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.
[ICCV 2025] Light-A-Video: Training-free Video Relighting via Progressive Light Fusion
| Date | Stars |
|---|---|
| 2026-07-24 | 517 |
| 2026-07-25 | 517 |
| 2026-07-28 | 516 |
| 2026-07-30 | 516 |
| 2026-08-06 | 516 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
<div align="center">
<img src='__assets__/title.png'/>
</div>
---
### ⭐️ **Our team's works:** [[**HiFlow**](https://bujiazi.github.io/hiflow.github.io/)] [[**MotionClone**](https://bujiazi.github.io/motionclone.github.io/)] [[**ByTheWay**](https://github.com/Bujiazi/ByTheWay)]
## Light-A-Video: Training-free Video Relighting via Progressive Light Fusion
This repository is the official implementation of Light-A-Video. It is a **training-free framework** that enables
zero-shot illumination control of any given video sequences or foreground sequences.
<details><summary>Click for the full abstract of Light-A-Video</summary>
> Recent advancements in image relighting models, driven by large-scale datasets and pre-trained diffusion models, have enabled the imposition of consistent lighting. However, video relighting still lags, primarily due to the excessive training costs and the scarcity of diverse, high-quality video relighting datasets. A simple application of image relighting models on a frame-by-frame basis leads to several issues: lighting source inconsistency and relighted appearance inconsistency, resulting in flickers in the generated videos. In this work, we propose Light-A-Video, a training-free approach to achieve temporally smooth video relighting. Adapted from image relighting models, Light-A-Video introduces two key techniques to enhance lighting consistency. First, we design a Consistent Light Attention (CLA) module, which enhances cross-frame interactions within the self-attention layers of the image relight model to stabilize the generation of the background lighting source. Second, leveraging the physical principle of light transport independence, we apply linear blending between the source video's appearance and the relighted appearance, using a Progressive Light Fusion (PLF) strategy to ensure smooth temporal transitions in illumination. Experiments show that Light-A-Video improves the temporal consistency of relighted video while maintaining the relighted image quality, ensuring coherent lighting transitions across frames.
</details>
**[Light-A-Video: Training-free Video Relighting via Progressive Light Fusion]()**
</br>
[Yujie Zhou*](https://github.com/YujieOuO/),
[Jiazi Bu*](https://github.com/Bujiazi/),
[Pengyang Ling*](https://github.com/LPengYang/),
[Pan Zhang<sup>†</sup>](https://panzhang0212.github.io/),
[Tong Wu](https://wutong16.github.io/),
[Qidong Huang](https://shikiw.github.io/),
[Jinsong Li](https://li-jinsong.github.io/),
[Xiaoyi Dong](https://scholar.google.com/citations?user=FscToE0AAAAJ&hl=en/),
[Yuhang Zang](https://yuhangzang.github.io/),
[Yuhang Cao](https://scholar.google.com/citations?hl=zh-CN&user=sJkqsqkAAAAJ),
[Anyi Rao](https://anyirao.com/),
[Jiaqi Wang](https://myownskyw7.github.io/),
[Li Niu<sup>†</sup>](https://www.ustcnewly.com/)
(*Equal Contribution)(<sup>†</sup>Corresponding Author)
[](https://arxiv.org/abs/2502.08590)
[](https://bujiazi.github.io/light-a-video.github.io/)
[](https://huggingface.co/spaces/fffiloni/Light-A-Video)
## 💡 Demo
[![]](https://github.com/user-attachments/assets/ea5a01b9-a5a5-4159-a61b-7fef8e44e6db)
## 📜 News
**[2025/6/26]** Happy to announce that Light-A-Video is accepted by ICCV 2025!
**[2025/3/14]** Support [CogVideoX](https://github.com/THUDM/CogVideo)!
**[2025/3/11]** Support [Wan2.1](https://github.com/Wan-Video/Wan2.1)!
**[2025/2/11]** Code is available now!
**[2025/2/10]** The paper and project page are released!
## 🏗️ Todo
- [x] Release a gradio demo.
- [x] Release Light-A-Video code with CogVideoX-2B pipeline.
## 📚 Gallery
We show more results in the [Project Page](https://bujiazi.github.io/light-a-video.github.io/).
<table class="center">
<tr>
<td><p style="text-align: center">..., red and Excerpt of 8,367 characters
Read on GitHub
54
3
1
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:bf30325231da2988, topic:video-generation, topic:video-editing