Error running ComfyUI workflow from pod on serverless
I’m encountering an error when running a ComfyUI workflow from a pod on RunPod serverless.
Previously, I was running the ComfyUI workflow on a pod with network storage mounted, and it worked fine. Now, I want to run the workflow via API, so I deployed the endpoint using the image:
timpietruskyblibla/runpod-worker-comfy:3.4.0-base
with my network storage mounted as the endpoint’s storage.
I exported the API JSON and attempted to test-run it, but I’m getting errors (see the images provided).
6 Replies
Hmm seems like there is a bug here isn't it
I see the logs are incomplete, usually there is container logs (from inside the container) too not only those start or stop
Maybe you have to add more execution timeout in your endpoint and check your logs, but I'm guessing there is a bug for the logs so open a ticket
@maverickdoge
Escalated To Zendesk
The thread has been escalated to Zendesk!
Ticket ID: #16909
@Jason So like if run it without my volume and with the deafult workflow its works, but still there are not more logs
Probably because of custom nodes not there or dependencies (python) are incomplete for your custom nodes
But without logs I'm not sure
@Jason yea probably somethig with the env or wf. How should i now go forward, should i wait till the ticket is processed or what u suggest since i need actually the enpoints to create some stuff
Yeah try something, if you want because tickets might take longer time Tha trying yourself