---
title: SkyReels-A1
canonical_url: "https://www.modelscope.cn/models/Skywork/SkyReels-A1"
md_url: "https://www.modelscope.cn/models/Skywork/SkyReels-A1.md"
repository: Skywork/SkyReels-A1
last_updated: 2025-03-04
license: apache-2.0
pipeline_tag: image-to-video
tasks:
  - image-to-video
base_model:
  - THUDM/CogVideoX-5b-I2V
base_model_relation: finetune
parameters: 11.7B
tensor_type:
  - F32
  - BF16
library_name:
  - onnx
  - safetensors
  - diffusers
  - pytorch
frameworks:
  - Pytorch
downloads: 1183
stars: 3
---

# SkyReels-A1

> SkyReels-A1 - Skywork 在 ModelScope 开源的模型。SkyReels-A1: Expressive Portrait Animation in Video Diffusion Transformers

Skywork/SkyReels-A1 是 ModelScope 魔搭社区上的 11.7B 参数image-to-video模型，采用 apache-2.0 许可，基于 THUDM/CogVideoX-5b-I2V 构建。

- **Repository**: Skywork/SkyReels-A1
- **License**: apache-2.0
- **Tasks**: image-to-video
- **Parameters**: 11.7B
- **Base model**: THUDM/CogVideoX-5b-I2V
- **Downloads**: 1183
- **Stars**: 3
- **Last updated**: 2025-03-04

Source: https://www.modelscope.cn/models/Skywork/SkyReels-A1

---

# SkyReels-A1: Expressive Portrait Animation in Video Diffusion Transformers
<p align="center">
  <img src="assets/logo2.png" alt="Skyreels Logo" width="60%">
</p>

<!-- <p align="center">
  <img src="assets/logo.jpg" alt="Skyreels Logo" width="200">
</p> -->

<p align="center">
<a href="https://github.com/SkyworkAI/SkyReels-A1" target="_blank">🌐 Github</a> · <a href="https://www.skyreels.ai/home?utm_campaign=huggingface_A1" target="_blank">👋 Playground</a> · <a href="https://discord.gg/PwM6NYtccQ" target="_blank">Discord</a>
</p>

This repo contains Diffusers style model weights for Skyreels A1 models. 
You can find the inference code on [SkyReels-A1](https://github.com/SkyworkAI/SkyReels-A1) repository.

## 🔥🔥🔥 News!!
* Mar 4, 2025: 🎉 We release audio-driven portrait image animation pipeline. [SkyReels-A1](https://github.com/SkyworkAI/SkyReels-A1)
* Feb 18, 2025: 👋 We release the inference code and model weights of SkyReels-A1.
* Feb 18, 2025: 🔥 We have open-sourced I2V video generation model [SkyReels-V1](https://github.com/SkyworkAI/SkyReels-V1). This is the first and most advanced open-source human-centric video foundation model.


---

![image/png](https://cdn-uploads.huggingface.co/production/uploads/62e34a12c9bece303d146af8/Ysbe66shplYZw2fjkFUHL.png)
Overview of SkyReels-A1 framework. Given an input video sequence and a reference portrait image, we extract facial expression-aware landmarks from the video, which serve as motion descriptors for transferring expressions onto the portrait. Utilizing a conditional video generation framework based on DiT, our approach directly integrates these facial expression-aware landmarks into the input latent space. In alignment with prior research, we employ a pose guidance mechanism constructed within a VAE architecture. This component encodes facial expression-aware landmarks as conditional input for the DiT framework, thereby enabling the model to capture essential low- dimensional visual attributes while preserving the semantic integrity of facial features.


---
Some generated results:


<video controls autoplay src="https://cdn-uploads.huggingface.co/production/uploads/62e34a12c9bece303d146af8/licoAeSaF-K8x7DO7SGUG.mp4"></video>

<video controls autoplay src="https://cdn-uploads.huggingface.co/production/uploads/62e34a12c9bece303d146af8/5q0p2jyw183fcJoeq0dvF.mp4"></video>


<video controls autoplay src="https://cdn-uploads.huggingface.co/production/uploads/62e34a12c9bece303d146af8/1aZweOIszlriQLRwSqnGq.mp4"></video>


<video controls autoplay src="https://cdn-uploads.huggingface.co/production/uploads/62e34a12c9bece303d146af8/5bfjDxGZJf-5WnGpFHppw.mp4"></video> 


## Citation

If you find SkyReels-A1 useful for your research, welcome to cite our work using the following BibTeX:
```bibtex
@article{qiu2025skyreels,
  title={SkyReels-A1: Expressive Portrait Animation in Video Diffusion Transformers},
  author={Qiu, Di and Fei, Zhengcong and Wang, Rui and Bai, Jialin and Yu, Changqian and Fan, Mingyuan and Chen, Guibin and Wen, Xiang},
  journal={arXiv preprint arXiv:2502.10841},
  year={2025}
}
```