Imagen fully distilled (oscillate (15,1))
Reported on 2 benchmarks across 2 tasks · 1 paper
Note: results are matched by exact model name. Different papers may use the same name for different model variants.
Computer Vision1 result
- CLIP R-Precision· 2022-10-0590.97best: 92.12 (Imagen original (constant=6))
Natural Language Processing1 result
- CLIP R-Precision· 2022-10-0590.97best: 92.12 (Imagen original (constant=6))