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

Adds support to new SDXL dreambooth LoRA training script features + QOL features #448

Merged
merged 4 commits into from
Nov 23, 2023

Conversation

linoytsaban
Copy link
Contributor

Aligns the notebook with the huggingface/diffusers#5508 + adds some QOL features to the notebook -while keeping it free tier - including:

loading data from a local folder
hub login with notebook_login()
auto-captioning option with blip
use of custom captions for training
updated documentation aligned with and highlighting the updated features of the script

Copy link

Check out this pull request on  ReviewNB

See visual diffs & provide feedback on Jupyter Notebooks.


Powered by ReviewNB

@linoytsaban linoytsaban marked this pull request as ready for review November 23, 2023 10:53
@apolinario
Copy link
Contributor

LGTM! nice revamp on the notebook and new template for upload to hub!

Copy link
Member

@pcuenca pcuenca left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Great work, I think the additions are very useful!

Not sure how to review the notebook diff effectively, so I'll just write down what I saw:

  • The model card metadata appears to be wrong, see https://huggingface.co/LinoyTsaban/corgy_dog_LoRA/blob/main/README.md. Critically, base_model is preceded by an additional yaml separator, so it doesn't work. Also maybe quote or bold the trigger phrase in the trigger words section, as it now flows with the text without separation.
  • There are some warnings about xFormers not working properly.
  • nit typos in the Launch training section: soley -> solely, in that case -> In that case

- added a call to create_repo and removed --push_to_hub tag
- removed xformers install as I think it will likely not work for most users
@pcuenca pcuenca merged commit 1dda4aa into huggingface:main Nov 23, 2023
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