jd7h / zero123plusplus

Turn an image into a set of images from different 3D angles

  • Public
  • 6.8K runs
  • GitHub
  • Paper
  • License

Input

Output

Run time and cost

This model runs on Nvidia A40 (Large) GPU hardware. Predictions typically complete within 116 seconds.

Readme

Zero123++

Zero123++ is a single image to consistent multi-view diffusion base model. The input image needs to be square, and the recommended image resolution is >=320x320

Output views are a fixed set of camera poses relative to the input view:

  • Azimuth: 30, 90, 150, 210, 270, 330.
  • Elevation: 30, -20, 30, -20, 30, -20.

Paper

If you found Zero123++ helpful, please cite the paper:

@misc{shi2023zero123plus,
      title={Zero123++: a Single Image to Consistent Multi-view Diffusion Base Model}, 
      author={Ruoxi Shi and Hansheng Chen and Zhuoyang Zhang and Minghua Liu and Chao Xu and Xinyue Wei and Linghao Chen and Chong Zeng and Hao Su},
      year={2023},
      eprint={2310.15110},
      archivePrefix={arXiv},
      primaryClass={cs.CV}
}