Skip to content

Videoshop: Localized Semantic Video Editing with Noise-Extrapolated Diffusion Inversion

Notifications You must be signed in to change notification settings

sfanxiang/videoshop

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

3 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Videoshop

[Project] [Paper] [Supplementary]

Videoshop: Localized Semantic Video Editing with Noise-Extrapolated Diffusion Inversion.

Code Usage

Make sure the input video has 14 frames. Run:

python3 run.py --video <INPUT VIDEO.mp4> --image <INPUT IMAGE.png> --output <OUTPUT VIDEO.mp4>

You can find more control knobs by invoking the script with --help:

python3 run.py --help

Citation

@misc{fan2024videoshop,
      title={Videoshop: Localized Semantic Video Editing with Noise-Extrapolated Diffusion Inversion}, 
      author={Xiang Fan and Anand Bhattad and Ranjay Krishna},
      year={2024},
      eprint={2403.14617},
      archivePrefix={arXiv},
      primaryClass={cs.CV}
}

About

Videoshop: Localized Semantic Video Editing with Noise-Extrapolated Diffusion Inversion

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages