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:

Synthesizes realistic healthy skin samples without disturbing other input properties.
Maps single-sample rare lesions onto novel skin-tones and locations non-parametrically.
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

bibtex

@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}
}

hcarrion/xanthogranuloma

cgDDI: Controllable Generation of Diverse Dermatological Imagery - xanthogranuloma

cgDDI Framework Overview

Citation

hcarrion/
xanthogranuloma