Show-o: One Single Transformer to Unify Multimodal Understanding and Generation

Benchmark Model Rank Results
text-to-image-generation-on-wiseShow-o#29Overall: 0.35Cultural: 0.28Time: 0.40Space: 0.48Biology: 0.30…
image-generation-on-wiseShow-o#56Overall: 0.35Cultural: 0.28Time: 0.40Space: 0.48Biology: 0.30…
text-to-image-generation-on-genevalUnd. and Gen. Show-o (Ours)#143Overall: 0.68