Downloads · 30 days
0
Specialgfhdhdh/kimodo-outputs
kimodo-outputs is a machine learning model from Specialgfhdhdh. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
Generated with NVIDIA Kimodo — a kinematic motion diffusion model trained on 700 hours of motion capture.
Downloads · 30 days
0
Access
Public
Updated Apr 28, 2026
Repo size
3.9 MB
Likes
0
Public
Click a slice to open those files.
.mp42.8 MB · 74%
From the Hugging Face model README
Generated with NVIDIA Kimodo — a kinematic motion diffusion model trained on 700 hours of motion capture.
| File | Description |
|---|---|
| motion.mp4 | 🎬 Rendered stick-figure skeleton animation (1280×720, H264, 3s @ 30fps) |
| motion.npz | Raw motion data: 90 frames × 77 joints (SOMA skeleton) with positions, rotations, foot contacts |
| run_kimodo.py | ✨ Self-contained script — clones, installs, generates, and renders to MP4 in one command |
"A person walks forward and waves hello."
# Just run it (installs everything automatically):
python run_kimodo.py
# Custom prompt:
python run_kimodo.py --prompt "A person dances happily."
# All options:
python run_kimodo.py --prompt "Person kicks a ball." --duration 4 --steps 100 --seed 123
Works on CPU or GPU. Auto-detects hardware and configures accordingly.