ModelsLab/Digital Impressions: Impressionist Style LoRA - V1.0

Version 1.0 was trained on several paintings with heavy, visible brushstrokes. The training images had no captions other than the trigger word. This allowed the style to be emphasized, but also a bit of overfitting on the subjects and composition. The style was captured using a selection of parameters to highlight the art style. It was trained without bucketing, and the random crop parameter was used to diversify the training dataset and prevent overfitting while learning the style.