Small Dataset - Trained on 88 screenshots from the digital board game: TalismanLarge dataset - Trained on 1000 cards from the 4th Edition
Works best with anime/hybrid model
STRENGTH/WEIGHT: 0.5 (to) 1.2
NEGATIVE STRENGTH/WEIGHT: -0.4
āØ If you enjoy my LoRAs and creations, you can support me with a little coffee on Ko-fi āš
It helps me keep training models, creating art and making more dreamy weird little projects šāØ Thank you so much for the support and kindness ~
Description
FAQ
Comments (2)
This looks cool, but the images seem a bit... off. Something about the aspect ratio, perhaps?
Thanks! Yeah, that's exactly it. If the strength/weight is too high it can get pretty stretched out. It's great/useful when mixed with other lora's at a lower strength though. It's more like an ingredient than a recipe.