trained on anythingv3 with clip skip: 2
you may add cwars trigger word, but model works fine without any
trained on anything v3, 512x512.
Add pointy ears to the negatives if you don't like elf/demon ears. Mostly generate something like TCG cards. Almost no interaction with realistic models.
early version to check concept, will be updated in several days
Also included a part of the dataset of images with txt captions
trained on anythingv3 with clip skip: 2
you may add cwars trigger word, but model works fine without any
1. Dieses Modell dient nur Lernzwecken. Urheber- und Auslegungsrechte liegen beim Originalautor.
2. Bist du der Originalautor eines Modells, kontaktiere uns bitte zur Authentifizierung über unsere offiziellen Kanäle. Wir schützen die Rechte aller Schöpfer. Hier klicken, um es zu verifizieren.
