A from-scratch training run of the main UniMate model ("UniMate: One Unified Model to Animate Diverse Skeletons", Mou et al., SIGGRAPH Asia 2026, arXiv 2609.05415) on a single GPU, using the authors' released code and the shipped configs/uniml3d60framesgraphadaln.json config unchanged. This repository holds two runs. The files at the root are v2, trained on an audited copy of the dataset from which 13 defective clips were removed and 18 repaired (see Why v2). The earlier v1 run on the unaudited data is kept under v1/ for comparison. Use v2. UniMate's sampler expects an experiment directory laid out the way training writes it, and this repository's root mirrors that layout. Download it, then…
SAVRN Model Hub · Models by Task
Text to 3D Models
1 open-weight text to 3d models in the SAVRN Model Hub, with Tarn59 publishing the most.
1Models
1Publishers
74M to 74MParameter range
1Licenses
Most Downloaded
| Model | Publisher | Parameters | License | Monthly downloads | Cheapest GPUs at 16-bit |
|---|---|---|---|---|---|
| UniMate-Weights | Tarn59 | 74M | mit | 83 | 1x MI300X, $1.85/hr |
All 1 Models
Questions
Which Text to 3d models are most downloaded?
By monthly downloads reported by the Hugging Face Hub: UniMate-Weights (83).