ji4chenli / t2v-turbo

Fast and High-Quality Text-to-video Generation

  • Public
  • 4.2K runs
  • GitHub
  • Paper

Run time and cost

This model costs approximately $0.016 to run on Replicate, or 62 runs per $1, but this varies depending on your inputs. It is also open source and you can run it on your own computer with Docker.

This model runs on Nvidia A40 (Large) GPU hardware. Predictions typically complete within 23 seconds. The predict time for this model varies significantly based on the inputs.

Readme

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}
}