Use flash_attention for SD2

[zpcore]

What does this PR do?

Use flash attention for SD2 base.

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.

[entrpn]

@zpcore sd 2 base doesn't require attention masks. What is the reasoning for adding it?

[zpcore]

@zpcore sd 2 base doesn't require attention masks. What is the reasoning for adding it?

You are right, the attention mask is always None. I don't know why the original code pass None mask to the attention. To be safe I just keep it there.

[entrpn]

@zpcore sd 2 base doesn't require attention masks. What is the reasoning for adding it?

You are right, the attention mask is always None. I don't know why the original code pass None mask to the attention. To be safe I just keep it there.

I believe it was added because there is a method to use masking for diffusion models, but this particular model and implementation we're targeting doesn't use it. LGTM.