@article{masteringtexttoimagediffusion,
  title = {Mastering Text-to-Image Diffusion: Recaptioning, Planning, and Generating with Multimodal LLMs},
  author = {Ling Yang and Zhaochen Yu and Chenlin Meng and Minkai Xu and Stefano Ermon and Bin Cui},
  year = {2024},
  eprint = {2401.11708},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2401.11708v3},
}