![Face LoRA - kaya_[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/1010880100956122513/4662ee21-598d-092d-87dc-d7ba9b55643e.png)
![Face LoRA - kaya_[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/1010880100956122513/3c623c8e-636a-c4c9-bada-b3d6dd2aa92d.png)
![Face LoRA - kaya_[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/1010880100956122513/f0c4020b-125f-f0ff-2c56-ce6fb2f416cd.png)
![Face LoRA - kaya_[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/1010880100956122513/c4a8ad49-b9d5-dfad-57fd-c14dc01d25c9.png)
![Face LoRA - kaya_[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/1010880100956122513/5a2bc287-a1c0-2012-4217-7d10824a68a5.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