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.
Official codes of VEnhancer: Generative Space-Time Enhancement for Video Generation
| Date | Stars |
|---|---|
| 2026-07-24 | 576 |
| 2026-07-25 | 576 |
| 2026-07-28 | 576 |
| 2026-07-30 | 576 |
| 2026-08-06 | 576 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
<div align="center">
<h1>VEnhancer: Generative Space-Time Enhancement<br>for Video Generation</h1>
<div>
<a href='https://scholar.google.com/citations?user=GUxrycUAAAAJ&hl=zh-CN' target='_blank'>Jingwen He</a>, 
<a href='https://tianfan.info' target='_blank'>Tianfan Xue</a>, 
<a href='https://github.com/ChrisLiu6' target='_blank'>Dongyang Liu</a>, 
<a href='https://github.com/0x3f3f3f3fun' target='_blank'>Xinqi Lin</a>, 
</div>
<a href='https://gaopengcuhk.github.io' target='_blank'>Peng Gao</a>, 
<a href='https://scholar.google.com/citations?user=GMzzRRUAAAAJ&hl=en' target='_blank'>Dahua Lin</a>, 
<a href='https://scholar.google.com/citations?user=gFtI-8QAAAAJ&hl=en' target='_blank'>Yu Qiao</a>, 
<a href='https://wlouyang.github.io' target='_blank'>Wanli Ouyang</a>, 
<a href='https://liuziwei7.github.io' target='_blank'>Ziwei Liu</a>
<div>
</div>
<div>
The Chinese University of Hong Kong, Shanghai Artificial Intelligence Laboratory, 
</div>
<div>
</div>
<div>
S-Lab, Nanyang Technological University 
</div>
<div>
<h4 align="center">
<a href="https://vchitect.github.io/VEnhancer-project/" target='_blank'>
<img src="https://img.shields.io/badge/🐳-Project%20Page-blue">
</a>
<a href="https://arxiv.org/abs/2407.07667" target='_blank'>
<img src="https://img.shields.io/badge/arXiv-2312.06640-b31b1b.svg">
</a>
<a href="https://youtu.be/QMR_5weifGg" target='_blank'>
<img src="https://img.shields.io/badge/Demo%20Video-%23FF0000.svg?logo=YouTube&logoColor=white">
<!-- </a>
<img src="https://api.infinitescript.com/badgen/count?name="> -->
</h4>
</div>
<strong>VEnhancer, an All-in-One generative video enhancement model that can achieve spatial super-resolution, temporal super-resolution, and video refinement for AI-generated videos.</strong>
<table class="center">
<tr>
<td colspan="1">AIGC video</td>
<td colspan="1">+VEnhancer</td>
</tr>
<tr>
<td>
<img src=assets/input_fish.gif width="380">
</td>
<td>
<img src=assets/out_fish.gif width="380">
</td>
</tr>
</table>
:open_book: For more visual results, go checkout our <a href="https://vchitect.github.io/VEnhancer-project/" target="_blank">project page</a>
---
</div>
## 🔥 Update
- [2024.09.12] 😸 Release our version 2 checkpoint: **[venhancer_v2.pt](https://huggingface.co/jwhejwhe/VEnhancer/resolve/main/venhancer_v2.pt)** . It is less creative, but is able to generate more texture details, and has better identity preservation, which is more suitable for enhancing videos with profiles.
- [2024.09.10] 😸 Support **Multiple GPU Inference** and **tiled VAE** for temporal VAE decoding. And more stable performance for long video enhancement.
- [2024.08.18] 😸 Support enhancement for **abitrary long videos** (by spliting the videos into muliple chunks with overlaps); **Faster sampling** with only 15 steps without obvious quality loss (by setting `--solver_mode 'fast'` in the script command); Use **temporal VAE** to reduce video flickering.
- [2024.07.28] 🔥 Inference code and pretrained video enhancement model are released.
- [2024.07.10] 🤗 This repo is created.
<!-- ## Open Source Plan
- [x] Release code of Multiple GPU Inference.
- [x] Release code of tiled VAE.
- [ ] Release model that is optimized for better idenity preservation. -->
<!-- :star::star::star: Star us :star::star::star:! And we will speed up the open-sourcing process :heart:. -->
## :astonished: Gallery
| Inputs & Results | Model Version |
| :---------- | :-: |
|Prompt: A close-up shot of a woman standing in a dimly lit room. she is wearing a traditional chinese outfit, which includes a red and gold dress with intricate designs and a matching headpiece.<br/><video src="https://github.com/user-attachments/assets/4a514853-65f6-40b8-8b5d-d14835bb9297" width="100%" controls autoplay></video>from [Open-Sora](Excerpt of 10,318 characters
Read on GitHub
21
Dongyang Liu
5
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:c72e1eb7e20825af, topic:video-generation, topic:text-to-video, desc:video generation
matched fp:c72e1eb7e20825af, topic:diffusion-models, readme:super resolution