InstantMesh
by Tencent ARC
Image-to-3D pipeline: a multiview diffusion model plus a sparse-view reconstructor that outputs a mesh in about 10 seconds.
AI 3D model generators Open source
1. Price: huggingface.co/TencentARC/InstantMesh
Open weights, free to download.
huggingface.co/TencentARC/InstantMeshNo quote yet: price is read from the official pages.
2. Commercial use: LICENSE on GitHub
“grants to You a perpetual, worldwide, non-exclusive, no-charge, royalty-free, irrevocable copyright license to reproduce”
InstantMesh code and files are Apache-2.0, but the default pipeline loads CC-BY-NC Zero123++ weights and needs the non-commercial nvdiffrast library.
LICENSE on GitHub3. Credit the author: LICENSE on GitHub
“You must give any other recipients of the Work or Derivative Works a copy of this License”
No credit on screen. Keep the license notice inside the code you ship.
LICENSE on GitHub4. Agent access: github.com/TencentARC/InstantMesh
There is no package or API. Files are downloaded by hand from the official site.
github.com/TencentARC/InstantMeshLicense checked Oct 25, 2026 against 1 official page. Tap a verdict to see its source. How we checked Report an error
InstantMesh: a 3D model from one picture
InstantMesh is free research software from Tencent ARC that turns one picture of an object into a 3D model you can open in 3D tools. It first draws the object from several sides, then builds the shape from those views. It runs on your own computer with an NVIDIA graphics card, not as a web service.
Where you can use it
A 3D model from a photo
Take one picture of an object, such as a toy or a product shot. You get a 3D file of it that you can open and edit in Blender or a game engine.
Models with a texture image
Get the colors as a separate texture picture instead of colored corners, which most game engines and 3D viewers expect. This takes longer.
A local try-out page
Start a small web page on your own machine where you drop a picture and look at the 3D result, before you write any scripts.
Pictures that already have no background
If your picture already has a clear, cut-out background, skip the built-in background removal so it does not cut into the object.
Rough props for a hobby game Idea
Make quick first versions of props from your own sketches or photos for a student or hobby game, then clean them up by hand.
Research on picture-to-3D
Train or fine-tune the models on your own data to compare methods in a study, using the released training code.
As reported by Tencent ARC: InstantMesh creates 3D assets within 10 seconds.
InstantMesh popularity
How to start
Tell your AI assistant
“On my Linux machine with an NVIDIA GPU, set up TencentARC/InstantMesh in a Python 3.10 environment with the exact torch 2.1.0 and xformers 0.0.22.post7 versions from its README, then turn photo.png into a textured .obj with --export_texmap.”
Show codeStep 1 or Step 2
On a computer with an NVIDIA graphics card, create a Python 3.10 environment and install the listed versions of the libraries.
conda create --name instantmesh python=3.10
conda activate instantmesh
pip install -U pip
conda install Ninja
conda install cuda -c nvidia/label/cuda-12.1.0
pip install torch==2.1.0 torchvision==0.16.0 torchaudio==2.1.0 --index-url https://download.pytorch.org/whl/cu121
pip install xformers==0.0.22.post7
pip install -r requirements.txt
Run the script on a picture. The model files download by themselves on the first run.
python run.py configs/instant-mesh-large.yaml examples/hatsune_miku.png --save_video
Mistakes to avoid
pip install torch (latest) and xformers (latest), then pip install -r requirements.txtThe pinned diffusers 0.20.2 and the xformers build are matched to PyTorch 2.1.0.
The default export stores colors on the mesh corners.
The UV unwrapping step is slow with the NeRF variants at resolution 256.
The default pipeline loads sudo-ai/zero123plus-v1.2 and needs nvdiffrast, both non-commercial.
License
Apache-2.0 license. The InstantMesh code and its own model files are under Apache-2.0, which allows paid use. But the default pipeline also loads a multi-view model whose weights are non-commercial, and a required rendering library is non-commercial too. Check both before any paid use.
“grants to You a perpetual, worldwide, non-exclusive, no-charge, royalty-free, irrevocable copyright license to reproduce” LICENSE on GitHub
“You must give any other recipients of the Work or Derivative Works a copy of this License” LICENSE on GitHub
“publicly display, publicly perform, sublicense, and distribute the Work and such Derivative Works in Source or Object form.” LICENSE on GitHub
Apache-2.0 allows passing on the InstantMesh code and weights with the license and a note on changed files.
“You must cause any modified files to carry prominent notices stating that You changed the files” LICENSE on GitHub
AllowedWith conditionsNot allowedNot stated or not checked yet
Is InstantMesh 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 InstantMesh. Paste them into your prompt or AGENTS.md.
- InstantMesh (AI 3D model generators). Image-to-3D pipeline: a multiview diffusion model plus a sparse-view reconstructor that outputs a mesh in about 10 seconds. Price: free; commercial use OK; no credit needed.
Connect: download from https://huggingface.co/TencentARC/InstantMesh (no API).
Rule: Keep the Apache-2.0 license and notices with the code or weights you ship.
Rule: Mark files you changed when you redistribute modified code.
License: https://github.com/TencentARC/InstantMesh/blob/main/LICENSE (checked 2026-10-25; details: https://agentgid.com/assets/instantmesh/)
3D models made with InstantMesh (Tencent ARC, Apache-2.0) and Zero123++ (CC-BY-NC 4.0 weights)Alternatives
InstantMesh This page
Pick TripoSR when speed matters most; its makers cite under half a second per picture on a data-center graphics card.
Pick Hunyuan3D 2.0 when you want a separate painting step that adds textures to the generated shape.
Pick TRELLIS when you also want 3D Gaussians or radiance fields, not only meshes, from a single picture.
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
Can I run it on a Mac?
Not with the official script. It is set up for NVIDIA graphics cards with CUDA 12.1 or newer.
What file do I get?
An .obj model with colors stored on its corners by default, or with a separate texture image when you add --export_texmap.
Do I have to download the model files by hand?
No. The script downloads them on the first run; you can also place them in the ckpts folder yourself.
Can I use it in a paid product?
The InstantMesh code and files are Apache-2.0, but the default pipeline also relies on non-commercial Zero123++ weights and the non-commercial nvdiffrast library, so check those first.
Which model variant is used by default?
The large mesh variant, instant-mesh-large; other variants are picked with a different config file.