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.
OmniVCus: Feedforward Subject-driven Video Customization with Multimodal Control Conditions (NeurIPS 2025)
| Date | Stars |
|---|---|
| 2026-07-24 | 498 |
| 2026-07-25 | 498 |
| 2026-07-28 | 498 |
| 2026-07-30 | 498 |
| 2026-08-06 | 498 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
<div align="center">
<p align="center"> <img src="img/logo.png" width="250px"> </p>
[](https://arxiv.org/abs/2506.23361)
[](https://caiyuanhao1998.github.io/project/OmniVCus/)
<a href="https://huggingface.co/datasets/CaiYuanhao/OmniVCus-Train">
<img src="https://img.shields.io/static/v1?label=%F0%9F%A4%97%20Hugging%20Face&message=Train%20Data&color=yellow">
</a>
<a href="https://huggingface.co/datasets/CaiYuanhao/OmniVCus-Test">
<img src="https://img.shields.io/static/v1?label=%F0%9F%A4%97%20Hugging%20Face&message=Test%20Data&color=yellow">
</a>
<a href="https://huggingface.co/CaiYuanhao/OmniVCus">
<img src="https://img.shields.io/static/v1?label=%F0%9F%A4%97%20Hugging%20Face&message=Model&color=yellow">
</a>
<h4>[NIPS 25] OmniVCus: Feedforward Subject-driven Video Customization with Multimodal Control Conditions</h4>
<p align="center">
<img src="img/demo_1.png" width="48%" alt="abo">
<img src="img/demo_2.png" width="48%" alt="gso">
<img src="img/demo_1.gif" width="48%" alt="flux_1">
<img src="img/demo_2.gif" width="48%" alt="green_man">
</p>
</div>
### Introduction
This is a re-implementation of our work "OmniVCus: Feedforward Subject-driven Video Customization with Multimodal Control Conditions" using public datasets and re-trained model based on public codes. In this work, we present a data construction pipeline that can create data pairs and a diffusion Transformer for subject-driven video customization under different control conditions. I will continue to complete this repo. If you find our repo useful, please give it a star ⭐ and consider citing our paper. Thank you :)
<p align="center">
<img src="img/method_framework.png" alt="pipeline" width="900">
</p>
<p align="center">The overall framework of our OmniVCus</p>
### News
- **2025.12.26 :** Training and testing codes, training data, and pre-trained models have been released. Please feel free to check and try. 🚀
- **2025.12.03 :** The data construction code has been uploaded. I will continue refine and construct this repo. Stay tuned. 💫
- **2025.09.19 :** Our paper has been accepted by NeurIPS 2025. 🎉 🎊
- **2025.06.30 :** Our paper is on [arxiv](https://arxiv.org/abs/2411.14384) now. 🚀
- **2025.06.28 :** Our [project page](https://caiyuanhao1998.github.io/project/OmniVCus/) has been built up. Feel free to check the video generation results on the project page.
## 1. Data Construction
We implement our data construction pipeline in the folder [`VideoCus-Factory`](https://github.com/caiyuanhao1998/Open-OmniVCus/tree/master/VideoCus-Factory), which can construct the multi-modal control conditions including subjects, depth, mask, motion, etc. We also provide the code in the folder [`Video-Depth-Anything`](https://github.com/caiyuanhao1998/Open-OmniVCus/tree/master/Video-Depth-Anything) for better constructing the video depth condition. Please enter the corresponding subfolders for environment installation and data preparation. The following is an example of constructing from a raw video.
<p align="center">
<table border="0" cellspacing="0" cellpadding="0" style="border-collapse:collapse;border:0;">
<!-- ===== Row 1 Prompt ===== -->
<tr>
<td colspan="3" align="center" style="border:0;padding:6px 10px;font-style:italic;">
Generated Prompt: a woman and a child playing with a toy train.
</td>
</tr>
<tr>
<td style="border:0;padding:10px;">
<img src="VideoCus-Factory/img/video_data.gif" width="250" height="140">
</td>
<td style="border:0;padding:10px;">
<img src="VideoCus-Factory/img/entity.png" width="250" height="140">
</td>
<td style="border:0;padding:10px;">
<img src="VideoCus-Factory/img/aug_entity.png" width="250" height="140">
</td>
</tr>
<tr>
<td align="center" style="border:Excerpt of 16,952 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:1415f5743cd07356, topic:video-generation, readme:video generation
matched fp:1415f5743cd07356, topic:transformer
matched fp:1415f5743cd07356, topic:diffusion-models