TripoSR Open-source 3D Generation Model - Free Deployment, Quickly Turn a Single Image into a 3D Model!

Triposr

Developed by TrianC0de

TripoSR is a fast feed-forward 3D generation model developed collaboratively by Stability AI and Tripo AI, capable of rapidly generating 3D models from a single image.

3D Vision Open Source License:MIT #Single Image 3D Reconstruction #Fast Feed-forward #Game Asset Generation

Downloads 21

Release Time : 3/18/2025

Model Overview

TripoSR is a single-image-based feed-forward 3D reconstruction model, focusing on quickly generating 3D models from 2D images, suitable for fields like game development and virtual reality.

Model Features

Fast Generation

Utilizes a feed-forward architecture to quickly generate 3D models from a single image.

High-Quality Output

Generates 3D models more suitable for practical applications through improved data processing and training methods.

Large-Scale Training

Trained on a substantial subset of the Objaverse dataset to enhance model generalization capabilities.

Model Capabilities

Single Image 3D Reconstruction

Fast 3D Model Generation

Game Asset Generation

Use Cases

Game Development

Rapid Game Asset Generation

Quickly generate game-ready 3D models from concept art.

Significantly shortens game development cycles.

Virtual Reality

VR Scene Construction

Rapidly convert 2D images into 3D objects for VR environments.

Accelerates VR content creation workflows.

🚀 TripoSR

TripoSR is a fast and feed - forward 3D generative model developed in collaboration between Stability AI and Tripo AI, enabling efficient 3D reconstruction from a single image.

🚀 Quick Start

Try our new model: SF3D with several improvements such as faster generation and more game - ready assets.

The model is available here and we also have a demo.

TripoSR

✨ Features

TripoSR is a fast and feed - forward 3D generative model developed in collaboration between Stability AI and Tripo AI.

📚 Documentation

📋 Model Details

📝 Model Description

We closely follow LRM network architecture for the model design. TripoSR incorporates a series of technical advancements over the LRM model in terms of both data curation as well as model and training improvements. For more technical details and evaluations, please refer to our tech report.

Property	Details
Developed by	Stability AI, Tripo AI
Model Type	Feed - forward 3D reconstruction from a single image
License	MIT
Hardware	We train `TripoSR` for 5 days on 22 GPU nodes each with 8 A100 40GB GPUs

🌐 Model Sources

Repository: https://github.com/VAST - AI - Research/TripoSR
Tech report: https://arxiv.org/abs/2403.02151
Demo: https://huggingface.co/spaces/stabilityai/TripoSR

📊 Training Dataset

We use renders from the [Objaverse](https://objaverse.allenai.org/objaverse - 1.0) dataset, utilizing our enhanced rendering method that more closely replicate the distribution of images found in the real world, significantly improving our model’s ability to generalize. We selected a carefully curated subset of the Objaverse dataset for the training data, which is available under the CC - BY license.

💻 Usage Examples

For usage instructions, please refer to our [TripoSR GitHub repository](https://github.com/VAST - AI - Research/TripoSR)
You can also try it in our gradio demo

⚠️ Important Note

The model should not be used to intentionally create or disseminate 3D models that people would foreseeably find disturbing, distressing, or offensive; or content that propagates historical or current stereotypes.

📄 License

The model is released under the MIT license.

Additional Information

Datasets: allenai/objaverse
Tags: 3d
Extra Gated Fields:
- Name: text
- Email: text
- Country: text
- Organization or Affiliation: text
- I ALLOW Stability AI to email me about new model releases: checkbox
Pipeline Tag: image - to - 3d

Featured Recommended AI Models

Empowering the Future, Your AI Solution Knowledge Base

English 简体中文繁體中文にほんご