![Face LoRA - hana_[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/1006035561456090434/9238e0a3-9ab6-f211-cece-420a81ed911d.png)
![Face LoRA - hana_[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/1006035561456090434/a65c3b67-2002-a8ce-111e-18bc10a7b86e.png)
![Face LoRA - hana_[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/1006035561456090434/69fadaf0-4ca1-123f-cfcb-5f0ba176761d.png)
![Face LoRA - hana_[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/1006035561456090434/52e1d64a-88e1-4dfc-c47e-d5c8c7a95e12.png)
![Face LoRA - hana_[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/1006035561456090434/cf579b00-5688-3fe2-2052-0f48161aabf4.png)
![Face LoRA - hana_[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/1006035561456090434/c6701c58-2a0c-f54c-8ccf-2faa584a8a1d.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