latents go from 16ch @ 8x compression to 64ch @ 16x, so roughly the same total latent budget but much more channel heavy. It’s also deeper/wider, and the old 2x2 transformer patching is gone.
On some images it still produces artifacts but can't say if it's the transformer or the VAE yet.
trentor · · focus · HN ↗
EDIT: It still produces artifacts it's better but unusable for production work. In midvalues you will see a slight dot pattern.
mdp2021 · · focus · HN ↗
Can you share the sources?
trentor · · focus · HN ↗
latents go from 16ch @ 8x compression to 64ch @ 16x, so roughly the same total latent budget but much more channel heavy. It’s also deeper/wider, and the old 2x2 transformer patching is gone.
On some images it still produces artifacts but can't say if it's the transformer or the VAE yet.