#20 · Primary category: 3D Generation & Asset Creation

ComfyUI-Trellis2

ComfyUI Wrapper for Microsoft Trellis.2 - Native and Compact Structured Latents for 3D Generation

Project last updated:08/03/26

GitHub Stars

808

Forks

107

Contributors

1

License

MIT

Why we included this project

ComfyUI users who want to turn a single image or a few views into a usable 3D asset can run Microsoft's Trellis.2 model directly inside their node graphs. The wrapper exposes the model as custom nodes that handle the main steps: generating sparse and multi-view structures, reconstructing and remeshing watertight meshes, filling holes, and texturing the final surface. It also includes example workflows and extra nodes for mesh cleanup, smoothing, and projection, so it's more than a thin wrapper around the Python library. Prebuilt wheels for Windows and Linux across several Torch versions make the heavy dependencies easier to install. That makes it a practical choice for artists and technical users building game assets, product previews, or 3D content pipelines who want to prototype without leaving ComfyUI.

Articles for this project

No articles for this project yet.

To suggest a topic or contribute an article, contact us.

Related projects in this category