UniMate open-sources unified text-to-animation model that drives diverse 3D skeletons

grandorganics · x · 2026-09-30

UniMate, a SIGGRAPH Asia 2026 paper from Princeton, UC Berkeley, MIT and NTU, is now open source under MIT license. It generates motion from text prompts for rigged 3D characters — humans, animals, creatures and robots alike.

Key features:

Preview checkpoints are on Hugging Face, and the UniML3D dataset with its data-processing pipeline has also been released. An interactive 3D demo is live.

Original post →

More from Multimodal

Multimodal channel →