![Face LoRA - momoko_[Z-Image] by user_693186431694192228 on Tensor.Art](https://image.tensorartassets.com/cdn-cgi/image/anim=true,plain=false,w=500,q=85/model_showcase/976707880860306729/34dfc9fe-b9d1-a5a2-0fd0-60e7c6e8a831.png)
![Face LoRA - momoko_[Z-Image] by user_693186431694192228 on Tensor.Art](https://image.tensorartassets.com/cdn-cgi/image/anim=true,plain=false,w=500,q=85/model_showcase/976707880860306729/3c109e6d-49ed-c523-8ef0-ced51e2e291b.png)
![Face LoRA - momoko_[Z-Image] by user_693186431694192228 on Tensor.Art](https://image.tensorartassets.com/cdn-cgi/image/anim=true,plain=false,w=500,q=85/model_showcase/976707880860306729/63e83a3f-75ba-ed94-1288-92c24de9ebfd.png)
![Face LoRA - momoko_[Z-Image] by user_693186431694192228 on Tensor.Art](https://image.tensorartassets.com/cdn-cgi/image/anim=true,plain=false,w=500,q=85/model_showcase/976707880860306729/3d79d2e4-db68-5e8b-4c58-2e54991c679a.png)
I created a set of three-view drawings with various expressions based on an AI-generated face and used them for training. As a result, it can output consistent faces from any angle and with any expression.
The optimal settings for this LoRA
Sampler : Euler
VAE : ae.sft (or None)
CFG scale : 1