StyleAvatar3D: Image-Text Diffusion for 3D Avatar Generation
A group from Tencent Research just released a paper in which they present a novel method for generating high-quality, stylized 3D avatars.
![StyleAvatar3D: Image-Text Diffusion for 3D Avatar Generation](/content/images/size/w1200/2023/06/teaser.png)
A group from Tencent Research just released a paper in which they present a novel method for generating high-quality, stylized 3D avatars.
![](https://ssv.ai/content/images/2023/06/image-1.png)
They utilize pre-trained image-text diffusion models for data generation and a Generative Adversarial Network (GAN)-based 3D generation network for training. The results look really stunning.
0:00
/
At the time of writing the code was not public yet, but apparently this is the repo where it will be released:
GitHub - icoz69/StyleAvatar3D: Official repo for StyleAvatar3D
Official repo for StyleAvatar3D. Contribute to icoz69/StyleAvatar3D development by creating an account on GitHub.