Hi
After hundreds of tests and comparisons (like this one) it looks like STABLE v1.2 the best mix to be used as base model.
25-30 steps and 5.5-6 CFG Scale will fit most of the prompts, just don't go crazy with weights.
Currently I'm slowly working on new lora - robots, aiming on Vladislav Ociacia visual style.
____________________________________________________
STABLE v1.2 - made another merge with sd 1.5 (due to tongue v1.1 lora merge, all girls looked more like bimbo then natural beauty)
STABLE v1.1 - now it's more sharp
STABLE v1 - starting new mix with fine tuning by own loras