Kimodo Motion Diffusion

This generates 3D motion for humans and humanoid robots using text prompts and kinematic constraints. It's trained on 700 hours of mocap data and handles everything from simple walking animations to complex choreographed sequences with keyframes and end effector control. You get models for SOMA human skeletons, Unitree G1 robots, and SMPL-X for AMASS export. The interactive web demo is genuinely useful for sketching out constraint timelines before you commit to generation. Needs about 17GB VRAM, so expect to run this on a 3090 or better. Output quality is solid, and the post-processing handles foot skating reasonably well. Good fit if you're prototyping robot behaviors or need motion capture without actual capture hardware.

skills.sh installs: 1.2K
GitHub stars: 61
last updated: Jul 14, 2026

View on GitHub

Install

$ npx -y skills add aradotso/trending-skills --skill kimodo-motion-diffusion --agent claude-code

Installs into .claude/skills of the current project.

Files

Kimodo Motion Diffusion

Skill by ara.so — Daily 2026 Skills collection.

Kimodo is a kinematic motion diffusion model trained on 700 hours of commercially-friendly optical mocap data. It generates high-quality 3D human and humanoid robot motions controlled through text prompts and kinematic constraints (full-body keyframes, end-effector positions/rotations, 2D paths, 2D waypoints).

Installation

# Clone the repository
git clone https://github.com/nv-tlabs/kimodo.git
cd kimodo

# Install with pip (creates kimodo_gen and kimodo_demo CLI commands)
pip install -e .

# Or with Docker (recommended for Windows or clean environments)
docker build -t kimodo .
docker run --gpus all -p 7860:7860 kimodo

Requirements: