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.
[IJCV] Show-1: Marrying Pixel and Latent Diffusion Models for Text-to-Video Generation
| Date | Stars |
|---|---|
| 2026-07-31 | 1148 |
| 2026-08-03 | 1148 |
| 2026-08-06 | 1148 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
<div align="center" width="100%">
<h1>🎬Show-1</h1>
</div>
<div>
<div align="center">
<a href='https://junhaozhang98.github.io/' target='_blank'>David Junhao Zhang<sup>*</sup></a> 
<a href='https://zhangjiewu.github.io/' target='_blank'>Jay Zhangjie Wu<sup>*</sup></a> 
<a href='https://jia-wei-liu.github.io/' target='_blank'>Jia-Wei Liu<sup>*</sup></a>
<br>
<a href='https://ruizhaocv.github.io/' target='_blank'>Rui Zhao<sup></sup></a> 
<a href='https://siacorplab.nus.edu.sg/people/ran-lingmin/' target='_blank'>Lingmin Ran<sup></sup></a> 
<a href='https://ycgu.site/' target='_blank'>Yuchao Gu<sup></sup></a> 
<a href='https://scholar.google.com/citations?user=No9OsocAAAAJ&hl=en' target='_blank'>Difei Gao<sup></sup></a> 
<a href='https://sites.google.com/view/showlab/home?authuser=0' target='_blank'>Mike Zheng Shou<sup>✉</sup></a>
</div>
<div>
<div align="center">
<a href='https://sites.google.com/view/showlab/home?authuser=0' target='_blank'>Show Lab, National University of Singapore</a>
</br>
<sup>*</sup> Equal Contribution 
<sup>✉</sup> Corresponding Author
</div>
-----------------
### [Project Page](https://showlab.github.io/Show-1) | [arXiv](https://arxiv.org/abs/2309.15818) | [PDF](https://arxiv.org/abs/2309.15818) | [🤗 Space](https://huggingface.co/spaces/showlab/Show-1) | [Colab](https://colab.research.google.com/github/camenduru/Show-1-colab/blob/main/Show_1_steps_colab.ipynb) | [Replicate Demo](https://replicate.com/cjwbw/show-1)
<a href="https://trendshift.io/repositories/3499" target="_blank"><img src="https://trendshift.io/api/badge/repositories/3499" alt="showlab%2FShow-1 | Trendshift" style="width: 250px; height: 55px;" width="250" height="55"/></a></p>
## News
- [10/06/2024] Show-1 was accepted to IJCV!
- [10/12/2023] Code and weights released!
## Setup
### Requirements
```shell
pip install -r requirements.txt
```
Note: PyTorch 2.0+ is highly recommended for more efficiency and speed on GPUs.
### Weights
All model weights for Show-1 are available on [Show Lab's HuggingFace page](https://huggingface.co/showlab): Base Model ([show-1-base](https://huggingface.co/showlab/show-1-base)), Interpolation Model ([show-1-interpolation](https://huggingface.co/showlab/show-1-interpolation)), and Super-Resolution Model ([show-1-sr1](https://huggingface.co/showlab/show-1-sr1), [show-1-sr2](https://huggingface.co/showlab/show-1-sr2)).
Note that our [show-1-sr1](https://huggingface.co/showlab/show-1-sr1) incorporates the image super-resolution model from DeepFloyd-IF, [DeepFloyd/IF-II-L-v1.0](https://huggingface.co/DeepFloyd/IF-II-L-v1.0), to upsample the first frame of the video. To obtain the respective weights, follow their [official instructions](https://huggingface.co/DeepFloyd/IF-II-L-v1.0).
## Usage
To generate a video from a text prompt, run the command below:
```bash
python run_inference.py
```
By default, the videos generated from each stage are saved to the `outputs` folder in the GIF format. The script will automatically fetch the necessary model weights from HuggingFace. If you prefer, you can manually download the weights using git lfs and then update the `pretrained_model_path` to point to your local directory. Here's how:
```bash
git lfs install
git clone https://huggingface.co/showlab/show-1-base
```
A demo is also available on the [`showlab/Show-1` 🤗 Space](https://huggingface.co/spaces/showlab/Show-1).
You can use the gradio demo locally by running:
```bash
python app.py
```
## Demo Video
https://github.com/showlab/Show-1/assets/55792387/32242135-25a5-4757-b494-91bf314581e8
## Citation
If you make use of our work, please cite our paper.
```bibtex
@article{zhang2023show,
title={Show-1: Marrying Pixel and Latent Diffusion Models for Text-to-Video Generation},
author={Zhang, David Junhao and Wu, Jay Zhangjie and Liu, Jia-Wei and Zhao, Rui and Ran, Lingmin and Gu, Yuchao and Gao, DifeExcerpt of 5,133 characters
Read on GitHub
16
Jay Wu · NVIDIA
12
Chenxi
4
Rui Zhao · National University of Singapore · Singapore
3
Ikko Eltociear Ashimine · Japan
1
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:43e6de6f290c747a, desc:video generation, desc:text-to-video