[Community Pipeline] Add some feature for regional prompting pipeline

[cjkangme]

What does this PR do?

Hi.
I am happily using a pipeline that implements Regional Prompting in the diffusers community pipeline.
While using the community pipeline, I created a PR as I thought it would be good to add the following:

• Fix negative prompt processing logic (minor error)
• Add Use base prompt logic
• Fix initialization errors occurring in the latest version

Using Example

I tried to imitate this example

2d animation style ADDBASE
masterpiece, high quality ADDCOMM
blue sky BREAK
green hair twintail BREAK
book shelf BREAK
messy desk BREAK
orange++ dress and sofa

mode: rows
div: 1,2,1,1;2,4,6
base_ratio: 0.3

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.

[sayakpaul]

Thanks for your PR! Do you maybe also want to update the README of regional prompting?

[cjkangme]

@sayakpaul
sure, I have made updates regarding the use_base option

[sayakpaul]

Could maybe also specify the reference that introduced this technique?

[cjkangme]

This technique was originally implemented in hako-mikan's regional-prompter, but not in the current community pipeline.
So, I don't think it's necessary to specify the reference again.

[sayakpaul]

@cjkangme could you run make style && make quality and push your changes?

[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.

[cjkangme]

@sayakpaul
I accidentally ran make style in the root directory and it modified some wrong files. So I reverted it 😅😅
nothing changed about the regional prompting

[cjkangme]

@sayakpaul

Hi
I've reapplied the make style, can you confirm?

[sayakpaul]

Thank you!

[vladmandic]

was this pr tested? i'm getting runtime error since the merge:

│ /home/vlado/.cache/huggingface/modules/diffusers_modules/git/regional_prompting_stable_diffusion.py:462 in promptsmaker                                                                                                                                                                                                                                                                                                          │
│                                                                                                                                                                                                                                                                                                                                                                                                                                  │
│   461 │   │   │   add = add.strip() + " "                                                                                                                                                                                                                                                                                                                                                                                        │
│ ❱ 462 │   │   prompts = [p.strip() for p in prompt.split(KBRK)]                                                                                                                                                                                                                                                                                                                                                                  │
│   463 │   │   out_p.append([add + p for i, p in enumerate(prompts)])                                                                                                                                                                                                                                                                                                                                                             │
╰──────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
AttributeError: 'list' object has no attribute 'split'

[cjkangme]

@vladmandic

Hi
I apologize for the issue.
There was a typo in my code that caused an error when prompts is a str type and negative_prompts is a list type

I've fixed the affected line and created PR #10251