This research extends the Character-LoRA project based on the Anima model, focusing on research and testing with the BACKGWA character.
The original SDXL-based model is Character-LoRA (BACKGWA), and the related research repository is BackGwa/Character-LoRA.
Detailed materials targeting the Anima model will be updated in the future.
Description
Character-LoRA has been extended and tested based on the Anima model.
Trained the LoRA using the Anima base-v1.0 model.
Revised the dataset labels to better match Anima’s prompting style.
Added labeling support for both natural-language prompts and tag-based prompts.