Posted for civitai.com and tensor.art only

Each of these LoRAs take me dozens of hours and GPU usage out of pocket. Every review is appreciated and encourages me to do more of these.

-MoC

Sasha Grey

is a former American pornographic actress, model, and musician born Marina Ann Hantzis on March 14, 1988, in North Highlands, California. With her porcelain doll-like complexion, raven-black hair, and petite yet curvy figure (measuring 5'6" and 34B-24-34), Grey quickly became a standout in the adult entertainment industry, which she entered in 2006. Her bold performances and striking features earned her numerous awards, including Penthouse Pet of the Month in 2007 and multiple AVN Awards. In addition to her work in adult films, Grey has also pursued a career in mainstream entertainment, appearing in films and television shows such as "The Girlfriend Experience" and "Entourage." Grey announced her retirement from the adult industry in 2011, and has since focused on her music and art endeavors.

Image Generation Suggestions

I generate these images using Mcmonkeyprojects' SwarmUI (a powerful but easy to use front end for ComfyUI). I find Forge results lacklustre at present.

Core Parameters
Model: Flux1-dev with clip_l, t5xxl_fp16.
Steps: 30
CFG Scale: 1

Sampling

I've had success with a good amount of samplers and schedulers, but at present am using the following,
Sampler: DEIS
Scheduler: Beta
Flux Guidance Scale: 3.5

Prompt
With SwarmUI use the <Segment:> feature to inpaint particular portions of the output. This can be nearly anything the segment model used was trained on, face, eyes, feet, top, etc.

A general statement I tag to most of these prompts is:
<segment:face,0.7>Imagine a real life highly grainy 35mm photograph of MoCModel face with incredibly lifelike intricately detailed eyes