Preview images were not upscaled, Adetailer was used on some of them, I recommend using both, just wanted to show the "bare" model. For v5 and v7 I didn't use Adetailer in preview images.

Make sure to use UI that supports v-prediction, otherwise you will get a noisy blob!

I encourage posting images of any kind! Ofc, check TOS.

Main parameters:

Steps: 28
CFG: 3-5
Sampler-scheduler: euler/euler a-normal, DDPM-exponential (better noses)
CFGZeroStar and sometimes Self-Attention Guidance: default for difficult backgrounds

Try to BREAK prompts into parts by 75 tokens max, this goes for most models..

Positive prompt:

number of characters (1girl/1boy), character name, artist prompt, scene/environment/camera angle, action, expression, items, quality prompts (masterpiece, best quality)

some heavily stylized characters might require prompt: nose, realistic.. you can put nose into Adetailer

Negative prompt:

lowres, worst quality

even longer negative should work, but I prefer simplicity.. tags worth noting include sketch, abstract, url

Enjoy..