Check out for more -- Ko-Fi or buymeacoffee
LORA network trained on Stable Diffusion 1.5.
Based on Oliva Casta.
Use the LORA natively or via the extension -- https://github.com/kohya-ss/sd-webui-additional-networks
Description
FAQ
Comments (10)
It works fantastically well!
Dude, these are amazing, can you do Kate Upton?
This is a lovely LoRA to throw in - sometimes at low weights - in order to make pretty nudes.
One question: What keyword (-s) did you use in the training? I'd like to know how tro trigger it maximally.
PLEASE HELP ME! I want to make loras with celebrity faces but it never comes out right. I'm using 10-15 images between 1500 and 2500 steps. Is there something I am missing in the description or a trick that I do not know??? You are clearly very talented with loras so I am wondering if you could help me out?
how did you train her, what steps did you use and can you provide your training data?
Hi, what's your original model and prompt, I just can't reproduce it
Can you show at least 1 full prompt ?
An AI model of an AI face lol
Hi I am really struggling with my own LORAs. Would you help me and share exactly what settings did you use (Kohya UI I assume) throughout the process? Also I wonder how many and what kind of images did you use, maybe if you could just share the caption txt files.
Also did you use any regularization images?
Thanks!
Isn't olivia already an AI character?