dindakai Style - Anima

Style LoRA for dindakai, trained on 38 images. Use @dindakai as the style trigger.

For captioning I followed the recommendations from the Anima prompting guide.

For example:

masterpiece, 1girl, character name, series name, @dindakai, {tags}, {natural language description}

I preprocessed and inpainted the dataset with an edit model, then generated stable tags with a community model. Training used compact structured captions, the @dindakai style trigger, shuffled descriptive tags, and short local-LLM descriptions to preserve the stylewhile keeping character, pose, outfit, and composition editable.