[Pipelines] Add community pipeline for Zero123

[kxhit]

What does this PR do?

As discussed in issue, this PR implements a diffusers inference pipeline for Zero123, a popular single image to novel view synthesis stable diffusion model, largely scaled pre-trained on Objaverse Dataset. See Zero123-hf repo for demos and clean workspace.

• Results from the pipeline are consistent with the original one.
• The weights for 'cc_projection' layer are not fully converted to diffuser, still need to load the original .ckpt.
• Documentation.

Before submitting

• This PR fixes a typo or improves the docs (you can dismiss the other checks if that's the case).
• Did you read the contributor guideline?
• Did you read our philosophy doc (important for complex PRs)?
• Was this discussed/approved via a Github issue or the forum? Please add a link to it if that's the case. A: Yes, issue
• Did you make sure to update the documentation with your changes? Here are the
  documentation guidelines, and
  here are tips on formatting docstrings.
• Did you write any new necessary tests? A: Simply run pipeline_zero1to3.py will call the main() to test the pipe.

Who can review?

Anyone in the community is free to review the PR once the tests have passed. Feel free to tag
members/contributors who may be interested in your PR.

[HuggingFaceDocBuilderDev]

The documentation is not available anymore as the PR was closed or merged.

[patrickvonplaten]

Looks great!