What does this PR do?

This PR adds an option to disable the NSFW safety_checker in the LoRA training evaluation script. This feature is implemented via a new parser argument --disable_safety_checker. When enabled, the safety_checker is set to None, preventing black images caused by false-positive NSFW detections during evaluation.

Motivation and Context

During evaluation, the safety_checker sometimes incorrectly flags images as NSFW, resulting in black outputs even when the images are safe. This change allows users to disable the safety_checker as needed, improving flexibility and usability.

Dependencies

No new dependencies are introduced with this change.

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?