Feature: HiDiffusion integration

[DustyShoe]

Summary

Added HiDiffusion support across backend and UI. The denoise pipeline can now apply HiDiffusion with optional RAU‑Net and Window Attention toggles, including metadata persistence/recall and graph wiring for SD1/SDXL and the SDXL refiner. The UI exposes aligned advanced switches with informational popovers.
Added HiDiffusion documentation and a “Learn more” link.

Related Issues / Discussions

https://github.com/megvii-research/HiDiffusion
Closes #8780

QA Instructions

1. UI: Canvas → Advanced Settings → confirm HiDiffusion + RAU‑Net + Window Attention toggles visible, aligned, truncation works at narrow width.
2. Popovers: hover labels for HiDiffusion/RAU‑Net/Window Attention; popover appears and HiDiffusion shows Learn More link.
3. Metadata: generate once with HiDiffusion ON + custom RAU/Window; verify metadata fields exist and Recall restores toggles.
4. SDXL: compare OFF vs ON at 1536+ (same seed). Then toggle RAU off / Window off to confirm output changes and no errors.
5. SD1.5: repeat step 4 at highest feasible res.
6. Regression: generate with HiDiffusion OFF; no errors/warnings.

Merge Plan

Should merge without issue.

• Just to be aware of changes in lockfiles: uv.lock, pyproject.toml.
• HiDiffusion package availability: it pulls from PyPI upstream. If a version change introduces breaking behavior, we may need to pin a specific version.
• name_or_path hack: we’re forcing _name_or_path to avoid HiDiffusion errors. If diffusers changes internals, this might need adjustment.
• No DB/schema breaking changes.

Checklist

• The PR has a short but descriptive title, suitable for a changelog
• Tests added / updated (if applicable)
• ❗Changes to a redux slice have a corresponding migration
• Documentation added / updated (if applicable)
• Updated What's New copy (if doing a release after this PR)

[DustyShoe]

I might be spoiled by SDXL too much, but SD1.5 did not impress me much. It produces better results than default denoise. Especially when generating whole image. Inpainting is a tricky one. You might want to try different schedulers. Hands are particularly messy at 1.5k px.
SDXL on other hand, behaves much better and i'm pretty happy with it.
Also noticed ~10% improvement in speed.

[DustyShoe]

I just realised that updated version of HiDiffusion is here: https://github.com/Teriks/dgenerate/tree/master/dgenerate/extras/hidiffusion
How we can use it if it works better?

[iwr-redmond]

You may wish to consider vendoring the code inside the Invoke package, e.g. invokeai.backend.hidiffusion. Both packages are licensed with Apache 2.0.

[DustyShoe]

I did include allegedly improved HiDiffusion in Invoke/backend/hidiffusion (for now, until we decide vendor it or not).
I'd like to have a feedback and suggestions on improvement.
Ref link: https://github.com/Teriks/dgenerate/tree/master/dgenerate/extras/hidiffusion

[iwr-redmond]

allegedly improved HiDiffusion

The quality fixes were for checkpoint detection and deterministic generation, rather than adjusting core functionality.

[JPPhoto]

@DustyShoe It looks like line endings are off throughout your entire PR. Can you fix this?

Try git add --renormalize . and then commit and push.

[DustyShoe]

@JPPhoto can you please verify, that you are on last commit?
Some issues were present earlier and should be fixed in [0ba1b66]
I'm unable to find any issue and git add --renormalize . returned no change.

[JPPhoto]

@JPPhoto can you please verify, that you are on last commit? Some issues were present earlier and should be fixed in [0ba1b66] I'm unable to find any issue and git add --renormalize . returned no change.

Looks fine now, must have been something weird on GitHub. Sorry!

[DustyShoe]

I already started to think that VSCode is playing tricks on me. Whew!