SadTalker is a cutting-edge technology developed by researchers from Xi'an Jiaotong University, Tencent AI Lab, and Ant Group. It aims to tackle the challenges of generating talking head videos from a single face image and speech audio, such as unnatural head movement, distorted expressions, and identity modification. SadTalker generates 3D motion coefficients (head pose, expression) from audio and implicitly modulates a novel 3D-aware face renderer for talking head generation. The technology has been presented at CVPR 2023.

September 16, 2024

Maket enables everyone to automate residential floorplans, 3D renders, and explore unlimited styles with generative AI.

September 16, 2024

No more coding restrictions. Welcome to Dora, where your aspiration of designing spectacular 3D animated websites turns into reality, all without writing a single line of code.

September 16, 2024

Create your own dream AI girlfriend in immersive 3D. Create personalized and immersive experiences with state-of-the-art 3D technology.

September 16, 2024

Connecting artists with the gaming industry. Create production-ready characters with AI and world-class artists.

September 16, 2024