SUDO-AI-3D/zero123plus
A diffusion base model that generates consistent multi-view images from a single input photograph for 3D reconstruction.
Not currently ranked — collecting fresh signals.
star history
Zero123++ is a multi-view diffusion model that converts a single image into six consistent views at different camera angles. The model uses a diffusion architecture with a novel camera encoding scheme to produce view-consistent outputs suitable for 3D generation pipelines. Version 1.2 improved robustness to varying camera intrinsics and includes an optional ControlNet-based normal map generator for improved downstream 3D reconstruction.
Frequently asked
- What is SUDO-AI-3D/zero123plus?
- A diffusion base model that generates consistent multi-view images from a single input photograph for 3D reconstruction.
- Is zero123plus open source?
- Yes — SUDO-AI-3D/zero123plus is open source, released under the Apache-2.0 license.
- What language is zero123plus written in?
- SUDO-AI-3D/zero123plus is primarily written in Python.
- How popular is zero123plus?
- SUDO-AI-3D/zero123plus has 2.1k stars on GitHub.
- Where can I find zero123plus?
- SUDO-AI-3D/zero123plus is on GitHub at https://github.com/SUDO-AI-3D/zero123plus.