Textual inversion text2image fine-tuning - hcarrion/prurigo_nodularis

These are textual inversion adaptation weights for stabilityai/stable-diffusion-2-1-base to generate images of the dermatological condition prurigo nodularis.

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

Resources

• Repository: GitHub Code
• Full Dataset: hcarrion/ControllableGenDDI

About the cgDDI Framework

cgDDI (Controllable Generation of Diverse Dermatological Imagery) is a hybrid framework designed to synthesize realistic healthy skin samples and map lesions onto novel skin-tones and locations. It trains disease-specific concepts via textual inversion and LoRA, enabling fair and diverse dermatological image generation to improve malignancy classification.

Citation

If you find this model or work 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}
}