This repository contains the textual inversion adaptation weights for generating verruca vulgaris (common warts) imagery, trained on top of stabilityai/stable-diffusion-2-1-base.

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

Resource Links

Repository: GitHub - ControllableGenDDI
Dataset: hcarrion/ControllableGenDDI

Usage

You can load these weights via diffusers to generate synthetic dermatological images of verruca vulgaris:

python

from diffusers import StableDiffusionPipeline
import torch

model_id = "stabilityai/stable-diffusion-2-1-base"
pipe = StableDiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.float16)
pipe.to("cuda")

# Load textual inversion weights
pipe.load_textual_inversion("hcarrion/verruca_vulgaris")

prompt = "a close-up photo of a skin lesion depicting <verruca_vulgaris-class> on light skin tone"
image = pipe(prompt).images[0]
image.save("verruca_vulgaris_synthetic.png")

Citation

bibtex

@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}
}