Nice to have the precomputed images for rapid exploration of parameters. I hadn't encountered the "ensemble of experts" configuration yet, thanks! I found an article that describes its implementation with Hugging Face diffusers APIs: <a href="https://ngwaifoong92.medium.com/sdxl-0-9-with-ensemble-of-expert-denoisers-3698a8c230f" rel="nofollow noreferrer">https://ngwaifoong92.medium.com/sdxl-0-9-with-ensemble-of-ex...</a>
It's pretty cool to play around with the precomputed generations, it let you develop a better intuition around the samplers.<p>Like how non-ancestral samplers converge to the same image.
This is a very limited "Settings Guide" there is a bunch of stuff they're not even mentioning, maybe not aware of. Such as the fact it now has 2 positive prompts + 2 negative prompts and tweaking the amount of the refinement.