cgDDI: Textual Inversion - acrochordon

This repository contains the textual inversion adaptation weights for stabilityai/stable-diffusion-2-1-base corresponding to the acrochordon (skin tags) disease class.

This model was introduced as part of the paper Controllable Generation of Diverse Dermatological Imagery for Fair and Efficient Malignancy Classification.

About cgDDI

cgDDI (Controllable Generation of Diverse Dermatological Imagery) is a hybrid framework designed to address the lack of equity in dermatological datasets by synthesizing realistic and diverse skin imagery. It allows learning disease-specific concept tokens using textual inversion on a base latent diffusion model, enabling the generation of synthetic, fair, and disease-conditioned skin samples.

• Paper: Controllable Generation of Diverse Dermatological Imagery for Fair and Efficient Malignancy Classification
• Repository: hectorcarrion/ControllableGenDDI
• Dataset: hcarrion/ControllableGenDDI

For notebooks and scripts showing how to train, sample, and evaluate this textual inversion model, please refer to the GitHub Repository.

Citation

If you find these models useful, please cite:

@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}
}