[WIP] Add InfiniteTalk Audio-Driven Video Generation Pipeline

[dg845]

What does this PR do?

This PR implements a pipeline for the InfiniteTalk audio-driven video generation model (paper, code, weights). The InfiniteTalk model is designed to handle infinite-length video and demonstrates SOTA performance for video dubbing. It is ultimately based on the Wan 2.1-I2V-14B image-to-video model (with extra audio components).

Fixes #12239.

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.
• 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?

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.

@yiyixuxu
@DN6
@supermeng

[ZivKidd]

Hello, I have reviewed the code you submitted. It seems there are still some areas that need improvement. Will you continue to update it?

[dg845]

Hi, I am currently planning to work on it, but may not be able to find time in the short term to do so.