cgDDI: acral_melanotic_macule

This model is a disease-conditioned generative adapter for acral melanotic macule, trained using the cgDDI (Controllable Generation of Diverse Dermatological Imagery) framework. It is based on stabilityai/stable-diffusion-2-1-base and learned via joint textual inversion and fine-tuning.

More details can be found in the associated paper: Controllable Generation of Diverse Dermatological Imagery for Fair and Efficient Malignancy Classification (MICCAI 2026).

Project Resources

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

Citation

If you find this model useful for your research, 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}
}