This model is based on SDXL and is designed for creating character images with a strong Gustav Klimt artistic style aesthetic.
The training set images are all 512x768 in size (primarily due to limited GPU memory, which consequently restricts the resolution of generated images). The dataset is derived from Klimt's original works and other pieces in a similar style.
Testing has shown that the generated images have good aesthetic quality. When using this model, it is recommended to employ image upscaling nodes to enhance the results.