PixArt-$α$: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis
Open paper
Benchmark
Model
Rank
Results
image-generation-on-wise
PixArt-XL-2-1024-MS
#5
Overall: 0.47
Cultural: 0.45
Time: 0.50
Space: 0.48
Biology: 0.49
…
on-wise
PixArt-Alpha
#3
Overall: 0.47
Cultural: 0.45
Time: 0.50
Space: 0.48
Biology: 0.49
…
Rank counts only results with a code link.