he model is aimed at photorealism and trying for a consistency with form

Recommended Negative Prompt:

(worst quality, low quality, illustration, 3d, 2d, painting, cartoons, sketch), open mouth

or another negative prompt

ᅠ

Recommended Generation Parameters:
Sampling Steps: 15-30+
Sampling Method: DPM++ 2M Karras / or another

Lora: <1.3/1.35 of 2.0 has seemed best

For Checkpoints, so far I've found most success using:

epiCRealism XL

RealVisXL V4.0

As per requested, no name, Nor will any permissions be given for use in commerce, monetization, or nsfw applications.