EVERYTHING XIAOMI
Get listed

TripoSR

TripoSR is an open-source model that reconstructs a 3D object from a single image.

Place
#16 of 24
Score
6.3
TripoSR's website

What TripoSR is

TripoSR is an open-source model that reconstructs a 3D object from a single image. Developed collaboratively by Tripo AI and Stability AI, it is intended for researchers, developers, and creatives working in 3D generative AI and content creation. The project provides a command-line inference script and a local Gradio app, which can be started with python gradio_app.py. The app includes background removal, foreground-ratio and marching-cubes-resolution controls, and OBJ and GLB outputs. Inference can bake a texture instead of using vertex colors, with configurable texture resolution. The project says generation takes less than 0.5 seconds on an NVIDIA A100 GPU; default inference options use about 6 GB of VRAM for one image. Local setup lists Python 3.8 or later, PyTorch, and dependencies from requirements.txt; CUDA is optional if available. The code, pretrained models, and interactive demo use the MIT license. The model is free at no cost. It supports image-to-3D and AI texturing, but not text-to-3D. Listed platforms are Linux, self-hosted, and web.

Good

  • Reconstructs objects from a single image
  • Code, models, and demo use the MIT license
  • Includes a local Gradio interface
  • Can output OBJ and GLB
  • Supports configurable texture baking

Watch out

  • Default inference uses about 6 GB of VRAM per image
  • Does not support text-to-3D
  • Local setup requires Python 3.8 or later and PyTorch

Who it suits

TripoSR may suit researchers, developers, and creatives who want to reconstruct 3D objects from images and can work with its local setup requirements.

Verdict

TripoSR offers a free, MIT-licensed path from a single image to a 3D model, with command-line and Gradio options. Its stated VRAM use and local software requirements are important considerations.

Plans and prices

From TripoSR's own pricing page, checked 8 Oct 2001.

All about pricing
PlanPriceWhat it gives you
TripoSRFreeMIT-licensed model and code · default inference uses about 6 GB VRAM per image

The facts

Each one read from TripoSR's own pages, with the date it was checked.

What it does

Demo features
The Gradio app offers background removal, foreground-ratio and marching-cubes-resolution controls, and OBJ and GLB outputs.checked 8 Oct 2001
Hardware requirement
Default inference options use about 6 GB of VRAM for a single image input.checked 8 Oct 2001
How it works
The model generates a 3D model in less than 0.5 seconds on an NVIDIA A100 GPU, according to its README.checked 8 Oct 2001
Input
The inference script accepts one or more image paths.checked 8 Oct 2001
Intended users
The project describes its intended audience as researchers, developers, and creatives working in 3D generative AI and 3D content creation.checked 8 Oct 2001
License
The codebase, pretrained models, and interactive demo are released under the MIT license.checked 8 Oct 2001
License holders
The MIT license file names Tripo AI and Stability AI in its 2024 copyright notice.checked 8 Oct 2001
Local installation
The README lists Python 3.8 or later, PyTorch, and dependencies installed from requirements.txt; CUDA is optional if available.checked 8 Oct 2001
Local interface
The repository includes a Gradio app that can be started with python gradio_app.py.checked 8 Oct 2001
Memory requirement
The default inference options use about 6 GB of VRAM for one image input.checked 8 Oct 2001
Output options
The inference script can bake a texture instead of using vertex colors and lets users specify texture resolution.checked 8 Oct 2001
Pricing
The TripoSR repository describes the model as open source under MIT, but does not state a subscription price for TripoSR.checked 8 Oct 2001
Product identity
TripoSR is an open-source model for fast 3D reconstruction from a single image, developed collaboratively by Tripo AI and Stability AI.checked 8 Oct 2001
Requirements
The setup instructions list Python 3.8 or newer and recommend installing CUDA if available.checked 8 Oct 2001
Run locally
The repository provides a command-line inference script and a local Gradio app.checked 8 Oct 2001
Single-image input
TripoSR reconstructs 3D objects from a single image.checked 8 Oct 2001
Speed
The project says it can generate a 3D model in less than 0.5 seconds on an NVIDIA A100 GPU.checked 8 Oct 2001
Texture output
Inference can output a texture instead of vertex colors using the --bake-texture option, with texture resolution configurable.checked 8 Oct 2001
What it does
TripoSR reconstructs a 3D object from a single image using an open-source model.checked 8 Oct 2001

Alternatives to TripoSR

All alternatives
  1. 1Meshy logo

    Meshy

    Free planAndroidiOSWebAPI
    8.3From $20 a month
    Visit
  2. 2Tripo AI logo

    Tripo AI

    Free planAndroidiOSWebAPI
    8.2From $4.58 a month
    Visit
  3. 3Polar Cloud logo

    Polar Cloud

    Free planAndroidiOSWebAPI
    8.1From $6.58 a month
    Visit
  4. 4

    Hunyuan3D

    Free planWebAPILinuxmacOS
    7.5CN¥100, paid once
    Visit
  5. 5Polycam logo

    Polycam

    Free planAndroidiOSWeb
    7.5From $12.50 a month
    Visit
  6. 6Hyper3D Rodin logo

    Hyper3D Rodin

    Free planWebAPI
    6.9From $30 a month
    Visit