Add dict input support to from_single_file for reusing loaded weights

[xalteropsx]

What does this PR do?

Extends FromSingleFileMixin.from_single_file() so that
pretrained_model_link_or_path_or_dict accepts a state dict in
addition to a path/URL. This lets users load multiple pipelines
(e.g. txt2img + img2img) from a single checkpoint without
re-reading and re-parsing the file from disk.

Fixes #14903

Before

def from_single_file(cls, pretrained_model_link_or_path, **kwargs): ...

user had to load the file twice:

txt2img = StableDiffusionPipeline.from_single_file(path)
img2img = StableDiffusionImg2ImgPipeline.from_single_file(path) # re-reads disk

After

def from_single_file(cls, pretrained_model_link_or_path_or_dict, **kwargs): ...

state_dict = load_file("sd_xl_base_1.0.safetensors")
txt2img = StableDiffusionPipeline.from_single_file(state_dict)
img2img = StableDiffusionImg2ImgPipeline.from_single_file(state_dict) # no re-read

How

• Accept dict in the first argument; when a dict is passed, skip
  download/file I/O and use the provided tensors directly.
• Existing str / os.PathLike behavior is unchanged (backward compatible).
• Updated docstring + type hints.

Who can review?

Anyone in the community is free to review
@sayakpaul @DN6 @yiyixuxu

[github-actions]

Hi @xalteropsx, thanks for the PR! It does not appear to link an issue it fixes. If this PR addresses an existing issue, please add a closing keyword (e.g. Fixes #1234) to the PR description so the issue is linked. See the contribution guide for more details. If this PR intentionally does not fix a tracked issue, a maintainer can add the no-issue-needed label to silence this reminder.

Please note that PRs without a linked issue are likely to be automatically closed 10 days after this notice.

Once the PR links an issue (or gets the no-issue-needed label), you can ignore this message — it stays here as a comment, but it no longer applies.