MiniT2I: A Minimalist Baseline for Text-to-Image Generation
Open paper
Benchmark
Model
Rank
Results
text-to-image-generation-on-prism-bench
MiniT2I-L/16
#6
Accuracy: 62.4
text-to-image-generation-on-geneval
MiniT2I-L/16
#36
Overall: 0.883
text-to-image-generation-on-dpg-bench
MiniT2I-L/16
#48
DPG-Bench Score: 85.9
Rank counts only results with a code link.