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.
Pusa: Thousands Timesteps Video Diffusion Model
| Date | Stars |
|---|---|
| 2026-07-31 | 686 |
| 2026-08-03 | 686 |
| 2026-08-06 | 686 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
<p align="center">
<img src="https://github.com/Yaofang-Liu/Pusa-VidGen/blob/f867c49d9570b88e7bbce6e25583a0ad2417cdf7/icon.png" width="70"/>
</p>
# Pusa: Thousands Timesteps Video Diffusion Model (ICLR 2026)
<p align="center">
<a href="https://yaofang-liu.github.io/Pusa_Web/"><img alt="Project Page" src="https://img.shields.io/badge/Project-Page-blue?style=for-the-badge"></a>
<a href="https://arxiv.org/abs/2507.16116"><img alt="Technical Report" src="https://img.shields.io/badge/Technical_Report-📜-B31B1B?style=for-the-badge"></a>
<a href="https://huggingface.co/RaphaelLiu/Pusa-Wan2.2-V1"><img alt="Model" src="https://img.shields.io/badge/Pusa_V1.0_Wan2.2-Model-FFD700?style=for-the-badge&logo=huggingface"></a>
<a href="https://huggingface.co/RaphaelLiu/PusaV1"><img alt="Model" src="https://img.shields.io/badge/Pusa_V1.0_Wan2.1-Model-FFD700?style=for-the-badge&logo=huggingface"></a>
</p>
<p align="center">
<a href="https://huggingface.co/datasets/RaphaelLiu/PusaV1_training"><img alt="Dataset" src="https://img.shields.io/badge/Pusa_V1.0-Dataset-6495ED"></a>
<a href="https://github.com/Yaofang-Liu/Mochi-Full-Finetuner"><img alt="Code" src="https://img.shields.io/badge/Code-Training%20Scripts-32CD32?logo=github"></a>
<a href="https://arxiv.org/abs/2410.03160"><img alt="Paper" src="https://img.shields.io/badge/📜-FVDM%20Paper-B31B1B?logo=arxiv"></a>
<a href="https://x.com/stephenajason"><img alt="Twitter" src="https://img.shields.io/badge/🐦-Twitter-1DA1F2?logo=twitter"></a>
<a href="https://www.xiaohongshu.com/discovery/item/67f898dc000000001c008339"><img alt="Xiaohongshu" src="https://img.shields.io/badge/📕-Xiaohongshu-FF2442"></a>
</p>
## **🔥🔥🔥🚀 New: Wan2.2 Support & LightX2V Acceleration🚀🔥🔥🔥**
- **MoE DiT Architecture**: Now supporting Wan2.2 models with separate high-noise and low-noise DiT models for enhanced quality
- **⚡ [LightX2V](https://github.com/ModelTC/LightX2V) Integration**: Achieve 4-step inference with lightning-fast generation while maintaining quality
- **Unified Framework**: Compatible with both Wan2.1 and Wan2.2 architectures
We are excited to release **Pusa V1.0**, a groundbreaking paradigm that leverages **vectorized timestep adaptation (VTA)** to enable fine-grained temporal control within a unified video diffusion framework. By finetuning the SOTA **Wan-T2V-14B** model with VTA, Pusa V1.0 achieves unprecedented efficiency, **surpassing Wan-I2V on Vbench-I2V with only $500 of training cost and 4k data**.
## :sparkles: Highlights
- **[ComfyUI](https://huggingface.co/Kijai/WanVideo_comfy/tree/main/Pusa)**, supported by [Kijai](https://github.com/kijai), thanks a lot!
- **[WAN2.2-14B-Rapid-AllInOne](https://huggingface.co/Phr00t/WAN2.2-14B-Rapid-AllInOne)**, big salute to [Phr00t](https://huggingface.co/Phr00t)!
## Showcases
### **Various tasks in one model, all in 4 steps with LightX2V**
**Text-to-Video, Image-to-Video, Start-End Frames, Video Completion, Video Extension, Video Transition, and more...**. Below are some showcases for Pusa-Wan2.2-V1. Please refer to **[Pusa V1.0 README](./PusaV1/README.md)** for detailed info.
**Example 1: Image-to-Video in 4 Steps**
<table border="0" style="width: 100%; text-align: center; margin-top: 20px;">
<tr>
<td align="center" style="padding: 8px;">
<strong>noise: 0.2, high_lora_alpha 1.5</strong><br>
<video src="https://github.com/user-attachments/assets/2eb2c158-fea7-4a7b-b5ee-239cea33ee01" width="100%" controls loop></video>
</td>
<td align="center" style="padding: 8px;">
<strong>noise: 0.3, high_lora_alpha 1.4</strong><br>
<video src="https://github.com/user-attachments/assets/5e0aedfa-d177-44cf-b707-ffd970952d33" width="100%" controls loop></video>
</td>
</tr>
<tr>
<td align="center" style="padding: 8px;">
<strong>noise: 0.2, high_lora_alpha 1.5</strong><br>
<video src="https://github.com/usExcerpt of 24,386 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:c4a2de50f275d272, desc:diffusion model
