FloodDiffusion: Text → Human Motion

Generate realistic human motion sequences from text descriptions.
Powered by ShandaAI/FloodDiffusionTiny. Interactive 3D viewer works on desktop & mobile.

Motion description

Length (latent tokens ≈ frames / 4)

10 120

Smoothing α (0 = max smooth, 1 = none)

0 1

Generate a motion to see the viewer

Examples

FloodDiffusion – Cai et al., 2025 (arXiv:2512.03520). Apache 2.0 license.