datasets for the first-stage autoencoders

Open wjn922 opened this issue 2 years ago • 1 comments

Thanks for the wonderful work!

I want to to know what datasets are used to train the first-stage autoencoders, as shown in https://github.com/CompVis/latent-diffusion/blob/main/scripts/download_first_stages.sh. Thanks.

Jun 14 '23 03:06 wjn922

according to the paper(Table 8.), the autoencoders are trained on OpenImages, evaluated on ImageNet-Val

Sep 04 '23 04:09 illrayy