Re:Introducing Images 2.6
by ViscountPenguin on Wednesday November 04, 2026 @11:27PM
(#50375181)
The problem isn't the classifier free guidance itself, but the choice of parameters. When a parameter above 1 is chosen you get images which very stronger conform to theme, but which there's not a good mathematical justification for.
Yeah, it must be some algorithmic thing like CFG, or some other technique, that causes the unrealistic AI look. Because Dall-E 2 didn't have it, but Dall-E 3 did to an extreme degree. Google's Imagen <= 3 also didn't have it, but Imagen 4 (and Nano Banana, which seems to use Imagen 4 in the background) suddenly had significant AI look, apart from much better prompt following and fewer visual mistakes (like too many fingers).
Yeah. I just read a bit about it and looked at some examples, and it seems CFG>1 is a hack to get sharper images from a given model, at the cost of giving them the "AI look". As models get better, we'll be able to use CFG=1 and much of the problem will go away.
With that being said, my understanding of that issue is a few years old, people have always said CFG is a havk until models get better at following prompts on their own. So thee “look” that tools like Nano Banana ends up with could be something else. It may or may not be a necessary artifact of some part of the process.