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: https://ngwaifoong92.medium.com/sdxl-0-9-with-ensemble-of-ex...
Agreed. Animations definitely helped. I noticed that more "errors" with wide landscape images than tall portrait ones. I have to imagine that's because the dataset is pulled from the web and the web has a preference for vertically segmented design
The SDXL model was trained on different aspect ratios, but each one of those aspect ratios has a precise resolution, so anything other than those resolutions would be considered out of distribution, so maybe when you were inspecting the wide landscape images you use an out-of-distribution resolution while with the portrait ones you didn't as much.
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.