This is for furry anthropomorphic but with human traits. Works very well with realism models but also worked well for me with animated models. Works well for both SFW and .
Trigger words: rfurry, anthropomorphic
Weights: I found it works best (via Foocus) with weights around 0.7-0.9. At 1.2+ the lora can override the model and the results can look funky, but play around and see what works best for you.
My first LORA training (with 300+ images), tested after training with multiple PONY models, all came out good for me.
Tested with random animals, male and female, mostly mammal based but I did have a few lizard types in the trained images.
Earlier versions used fewer images and did not get very good results. Used 300+ good images to create this lora.
v1.0: 300+ images used to train. 7 hours training with my 12GB RTX2060.
1. The rights to reposted models belong to original creators.
2. Original creators should contact SeaArt.AI staff through official channels to claim their models. We are committed to protecting every creator's rights. Click to Claim
