Downloads · 30 days
0
syntverk-mesh-models
syntverk/syntverk-mesh-models
syntverk-mesh-models is a machine learning model from syntverk. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
Pre-exported ONNX models for 3D mesh generation and auto-rigging in Syntverk, a native agentic coding tool.
Access
Public
Updated Apr 7, 2026
Repo size
10.1 GB
Likes
1
Public
Repo makeup
Click a slice to open those files.
.onnx4.4 GB · 57%
At a glance
- License
- apache-2.0
- Access
- Public
- Created
- Apr 5, 2026
- Updated
- Apr 7, 2026
- SHA
- 5fd03466
Model card
From the Hugging Face model README
Syntverk Mesh Models (ONNX)
Pre-exported ONNX models for 3D mesh generation and auto-rigging in Syntverk, a native agentic coding tool.
Models
Hunyuan3D-2mini (Shape Generation)
Image → 3D mesh via flow-matching diffusion.
| File | Size | Description |
|---|---|---|
dinov2_encoder.onnx + weights | ~3.5 GB | DINOv2-giant image encoder (fp16) |
shape_dit.onnx | ~3 MB | Diffusion transformer (fp16) |
vae_transformer.onnx | ~385 MB | VAE latent decoder (fp16) |
vae_cross_attn_decoder.onnx | ~25 MB | VAE geometry decoder (fp16) |
Original model: Tencent/Hunyuan3D-2mini (Apache 2.0)
Puppeteer (Auto-Rigging)
Mesh → skeleton + skinning weights.
| File | Size | Description |
|---|---|---|
skeleton_encoder.onnx | ~245 MB | Michelangelo point cloud encoder (fp32) |
skeleton_gpt.onnx | ~580 MB | SkeletonGPT OPT-350M transformer (fp16) |
skinning_net.onnx | varies | SkinningNet with PartField + TAJA |
weights/*.npy | ~11 MB | Embedding weights for token generation |
puppeteer_config.json | <1 KB | Model configuration |
Original model: Seed3D/Puppeteer (Apache 2.0)
Usage
These models are automatically downloaded by Syntverk on first use.
Place them in ~/.local/share/syntverk/models/mesh/.
~/.local/share/syntverk/models/mesh/
├── hunyuan3d-mini/
│ ├── dinov2_encoder.onnx
│ ├── ... (weight files)
│ ├── shape_dit.onnx
│ ├── vae_transformer.onnx
│ └── vae_cross_attn_decoder.onnx
└── puppeteer/
├── skeleton_encoder.onnx
├── skeleton_gpt.onnx
├── skinning_net.onnx
└── weights/
└── *.npy
License
The ONNX exports are derived from models under Apache 2.0:
- Hunyuan3D-2mini: Copyright Tencent
- Puppeteer: Copyright ByteDance
- Michelangelo: Copyright original authors
- PartField: Copyright original authors
This repository packages those weights in ONNX format for use with ONNX Runtime.
- License
- apache-2.0
- Created
- Apr 5, 2026
- Updated
- Apr 7, 2026