ELDiff: When Evidential Learning Meets Text-to-Image Diffusion
Open paper
Benchmark
Model
Rank
Results
text-to-image-generation-on-t2i-compbench
ELDiff (SD v3.5 Medium)
#2
Color: 0.8452
Texture: 0.7435
Spatial: 0.3925
Shape: 0.6241
…
Rank counts only results with a code link.