@misc{girdhar2023video,
  title={Emu Video: Factorizing Text-to-Video Generation by Explicit Image Conditioning},
  author={Rohit Girdhar and Mannat Singh and Andrew Brown and Quentin Duval and Samaneh Azadi and Sai Saketh Rambhatla and Akbar Shah and Xi Yin and Devi Parikh and Ishan Misra},
  year={2023},
  eprint={2311.10709},
  archivePrefix={arXiv},
  primaryClass={cs.CV},
  url={https://arxiv.org/abs/2311.10709}
}