Dataset (visualizations)
Our custom dataset contains high-quality generated images and input data. Each folder is named after a subject and includes two subfolders: input (containing subject images for fine-tuning Diffusion models) and generated (storing images produced by the fine-tuned model).
Some subject input images are sourced from DreamBooth and Custom Diffusion, while the rest are collected from the web. The web-sourced data is acknowledged in the paper.
If you think this project is helpful, please feel free to leave a star⭐️ and cite our paper:
@InProceedings{Marjit_2025_WACV,
author = {Marjit, Shyam and Singh, Harshit and Mathur, Nityanand and Paul, Sayak and Yu, Chia-Mu and Chen, Pin-Yu},
title = {DiffuseKronA: A Parameter Efficient Fine-Tuning Method for Personalized Diffusion Models},
booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)},
month = {February},
year = {2025},
pages = {3529-3538}
}