Trusted by developers worldwide

Stable Fast 3D

Generate high-quality 3D assets from single images in just 0.5 seconds

Powered by Stability AI's cutting-edge technology

0.5s

Generation Time

100K+

Assets Generated

99.9%

Uptime

What is Stable Fast 3D?

Transform your workflow with our industry-leading 3D generation technology

Stable Fast 3D(SF3D) is Stability AI's latest innovation that transforms single images into detailed 3D assets in just 0.5 seconds. This groundbreaking technology sets a new standard for speed and quality in 3D reconstruction.

Generate high-quality 3D assets from a single image
Unprecedented speed: 0.5 seconds per asset
UV unwrapped mesh and material parameters
Reduced illumination bake-in for better textures

See It In Action

Watch how Stable Fast 3D transforms images into 3D assets

Key Features

Everything you need for professional 3D asset generation

Lightning-Fast Processing

Generate 3D assets in just 0.5 seconds on a GPU with 7GB VRAM.

High-Quality Output

Enjoy detailed UV unwrapped meshes and accurate material parameters.

Versatile Applications

Perfect for gaming, VR, e-commerce, and architectural visualization.

Advanced Technology

Built on TripoSR with significant architectural improvements.

Try Stable Fast 3D

Experience the power of instant 3D generation

If the demo doesn't load, visit it directly on Hugging Face .

Get Started Today

Experience the power of Stable Fast 3D. Upload an image and watch it transform into a detailed 3D asset in seconds.

Try Demo

Enterprise Ready

Integrate Stable Fast 3D into your applications with our robust, scalable API designed for enterprise use.

View API Docs

API Documentation

Integrate Stable Fast 3D into your workflow with our simple REST API

Quick Start

  1. 1 Get your API key from Stability AI
  2. 2 Make a POST request to our endpoint
  3. 3 Receive your 3D asset in GLB format

Parameters

image Required
texture_resolution Optional
foreground_ratio Optional

Example Request

curl -X POST \ 'https://api.stability.ai/v1/generation/stable-fast-3d' \ -H 'Content-Type: multipart/form-data' \ -H 'Authorization: Bearer YOUR_API_KEY' \ -F 'image=@path/to/your/image.jpg' \ -F 'texture_resolution=1024' \ -F 'foreground_ratio=0.85'

💡 Pro Tip

Each successful generation costs 2 credits. Failed generations are not charged.

Licensing Information

Stable Fast 3D is released under the Stability AI Community License .

✅ Allowed Uses

  • • Non-commercial use
  • • Commercial use for organizations with up to $1M annual revenue

🏢 Enterprise

For organizations exceeding $1M annual revenue, contact us for Enterprise Licenses.

Resources & Links

Everything you need to get started with Stable Fast 3D

GitHub

Model code and implementation

View Repository

Hugging Face

Model weights and demo

View Model

API Docs

Complete API reference

View Docs

Support

Get help and feedback

Contact Us

How We Compare

See how Stable Fast 3D stacks up against other 3D generation solutions

Google's DreamFusion

Uses text-to-3D generation, offering a different approach to creating 3D assets.

Text-based input • Research-focused

NVIDIA's GET3D

Generates textured 3D meshes from images, with a focus on high-quality results.

Image-based • High quality output

Point-E by OpenAI

Generates 3D point clouds from text descriptions, offering a unique perspective on 3D generation.

Point cloud output • Text-based

Magic3D by NVIDIA

Another text-to-3D model that aims to create high-quality 3D models from text descriptions.

Text-based • High resolution

Why Choose Stable Fast 3D?

While these alternatives offer various approaches to 3D generation, Stable Fast 3D stands out for its exceptional speed (0.5 seconds) and the quality of its output from single images, making it ideal for production workflows.

Frequently Asked Questions

Get answers to common questions about Stable Fast 3D

What file formats can I use as input for Stable Fast 3D?

Stable Fast 3D accepts JPEG, PNG, and WebP image formats as input.

What are the image size requirements?

Every side of the input image must be at least 64 pixels, and the total pixel count must be between 4,096 and 4,194,304 pixels.

What is the texture resolution option?

The texture resolution determines the detail level of the albedo (color) and normal maps. Options are 512, 1024 (default), or 2048 pixels. Higher resolution provides more detail but results in larger asset sizes.

How much does each generation cost?

Each successful generation costs 2 credits. Failed generations are not charged.

What format is the output in?

The output is a binary blob that includes a glTF asset, containing JSON, buffers, and images in the GLB file format.

Ready to Get Started?

Join thousands of developers already using Stable Fast 3D