@misc{fu2023guiding,
  title={Guiding Instruction-based Image Editing via Multimodal Large Language Models},
  author={Tsu-Jui Fu and Wenze Hu and Xianzhi Du and William Yang Wang and Yinfei Yang and Zhe Gan},
  year={2023},
  eprint={2309.17102},
  archivePrefix={arXiv},
  primaryClass={cs.CV},
  url={https://arxiv.org/abs/2309.17102}
}