Model Architecture • How To Use • Citation • Acknowledgement • Visualization
# Clone this repository
$ git clone https://github.com/NJU-PCALab/CoDi
# Go into the repository
$ cd CoDi
### Install dependencies ###
$ conda env create --file environment.yml
$ conda activate codi
### Install dependencies ENDs ###
# Run infer code
$ python main.py
# Run benchmark generation code
$ python gen_benchmark.pyIf our work assists your research, feel free to give us a star ⭐ or cite us using:
@article{gao2025codi,
title={Subject-Consistent and Pose-Diverse Text-to-Image Generation},
author={Gao, Zhanxin and Zhu, Beier and Yao, Liang and Yang, Jian and Tai, Ying},
journal={arXiv preprint arXiv:2507.08396},
year={2025}
}
We gratefully acknowledge the following repositories for providing useful components and functions that contributed to our work.