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

Sha Rizel

is a stunning Ukrainian glamour model and television personality, born on August 19, 1988, in Kiev, Ukraine. With her curvy figure, measuring 42-24-38, and standing at 5'7" (170cm) with a weight of 112 lbs (51kg), Sha has captivated audiences with her natural beauty. She began her modeling career in 2009, working with renowned photographer Satoshi Kizu, and later transitioned to ???? modeling, becoming a popular fixture on Scoreland and other adult platforms. Sha has won numerous awards, including Scoreland's Newcomer of the Year in 2013 and induction into the Big-Boob Hall of Fame in 2022. With her striking blue eyes, long black hair, and charming personality, Sha Rizel has solidified her status as a beloved adult model and television personality.

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