Features
Single-camera motion capture (no suit)
Depth camera motion and facial capture
Full-body capture using VR equipment
iPhone-based face, hands, upper body capture
Free webcam facial capture (EGAO)
NVIDIA GPU-accelerated facial capture (NVIS)
Text-to-motion generation (MOTS)
Camera-based gesture recognition (SOMA)
Real-time streaming via native plugins
VMC protocol support for VTuber apps
FBX export with facial expressions
Retarget onto custom skeletons
Open-source robot motion retargeting (GMR)
All processing runs locally
AI 3D character generation from text or images
Auto-rigging for animation
Markerless AI motion capture for face, body, hands
Neural Layer AI rendering with LoRA consistency
Camera tracking extraction
Nano Banana image generation
Trellis 2.0 3D conversion
Wonder 3D model generation
Live action to CG compositing
USD export to Maya, Blender, Unreal, 3ds Max
Credit-based usage system
Improved grounding in mocap
