Scaling Properties of Text Conditioning in Visual Generation
Open paper
Benchmark
Model
Rank
Results
image-generation-on-wise
Qwen-Image + Structured Prompter
#1
Overall: 0.89
text-to-image-generation-on-tiif-bench-mini
Qwen-Image + Structured Prompter
#3
Accuracy: 89.1
Rank counts only results with a code link.