PixArt-Σ: Weak-to-Strong Training of Diffusion Transformer for 4K Text-to-Image Generation
Open paper
Benchmark
Model
Rank
Results
image-generation-on-textatlaseval
PixArt-Sigma
#2
TextVsionBlend OCR (F1 Score): 1.57
TextVisionBlend OCR (Accuracy): 2.40
…
text-to-image-generation-on-geneval
PixArt-Σ
#16
Overall: 0.53
Rank counts only results with a code link.