News for hackers. Stuff that matters.

A comment on Visual Anagrams: Generating Optical Illusions with Diffusion Models. Parent comment

Re:Visual Anagrams: Generating Optical Illusions with Diffus... by ShamelessC on Thursday November 30, 2023 @02:57PM (#38478286)
> Per the code, the technique is based off of DeepFloyd-IF, which is not as easy to run as a Stable Diffusion variant.

I haven't dug in yet, but it _should_ be possible to use their ideas in other diffusion networks? It may be a non-trivial change to the code provided though. Happy to be corrected of course.

[ Parent | on HN ]
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).

[ Parent | on HN ]