This is my first attempt at creating a character LoRA for Wan 2.2 14B.
I found this character as one of Stable Yogi's ones so it is not an original creation of mine. It is simply more of a test for me to try out the process of creating a character LoRA and if my system is able to run it.
I trained the LoRA using images that were created by Stable Yogi's Demo AI Influencer 014 since I have yet to figure out how to create a good dataset.
The trigger word is "instagirlsusan". (I know this may sound like I'm trying to copy the Instagirl people, but I kept getting issues with the other trigger words I tried so I decided to use one that I knew for a fact worked.)
As always, I'm open to any kind of feedback :)
Description
FAQ
Comments (2)
Hello! Have you had any experience training LoRA on real people with tattoos? How can LoRA be trained to draw tattoos correctly?
I have trained a LoRA on a real person successfully, though I haven't tried anyone with tattoos and I'm not sure if that could cause an issue. Seeing as it's able to learn different facial expressions while keeping the facial features consistent I don't see why it wouldn't work. If you'd like specific help with anything feel free to message me :)
Details
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.