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). Requirements: The demo provides: T = number of frames (30fps), J = number of joints (skeleton-dependent) Out of VRAM (~17GB required): Model download issues: Motion quality issues: Foot skating artifacts: Interactive demo not loading: - ~17GB VRAM (GPU: RTX 3090/4090, A100 recommended) - Linux (Windows supported via Docker) - Models download automatically on first use from Hugging Face - 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 - 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...