---
license: openrail++
tags:
- Polyp-Gen
library_name: diffusers
pipeline_tag: image-to-image
language:
- en
base_model:
- sd2-community/stable-diffusion-2-inpainting
---

# Polyp-Gen: Realistic and Diverse Polyp Image Generation for Endoscopic Dataset Expansion

Polyp-Gen is a text-guided full-automatic diffusion-based endoscopic image generation framework for realistic and diverse polyp image generation for endoscopic dataset expansion, as presented in [Polyp-Gen: Realistic and Diverse Polyp Image Generation for Endoscopic Dataset Expansion](https://huggingface.co/papers/2501.16679). You can use our model for polyp generation.

Code is available [here](https://github.com/CUHK-AIM-Group/Polyp-Gen).

This model card is based on `stable-diffusion-2-inpainting` model, available [here](https://huggingface.co/sd2-community/stable-diffusion-2-inpainting).

## Citation

If you find this work helpful, please consider to **star🌟** this repo and cite the following paper:

```bib
@article{liu2025polyp,
  title={Polyp-Gen: Realistic and Diverse Polyp Image Generation for Endoscopic Dataset Expansion},
  author={Liu, Shengyuan and Chen, Zhen and Yang, Qiushi and Yu, Weihao and Dong, Di and Hu, Jiancong and Yuan, Yixuan},
  journal={arXiv preprint arXiv:2501.16679},
  year={2025}
}
```