• Home
  • Categories
  • Pricing
  • Submit
    Built with
    Ever Works
    Ever Works

    Connect with us

    Stay Updated

    Get the latest updates and exclusive content delivered to your inbox.

    Product

    • Categories
    • Pricing
    • Help

    Clients

    • Sign In
    • Register
    • Forgot password?

    Company

    • About Us
    • Admin
    • Sitemap

    Resources

    • Blog
    • Submit
    • API Documentation
    All product names, logos, and brands are the property of their respective owners. All company, product, and service names used in this repository, related repositories, and associated websites are for identification purposes only. The use of these names, logos, and brands does not imply endorsement, affiliation, or sponsorship. This directory may include content generated by artificial intelligence.
    Copyright © 2025 Ever. All rights reserved.·Terms of Service·Privacy Policy·Cookies
    Decorative pattern
    Decorative pattern
    1. Home
    2. Machine Learning & Ai
    3. Awesome 3D Base Models

    Awesome 3D Base Models

    Curated collection of 3D foundation models that serve as bridges between text/images and 3D data, similar to how Stable Diffusion connects text to images.

    Surveys

    Loading more......

    Information

    Websitegithub.com
    PublishedMar 20, 2026

    Categories

    1 Item
    Machine Learning & Ai

    Tags

    3 Items
    #3d#foundation-models#ai

    Overview

    Similar to 2D base models like Stable Diffusion and Flux that build a bridge between text and images, 3D Base Models are foundation models that bridge text/images and 3D data.

    What are 3D Base Models?

    3D base models are large-scale pre-trained models that can generate, understand, and manipulate 3D content from various inputs like text descriptions, images, or other 3D data.

    Features

    • Text-to-3D generation models
    • Image-to-3D reconstruction models
    • 3D understanding and segmentation
    • Multi-modal 3D representations
    • Physics-based 3D generation tools

    Recent Models (2025-2026)

    Step1X-3D (May 2025)

    • Training code and dataset available
    • Large-scale 3D generation
    • Multi-modal inputs

    Other Notable Models

    • Point-E - OpenAI's text-to-3D model
    • Shap-E - 3D generation from text and images
    • Zero-1-to-3 - View synthesis from single image
    • Wonder3D - Single image to 3D with diffusion

    Applications

    • Content creation for games and VR
    • Product design and prototyping
    • Digital asset generation
    • 3D printing preparation
    • Architectural visualization

    Training Data

    These models are typically trained on large-scale 3D datasets including:

    • Objaverse - 800K+ 3D objects
    • ShapeNet - Annotated 3D models
    • 3D-FUTURE - Indoor scenes

    Pricing

    Mostly open-source research models.