--- pipeline_tag: image-to-video tags: - video-generation - talking-avatar - human-animation - audio-driven - smpl-x - wan2.2 ---

MegaAvatar: Controllable Talking Avatar Generation

**Junyao Gao\*1,2   Sibo Liu\*1   Weidong Zhang1   Cairong Zhao2‡   Jun Zhang1‡** 1Tencent AIPD   2Tongji University   \*Equal contribution   ‡Corresponding authors [![GitHub](https://img.shields.io/badge/GitHub-MegaAvatar-black)](https://github.com/Jeoyal/MegaAvatar) [![arXiv](https://img.shields.io/badge/arXiv-Paper-red)](https://arxiv.org/abs/2609.39273) [![Dataset](https://img.shields.io/badge/%F0%9F%A4%97%20HuggingFace-Dataset-yellow)](https://huggingface.co/datasets/Gaojunyao/MegaAvatar)
--- MegaAvatar is a controllable talking avatar generation framework built on top of **Wan2.2-TI2V-5B**. Given a reference portrait image, MegaAvatar generates talking avatar videos with: - controllable body and head motion using SMPL-X; - speech-synchronized lip motion and facial expressions using audio; - identity-preserving facial appearance. MegaAvatar supports both **SMPL-X-driven** and **audio-driven** generation. ## Model Download ```bash hf download Gaojunyao/MegaAvatar --include "checkpoints/*" --local-dir . ``` The released checkpoints include: ```text checkpoints/ ├── megaavatar.safetensors └── audio2smplx/ ``` - `megaavatar.safetensors`: MegaAvatar video generation model. - `audio2smplx/`: audio-to-SMPL-X components. ## Usage Please refer to the official GitHub repository for installation, inference, and training instructions: https://github.com/Jeoyal/MegaAvatar MegaAvatar supports: ```text Reference Image + SMPL-X + Audio → Talking Avatar Video Reference Image + Audio → SMPL-X → Talking Avatar Video ``` ## Related Resources - Code: https://github.com/Jeoyal/MegaAvatar - Model: https://huggingface.co/Gaojunyao/MegaAvatar - Dataset: https://huggingface.co/datasets/Gaojunyao/MegaAvatar - Paper: https://arxiv.org/abs/2609.39273 ## Acknowledgements This project benefits from [FantasyTalking](https://github.com/Fantasy-AMAP/fantasy-talking), [SpeakerVid-5M-Code](https://github.com/Dorniwang/SpeakerVid-5M-Code), and [DiffSynth-Studio](https://github.com/modelscope/DiffSynth-Studio). ## Citation ```bibtex @article{gao2026megaavatar, title={MegaAvatar: Controllable Talking Avatar Generation}, author={Gao, Junyao and Liu, Sibo and Zhang, Weidong and Zhao, Cairong and Zhang, Jun}, journal={arXiv preprint arXiv:2609.39273}, year={2026} } ```