Interesting. I didn’t see an essential difference with higher values, so I settled on 25. Maybe I’m just impatient and my brain prefers more options even if they’re individually imperfect.
Depends on the diffuser you're using, the _a (ancestral) diffusers are aberrant in that they can yield good results with very low sample counts. I typically use 16 samples and get reasonably good results, but it's highly dependent on the prompt and settings as well.
