cgDDI: Textual Inversion for Folliculitis

This repository contains the textual inversion adaptation weights for stabilityai/stable-diffusion-2-1-base learned for the disease concept of folliculitis (<folliculitis-class>).

It is part of the cgDDI (Controllable Generation of Diverse Dermatological Imagery) framework presented in the paper Controllable Generation of Diverse Dermatological Imagery for Fair and Efficient Malignancy Classification.

Resources and Links

• GitHub Repository: hectorcarrion/ControllableGenDDI
• Dataset: hcarrion/ControllableGenDDI
• Paper: Hugging Face Paper Page

Usage

This model can be used with the Hugging Face diffusers library to generate synthetic dermatological images of folliculitis for medical fairness research and clinical educational purposes.

Please refer to the official GitHub notebooks for detailed instructions on textual inversion pipeline setups, LoRA training, and semantic sampling using the learned concept <folliculitis-class>.

Citation

@inproceedings{carrion2026cgddi,
  title     = {Controllable Generation of Diverse Dermatological Imagery for Fair and Efficient Malignancy Classification},
  author    = {Carri{\'o}n, H{\'e}ctor and Norouzi, Narges},
  booktitle = {Medical Image Computing and Computer-Assisted Intervention (MICCAI)},
  year      = {2026},
  publisher = {Springer},
  series    = {Lecture Notes in Computer Science}
}