Thorn from Hex Girls namely from Scooby-Doo! And The Witch's Ghost (1999) direct to video movie.
Trained on 10 images.
Anima-base v1 used for training.
Description
FAQ
Comments (1)
If it’s not too much trouble, could I ask for some tips on training a LoRA?
I have a dataset with about 30 images of a character. I’m using AI Toolkit, but I’m not sure if it’s the best place for training; in my tests, the LoRAs usually turn out too inflexible and with an overly strong style. I apologize if this isn't very clear—English isn't my native language, and I’m not very experienced with training LoRAs.
Details
Downloads
106
Platform
CivitAI
Platform Status
Available
Created
9/27/2026
Updated
11/18/2026
Deleted
-
Trigger Words:
th04nx, 1girl, solo, pale skin, dark red and black hair, long hair, green eyes, red lips, fangs, vampire,
black elbow length bridal gauntlets, black dress with red accent with red accent, red bat necklace,
