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

Update opimizations to Gradio #48

Merged
merged 1 commit into from
Oct 12, 2024
Merged

Update opimizations to Gradio #48

merged 1 commit into from
Oct 12, 2024

Conversation

tpc2233
Copy link
Contributor

@tpc2233 tpc2233 commented Oct 12, 2024

Now user can choose between 768p and 384p models in the UI
cpuoffloading is now use by default
updates to model loader and functions
hf download double checks model locally
terminal --verbose with more info to the user

Now user can choose between 768p and 384p models in the UI
cpuoffloading is now use by default
updates to model loader and functions
terminal --verbose with more info to the user
@FurkanGozukara
Copy link

very nice. i think all settings as cpu offloading or tile size like 256 128 should be optional from interface

@feifeiobama feifeiobama merged commit 221bacc into jy0205:main Oct 12, 2024
@feifeiobama
Copy link
Collaborator

This is very thoughtful, thank you @tpc2233 for the contribution!

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