Comic
Our family of foundation models for capturing motion from humans and objects to environments


TRUSTED BY
Scroll horizontally or use the left and right arrow keys to explore all logos.
Our models
Our family of foundation models for capturing motion from humans and objects to environments

Foundation models for generating & editing human motion, rapidly and at scale, from text or poses

Products

Realistic human performance generation from text, at scale


Universal motion retargeter to robots, 3D characters and other embodiments

Have ChatGPT, Claude, or your agent capture motion, generate animation, or create rigged characters



Research
The AI systems that will operate within the physical world — humanoid robots, world models, autonomous agents — need training data that reflects that reality.
At Cartwheel, we build the kinetic world models and datasets that make physical AI training tractable at scale.
We've discovered that human motion data scales. Models that generate human kinematic spatiotemporal data improve at a predictable rate with increased training data, compute, model size and the correct training approach.
All rapidly scaling data modalities did so after a similar pattern was discovered: language, code, image, audio, video, self-driving. Human kinematics scale in the same regime as language, with 300x more efficiency.
We've built and trained on the largest human motion corpus assembled to date.
Capture motion, generate in batches, retarget and more
Start free trialCustom datasets, models, and evals