SUDO-AI-3D/zero123plus

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

2095 stars · 148 forks observed · 2026-08-28

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

Zero123++ is a diffusion base model that generates consistent multi-view images from a single input image, intended as a stepping stone for 3D asset generation. The repository provides a custom diffusers pipeline, example scripts, and a ControlNet normal-image generator for producing view-space normal maps and alpha masks.

Use cases

• generate multiple consistent views of an object from one photo
• create 3D assets from a single image
• generate view-space normal maps for 3D reconstruction
• produce alpha masks for object matting
• novel view synthesis of objects
• build image-to-3d pipelines with diffusers

When to choose

• you need multi-view image generation from a single image as input to 3D reconstruction
• you want a diffusers-compatible pipeline for image-to-3d research
• you need normal maps or alpha masks to support 3D generation workflows

When to avoid

• you need a commercial-use license for the model weights (they are CC-BY-NC 4.0)
• you want text-to-image generation rather than single-image-to-multi-view
• you lack a GPU or PyTorch environment

Facets

library · maturity active

machine-learning deep-learning image-processing stable-diffusion artificial-intelligence computer-vision graphics machine-learning python image-to-3d multi-view-diffusion diffusers novel-view-synthesis 3d-generation research-project gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="SUDO-AI-3D/zero123plus")