![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/996733242113572007/2f088100-54b0-39d1-c323-4830a3cae593.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/996733242113572007/796ced7f-6540-cc93-da85-ed1275e4c387.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/996733242113572007/a9360cba-1fe6-6ae9-f624-ef6c6b206aa5.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/996733242113572007/04c3df2d-1c89-13ad-4aa5-b35bf9a6f839.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/996733242113572007/e13dd4ba-964a-665f-9c75-e2726846a4c0.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