Kimodo Motion Diffusion Skill by [ara.so](https://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 Requirements: ~17GB VRAM (GPU: RTX 3090/4090, A100 recommended) Linux (Windows supported via Docker) Models download automatically on first use from Hugging Face Available Models Model Skeleton Dataset Use Case Kimodo SOMA RP v1 SOMA (human) Bones Rigplay 1 (700h) General human motion Kimodo G1 RP v1 Unitree G1 (robot) Bones Rigplay 1 (700h) Humanoid robot motion Kimodo SOMA SEED v1 SOMA BONES SEED (288h) Benchmarking Kimodo G1 SEED v1 Unitree G1 BONES SEED (288h) Benchmarking Kimodo SMPLX RP v1 SMPL X Bones Rigplay 1 (700h) Retargeting/AMASS export CLI: kimodo gen Basic Text to Motion Output Formats Multi Prompt Sequences Constraint Based Generation Interactive Demo The demo provides: Timeline editor for text prompts and constraints Full body keyframe constraints 2D root path/waypoint editor End effector position/rotation control Real time 3D visualization with skeleton and skinned mesh Export of constraints as JSON and motions as NPZ Low Level Python API Basic Model Inference Advanced API with Guidance and Constraints Working with Constraints Programmatically Loading and Using Saved Constraints Saving and Loading Generated Motions Robotics Integration MuJoCo Visualization (G1 Robot) ProtoMotions Integration GMR Retargeting (SMPL X to Other Robots) NPZ Output Format Reference Key Shape Description posed joints [T, J, 3] Global joint positions in meters global rot mats [T, J, 3, 3] Global joint rotation matrices local rot mats [T, J, 3, 3] Parent relative joint rotation matrices foot contacts [T, 4] Contact labels: [L heel, L toe, R heel, R toe] smooth root pos [T, 3] Smoothed root trajectory from model root positions [T, 3] Actual root joint (pelvis) trajectory global root heading [T, 2] Heading direction (2D unit vector) T = number of frames (30fps), J = number of joints (skeleton dependent) Scripts Reference Common Patterns Batch Generation Pipeline Comparing Model Variants Troubleshooting Out of VRAM (~17GB required): Model download issues: Motion quality issues: Be specific in prompts: "a person walks forward at a moderate pace" "walking" For complex motions, use the interactive demo to add keyframe constraints Increase diffusion steps (default ~20 30, try 50 for higher quality) Generate multiple samples ( num samples 5 ) and select the best Avoid prompts with extremely fast or physically impossible actions The model operates at 30fps; very short durations (<1s) may yield poor results Foot skating artifacts: Interactive demo not loading:

kimodo-motion-diffusion