Tasks SotA Datasets Papers Methods Submit About

Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable Benchmarks All SotA Datasets Papers Methods

Community

Submit Results About

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Models/PixArt-Sigma

PixArt-Sigma

Reported on 15 benchmarks across 1 task · 1 paper · 11 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Medical15 results

Image GenerationonTextAtlasEval
StyledTextSynth Clip Score· 2024-03-07
0.2764
best: 0.2938 (Grok3)
SOTA
PixArt-Σ: Weak-to-Strong Training of Diffusion Transformer for 4K Text-to-Image Generation arXiv:2403.04692
Image GenerationonTextAtlasEval
StyledTextSynth FID· 2024-03-07
82.83
best: 71.09 (SD3.5 Large)
SOTA
PixArt-Σ: Weak-to-Strong Training of Diffusion Transformer for 4K Text-to-Image Generation arXiv:2403.04692
Image GenerationonTextAtlasEval
StyledTextSynth OCR (Cer)· 2024-03-07
0.9
best: 0.73 (Grok3)
SOTA
PixArt-Σ: Weak-to-Strong Training of Diffusion Transformer for 4K Text-to-Image Generation arXiv:2403.04692
Image GenerationonTextAtlasEval
TextScenesHQ Clip Score· 2024-03-07
0.2347
best: 0.3367 (Dalle3)
SOTA
PixArt-Σ: Weak-to-Strong Training of Diffusion Transformer for 4K Text-to-Image Generation arXiv:2403.04692
Image GenerationonTextAtlasEval
TextScenesHQ FID· 2024-03-07
72.62
best: 64.44 (SD3.5 Large)
SOTA
PixArt-Σ: Weak-to-Strong Training of Diffusion Transformer for 4K Text-to-Image Generation arXiv:2403.04692
Image GenerationonTextAtlasEval
TextScenesHQ OCR (Cer)· 2024-03-07
0.91
best: 0.57 (Grok3)
SOTA
PixArt-Σ: Weak-to-Strong Training of Diffusion Transformer for 4K Text-to-Image Generation arXiv:2403.04692
Image GenerationonTextAtlasEval
TextVisionBlend Clip Score· 2024-03-07
0.1891
best: 0.1979 (Infinity-2B)
SOTA
PixArt-Σ: Weak-to-Strong Training of Diffusion Transformer for 4K Text-to-Image Generation arXiv:2403.04692
Image GenerationonTextAtlasEval
TextVisionBlend FID· 2024-03-07
81.29
SOTA
PixArt-Σ: Weak-to-Strong Training of Diffusion Transformer for 4K Text-to-Image Generation arXiv:2403.04692
Image GenerationonTextAtlasEval
TextVisionBlend OCR (Accuracy)· 2024-03-07
2.4
best: 41.54 (Grok3)
SOTA
PixArt-Σ: Weak-to-Strong Training of Diffusion Transformer for 4K Text-to-Image Generation arXiv:2403.04692
Image GenerationonTextAtlasEval
TextVisionBlend OCR (Cer)· 2024-03-07
0.83
best: 0.57 (Grok3)
SOTA
PixArt-Σ: Weak-to-Strong Training of Diffusion Transformer for 4K Text-to-Image Generation arXiv:2403.04692
Image GenerationonTextAtlasEval
TextVsionBlend OCR (F1 Score)· 2024-03-07
1.57
best: 44.22 (Grok3)
SOTA
PixArt-Σ: Weak-to-Strong Training of Diffusion Transformer for 4K Text-to-Image Generation arXiv:2403.04692
Image GenerationonTextAtlasEval
StyledTextSynth OCR (Accuracy)· 2024-03-07
0.42
best: 30.58 (Dalle3)
PixArt-Σ: Weak-to-Strong Training of Diffusion Transformer for 4K Text-to-Image Generation arXiv:2403.04692
Image GenerationonTextAtlasEval
StyledTextSynth OCR (F1 Score)· 2024-03-07
0.62
best: 38.25 (Dalle3)
PixArt-Σ: Weak-to-Strong Training of Diffusion Transformer for 4K Text-to-Image Generation arXiv:2403.04692
Image GenerationonTextAtlasEval
TextScenesHQ OCR (Accuracy)· 2024-03-07
0.34
best: 69.26 (Dalle3)
PixArt-Σ: Weak-to-Strong Training of Diffusion Transformer for 4K Text-to-Image Generation arXiv:2403.04692
Image GenerationonTextAtlasEval
TextScenesHQ OCR (F1 Score)· 2024-03-07
0.53
best: 51.63 (Dalle3)
PixArt-Σ: Weak-to-Strong Training of Diffusion Transformer for 4K Text-to-Image Generation arXiv:2403.04692