Model · 3D

Stable Point Aware 3D (SPAR3D)

Stability AI's downloadable model that builds a textured 3D model from one picture in about a second. You can nudge the rough point shape before the final mesh is made. Free for businesses under $1M revenue a year.

Go to Stable Point Aware 3D (SPAR3D)’s website

At a glance

Open or closed
Downloadable, with conditions
You can download and run it, but the licence limits use
Gated download: you share contact details and accept the licence.
source · checked 12 Oct 2026 · checked on the maker's own page
Licence
Stability AI Community License (Community licence with conditions (e.g. revenue cap))
Free for research, non-commercial use, and commercial use under US$1M annual revenue; above that an Enterprise licence is needed.
source · checked 12 Oct 2026 · checked on the maker's own page
Can I sell what I make?
Yes, with conditions
  • Only below a revenue limit
Commercial use allowed for individuals and organisations with under US$1M annual revenue.
source · checked 12 Oct 2026 · checked on the maker's own page
Cost
Free option: Weights free to download (gated); free online demo on Hugging Face.
Plans below.
How you use it
On your own computer, Through another service, Inside another tool
Windows and Apple Silicon (macOS 15.2+) support is experimental. README also says ~6 GB for a single image with default options, which conflicts with the 10.5 GB figure.
source · checked 12 Oct 2026 · checked on the maker's own page
Skill needed
Technical
source · checked 12 Oct 2026 · checked, but the page was unclear or partial
Made by
Stability AI
No company location stated on the pages read.
source · checked 12 Oct 2026 · checked on the maker's own page
Status
Available
source · checked 12 Oct 2026 · checked on the maker's own page

What you can make with it

image to 3D model

Outputs a UV-unwrapped, textured mesh with roughness and metallic values; built on SF3D.
source · checked 12 Oct 2026 · checked on the maker's own page

Plans and prices

No paid plans listed.

source · checked 12 Oct 2026 · checked on the maker's own page

Rights and safety

Limits
max megapixels: 0.26; note: Input image is 512x512. Under 1 second per model (model card).
source · checked 12 Oct 2026 · checked, but the page was unclear or partial

Related

Where you can run it

Hugging Face

Other options for “A 3D object or scene, from a photo”

3D AI Studio, ComfyUI, CSM (Cube), Dzine, fal, Hugging Face, Hunyuan 3D (Tencent), Hunyuan3D 2, Hyper3D Rodin, InstantMesh, Kaedim, KIRI Engine, Krea, Meshy, Mixar, Polycam, Scenario, Sloyd, Spline AI, Stable Fast 3D, Step1X-3D, TRELLIS, Tripo AI, TripoSR

About this entry

Facts last checked 12 Oct 2026 against the maker’s own pages (each fact links to its source). Entry status: draft. Plain-English summary written by Plainly.