hcarrion/focal-acral-hyperkeratosis

Textual inversion text2image fine-tuning - hcarrion/focal-acral-hyperkeratosis

These are textual inversion adaptation weights for stabilityai/stable-diffusion-2-1-base to learn the concept of focal-acral-hyperkeratosis (using the token <focal-acral-hyperkeratosis-class>).

This model is part of cgDDI (Controllable Generation of Diverse Dermatological Imagery), a hybrid framework presented in the paper Controllable Generation of Diverse Dermatological Imagery for Fair and Efficient Malignancy Classification (MICCAI 2026).

Code & Resources

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

For notebooks and instructions on how to train, fine-tune, and perform semantic sampling with these disease-conditioned LoRA and textual inversion models, please refer to the official GitHub repository.

Citation

If you find cgDDI 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}
}