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

Sd3.5 medium support #531

Open
KintCark opened this issue Dec 28, 2024 · 3 comments
Open

Sd3.5 medium support #531

KintCark opened this issue Dec 28, 2024 · 3 comments

Comments

@KintCark
Copy link

I'm trying to use sd3.5 medium but it keeps saying no t5xxl can we use it separately instead of a all in one model?

@stduhpf
Copy link
Contributor

stduhpf commented Dec 28, 2024

SD3.5 doesn't come with any text encoders in the official model file. You need to provide clip_l, clip_g and t5xxl separately.
(see #451). The all in one models are not officially supported, maybe they'll work, but maybe not.

@KintCark
Copy link
Author

  • Ok I did that but it keeps saying no t5xxl I provided clip g clip l and t5xxl

@stduhpf
Copy link
Contributor

stduhpf commented Dec 28, 2024

I can't reporoduce your issue 🫤 . Can you provide the full logs? (with -v if possible)

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

No branches or pull requests

2 participants