Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[Feature] Support DeBias Estimation Loss #79

Merged
merged 1 commit into from
Oct 24, 2023

Conversation

okotaku
Copy link
Owner

@okotaku okotaku commented Oct 24, 2023

Motivation

Support Debias the Training of Diffusion Models.

Modification

  • Refactor Loss
  • Support DeBias Estimation Loss

Results (Optional)

stable_diffusion_xl_pokemon_blip_debias_estimation_loss

example1

Checklist

Before PR:

  • Pre-commit or other linting tools are used to fix the potential lint issues.
  • Bug fixes are fully covered by unit tests, the case that causes the bug should be added in the unit tests.
  • The modification is covered by complete unit tests. If not, please add more unit test to ensure the correctness.
  • The documentation has been modified accordingly, like docstring or example tutorials.

@okotaku okotaku self-assigned this Oct 24, 2023
@okotaku okotaku merged commit 42bbaf5 into main Oct 24, 2023
@okotaku okotaku deleted the feat/debias_estimation_loss branch October 24, 2023 02:02
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

1 participant