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:
- One unified model handles different skeletons with no per-rig retraining
- Generates transitions between existing keyframes
- Text-based motion editing while keeping selected joints fixed
- Extends animations via sequences of prompts
- Exports animated meshes as FBX and GLB
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.
More from Multimodal
- Argil soft-launches AI storytelling studio, cutting 30s video production from 3 hours to 10 minutes — kevinnbass · 2026-09-30
- NVIDIA's Physis-Lang puts physics reasoning in captions, tops Physics-IQ with Cosmos 3 — NVIDIAAI · 2026-09-30
- One image + one mp3: Opus 5.5 renders a 20-second video scene in 30 minutes — justin_hart · 2026-09-30
- This AI video is so realistic the author's grandma asked if it was AI — techhalla · 2026-09-30
- ComfyUI seeks testers for new Asset System: indexed files, persistent output history — Lexius2129 · 2026-09-30
- Community finetunes Qwen-Image-2.1 VAE to kill checkerboard artifacts, plus realtime AE — bdsqlsz · 2026-09-30