![Face LoRA - kumiko_[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/977366843733885961/b8a2297a-589b-3791-a7ed-f9b4bb7d15b1.png)
![Face LoRA - kumiko_[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/977366843733885961/d6456f67-b32b-3ca1-84a5-dbb6cadfec46.png)
![Face LoRA - kumiko_[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/977366843733885961/75ae1d84-f3f8-eca4-09ba-03f979f0116d.png)
![Face LoRA - kumiko_[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/977366843733885961/057ec51d-a0c2-e0df-84b0-dd644a5136f8.png)
![Face LoRA - kumiko_[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/977366843733885961/f7b6e1d6-97fe-d2b8-b50a-c7bd9452d539.png)
![Face LoRA - kumiko_[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/977366843733885961/babb3022-b144-e1e4-7a33-7459c38d4f00.png)
![Face LoRA - kumiko_[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/977366843733885961/4a3d5f9f-7ed8-010c-ef11-9221031fc3d6.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