[radarsat1]

Thanks for the corrections, I was including autoencoders that use an additional adversarial loss (such as VQGAN) when I said GAN.

> Dalle 1 works thx to the autoregressive model (also no GAN)

It uses an autoregressive model to predict codes for a pretrained VQGAN, doesn't it?

Doesn't Stable Diffusion's autoencoder also use an adversarial loss? Otherwise wouldn't it suffer the typical blurring problems well known to MSE?

[GaggiX]

Yes, all the autoencoders you see used in practice have adversarial loss + MSE + perceptual loss, the VAE used with Stable Diffusion also uses KL regularization, while VQGAN uses all other losses to make use of the codebook.