Fix lora alpha and metadata handling

[Tanuj-rai]

What does this PR do?

This PR adds --lora_alpha and metadata handling in training scripts in 'train_dreambooth_lora_sdxl.py'.

Fixes #11730

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?

@linoytsaban @sayakpaul

[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.

[linoytsaban]

thanks! made some small changes

[Tanuj-rai]

thanks! made some small changes

Thank you @linoytsaban , for reviewing and suggesting changes. I’ve implemented the requested updates.

[linoytsaban]

thanks @Tanuj-rai :) I just noticed lora_alpha is missing from the text_encoder config, after that's merged we'd be good to go

diffusers/examples/dreambooth/train_dreambooth_lora_sdxl.py

Lines 1245 to 1249 in 4f69b28

	text_lora_config = get_lora_config(
	rank=args.rank,
	dropout=args.lora_dropout,
	use_dora=args.use_dora,
	target_modules=text_target_modules,

[Tanuj-rai]

thanks @Tanuj-rai :) I just noticed lora_alpha is missing from the text_encoder config, after that's merged we'd be good to go

diffusers/examples/dreambooth/train_dreambooth_lora_sdxl.py

Lines 1245 to 1249 in 4f69b28

	text_lora_config = get_lora_config(
	rank=args.rank,
	dropout=args.lora_dropout,
	use_dora=args.use_dora,
	target_modules=text_target_modules,

Thank you @linoytsaban for pointing it out. I have now added the lora_alpha in the text_encoder config.