Generate video outpaint code with WAN 2.1

[SlimRG]

What does this PR do?

This PR introduces video outpainting capabilities for the WAN 2.1 model. It provides a WanVideoOutpaintPipeline that extends existing video content by expanding its dimensions (height and/or width) and generating coherent new frames in the padded regions. This leverages WAN's Spatial-Temporal Guidance (STG) to ensure temporal consistency and high-quality content generation in the newly created areas.

The implementation allows users to:

• Expand video dimensions to desired resolutions or aspect ratios.
• Fill outpainted regions with AI-generated content based on a text prompt and the original video.
• Utilize various padding modes (constant, edge, reflect, symmetric).

This feature enhances the utility of WAN 2.1 for video manipulation and content creation.

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 @sayakpaul

---

[cursor]

Cursor Agent can help with this pull request. Just @cursor in comments and I'll start working on changes in this branch.
_{Learn more about Cursor Agents}