π Launch Sale β 20% OFF all credit packages!
Get Credits
Direct download links for Microsoft TRELLIS 2 model weights, ComfyUI custom nodes, and all required dependencies. Includes checksums, hardware requirements, and step-by-step download instructions.
Last updated: April 21, 2026
This page provides direct download links for all TRELLIS 2 components β model weights, custom nodes, and dependencies β so you can get started quickly without hunting through multiple repositories.
If you'd rather not download anything, you can use TRELLIS 2 online with no installation required.
| Component | Size | Source | Download |
|---|---|---|---|
| Model Weights |
Join the community
Subscribe to our newsletter for the latest news and updates
| ~8 GB |
| HuggingFace |
| Download |
| Source Code | ~500 MB | GitHub | Download |
| ComfyUI Node | ~50 MB | GitHub | Download |
| Sample Workflow | ~5 KB | Community | RunComfy |
The official pre-trained model from Microsoft Research.
Download Methods:
# Method 1: HuggingFace CLI (recommended)
pip install huggingface-hub
huggingface-cli download microsoft/TRELLIS.2-4B --local-dir ./trellis2-weights/
# Method 2: Git LFS
git lfs install
git clone https://huggingface.co/microsoft/TRELLIS.2-4B
# Method 3: Direct download from browser
# Visit https://huggingface.co/microsoft/TRELLIS.2-4B
# Click "Files and versions" β download individual filesDirectory Structure After Download:
trellis2-weights/
βββ config.json
βββ model.safetensors
βββ scheduler/
βββ text_encoder/
βββ tokenizer/
βββ unet/
βββ vae/git clone https://github.com/microsoft/TRELLIS.2.git
cd TRELLIS.2cd ComfyUI/custom_nodes/
git clone https://github.com/PozzettiAndrea/ComfyUI-TRELLIS.git# Create virtual environment
python -m venv venv
source venv/bin/activate # Linux
# .\venv\Scripts\activate # Windows
# Install PyTorch with CUDA
pip install torch torchvision --index-url https://download.pytorch.org/whl/cu121
# Install TRELLIS 2 requirements
pip install -r requirements.txt| Package | Version | Purpose |
|---|---|---|
torch | 2.1+ | Deep learning framework |
torchvision | 0.16+ | Image processing |
xformers | 0.0.23+ | Memory-efficient attention |
transformers | 4.36+ | Text encoder |
diffusers | 0.25+ | Diffusion pipeline |
trimesh | 4.0+ | Mesh processing |
pygltflib | 1.16+ | GLB export |
| Component | Minimum | Recommended |
|---|---|---|
| GPU | NVIDIA 8GB VRAM | NVIDIA 16GB+ VRAM |
| RAM | 16 GB | 32 GB |
| Storage | 15 GB | 30 GB (SSD) |
| CUDA | 11.8 | 12.1+ |
3D technology specialists focused on AI-powered 3D model generation, format conversion, and browser-based 3D rendering. We test and review 3D tools so you don't have to.