List your company
ResearchFormerly WizWand

Contextual Image Generation on VIST 28 (test)

0.641CLIP SimilarityGILL
0.57860.59480.6110.6272May 26, 2023
Updated 8mo ago

Evaluation results

MethodLinks
GILLinput_context=5 captions, 4 images2023.050.6410.693
GILLinput_context=5 captions2023.050.6120.696
Stable Diffusioninput_context=5 captions2023.050.5980.704
Stable Diffusioninput_context=1 caption2023.050.5920.703
GLIDEinput_context=5 captions2023.050.5910.745
GLIDEinput_context=1 caption2023.050.5820.753
GILLinput_context=1 caption2023.050.5810.702