[#10076] Adds conversion script from diffusers to cogvideox

[KaranpreetRaja]

What does this PR do?

This PR adds a conversion script convert_diffusers_to_cogvideox.py that enables converting models from the Diffusers format back to the original CogVideoX format. This complements the existing convert_cogvideox_to_diffusers.py script, allowing for bidirectional conversion between the two formats.

The script provides functionality to:

• Convert Transformer models from Diffusers to CogVideoX format
• Convert VAE models from Diffusers to CogVideoX format
• Support both Image-to-Video and regular CogVideoX models
• Handle different model versions (1.0 and 1.5)
• Support FP16, BF16, and FP32 precision

Fixes #10076

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.
  • Approved in Do we have any script covert from hf format to orginal format? #10076
• Did you make sure to update the documentation with your changes? Here are the
  documentation guidelines, and
  here are tips on formatting docstrings.
  • Other conversion scripts do not have any documentation
• Did you write any new necessary tests?
  • Other conversion scripts do not have any tests, can commit tests if needed

[github-actions]

This issue has been automatically marked as stale because it has not had recent activity. If you think this still needs to be addressed please comment on this thread.

Please note that issues that do not follow the contributing guidelines are likely to be ignored.

[Yasserbhb]

@hlky @foreverpiano @KaranpreetRaja This PR has been inactive for a year. Would the team still be interested in this feature? I'd like to pick it up as my first contribution. would like to address any missing pieces and fixes .