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
was born on July 9, 1993 in Kiev, Ukraine. She stands at 5'6 (167 cm) with measurements of 36C-25-37 and weighs around 108 pounds (49 kg). With her brown hair and blue eyes, Emily exudes natural beauty. She began pursuing modeling and acting from a young age after relocating to the United States for her studies.
Emily, also known by her aliases Anne T. and Tania Fox, kicked off her professional career in 2012 at age 18. Since then she has earned fame in the film industry through her work in movies, magazines, and camming. Emily is proud to have a surgery-free figure and enjoys showcasing her talents. Through relentless efforts, she has gained notable achievements like being named Playboy's Cyber Girl of the Month.
When not on film sets, Emily keeps herself occupied with diverse hobbies like photography, artwork, traveling and spending time with animals. She also runs her self-titled website and YouTube channel. Emily advocates living a balanced lifestyle while successfully pursuing her dreams. She continues to explore new opportunities and entertain audiences with her versatility.
Most images have been generated with LORA weighted between 0.65 to 0.75.
Lower weighting needed often for headshots.
Samples done with CyberRealistic v20 with sampling steps above 20, generally ~40 using Euler a, and DPM++ SDE Karras.
When testing a prompt, I often do a low lowres gen of multiple images, then choose the seed I like and upscale.
Portrait and close-ups work great using Hires. fix and 8X NMKD-Faces at 0.15 denoise strength.
Sometimes I just send it to Ultimate SD upscale after a quick render and run 2x at a scale of two, but often just the Hires. fix is good enough to capture enough details for the subject matter.
Ultimate SD upscale script used @ ~.15 - .4 denoising using 8x NMKD Faces or 4X UltraSharp redraw upscalers.
Feedback appreciated. Please leave a review if you've used this LORA. 👍
Leave a comment if you are having issues getting good output, I'll try to respond.
This aims to be my highest quality LoRA to date
trained at 1280x1280px
optimally trained native resolutions are: 960x1472, 1024x1344/1472 and 1216x1216
Adetailer not always needed for shots (though it can still add missing details)