Skip to content

Conversation

Aiden-Frost
Copy link
Contributor

Instructpix2pix_lora to use PEFT

Fixes
As discussed in issues: #10062
Tested on Google Colab by running the sample train command provided in README.

Who can review?

@sayakpaul @duduke121

@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.

Copy link
Member

@sayakpaul sayakpaul left a comment

Choose a reason for hiding this comment

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

Looking very nice! Thanks for working on this!

Do you have some example training runs and results for us to see?

@Aiden-Frost
Copy link
Contributor Author

Aiden-Frost commented Dec 21, 2024

Screenshot 2024-12-20 at 7 02 50 PM

Thanks for looking into the PR. Sorry for the delay. I have made the changes you have suggested and trained the model for only 3 epochs (1500 steps). I have attached a screenshot of cartoonizing one of the images.

Copy link
Member

@sayakpaul sayakpaul left a comment

Choose a reason for hiding this comment

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

Looking really nice! Thanks for working on this.

@yiyixuxu
Copy link
Collaborator

yiyixuxu commented Jan 6, 2025

can you run make style?

@sayakpaul sayakpaul merged commit f1e0c7c into huggingface:main Jan 7, 2025
9 checks passed
@sayakpaul
Copy link
Member

Thanks for your awesome contributions!

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Projects
None yet
Development

Successfully merging this pull request may close these issues.

4 participants