Skip to content
SPECIFICTION
Get listed

TripoSR

github.com

Free plan WebLinuxSelf-hosted
Visit github.com
Spec score 7.7 #18 of 24 in AI 3D Model Generators

What it is

TripoSR is a free, MIT-licensed open-source model that reconstructs a 3D object from one image. Tripo AI and Stability AI developed it collaboratively for researchers, developers, and creatives working in 3D generative AI and content creation. The project states that generation can take less than 0.5 seconds on an NVIDIA A100 GPU. Its repository provides command-line inference and a local Gradio app launched with Python. The app offers background removal, foreground-ratio and marching-cubes-resolution controls, and OBJ or GLB output. Inference accepts one or more image paths and can bake textures instead of vertex colors, with configurable texture resolution. Default settings use about 6 GB of VRAM for one image. Local setup lists Python 3.8 or newer, PyTorch, and requirements.txt dependencies; CUDA is optional when available. TripoSR supports image-to-3D and AI texturing, but not text-to-3D. Its listed platforms are Linux, self-hosted, and web.

Spec sheet

What it does
TripoSR reconstructs a 3D object from a single image using an open-source model.Read 8 Oct 2026 · github.com
Intended users
The project describes its intended audience as researchers, developers, and creatives working in 3D generative AI and 3D content creation.Read 8 Oct 2026 · github.com
License
The source code and pretrained models are released under the MIT license.Read 8 Oct 2026 · github.com
Demo features
The Gradio app offers background removal, foreground-ratio and marching-cubes-resolution controls, and OBJ and GLB outputs.Read 8 Oct 2026 · github.com
Hardware requirement
Default inference options use about 6 GB of VRAM for a single image input.Read 8 Oct 2026 · github.com
How it works
The model generates a 3D model in less than 0.5 seconds on an NVIDIA A100 GPU, according to its README.Read 8 Oct 2026 · github.com
Input
The inference script accepts one or more image paths.Read 8 Oct 2026 · github.com
License holders
The MIT license file names Tripo AI and Stability AI in its 2024 copyright notice.Read 8 Oct 2026 · github.com
Local installation
The README lists Python 3.8 or later, PyTorch, and dependencies installed from requirements.txt; CUDA is optional if available.Read 8 Oct 2026 · github.com
Local interface
The repository includes a Gradio app that can be started with python gradio_app.py.Read 8 Oct 2026 · github.com
Memory requirement
The default inference options use about 6 GB of VRAM for one image input.Read 8 Oct 2026 · github.com
Output options
The inference script can bake a texture instead of using vertex colors and lets users specify texture resolution.Read 8 Oct 2026 · github.com
Pricing
The TripoSR repository describes the model as open source under MIT, but does not state a subscription price for TripoSR.Read 8 Oct 2026 · github.com
Product identity
TripoSR is an open-source model for fast 3D reconstruction from a single image, developed collaboratively by Tripo AI and Stability AI.Read 8 Oct 2026 · github.com
Requirements
The setup instructions list Python 3.8 or newer and recommend installing CUDA if available.Read 8 Oct 2026 · github.com
Run locally
The repository provides a command-line inference script and a local Gradio app.Read 8 Oct 2026 · github.com
Single-image input
TripoSR reconstructs 3D objects from a single image.Read 8 Oct 2026 · github.com
Speed
The project says it can generate a 3D model in less than 0.5 seconds on an NVIDIA A100 GPU.Read 8 Oct 2026 · github.com
Texture output
Inference can output a texture instead of vertex colors using the --bake-texture option, with texture resolution configurable.Read 8 Oct 2026 · github.com

Plans and prices

TripoSR Free MIT-licensed model and code · default inference uses about 6 GB VRAM per image Read 8 Oct 2026 · github.com

Every TripoSR plan and price →

Strong points and limits

Strong points

  • Free MIT-licensed model and code
  • Single-image 3D reconstruction
  • Local command-line and Gradio interfaces
  • OBJ and GLB outputs
  • Configurable baked texture resolution

Limits

  • Default inference uses about 6 GB VRAM
  • Requires Python and PyTorch setup
  • No text-to-3D support
  • CUDA is optional, not guaranteed

Who it suits

TripoSR suits researchers, developers, and creatives building 3D content from reference images. It is appropriate for users able to run Python and provide the listed local dependencies and GPU memory.

Verdict

TripoSR offers a local, open-source route from one image to a textured 3D object. Its practical requirements include Python setup and about 6 GB of VRAM under default inference options.

Where Specifiction places it

Alternatives to TripoSRAll alternatives →