SkyReels-A1: Expressive Portrait Animation in Video Diffusion Transformers

👁 Skyreels Logo

🌐 Github · 👋 Playground · Discord

This repo contains Diffusers style model weights for Skyreels A1 models. You can find the inference code on SkyReels-A1 repository.

🔥🔥🔥 News!!

• Mar 4, 2025: 🎉 We release audio-driven portrait image animation pipeline. 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. This is the first and most advanced open-source human-centric video foundation model.

👁 image/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:

Citation

If you find SkyReels-A1 useful for your research, welcome to cite our work using the following 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}
}

Base model