DALL-E and Stable Diffusion quite a bit, I’m pretty convinced those drawings are heavily cherry picked
But those use a different algorithm, diffusion vs. feedforward. It’s possible that those examples are cherrypicked but I wouldn’t be so sure until the full model comes out.
But those use a different algorithm, diffusion vs. feedforward. It’s possible that those examples are cherrypicked but I wouldn’t be so sure until the full model comes out.
both DALL-E and stable diffusion use diffusion, which is a many-step feedforward algorithm.
Oh, 😳. Well my misunderstanding aside, they are both built using diffusion, while those pics (from Google MUSE) are from a model that doesn’t use diffusion. https://metaphysic.ai/muse-googles-super-fast-text-to-image-model-abandons-latent-diffusion-for-transformers/