Skip to content

Zero123++

Turn one image into consistent multi-view images

Visit official site

What Zero123++ is

The model is described as a diffusion foundation model that turns a single image into consistent multi-view images, with a stable diffusion VAE.

What you can do with it

  • Generate multi-view images from a single input image
  • Produce opaque images with a grey background
  • Run a depth ControlNet

Model notes

  • The material calls it a single-image to multi-view consistent diffusion foundation model
  • A stable diffusion VAE is included
  • Model and source code are available on the official website

Pros & cons

✓ What we like

  • Multi-view generation starts from one input image
  • The model and source code are available on the site

! What to watch out for

  • The described outputs use a grey background
  • The depth ControlNet is listed among the uses

FAQ

What does the model generate?

The material states consistent multi-view images from a single input image.

Where are the model and code?

The material states both are available on the official website.

Last reviewed: 2026-11-15

More AI image generation tools

View all →

How we review