Skip to content

[train_dreambooth_lora_sdxl] Add --image_interpolation_mode option for image resizing (default to lanczos) #11490

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

Merged
merged 2 commits into from
May 5, 2025

Conversation

MinJu-Ha
Copy link
Contributor

@MinJu-Ha MinJu-Ha commented May 5, 2025

related to #11390

This PR adds support for --image_interpolation_mode in train_dreambooth_lora_sdxl.py,
setting the default to lanczos for improved image resizing quality.

This is consistent with the changes made in #11206 to other training scripts.

@asomoza

@MinJu-Ha
Copy link
Contributor Author

MinJu-Ha commented May 5, 2025

Since train_dreambooth_lora_sdxl.py already has code blocks for lanczos as shown below, I only modified self.transforms part to make use of the parsed interpolation argument.

image image

@asomoza
Copy link
Member

asomoza commented May 5, 2025

yes, indeed I forgot to update that part of the code, thanks!

@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.

@asomoza
Copy link
Member

asomoza commented May 5, 2025

thanks!

@asomoza asomoza merged commit ec93239 into huggingface:main May 5, 2025
9 checks passed
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.

3 participants