Alolan Ninetales LoRA trained on NovelAI with Kohya training scripts using the DAdaptAdam optimizer at 512x512 resolution. Very consistent, biggest issue I ran into was tail placement and count. Adding (multi tail) to my prompt when Ninetales was clothed helped me get more consistent tails. Should have wide compatibility with model mixes based on NovelAI, which is most of them. Trained on an all female dataset.
Description
Initial release
FAQ
Comments (8)
Oh no... What... What is happening to me
Welcome to the dark side, my friend ( ͡° ͜ʖ ͡°)
Very nice
Can I please ask for a Giratina lora? 🙏
I've got it on my list, but based on the peek at the current Giratina art, I'm not confident it'll make a good LoRA. I'll upload one if the results are usable 😆
@KomodoStar hell yeah 🫡
you make me Furry
owned