I am wondering why the dimensionality of Latent Space in Stable Diffusion is 64x64x3. Since the encoding is performed by Variational Autoencoder it must output some mean and log variance that we can use to sample a latent vector of shape (latent_dim, ). But how Stable Diffusion uses 64x64x3 latent space when we expect shape (latent, )?



Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

Browse other questions tagged or ask your own question.