Upload README.md with huggingface_hub
Browse files
README.md
ADDED
|
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- video-editing
|
| 5 |
+
- diffusion
|
| 6 |
+
- wan
|
| 7 |
+
pipeline_tag: video-to-video
|
| 8 |
+
---
|
| 9 |
+
|
| 10 |
+
<div align="center">
|
| 11 |
+
|
| 12 |
+
# NOVA: Sparse Control, Dense Synthesis for Pair-Free Video Editing
|
| 13 |
+
|
| 14 |
+
**CVPR 2026**
|
| 15 |
+
|
| 16 |
+
[](https://github.com/WeChatCV/NovaEdit)
|
| 17 |
+
|
| 18 |
+
</div>
|
| 19 |
+
|
| 20 |
+
|
| 21 |
+
|
| 22 |
+
## Overview
|
| 23 |
+
|
| 24 |
+
NOVA is a pair-free video editing model built on **WAN 1.3B Fun InP**. It uses sparse keyframe control (e.g., a single edited first frame) to guide dense video synthesis, trained without requiring paired before/after video data.
|
| 25 |
+
|
| 26 |
+
- **Pair-free training** via degradation simulation
|
| 27 |
+
- **Sparse keyframe control**: provide one or more edited keyframes
|
| 28 |
+
- **Optional coarse mask** for improved editing accuracy
|
| 29 |
+
|
| 30 |
+
## Usage
|
| 31 |
+
|
| 32 |
+
See the [GitHub repository](https://github.com/WeChatCV/NovaEdit) for installation, inference, training, and the interactive Gradio demo.
|
| 33 |
+
|
| 34 |
+
## Acknowledgements
|
| 35 |
+
|
| 36 |
+
- [KlingTeam/ReCamMaster](https://github.com/KlingTeam/ReCamMaster)
|
| 37 |
+
- [zibojia/MiniMax-Remover](https://github.com/zibojia/MiniMax-Remover)
|