-
-
Notifications
You must be signed in to change notification settings - Fork 233
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 nodes from snapshot.json in network-volume are not restored #79
Comments
@A-BMT02 thanks for reporting this. The new method that I added here does only work when you build your own Docker image. It will not install custom nodes from a snapshot.json that is part of a network volume. But I see that this is a nice feature idea. I usually try to avoid having any actions happening at execution time, where you install something if a request to the serverless endpoint is coming in. BUT if we would install these changes on the network-volume, then this would also work. I will try adding the |
Looking forward to see how this gets implemented ;) I added the line But Its still not recognizing the custom_nodes folder even though it's in the root directory (/workspace) All the other folders in the root directory are added except the custom_nodes . Am i missing something ? my comfyui.log file says |
Hey @TimPietrusky, I'm looking at some new RunPod serverless solutions and this fix would be very helpful for our use-case. Is this network-volume stored custom nodes feature likely to be running in the near future, or should I look into building our own docker? @A-BMT02 did you manage to figure this out? Thanks! |
Originally posted by @A-BMT02 in #30 (comment)
I can't seem to get this working . When i start a runpod pod and open my comfy ui on port 8188 it works fine , i can generate my images fine
But when i use the serverless endpoint with the same workflow json , i get an error
2024-11-19 14:00:45.074 [c7msa02ut39p9w] [info] invalid prompt: {'type': 'invalid_prompt', 'message': 'Cannot execute because node FaceDetailer does not exist.',
It seems like the custom nodes are not being recognized in the serverless endpoint even though i have the snapshot.json in the /runpod-volume (/workspace) directory
If i try a request with no custom nodes on the runpod serverless endpoint , it works fine.
The text was updated successfully, but these errors were encountered: