@article{emmayourtexttoimagediffusionmodelcan,
  title = {EMMA: Your Text-to-Image Diffusion Model Can Secretly Accept Multi-Modal Prompts},
  author = {Yucheng Han and Rui Wang and Chi Zhang and Juntao Hu and Pei Cheng and Bin Fu and Hanwang Zhang},
  year = {2024},
  eprint = {2406.09162},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2406.09162v1},
}