Convert HunyuanImage to diffusers style

[Bili-Sakura]

What does this PR do?

This PR initiates the conversion of the Tencent HunyuanImage-2.1 model to the Diffusers library style. It primarily implements the model's unique 32x spatial compression VAE, AutoencoderKLHunyuanImage, which features 64 latent channels. This VAE includes support for gradient checkpointing and slicing.

Additionally, this PR establishes a comprehensive set of documentation (HUNYUANIMAGE_CONVERSION_GUIDE.md, CONVERSION_SUMMARY.md, CONVERSION_STATUS.txt) to guide the remaining conversion efforts for the transformer and pipeline components. This lays the essential groundwork for integrating HunyuanImage-2.1, a 17B parameter model with a distinct architecture (32x VAE, dual-stream DiT, ByT5 text encoder), into Diffusers.

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 @stevhliu

---

 

[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}