threestudio

The threestudio repository describes a unified framework for generating 3D content.

github.com/threestudio-project/threestudio
threestudio homepage screenshot

About threestudio

threestudio is an open-source framework for creating 3D content from text prompts, single images, or few-shot images by lifting 2D text-to-image generation models. It gathers implementations of many published methods in one codebase, including DreamFusion, ProlificDreamer, Magic3D, Zero-1-to-3, Magic123, HiFA, SDI, and TextMesh, alongside editing and 4D work such as InstructNeRF2NeRF and Control4D. A custom extension system allows additional methods to be added, and textured meshes can be exported.

The project can be run locally through a Gradio web interface, in Google Colab, or through notebooks, with installation and setup instructions in the repository. Text-to-3D has also been offered online via Hugging Face Spaces and a self-hosted service using GPU support from Tencent, both of which rely on third-party hosting. Several listed methods are labeled as experimental implementations that require following separate instruction pages, and the repository states no pricing information.

Key features

  • Generates 3D content from text prompts, single images, or few-shot images
  • Implements many 2D-lifting methods, including DreamFusion, ProlificDreamer, and Magic3D
  • Includes 3D editing methods such as InstructNeRF2NeRF and Control4D
  • Custom extension system for adding other implementations, such as MVDream and GaussianDreamer
  • Supports exporting textured meshes
  • Local Gradio web interface, Colab notebook, and 2D playground notebooks
Best for: Researchers and developers who want to run, compare, or extend 3D generation and editing methods in a single open-source codebase.
Good for
  • Open-source repository consolidating many published 3D generation methods
  • Accepts text prompts, single images, and few-shot images as input
  • Extension system and multiple run options, including Colab and a local web interface
Watch out for
  • Several methods are experimental implementations that require following separate instruction pages
  • Online demos depend on third-party hosting, such as Hugging Face Spaces or Tencent-provided GPUs
  • No pricing or subscription information is stated in the source

threestudio at a glance

Type
Open-source project
Pricing
Not confirmed. Check the site
Open source
Yes · Source code
Language
English
Last checked
Oct 6, 2026 · Online when checked
Listed
Oct 5, 2026

threestudio alternatives

Tools and sites you could use instead, ranked by how closely they match.

All 24 alternatives

Civitai

github.com/civitai/civitai

A GitHub repository containing models, textual inversions, and other resources for image generation.

Open source
24 alternatives

Lora

github.com/cloneofsimo/lora

This repository demonstrates low rank adaptation for quickly fine tuning diffusion models.

Open source
24 alternatives

Popular in AI Image Generators

Well-known listings from the same topic.

All 363

threestudio FAQ

What kinds of input can threestudio use to create 3D content?
It works from text prompts, single images, and few-shot images by lifting 2D text-to-image generation models.
Can threestudio be tried without a local installation?
Yes. Text-to-3D has been available online through Hugging Face Spaces and a self-hosted service with GPU support from Tencent, and the project can also be run in Google Colab.
Can developers add their own methods to threestudio?
Yes. A custom extension system allows users to add extensions, and several third-party methods have been integrated this way.
Is something wrong or out of date?

Tell us and an editor will check it.

Own this website?

Claim the listing and suggest updates yourself. An editor checks every claim first.

Claim this listing