showlab/Tune-A-Video
A method for one-shot fine-tuning of text-to-image diffusion models to enable text-to-video generation.
Not currently ranked — collecting fresh signals.
star history
Tune-A-Video adapts pre-trained text-to-image diffusion models to video generation by fine-tuning on a single video-text pair. It extends 2D diffusion to temporal dimensions using sparse temporal attention. The method was published at ICCV 2023 and supports applications like video editing and text-driven video synthesis.
Frequently asked
- What is showlab/Tune-A-Video?
- A method for one-shot fine-tuning of text-to-image diffusion models to enable text-to-video generation.
- Is Tune-A-Video open source?
- Yes — showlab/Tune-A-Video is open source, released under the Apache-2.0 license.
- What language is Tune-A-Video written in?
- showlab/Tune-A-Video is primarily written in Python.
- How popular is Tune-A-Video?
- showlab/Tune-A-Video has 4.4k stars on GitHub.
- Where can I find Tune-A-Video?
- showlab/Tune-A-Video is on GitHub at https://github.com/showlab/Tune-A-Video.