Modification on the PAG community pipeline

[HyoungwonCho]

What does this PR do?

Perturbed-Attention Guidance

This implementation is based on Diffusers. StableDiffusionPAGPipeline is a modification of StableDiffusionPipeline to support Perturbed-Attention Guidance (PAG). For more information about PAG, please refer to Project / arXiv / GitHub

Hi! We have updated some of the implementations of the Perturbed-Attention Guidance, which we previously contributed to community pipelines.

Fixes # (issue)

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.

[bghira]

did you mean to commit this file too?

[HyoungwonCho]

Sorry, I excluded the sample.py file.

This pull request is a request that I sent by modifying some of the PAG codes that I previously contributed. I would appreciate it if you could reflect it.

[yiyixuxu]

thanks!

[yiyixuxu]

can we run make quality?
will merge once the tests pass

[yiyixuxu]

cc @asomoza here

[HuggingFaceDocBuilderDev]

The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update.

[asomoza]

Thanks for your work, this looks great, I didn't have the chance to be for the first PR so I'm just trying this one out.

I really need to sit down and test the effects of PAG because I find them really interesting, for example some of the blocks I often use for LoRAs:

normal	scale 5.0, "m0"	scale=5.0, "d4", "d5", "m0"	scale=7.0, "d4", "d5", "m0"

Still I think it would be better to use SDXL to showcase it, this one is supposed to be a "steam powered mechanic spider robot" but at least PAG makes it more of a "spider".

[HyoungwonCho]

@yiyixuxu Thank you, I removed the white space in the code for code quality check.

[HyoungwonCho]

@asomoza Thank you for your interest in our work!

Thanks to multimodalart, users can try PAG on SDXL on Hugging Face Spaces.

For more information, please visit our github page.

[HyoungwonCho]

I am struggling with build error. If this is resolved, I will open a new pull request.