BigGAN+ [Brock et al.] (chx96)

Reported on 4 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.

Medical2 results

Image GenerationonImageNet 256x256
FID· 2021-09-10
8.1
best: 1.06 (SiT-XL/2 + UCGM-S (E2E-VAE + 40 sampling steps + CFG))
Instance-Conditioned GAN arXiv:2109.05070
Image GenerationonImageNet 256x256
Inception score· 2021-09-10
144.2
best: 338.08 (LEGO-XL)
Instance-Conditioned GAN arXiv:2109.05070

Computer Vision2 results

Conditional Image GenerationonImageNet 256x256
FID· 2021-09-10
8.1
best: 3.39 (DiGIT)
Instance-Conditioned GAN arXiv:2109.05070
Conditional Image GenerationonImageNet 256x256
Inception score· 2021-09-10
144.2
best: 221.57 (ADM-G + EDS + ECT (ED-DPM, classifier_scale=1.0))
Instance-Conditioned GAN arXiv:2109.05070