CharacterShot / README.md
Gaojunyao's picture
Improve model card: add metadata, library name, and paper/code links (#1)
1998e88 verified
---
license: mit
library_name: diffusers
pipeline_tag: image-to-video
tags:
- character-animation
- 4d
- image-to-video
---
---
# CharacterShot: Controllable and Consistent 4D Character Animation
[**CharacterShot**](https://arxiv.org/abs/2508.07409) is a controllable and consistent 4D character animation framework that enables the creation of dynamic 3D characters (i.e., 4D character animation) from a single reference character image and a 2D pose sequence.
- **Paper:** [CharacterShot: Controllable and Consistent 4D Character Animation](https://arxiv.org/abs/2508.07409)
- **Repository:** [https://github.com/Jeoyal/CharacterShot](https://github.com/Jeoyal/CharacterShot)
## Introduction
CharacterShot utilizes a powerful 2D character animation model based on a DiT image-to-video architecture. It lifts these animations to 3D using dual-attention modules and camera priors to ensure spatial-temporal and spatial-view consistency. The final representation is optimized using neighbor-constrained 4D Gaussian Splatting, resulting in stable and continuous character representations.
The model was trained on **Character4D**, a large-scale dataset containing 13,115 unique characters with diverse appearances and motions.
## Citation
```bibtex
@article{gao2025charactershot,
title={CharacterShot: Controllable and Consistent 4D Character Animation},
author={Gao, Junyao and Li, Jiaxing and Liu, Wenran and Zeng, Yanhong and Shen, Fei and Chen, Kai and Sun, Yanan and Zhao, Cairong},
journal={arXiv preprint arXiv:2508.07409},
year={2025}
}
```
## Acknowledgements
The code is built upon [CogVideo](https://github.com/THUDM/CogVideo).