Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
LVDM: Latent Video Diffusion Models for High-Fidelity Long Video Generation
| Date | Stars |
|---|---|
| 2026-07-31 | 503 |
| 2026-08-06 | 503 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
<div align="center">
<h2> LVDM: <span style="font-size:12px">Latent Video Diffusion Models for High-Fidelity Long Video Generation </span> </h2>
<a href='https://arxiv.org/abs/2211.13221'><img src='https://img.shields.io/badge/ArXiv-2211.14758-red'></a> <a href='https://yingqinghe.github.io/LVDM/'><img src='https://img.shields.io/badge/Project-Page-Green'></a>
<div>
<a href='https://github.com/YingqingHe' target='_blank'>Yingqing He <sup>1</sup> </a> 
<a href='https://tianyu-yang.com/' target='_blank'>Tianyu Yang <sup>2</a> 
<a href='https://yzhang2016.github.io/' target='_blank'>Yong Zhang <sup>2</sup></a> 
<a href='https://scholar.google.com/citations?hl=en&user=4oXBp9UAAAAJ&view_op=list_works&sortby=pubdate' target='_blank'>Ying Shan <sup>2</sup></a> 
<a href='https://cqf.io/' target='_blank'>Qifeng Chen <sup>1</sup></a>  </br>
</div>
<br>
<div>
<sup>1</sup> The Hong Kong University of Science and Technology   <sup>2</sup> Tencent AI Lab  
</div>
<br>
<br>
<b>TL;DR: An efficient video diffusion model that can:</b>
1️⃣ conditionally generate videos based on input text;
2️⃣ unconditionally generate videos with thousands of frames.
<br>
</div>
## 🍻 Results
### ☝️ Text-to-Video Generation
<table class="center">
<!-- <td style="text-align:center;" width="50">Input Text</td> -->
<td style="text-align:center;" width="170">"A corgi is swimming fastly"</td>
<td style="text-align:center;" width="170">"astronaut riding a horse"</td>
<td style="text-align:center;" width="170">"A glass bead falling into water with a huge splash. Sunset in the background"</td>
<td style="text-align:center;" width="170">"A beautiful sunrise on mars. High definition, timelapse, dramaticcolors."</td>
<td style="text-align:center;" width="170">"A bear dancing and jumping to upbeat music, moving his whole body."</td>
<td style="text-align:center;" width="170">"An iron man surfing in the sea. cartoon style"</td>
<tr>
<td><img src=assets/t2v-001.gif width="170"></td>
<td><img src=assets/t2v-002.gif width="170"></td>
<td><img src=assets/t2v-003.gif width="170"></td>
<td><img src=assets/t2v-007.gif width="170"></td>
<td><img src=assets/t2v-005.gif width="170"></td>
<td><img src=assets/t2v-004.gif width="170"></td>
</tr>
</table >
### ✌️ Unconditional Long Video Generation (40 seconds)
<table class="center">
<td><img src=assets/sky-long-001.gif width="170"></td>
<td><img src=assets/sky-long-002.gif width="170"></td>
<td><img src=assets/sky-long-003.gif width="170"></td>
<td><img src=assets/ucf-long-001.gif width="170"></td>
<td><img src=assets/ucf-long-002.gif width="170"></td>
<td><img src=assets/ucf-long-003.gif width="170"></td>
<tr>
</tr>
</table >
## ⏳ TODO
- [x] Release pretrained text-to-video generation models and inference code
- [x] Release unconditional video generation models
- [x] Release training code
- [ ] Update training and sampling for long video generation
<br>
---
## ⚙️ Setup
### Install Environment via Anaconda
```bash
conda create -n lvdm python=3.8.5
conda activate lvdm
pip install -r requirements.txt
```
### Pretrained Models and Used Datasets
<!-- <div style="text-indent:25px"> -->
<!-- <details><summary></summary> -->
Download the pretrained checkpoints via the following commands in Linux terminal:
```
mkdir -p models/ae
mkdir -p models/lvdm_short
mkdir -p models/t2v
# sky timelapse
wget -O models/ae/ae_sky.ckpt https://huggingface.co/Yingqing/LVDM/resolve/main/ae/ae_sky.ckpt
wget -O models/lvdm_short/short_sky.ckpt https://huggingface.co/Yingqing/LVDM/resolve/main/lvdm_short/short_sky.ckpt
# taichi
wget -O models/ae/ae_taichi.ckpt https://huggingface.co/Yingqing/LVDM/resolve/main/ae/ae_taichi.ckpt
wget -O models/lvdm_short/short_taichi.ckpt https://huggingface.co/Yingqing/LVDM/resolve/main/lvdm_short/short_taichi.ckpt
# text2video
wget -O models/t2v/model.ckpt https://huggingface.Excerpt of 8,588 characters
Read on GitHub
Joy · HKUST
3
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:177e8a615e966513, desc:video generation