draft was wrong, not the code
PixArt-alpha/PixArt-sigma/train_scripts/train_pixart_lcm.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from Luo-Yihong/YOSO, is pointer only (licence: NONE) · get_code("a15cfd7932844ef9")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from Luo-Yihong/YOSO, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_1d_sincos_pos_embed_from_grid Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
this paper's copy was not recorded; identical code first harvested from hustvl/dig
pointer only · get_code("e5947aba1d10885f")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

randomize_seed_fn Ran
ran, honoured the contract we drafted
PixArt-alpha/PixArt-sigma/app/app_pixart_sigma.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from Ji4chenLi/t2v-turbo, is pointer only (licence: NONE) · get_code("1c00f3d9c2aa103c")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from Ji4chenLi/t2v-turbo, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

scalings_for_boundary_conditions Ran
ran, violated the contract we drafted
PixArt-alpha/PixArt-sigma/train_scripts/train_pixart_lcm.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from Luo-Yihong/YOSO, is pointer only (licence: NONE) · get_code("bf8e9418920783fb")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from Luo-Yihong/YOSO, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_2d_sincos_pos_embed_from_grid Not yet run
unverified (harvested, no recorded run)
this paper's copy was not recorded; identical code first harvested from VinAIResearch/DiMSUM
pointer only · get_code("665d8a4e8f673a4c")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

onestep_sampler Not yet run
unverified (harvested, no recorded run)
PixArt-alpha/PixArt-sigma/train_scripts/train_pixart_dmd.py
code served (permissive licence) · get_code("168a4054b9fdff36")
How it ran

no invocation recorded.

save_image Not yet run
unverified (harvested, no recorded run)
PixArt-alpha/PixArt-sigma/app/app_pixart_sigma.py
code served (permissive licence) · get_code("b5d5cc55585820d9")
How it ran

no invocation recorded.

Also present in other papers' code

Of 9 samples lifted from this paper's linked repositories, 9 carry a function identity and 0 do not. Of the 9 distinct functions with an identity, 6 are also present in other papers whose code we hold (5 with at least one paper dated earlier, 5 the same month, 5 later) and 3 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
get_2d_sincos_pos_embed_from_grid 190 other papers
74 dated earlier, 6 the same month, 109 later, 1 same year, order not determinable · 65 only as an assembly brick
1807.10221 (2018-07)
Unified Perceptual Parsing for Scene Understanding
2105.12723 (2021-05)
Nested Hierarchical Transformer: Towards Accurate, Data-Efficient and Interpretable Visual Understanding
2111.06377 (2021-11)
Masked Autoencoders Are Scalable Vision Learners
and 187 more not named here
get_1d_sincos_pos_embed_from_grid 42 other papers
8 dated earlier, 34 later · 22 only as an assembly brick
2212.09748 (2022-12)
Scalable Diffusion Models with Transformers
2303.14389 (2023-03)
Masked Diffusion Transformer is a Strong Image Synthesizer
2305.13311 (2023-05)
VDT: General-purpose Video Diffusion Transformers via Mask Modeling
and 39 more not named here
extract_into_tensor 32 other papers
15 dated earlier, 3 the same month, 14 later · 7 only as an assembly brick
2006.11239 (2020-06)
Denoising Diffusion Probabilistic Models
2010.02502 (2020-10)
Denoising Diffusion Implicit Models
2112.02815 (2021-12)
Make It Move: Controllable Image-to-Video Generation with Text Descriptions
and 29 more not named here
append_dims 27 other papers
9 dated earlier, 3 the same month, 13 later, 2 same year, order not determinable · 2 only as an assembly brick
2204.06125 (2022-04)
Hierarchical Text-Conditional Image Generation with CLIP Latents
2304.09787 (2023-04)
NeuralField-LDM: Scene Generation with Hierarchical Latent Diffusion Models
2307.12493 (2023-07)
TF-ICON: Diffusion-Based Training-Free Cross-Domain Image Composition
and 24 more not named here
randomize_seed_fn 4 other papers
1 the same month, 3 later
2403.16627 (2024-03)
SDXS: Real-Time One-Step Latent Diffusion Models with Image Conditions
2410.05677 (2024-10)
T2V-Turbo-v2: Enhancing Video Generation Model Post-Training through Data, Reward, and Conditional Guidance Design
2503.09641 (2025-03)
SANA-Sprint: One-Step Diffusion with Continuous-Time Consistency Distillation
and 1 more not named here
scalings_for_boundary_conditions 2 other papers
1 dated earlier, 1 the same month
2401.05252 (2024-01)
PIXART-δ: Fast and Controllable Image Generation with Latent Consistency Models
2403.12931 (2024-03)
You Only Sample Once: Taming One-Step Text-To-Image Synthesis by Self-Cooperative Diffusion GANs

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

In this paper, we introduce PixArt-Σ, a Diffusion Transformer model~(DiT) capable of directly generating images at 4K resolution. PixArt-Σrepresents 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-Σis 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-Σare twofold: (1) High-Quality Training Data: PixArt-Σincorporates 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-Σachieves 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.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2403.04692")
get_code_for_paper("2403.04692")
have("2403.04692")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2403.04692.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2403.04692.svg)](https://syntology.ai/paper/2403.04692)

Connect an agent — have() is free.