Skip to content

Adds FLUX attention masking and additional time embedder #9

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.

Sign up for GitHub

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

Jump to bottom
Merged
merged 4 commits into from
Jul 2, 2025
Merged

Adds FLUX attention masking and additional time embedder #9

merged 4 commits into from
Jul 2, 2025

Conversation

clementchadebec
Copy link
Collaborator

Added features

  • Adds attention masking to Flux
  • Add the possibility to add an extra vector embedding added to the timesteps embedding for Unet and FluxTransformer

benjaminaubin
benjaminaubin requested changes Jul 1, 2025
View reviewed changes
Copy link
Collaborator

@benjaminaubin benjaminaubin left a comment

Choose a reason for hiding this comment

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

Hi @clementchadebec , thank you for sharing those modifications to allow anyone playing with Kontext

@clementchadebec
Copy link
Collaborator Author

I removed the changes unet_2d_condition.py since they were not useful and not tested for now

@clementchadebec clementchadebec merged commit c743e85 into clipdrop-main Jul 2, 2025
2 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@benjaminaubin benjaminaubin benjaminaubin approved these changes

@gonzaiq gonzaiq Awaiting requested review from gonzaiq

Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
2 participants
@clementchadebec @benjaminaubin