What is Kinetix?

Kinetix is a research lab that combines 3D and machine learning to understand and generate human motion. They build state-of-the-art generative models and core technologies for character animation, focusing on human pose estimation, computer vision, and foundational 3D character workflows. Their flagship model, Kamo-1, is a 3D-conditioned video generation model that brings physical grounding and precise control to AI video generation.

How to use Kinetix?

Kinetix's technologies are integrated into various platforms: Unity Muse for 3D animation generation, OVERDARE's Emote Creator for in-game custom animations, and Adobe Mixamo for AI-powered character animation. Developers and creators can use these integrations to generate 3D animations from videos or control video generation with 3D priors.

Core features of Kinetix

3D-conditioned video generation model (Kamo-1)
Multimodal conditioning (3D camera trajectories, 3D character animations, reference images, natural language)
Human pose estimation and computer vision
Video-to-animation model
Integration with Unity Muse, Adobe Mixamo, and OVERDARE
Moderation system for user-generated animations