📝Biography📝
(generation advice below) 👇
🌟Holly Hendrix🌟
was born on April 20th, 1997 in LaFayette, GA. The daughter of Guyanese immigrants, she attended public schools before attending community college for two years. Leaving home for Orlando, FL, she began a successful career in mainstream modeling. Frustrated with limitations, Hendrix transitioned to adult modelling, entering the industry in May 2015. At the age of 18, she chose the professional pseudonym "Hendrix", inspired by her love of musician Jimi Hendrix.
Within just a few short months, Hendrix began appearing in popular adult media. By February 2017, Hendrix had starred in over 100 adult films. Winning several industry awards, Hendrix has become famous for her ability to perform well in difficult scenes.
Hendrix enjoys playing video games, sports, and going out dancing. A self-described foodie, she loves trying new recipes and learning how to make different dishes. An avid reader, she enjoys books on science fiction and fantasy genres. Passionate about tattoo artwork, she has multiple body modifications, including piercings in both nipples and navels. Since December 2019, Hendrix has maintained a relationship with fellow female adult entertainer Lena Paul.
💡Generation Advice💡
🔧Prompt and Sampling🔧
Most images have been generated with LORA weighted @ 1.
Most samples done with CyberRealistic v2.1 with sampling steps ~40.
🚀Upscaling🚀
Using UnChillStablyRealOut and CyberRealistic, this LORA seems friendly to Hi-Res fix upscaling and the Ulti SD upscale script.
Sometimes I just send it to Ultimate SD upscale after a quick render and run 2x at a scale of two.
Ultimate SD upscale script used @ ~.15 - .4 denoising using 8x NMKD Faces or 4X UltraSharp redraw upscalers.
🗒️Side Notes🗒️
The prompts continue to evolve. CyberRealistic is a reasonably flexible model for being realism focused. I still think they have trumped the SD 1.5 game. 👑
Leave a review if you liked using this.
Leave a comment if you are having issues getting good output, I'll try to respond.
Description
FAQ
Comments (5)
Hey i hate to ask, anywhere to make requests of a model? and how much harder is it to make a textualinversion than a lora?
TI takes about the same amount of work to train, but trains a little faster in general. The time-consuming step is making the dataset, cropping, tagging, etc.
Once you have a tagged dataset, you can train both a LoRA and a TI on that dataset.
A LoRA is generally more powerful and is better at catching the likeness of a person. I't also very easy to merge LoRAs and to make completely new imaginary people with a repeatable look.
Awesome! I'm seeing her on Monday 😉
Y'all laugh if you want, I'll tell her you said Hi
@Bozack3000 Ask her if my bio is accurate :)
Details
Files
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.