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.