alaradirik / cog-wonder3d Goto Github PK

Cog wrapper for Wonder3D: Single Image to 3D using Cross-Domain Diffusion based on the original repository, see the paper, project page and Replicate demo for details.

Wonder 3D is an image-to-3D model that uses a multi-view diffusion model as its backbone to generate 3D assets in a few minutes. You need to have Cog and Docker installed to run this model locally. Follow the model pushing guide to push your own fork of Wonder3D to Replicate.

To build the docker image with cog and run a prediction:

cog predict -i image=@example_images/sample.jpg -i remove_bg=True -i num_steps=3000

To start a server and send requests to your locally deployed API:

cog run -p 5000 python -m cog.server.http

@misc{long2023wonder3d,
      title={Wonder3D: Single Image to 3D using Cross-Domain Diffusion}, 
      author={Xiaoxiao Long and Yuan-Chen Guo and Cheng Lin and Yuan Liu and Zhiyang Dou and Lingjie Liu and Yuexin Ma and Song-Hai Zhang and Marc Habermann and Christian Theobalt and Wenping Wang},
      year={2023},
      eprint={2310.15008},
      archivePrefix={arXiv},
      primaryClass={cs.CV}
}