This model focuses on making the character look cute.
The datasets used were carefully selected manually one by one from all over the internet to suit the objectives of this model.
No artist tags are used during training because this model aims only to change the character's appearance.
This version is an improvement from the previous version by merging 2 LoRas which were trained to focus on improving the ??????? and color of the previous model.
The downside of combining LoRa is that the artist style and some of the characters that have been trained won't really work in this model
You can look in the about this version section to see the details of the Merge Lora.
For Testing :
Merge Detail :
LoRa1 Composition
Datasets: 803
Text Encoder: True
Weight : 0.4
LoRa2 Color and Lighting
Datasets: 220
Text Encoder : False
Weight : 0.2
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.
