












V3.0:
More soap and elbow grease on the dataset. Also isolated her blue dress. She does have several outfits but if i don't remember them they were not iconic enough. Also made her face markings as part of her trigger so it might be hard to get rid of them.
Works fine with: <lora:BelldandyV3:0.7>, belldandy,
Oufits:
Belldandy_Blue_Dress
As always I'll add the tag summary inside the dataset so people can experiment.
V2.0:
Retrained the LORA. As it was my first LORA, The dataset wasn't as good as I would have liked(I have since gained a lot of experience cleaning datasets). Still some crappy images evaded even this second filter.
Had nice results with: Belldandy, blue_eyes, brown_hair, (facial_mark:1.3), <lora:Belldandy:.45>
Here are some useful tags from the tags summary:
long_hair
facial_mark
forehead_mark
blue_eyes
jewelry
brown_hair
smile
large_breasts
earrings
choker
bracelet
antenna_hair
blush
ponytail
sweat
huge_breasts
bangle
V1.0:
Her clothes seems to have a strong bias to blue and white.
Got good results with <lora:Bdandy:.4>, (Belldandy), (facial_mark:1.1),
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.
