These are disease-conditioned textual inversion adaptation weights for
stabilityai/stable-diffusion-2-1-base.
This model was trained as 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.
1@inproceedings{carrion2026cgddi,
2 title = {Controllable Generation of Diverse Dermatological Imagery for Fair and Efficient Malignancy Classification},
3 author = {Carri{\'o}n, H{\'e}ctor and Norouzi, Narges},
4 booktitle = {Medical Image Computing and Computer-Assisted Intervention (MICCAI)},
5 year = {2026},
6 publisher = {Springer},
7 series = {Lecture Notes in Computer Science}
8}
