TRELLIS
by Microsoft
Microsoft's image-to-3D model that outputs meshes, 3D Gaussians or radiance fields from a single image.
AI 3D model generators Open source
1. Price: huggingface.co
Open weights, free to download.
huggingface.coNo quote yet: price is read from the official pages.
2. Commercial use: LICENSE on GitHub
“i.e., for research and/or evaluation purposes only.”
Models and most code are MIT, but nvdiffrast (used by the GLB export) and diffoctreerast are for research or evaluation only.
LICENSE on GitHub3. Credit the author: LICENSE on GitHub
“The above copyright notice and this permission notice shall be included in all”
No credit on screen. Keep the license notice inside the code you ship.
LICENSE on GitHub4. Agent access: github.com/microsoft/TRELLIS
There is no package or API. Files are downloaded by hand from the official site.
github.com/microsoft/TRELLISLicense checked Nov 10, 2026 against 3 official pages. Tap a verdict to see its source. How we checked Report an error
TRELLIS: 3D models from a single picture
TRELLIS is a free AI model from Microsoft that turns one picture of an object into a 3D model. You can save the result as a ready 3D file, a point-cloud style scene file or a spinning preview video. It runs on a Linux computer with a large graphics card, and some of its helper parts are licensed for research only.
Where you can use it
A 3D object from one photo
Give it a single picture of an object, such as a lamp or a figurine. You get a 3D model with colors as a GLB file for games, 3D viewers or Blender.
Spinning preview videos
Render a short video that turns around the new object, for a product page, a pitch or a quick review with your team.
Scenes for 3D splat viewers
Save the object as a cloud of soft 3D points in a PLY file, which splat viewers on the web can show with fine detail.
Variants of the same object
Make several versions of one object, or change one part of it, for example to try different looks for a game item.
3D from a text idea
Start from a sentence instead of a photo. The makers advise making a picture first with an image model, then turning that picture into 3D.
As reported by Microsoft: Trained with up to 2 billion parameters on a set of 500K 3D objects.
TRELLIS popularity
How to start
Tell your AI assistant
“On my Linux machine with an NVIDIA card of at least 16 GB, set up microsoft/TRELLIS with setup.sh, turn photo.png into photo.glb with TrellisImageTo3DPipeline and to_glb, and list which installed parts are licensed for research only.”
Show codeStep 1 or Step 2 or Step 3
On Linux with an NVIDIA card and the CUDA Toolkit, get the code with its submodules.
git clone --recurse-submodules https://github.com/microsoft/TRELLIS.git
cd TRELLIS
Create the conda environment and install the parts you need with the setup script.
. ./setup.sh --new-env --basic --xformers --flash-attn --diffoctreerast --spconv --mipgaussian --kaolin --nvdiffrast
Load the image model by its Hugging Face name, or from a local folder you downloaded.
TrellisImageTo3DPipeline.from_pretrained("microsoft/TRELLIS-image-large")
Mistakes to avoid
Several renderers come in as submodules and must be compiled; without them the pipeline does not install.
The default attention backend is flash-attn.
The makers say the text models are less creative and detailed.
to_glb imports nvdiffrast, and nvdiffrast's license allows non-commercial use only.
The auto setting runs a benchmark first, which only pays off over many runs.
License
MIT (models and most code); some submodules use other licenses. The models and most of the code are MIT, so they are free to use and share with the notice. Some helper parts used for rendering and for the 3D file export are for research or evaluation only, so check them before paid use.
“i.e., for research and/or evaluation purposes only.” LICENSE on GitHub
“The above copyright notice and this permission notice shall be included in all” LICENSE on GitHub
“The following submodules may have different licenses” github.com/microsoft/TRELLIS
The MIT weights may be shared with the notice; diffoctreerast may only be shared with its full license and stays research-only.
“you include a complete copy of this License with your distribution” LICENSE on GitHub
AllowedWith conditionsNot allowedNot stated or not checked yet
Is TRELLIS free for commercial use? The full answer Not legal advice. Check the license page before you ship.
For your agent
License rules tell your agent what it may do with TRELLIS. Paste them into your prompt or AGENTS.md.
- TRELLIS (AI 3D model generators). Microsoft's image-to-3D model that outputs meshes, 3D Gaussians or radiance fields from a single image. Price: free; commercial use with conditions; no credit needed; ship inside your app with conditions.
Connect: download from https://huggingface.co/microsoft/TRELLIS-image-large (no API).
Rule: Model weights are MIT; keep the license notice when you redistribute them.
Rule: The diffoctreerast renderer submodule is research and evaluation only; keep it out of commercial pipelines.
Rule: Check the modified FlexiCubes submodule license before shipping.
Rule: The nvdiffrast (NVIDIA, research or evaluation only) and mip-splatting (research licence) dependencies are not for commercial use.
License: https://github.com/microsoft/TRELLIS/blob/main/LICENSE (checked 2026-11-10; details: https://agentgid.com/assets/trellis/)
Alternatives
TRELLIS This page
Pick Hunyuan3D 2.0 when you also want to paint colors onto models made by hand; its license excludes the EU, the UK and South Korea.
Pick TripoSR for fast rough models; its makers cite under 0.5 seconds per model on an A100 graphics card.
Pick InstantMesh for a two-step pipeline that first draws several views and then builds a mesh in about 10 seconds.
OpenAI's text-to-3D and image-to-3D model that outputs textured meshes or neural radiance fields.
Official code and models for generating 3D point clouds from text or images, plus a model that turns point clouds into meshes.
Questions
What files do I get?
A GLB file with a textured mesh, a PLY file with 3D Gaussians, and preview videos of each form.
Can I sell the models I make?
The TRELLIS models are MIT. The GLB export imports nvdiffrast, which is for research or evaluation only, so check that part or replace it before paid use.
Does it run on a Mac or Windows?
It is tested only on Linux with an NVIDIA card; Windows setups are discussed by the community but not fully tested.
Can I use several photos of the same object?
Yes, the picture model accepts several images, but this works without extra training and may not give the best result for every set.
Which model should I download?
TRELLIS-image-large (1.2B parameters); the makers recommend the picture models over the text ones, and it also holds all the shared parts.