Those companies don’t make the technical details public and I don’t follow the leaks and rumors. They almost certainly use, broadly, the same approach (latent diffusion). That is, their AIs work with a compressed version of the image to save on computing power.
Is dalle3 and midjourney using other methods?
Those companies don’t make the technical details public and I don’t follow the leaks and rumors. They almost certainly use, broadly, the same approach (latent diffusion). That is, their AIs work with a compressed version of the image to save on computing power.