https://github.com/srpkdyy/VideoLDM

Unofficial PyTorch implementation of the VideoLDM.
https://github.com/srpkdyy/VideoLDM

Last synced: 6 months ago
JSON representation

Unofficial PyTorch implementation of the VideoLDM.

• Host: GitHub
• URL: https://github.com/srpkdyy/VideoLDM
• Owner: srpkdyy
• License: mit
• Created: 2023-05-16T15:05:01.000Z (over 2 years ago)
• Default Branch: master
• Last Pushed: 2023-07-03T14:12:15.000Z (over 2 years ago)
• Last Synced: 2024-10-31T01:35:59.783Z (11 months ago)
• Language: Python
• Size: 67.4 KB
• Stars: 145
• Watchers: 12
• Forks: 9
• Open Issues: 7
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

• awesome-diffusion-categorized - [Code

README

          
# Video LDM

![model](assets/4-Figure4-1.png)

## Overview

This is an unofficial PyTorch implementation of the following paper.

> **Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Models**


> Andreas Blattmann, Robin Rombach, Huan Ling, Tim Dockhorn, Seung Wook Kim, Sanja Fidler, Karsten Kreis 


> https://arxiv.org/abs/2304.08818

## Usage

```python

from videoldm import VideoLDM

model = VideoLDM.from_pretrained(

    'CompVis/stable-diffusion-v1-4',

    subfolder='unet',

    low_cpu_mem_usage=False

)

```

## Comments

- This code builds on [diffusers](https://huggingface.co/docs/diffusers/index). Thanks for open-sourcing!