[Single File] Add Single File support for Lumina Image 2.0 Transformer

[DN6]

What does this PR do?

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.

[nitinmukesh]

As I understand this should close the following feature request
#10749

Thank you for making this feature available.

[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.

[a-r-r-o-w]

LGTM!

Not for this PR, but I've been meaning to start a discussion on how we can go from Diffusers format -> original format. It seems like a lot of the community likes using the diffusers training scripts, or a trainer that uses model implementations in diffusers, for a lot of things but majority of users are unable to use the trained artifacts (for example, ComfyUI does not want to support multiple lora conversion utilities and wants to just stick with original model format). To reduce such friction, being able to export a diffusers model in original weight format might be a well-received feature. Let's discuss more on whether we should look into this and how to make it possible