SUDO-AI-3D / zero123plus

Code repository for Zero123++: a Single Image to Consistent Multi-view Diffusion Base Model.
Apache License 2.0
1.56k stars 108 forks source link

How to get the textured mesh? #46

Closed wqdong8 closed 7 months ago

wqdong8 commented 7 months ago

hi, great work! I want to know how to get the final mesh from the generated multi view image? Like One-2-3-45, use SparseNeuS?

Dustinpro commented 7 months ago

Thanks! We just released One-2-3-45++, which uses Zero123++ as the multiview generation module. You can find the interactive demo at https://www.sudo.ai/3dgen, where you can get a mesh from a single image or a text prompt.

wqdong8 commented 7 months ago

Thank you for your reply. I have tried the SUDO-ai Image-to-3D, but the generated mesh seems to have some artifacts, for example, holes. Is there any way to solve it?

front_rgba

下载 (3)

image
Dustinpro commented 7 months ago

It is a stochastic process, so giving it another try may result in a better mesh.

Screenshot 2023-11-15 at 01 37 14
wqdong8 commented 7 months ago

Wow, thanks !