ComfyUI workflow to generate good quality images with base NoobAI vpred model and a refiner.
For convenience I moved guide for this workflow into separate article How to generate good images with NoobAI vpred.
Description
Added support for prompt wildcards. See the guide for more info.
Re-implemented "Adjust Details" feature for txt2img stage. Now it is possible both to increase and decrease desired details level, with less artifacts.

