cgDDI: Controllable Generation of Diverse Dermatological Imagery - xanthogranuloma

This repository contains textual inversion adaptation weights for stabilityai/stable-diffusion-2-1-base representing the xanthogranuloma disease concept.

It was introduced as part of the cgDDI framework in the paper Controllable Generation of Diverse Dermatological Imagery for Fair and Efficient Malignancy Classification.

• Repository: hectorcarrion/ControllableGenDDI
• Dataset: hcarrion/ControllableGenDDI

cgDDI Framework Overview

cgDDI (Controllable Generation of Diverse Dermatological Imagery) is a hybrid framework that:

1. Synthesizes realistic healthy skin samples without disturbing other input properties.
2. Maps single-sample rare lesions onto novel skin-tones and locations non-parametrically.
3. Allows for efficient parametric generation with as few as 10 training samples via textual inversion and LoRA.

This checkpoint corresponds to one of the 65 disease-conditioned concept tokens learned using textual inversion to generate realistic dermatological imagery.

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}
}