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.
[CVPR 2026 Highlight] High-Quality Text-to-Video Generation with Alpha Channel
| Date | Stars |
|---|---|
| 2026-07-31 | 395 |
| 2026-08-03 | 398 |
| 2026-08-06 | 398 |
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>
Wan-Alpha (CVPR 2026 Highlight)
</h1>
<h3>Video Generation with Stable Transparency via Shiftable RGB-A Distribution Learner</h3>
[](https://arxiv.org/pdf/2509.24979)
[](https://donghaotian123.github.io/Wan-Alpha/)
[](https://huggingface.co/htdong/Wan-Alpha)
[](https://huggingface.co/htdong/Wan-Alpha_ComfyUI)
[](https://huggingface.co/htdong/Wan-Alpha-v2.0)
</div>
<img src="assets/teaser.png" alt="Wan-Alpha Qualitative Results" style="max-width: 100%; height: auto;">
>Qualitative results of video generation using **Wan-Alpha-v2.0**. Our model successfully generates various scenes with accurate and clearly rendered transparency. Notably, it can synthesize diverse semi-transparent objects, glowing effects, and fine-grained details such as hair.
---
### 🔥 News
* **[2026.03.17]** Released checkpoints for Wan-Alpha v1.0 and v2.0 VAE.
* **[2026.03.10]** Released Wan-Alpha v2.0 and Wan-Alpha VAE training codes and training datasets.
* **[2026.02.21]** 🎉 Wan-Alpha v2.0 has been accepted by **CVPR 2026**!
* **[2025.12.16]** Released Wan-Alpha v2.0, the Wan2.1-14B-T2V–adapted weights and inference code are now open-sourced.
* **[2025.12.16]** We update our paper on [arXiv](https://arxiv.org/pdf/2509.24979).
* **[2025.09.30]** Our technical report is available on [arXiv](https://arxiv.org/pdf/2509.24979).
* **[2025.09.30]** Released Wan-Alpha v1.0, the Wan2.1-14B-T2V–adapted weights and inference code are now open-sourced.
---
### 📝 To-Do List
- [x] **Paper**: Available on [arXiv](https://arxiv.org/pdf/2509.24979).
- [x] **Inference Code**: Released inference pipeline for Wan-Alpha v1.0 and v2.0.
- [x] **Model Weights**: Released checkpoints for Wan-Alpha v1.0 and v2.0.
- [x] **Dataset**: Open-source the VAE and T2V training dataset.
- [x] **Training Code (VAE&T2V)**: Release training scripts for the VAE and text-to-RGBA video generation.
- [x] **VAE Checkpoints**: Release checkpoints for Wan-Alpha v1.0 and v2.0 VAE.
- [ ] **Image-to-Video**: Release Wan-Alpha-I2V model weights.
### 🌟 Showcase
##### Text-to-Video Generation with Alpha Channel
<!-- | Prompt | Preview Video | Alpha Video |
| :---: | :---: | :---: |
| "Medium shot. A little girl holds a bubble wand and blows out colorful bubbles that float and pop in the air. The background of this video is transparent. Realistic style." |
<div style="display: flex; gap: 10px;">
<img src="girl.gif" alt="..." style="flex: 1; min-width: 200px;">
</div> |
<div style="display: flex; gap: 10px;">
<img src="girl_pha.gif" alt="..." style="flex: 1; min-width: 200px;">
</div> | -->
| Prompt | Preview Video | Alpha Video |
| :---: | :---: | :---: |
| "The background of this video is transparent. It features a beige, woven rattan hanging chair with soft seat and back cushions. Realistic style. Medium shot." | <img src="assets/squirrel.gif" width="320" height="180" style="object-fit:contain; display:block; margin:auto;"/> | <img src="assets/squirrel_pha.gif" width="320" height="180" style="object-fit:contain; display:block; margin:auto;"/> |
##### For more results, please visit [Our Website](https://donghaotian123.github.io/Wan-Alpha/)
### 🚀 Quick Start
##### 1. Environment Setup
```bash
# Clone the project repository
git clone https://github.com/WeChatCV/Wan-Alpha.git
cd Wan-Alpha
# Create and activate Conda environment
conda create -n Wan-Alpha python=3.11 -y
conda activate Wan-Alpha
# Install dependencies
pip install -r requirements.txt
```
##### 2. Model Download
Download [Wan2.1-T2V-14B](https://huggingface.co/Wan-AI/Wan2.1-T2V-14B)
Download [LighExcerpt of 10,819 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:5cabc6686608f8e7, desc:video generation, desc:text-to-video