Palatte (20-30% free form)

Reported on 4 benchmarks across 2 tasks · 1 paper · 2 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Medical2 results

Image GenerationonPlaces2 val
FID· 2021-11-10
11.7
SOTA
Palette: Image-to-Image Diffusion Models arXiv:2111.05826
Image GenerationonPlaces2 val
PD· 2021-11-10
35
best: 115.4 (HiFill (128×128 center mask))
Palette: Image-to-Image Diffusion Models arXiv:2111.05826

Computer Vision2 results

Image InpaintingonPlaces2 val
FID· 2021-11-10
11.7
SOTA
Palette: Image-to-Image Diffusion Models arXiv:2111.05826
Image InpaintingonPlaces2 val
PD· 2021-11-10
35
best: 115.4 (HiFill (128×128 center mask))
Palette: Image-to-Image Diffusion Models arXiv:2111.05826