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

How to find Ultralytics detector models on network volume? #91

Open
boesolutions opened this issue Jan 7, 2025 · 0 comments
Open

How to find Ultralytics detector models on network volume? #91

boesolutions opened this issue Jan 7, 2025 · 0 comments

Comments

@boesolutions
Copy link

Hey, I love this worker, very useful.

I've succesfully set up custom nodes and model paths from my network volume (built my own image), however I can't seem to make the Ultralytics path work:

2025-01-07T12:31:05.890963520Z Failed to validate prompt for output 2086:
2025-01-07T12:31:05.890995476Z * UltralyticsDetectorProvider 2088:
2025-01-07T12:31:05.891092390Z   - Value not in list: model_name: 'hand_yolov8s.pt' not in []
2025-01-07T12:31:05.891114012Z Output will be ignored

I've set the path in extra_model_paths.yaml like:
ultralytics: models/ultralytics/
(not sure if I'm allowed to add these kind of extra model paths, but Ultralytics and some more, like SAM are requiring their own folders for extra models)

and it did recognised the folder on startup:
2025-01-07T12:29:35.838727365Z Adding extra search path ultralytics /runpod-volume/storage/stable_diffusion/models/ultralytics/

Other paths are fine, base models and loras are found. Since the log says value not in [], I guess it did not even fetch the list of ultralytics models I have in that folder, hence not finding the referenced one either.

So am I setting the path wrong or what's the correct way of reaching Ultralytics models on the volume?

Any help would be appreciated.

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