Digital Impressions: Impressionist Style LoRA - V2.0 API Documentation

Version 2.0 was trained on the same dataset and with the same settings, but the dataset was captioned first with captions that followed the guidelines in the dataset preparation guide. Adding captions resulted in a LoRA that lost some of its unique stylistic appearance but showed better prompt adherence and generalizability, as well as subjects with a more varied array of characteristics. The differences between training styles were highlighted in more detail in Understanding Prompting and Captioning for LoRAs.