lucidrains/video-diffusion-pytorch
A Pytorch implementation of diffusion models for generating videos from text descriptions.
Not currently ranked — collecting fresh signals.
star history
This repository implements Jonathan Ho’s Video Diffusion Models paper, extending denoising diffusion probabilistic models (DDPMs) from 2D images to 3D video generation. It uses a space-time factored U-net architecture and incorporates BERT-large for text embedding conditioning to enable text-to-video synthesis. The model can be trained on video data and sampled to generate new videos.
Frequently asked
- What is lucidrains/video-diffusion-pytorch?
- A Pytorch implementation of diffusion models for generating videos from text descriptions.
- Is video-diffusion-pytorch open source?
- Yes — lucidrains/video-diffusion-pytorch is open source, released under the MIT license.
- What language is video-diffusion-pytorch written in?
- lucidrains/video-diffusion-pytorch is primarily written in Python.
- How popular is video-diffusion-pytorch?
- lucidrains/video-diffusion-pytorch has 1.4k stars on GitHub.
- Where can I find video-diffusion-pytorch?
- lucidrains/video-diffusion-pytorch is on GitHub at https://github.com/lucidrains/video-diffusion-pytorch.