LIVE
Mistral Makes Large 4 Available as Open Weights29/10/26 · Mistral AI|Gemini 4 Carbon tops the Artificial Analysis Intelligence Index v529/10/26 · Google|Mistral Large 4 now available on Hugging Face29/10/26 · Mistral AI|Google Introduces "Gemini 4 Carbon" as Next Step in Its Model Lineup28/10/26 · Google|DeepMind unveils Genie 4, a new generation of world model27/10/26 · Google DeepMind|Anthropic files IPO prospectus, with risk disclosures taking center stage26/10/26 · Anthropic|Robot policy trained only in simulation matches top real-world systems26/10/26|OpenAI unveils GPT-6.1 Terra, a model built for computer use26/10/26 · OpenAI|New benchmark checks whether LLMs actually test their temporal medical claims29/10/26|An ODE-based sampling method speeds up discrete diffusion models29/10/26|OpenAI revises its Model Spec with five guiding values for AI behavior29/10/26 · OpenAI|Inside Proton's internal clash over its AI pivot29/10/26 · Proton|Mistral Makes Large 4 Available as Open Weights29/10/26 · Mistral AI|Gemini 4 Carbon tops the Artificial Analysis Intelligence Index v529/10/26 · Google|Mistral Large 4 now available on Hugging Face29/10/26 · Mistral AI|Google Introduces "Gemini 4 Carbon" as Next Step in Its Model Lineup28/10/26 · Google|DeepMind unveils Genie 4, a new generation of world model27/10/26 · Google DeepMind|Anthropic files IPO prospectus, with risk disclosures taking center stage26/10/26 · Anthropic|Robot policy trained only in simulation matches top real-world systems26/10/26|OpenAI unveils GPT-6.1 Terra, a model built for computer use26/10/26 · OpenAI|New benchmark checks whether LLMs actually test their temporal medical claims29/10/26|An ODE-based sampling method speeds up discrete diffusion models29/10/26|OpenAI revises its Model Spec with five guiding values for AI behavior29/10/26 · OpenAI|Inside Proton's internal clash over its AI pivot29/10/26 · Proton|
Appofficial publisher

TripoSR

App : A product you use directly

Image to 3D in under one second, open source, runs locally.

The fastest and lightest of the local 3D models.

Official site GitHub · 7,213 ★
Overall score
7.7 /10
Security: nothing to flag
Utility
8.0
Reliability
9.0
Security
No caveat on record
Ease
Technical · Technical

Security reflects where data goes, requested permissions and incidents on record at the verification date. It is not a guarantee of zero risk: check the deployment mode and the connections you enable.

What it does, concretely

Creating a 3D model from a single photo is usually a lengthy and technical task, reserved for specialized software or paid online services. TripoSR addresses this by generating a complete 3D object from a single image in under half a second on a modern GPU.

In practice, you provide an input image and the model produces a 3D file with vertex colors or an exportable texture. Processing happens entirely on your local machine, via a command-line interface or a Gradio graphical interface accessible in your browser. The model requires approximately 6 GB of VRAM for a single image.

TripoSR is aimed at developers, researchers, and creators who want to integrate 3D reconstruction into their projects without relying on a cloud service. It is particularly useful for rapidly prototyping 3D assets from photos of real objects.

However, installation requires Python, PyTorch, and a precise CUDA configuration, making it less accessible to users without technical experience. Those looking for a turnkey solution without a command line will find it difficult to get started.

What it offers

  • ·3D reconstruction from a single image in under 0.5 seconds on an NVIDIA A100 GPU.
  • ·Export of the 3D model with vertex colors or baked texture depending on the chosen option.
  • ·Configurable texture resolution via the --texture-resolution option.
  • ·Processing of multiple images in a single command by separating paths with spaces.
  • ·Local graphical interface via Gradio, accessible from a browser without additional configuration.
  • ·Online demo available on Hugging Face Spaces for testing without installation.
  • ·Source code, pre-trained models, and demo released under the MIT license.

In practice

Price
Free
Commercial use
Commercial use: yes
Available on
linux, windows
Licence
MIT
Runs locally
Yes, 6 GB VRAM recommended
FR interface
No

Security and data

Rating
Security: nothing to flag
Your data
Data stays local
Maintenance
Active

Links and repository checked on 25 October 2026 · added on 1 March 2024

How to install TripoSR

1. Install Python 3.8 or higher on your machine. 2. Install CUDA if your GPU supports it, noting the major version used. 3. Install PyTorch making sure to choose the version compiled with the same CUDA major version (see pytorch.org/get-started/locally). 4. Update setuptools with pip install --upgrade setuptools. 5. Clone the TripoSR GitHub repository and install dependencies with pip install -r requirements.txt. 6. Run a reconstruction with python run.py your_image.png --output-dir output/ and verify that the generated files appear in the output folder.
pip install -r requirements.txt

In the same category

Whole category 3D & printing →

TripoSR: review, price, security and alternatives 2026 · nAIvigate