cgDDI: foreign_body_granuloma Textual Inversion

This repository contains the textual inversion adaptation weights (learned concept <foreign_body_granuloma-class>) for stabilityai/stable-diffusion-2-1-base.

These weights were developed 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.

About cgDDI

cgDDI is a hybrid framework designed to synthesize realistic dermatological images across diverse skin tones to support fair and efficient malignancy classification. It addresses the lack of expertly annotated images for underrepresented skin tones and rare diseases by using textual inversion and LoRA-based models to generate disease-specific concepts.

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

Citation

If you find this model useful in 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}
}