---
license: apache-2.0
base_model:
- Wan-AI/Wan2.1-I2V-14B-720P
pipeline_tag: image-to-video
---

## Paper

[https://arxiv.org/abs/2505.20255](https://arxiv.org/abs/2505.20255)


## Introduction

We leverage **"3DGS Avatar + Background Video"** as guidance for the video diffusion model to **insert and animate anyone into any scene following given motion sequence**.