So, this thing is trained on the portraits from the Baldur's Gate diology.
The base model is SD 1.5
Training method - https://colab.research.google.com/github/Linaqruf/kohya-trainer/blob/main/kohya-LoRA-dreambooth.ipynb
Images were generated with this model: Deliberate | Stable Diffusion Checkpoint | Civitai
Description
SD 1.5 version