English translation is being prepared.
View original postEnglish translation is being prepared.
View original
Last October, we introduced Representation Autoencoders (RAE), showing that training diffusion on frozen semantic representations works and outperforms VAEs on ImageNet. We received many questions: Can this scale to complex settings like T2I? Do the advantages hold? The answer is YES. 🧵
Body
The English body is being prepared. You can open the original source.