[Z-Image]
Realistic (fictional!) concept for Vachia V. VachiaV is the trigger - model is pretty consistent for her overall, adding in short hair and/or blue eyes can help. Tested between 0.8 - 1.5 strength - slightly over baked, she works best at 0.9 strength.
Data was created through Nano Banana Pro - first a face was composited and edited, then training images were generated. I would consider this a prototype but the results are very good! I hope you enjoy!
[Illustrious]
Illustrious LoRA of my original character Vachia V Training went well, character is well defined with simple Aluna S tag with good flexibility with actions and other style LoRAs. Tested at 1.0 strength (in theory could lower it if anything causes issues) with both Euler A and DPM++ 2M Karras, but theory states it should work with whatever you personal preference is. Have fun and enjoy!
[Pony]
Character LoRA created using images made in PDXL. Still refining datasets. Works very well between 0.7 and 1 strength, I only use "blue eyes" to keep it on track as the eyes can lean aqua-ish in color without. Part of a series of OC I intend to upload - check out my other LoRAs! Thanks for visiting, hope you enjoy.
[Creator Notes]
Everything I make is for one purpose - fun. I don't mind not knowing much about AI (tbh don't even really understand how I managed to install A1111/Forge, Git is an enigma to me) , it allows me to create, learn, and grow. Personal projects are fountains of enjoyment for me, and in sharing them I hope to share some of that with the world - hopefully someone else feels inspired to create something!