README.md

---
license: other
license_name: mixed-mit-and-nvidia-non-commercial
license_link: https://huggingface.co/Thelocallab/CUDA-wheels/blob/main/README.md
tags:
- comfyui
- trellis
- windows
- cuda
- wheels
- 3d-generation
- prebuilt
library_name: other
---

# Prebuilt Windows CUDA Wheels for TRELLIS.2 / 3D Generation in ComfyUI

Precompiled Python wheels for the CUDA extensions that
[TRELLIS.2](https://github.com/microsoft/TRELLIS.2) needs — so you don't have to set up
MSVC, the CUDA toolkit, and Triton on Windows just to run image-to-3D.

If you've ever watched `setup.sh --cumesh --o-voxel --flexgemm --nvdiffrast --nvdiffrec`
fail on Windows, this is for you.

> ### ⚠️ Read this before downloading — licences differ per package
>
> These are **builds of other people's source code**, not original work, and they are **not
> all under the same terms**:
>
> - **`cumesh`, `flex_gemm`, `o_voxel`** — components of
>   [microsoft/TRELLIS.2](https://github.com/microsoft/TRELLIS.2), **MIT licensed**.
>   Unmodified compilations, redistributed under the same terms.
> - **`nvdiffrast`, `nvdiffrec_render`** — NVIDIA research code, governed by the
>   **[NVIDIA Source Code License (1-Way Commercial)](https://github.com/NVlabs/nvdiffrast/blob/main/LICENSE.txt)**,
>   which restricts use to **non-commercial research and evaluation**. That restriction
>   applies to compiled binaries as much as to source. TRELLIS.2's own README carves these
>   two out as "governed by its own License."
>
> **If your use is commercial, do not use the `nvdiffrast` or `nvdiffrec_render` wheels
> here.** Contact [NVIDIA Research Licensing](https://www.nvidia.com/en-us/research/inquiries/)
> instead. Mirroring these files does not grant you rights you wouldn't otherwise have, and
> nothing in this repo modifies NVIDIA's terms — read them yourself before you install.

## What's here

| Package | Version | Python / Platform | Upstream | Licence |
|---|---|---|---|---|
| `cumesh` | 1.0 | cp311-win · cp312-win · cp312-linux | [TRELLIS.2](https://github.com/microsoft/TRELLIS.2) | MIT |
| `flex_gemm` | 0.0.1 | cp311-win · cp312-win · cp312-linux | [TRELLIS.2](https://github.com/microsoft/TRELLIS.2) | MIT |
| `o_voxel` | 0.0.1 | cp311-win · cp312-win · cp312-linux | [TRELLIS.2](https://github.com/microsoft/TRELLIS.2) | MIT |
| `nvdiffrast` | 0.4.0 | cp311-win · cp312-win · cp312-linux | [NVlabs](https://github.com/NVlabs/nvdiffrast) | **NVIDIA, non-commercial** |
| `nvdiffrec_render` | 0.0.0 | cp311-win · cp312-win · cp312-linux | [NVlabs](https://github.com/NVlabs/nvdiffrec) | **NVIDIA, non-commercial** |

What each one does:

- **CuMesh** — CUDA mesh processing: post-processing, remeshing, simplification, UV unwrapping
- **FlexGEMM** — Triton-based sparse convolution
- **O-Voxel** — conversion between textured meshes and the O-Voxel representation
- **nvdiffrast** — differentiable rasterisation, used to render the generated 3D assets
- **nvdiffrec_render** — split-sum renderer for PBR materials

Note that `cp311` is Windows-only here; `cp312` covers Windows and Linux.

## Install

Match the wheel to your ComfyUI Python version. Check it first:

```bash
python -c "import sys; print(sys.version)"
```

Then install into the **same** environment ComfyUI uses — activate your venv first, or use
the portable build's embedded Python:

```bash
# Windows, Python 3.12 — MIT-licensed components
pip install cumesh-1.0-cp312-cp312-win_amd64.whl
pip install flex_gemm-0.0.1-cp312-cp312-win_amd64.whl
pip install o_voxel-0.0.1-cp312-cp312-win_amd64.whl
```

For ComfyUI portable, prefix with the embedded interpreter:

```bash
python_embeded\python.exe -m pip install <wheel>
```

Verify:

```bash
python -c "import cumesh, flex_gemm, o_voxel; print('ok')"
```

### Troubleshooting

- **`is not a supported wheel on this platform`** — Python version mismatch. `cp311` wheels
  require Python 3.11 and `cp312` requires 3.12. They are not interchangeable.
- **Imports fine in a terminal but ComfyUI can't find them** — you installed into the wrong
  environment. ComfyUI portable does *not* use your system Python.
- **CUDA errors at runtime** — these are compiled extensions, so your installed PyTorch CUDA
  build has to match. Check with `python -c "import torch; print(torch.version.cuda)"`.
- **Still stuck** — build from upstream source instead. That always works; it's just slow.

## Guides

Full walkthroughs, including the ComfyUI node setup these wheels are for:

- [Microsoft TRELLIS 2 image-to-3D in ComfyUI](https://www.locallabdigest.com/blog/microsoft-trellis-2-3d-comfyui)
- [Hunyuan 3D in ComfyUI](https://www.locallabdigest.com/blog/hunyuan-3d-comfyui)

More local-AI guides at [locallabdigest.com](https://www.locallabdigest.com).

## No warranty

Third-party compiled binaries, provided as-is, with no warranty of any kind. If running
precompiled CUDA extensions from someone else isn't acceptable in your situation, build from
upstream source. All credit for the underlying work belongs to the upstream authors listed
above.