![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/973058127173796473/3484711a-7f8b-693c-53dd-f52f99cd6f4f.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/973058127173796473/747e4a2c-54e9-29c0-b39b-98b412fbb2ba.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/973058127173796473/121fa44b-d169-74ad-ccb9-1032941d4530.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/973058127173796473/ed6e7cd8-667d-8372-f4e6-56cf6c1d10ac.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/973058127173796473/acc113a2-e1d0-33c1-5158-14a695c2d1eb.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/973058127173796473/d3848ca8-f182-b1d0-c6c5-c941b47c9c16.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