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

Custom file path for loaded models #313

Open
Tucarius opened this issue Jan 27, 2025 · 0 comments
Open

Custom file path for loaded models #313

Tucarius opened this issue Jan 27, 2025 · 0 comments

Comments

@Tucarius
Copy link

Tucarius commented Jan 27, 2025

While currently you can specify a model to download from hugging face via the models.yaml file. Having the ability to specify a custom file directory to load pre existing models from would be very beneficial.
I for example have fluxgym installed on a hdd, and have my model folder installed on a much faster ssd.
The file names of the files i have may also not quite match those from the original flux dev repository, but they are still the expected safetensor files (for example).
I don't want to have to worry about the models unnecessarily downloading ~40GB of files i don't actually need, or taking forever to read from the hdd into memory once they have. This would easily solve both of those problems.
Note this isn't limited to the flux model, but the clip and text encoder models also, which i also have located on my ssd.

(It seems adding labels to github issues is a restricted thing)

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

1 participant