Re:The AI Unbundling
by sebzim4500 on Monday September 12, 2022 @01:41PM
(#32813943)
>there are relatively few illustration problem you could have where DALL-E/SD/... would help more than searching for an existing image
This is probably true if you want a single image, but if you want many images that look consistent with each other then google images will be little help. Stable diffusion with textual inversion can just about do it though. I would imagine in a few years it will be able to do that better than it can currently generate a single image.
This is probably true if you want a single image, but if you want many images that look consistent with each other then google images will be little help. Stable diffusion with textual inversion can just about do it though. I would imagine in a few years it will be able to do that better than it can currently generate a single image.