Stability-AI/stable-point-aware-3d

Health v2 · maintenance only

Flags: no_releases no_license

Adoption not part of the score

1068 stars · 108 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

SPAR3D is Stability AI's open-source model for fast single-image 3D mesh reconstruction using a two-stage pipeline with point cloud conditioning. It includes a point diffusion model, editable intermediate point clouds, and a Gradio demo, achieving ~0.7 second inference.

Use cases

• reconstruct a 3D mesh from a single photo
• generate 3D models from images for games or AR
• edit the backside of a reconstructed mesh via point cloud
• fast image-to-3D asset creation pipeline
• run single-image 3D reconstruction on GPU locally

When to choose

• you need fast (sub-second) single-image to 3D mesh conversion
• you want editable intermediate point clouds to fix occluded geometry
• you need a state-of-the-art open-source image-to-3D model with a demo

When to avoid

• you need multi-view or video-based 3D reconstruction
• you have no GPU and cannot tolerate slow low-VRAM mode
• you need permissively licensed code for commercial use without checking the custom Stability AI license

Facets

library · maturity active

machine-learning image-processing graphics simulation computer-vision graphics artificial-intelligence deep-learning python windows 3d-reconstruction single-image-to-3d mesh-generation point-cloud diffusion-model stability-ai spar3d gradio-demo gpu linux macos

Member repositories

For agents

markdown · JSON · MCP: product_card(name="Stability-AI/stable-point-aware-3d")