trained for the model Tint<a target="_blank" rel="ugc" href="https://civarchive.com/models/1505334/tint-full-chroma-finetune-for-transformation-content">https://civarchive.com/models/1505334/tint-full-chroma-finetune-for-transformation-content</a>, to be able to generate transformation sequences with two people instead of just a single person to something elsefor tagging, it uses images with either llm tags or my own prompts that are basically just two-five sentences saying "transformation sequence x into y" "transformation comic x into y" "before and after x into y" or just a simple literal description for single imagesRecommend you use this at strength 0.8You can use first/last frame references and structure control with the models in the kofi page:<a target="_blank" rel="ugc" href="https://ko-fi.com/tintbot">https://ko-fi.com/tintbot</a>

Files with SHA256: 367a2b4d22df6efddb0649963b05790bc817d97b87a72496da6576982a7c62fa