This model serves as an enhancement LoRA to stabilize the smaller WAN model. This should make better videos more achievable for people with lower-end machinery.This model does not have any trigger words, however "penis" is typically required to see male genitals. It's a quality/stability enhancement for the WAN2.1 1.3B model. The model is trained on SFW and NSFW videos. This LoRA WILL NOT WORK for the 14B model.Training data was generated using other AI models and some of my own content found on my other socials. Training data is included as a ZIP if you are curious.

TinkerWAN - WAN 1.3B Stability and Quality enhancement LoRA

This version is much more consistent when producing female genitals. WAN appears to be trained on "ken-like" men and women, so I'll need to do more more training to get male genitals to look much better. It should be better, regardless.

Files with SHA256: 1a75081f325d847b0b6cc26a174ecefb47d1729c32bf260b5d32a2ecbcf1aab0