T2V-Turbo: Breaking the Quality Bottleneck of Video Consistency Model with Mixed Reward Feedback

Fast and High-Quality Text-to-video Generation 🚀

This demo uses the T2V-Turbo (VC2) model, with resolution of 320x512

Citation

@misc{li2024t2vturbo,
      title={T2V-Turbo: Breaking the Quality Bottleneck of Video Consistency Model with Mixed Reward Feedback}, 
      author={Jiachen Li and Weixi Feng and Tsu-Jui Fu and Xinyi Wang and Sugato Basu and Wenhu Chen and William Yang Wang},
      year={2024},
      eprint={2405.18750},
      archivePrefix={arXiv},
      primaryClass={cs.CV}
}