Make-A-Character

Make-A-Character: High Quality Text-to-3D Character Generation within Minutes

Institute for Intelligent Computing, Alibaba Group

Introduction

With Make-A-Character, you can effortlessly generate controllable, realistic, animatable 3D characters from text descriptions, which are compatible to standard CG pipelines.

For better visual experience, please visit

Note: Please don't forget to give us a star :star: if you like this project, Thanks!

🔥News

(2025-1-15) Technical report for Make-A-Character 2 is released.

(2024-3-1) Audio-driven Video Generation 魔搭 Demo is now available !!! Have a try 🔥🔥🔥

(2023-12-31) HuggingFace Demo is available.

(2023-12-28) 魔搭 Demo is available.

(2023-12-24) Technical report is released.

We will continue to update our progress on 3D human generation & animation within this repository, star the project to stay informed with the latest developments.

Todo

• provide hands-on experience on ModelScope.
• provide hands-on experience on Huggingface.
• generating voice-chat video using customized 3D character.

Examples

An old man with wrinkles on his face, he has gray hair.	A cool girl, sporting ear-length short hair, freckles on her cheek.	Chinese girl, Bobo haircut with a straight bangs, around 20 years old. She has a V-shaped face, cameo lipstick.	A boy with brown skin and black glasses, green hair.	A girl, she is thin, willow leaf eyebrow, oval face, long curly hair.
A handsome man with glasses, brown hair and black eyes.	Pretty girl, diamond face, blue eyes.	A chubby lady with round face.	An elderly lady, gray short hair.	A middle-aged man, sword-like eyebrow, black short hair.

More Works

Welcome to follow our other interesting works:

• Textoon (open-sourced)

BibTeX

@article{ren2023makeacharacter,
      title={Make-A-Character: High Quality Text-to-3D Character Generation within Minutes},
      author={Jianqiang Ren and Chao He and Lin Liu and Jiahao Chen and Yutong Wang and Yafei Song and Jianfang Li and Tangli Xue and Siqi Hu and Tao Chen and Kunkun Zheng and Jianjing Xiang and Liefeng Bo},
      year={2023},
      journal = {arXiv preprint arXiv:2312.15430}
}