Re:Visual Anagrams: Generating Optical Illusions with Diffus...
by minimaxir on Thursday November 30, 2023 @03:00PM
(#38478319)
I suspect the trick only works because DeepFloyd-IF operates in pixel space while other diffusion models operate in the latent space.
> Our method uses DeepFloyd IF, a pixel-based diffusion model. We do not use Stable Diffusion because latent diffusion models cause artifacts in illusions (see our paper for more details).
> Our method uses DeepFloyd IF, a pixel-based diffusion model. We do not use Stable Diffusion because latent diffusion models cause artifacts in illusions (see our paper for more details).