Move a Pod to Serverless?
Hello everyone. I have a kind of high level / conceptual type question:
The background: I have used comfyui on my physical computer. As many of you know, with comfyui if your settings/models arent jiving, then it will fail. I want to scale up comfyui to roll out to my small company so anyone can use it via a internal website I have created (via a API, so they wont 'see' comfyui). Basically scale and deploy specific stable diffusion workflows. I have attempted to use a few different serverless companies, with not much luck. Its slighty beyond my knowledge / skillset. What I like from trying the pre-built A1111 serverless sample file is that I can see the logs to troubleshoot issues which helps me understand what is going on more than the others companies i have tried.
My question: Since I'm not skilled with Docker, Im wondering if its easier for me to start and configure a Pod to troubleshoot and get things setup and configured (not just the 'hardware' but also the actual config of comfyui). Then, can that pod be transitioned / exported and then reimported to a serverless setup? Is this process possible? or am i thinking about it the wrong way?
2 Replies
Suggest you look at the following. It builds ComfyUI as a serverless worker. You can add any models, custom nodes, etc. when building your image and it accepts the workflow (in JSON format) as the input. https://github.com/blib-la/runpod-worker-comfy
GitHub
GitHub - blib-la/runpod-worker-comfy: ComfyUI as a serverless API o...
ComfyUI as a serverless API on RunPod. Contribute to blib-la/runpod-worker-comfy development by creating an account on GitHub.
That is what I ended up trying, but im running into issues. I'm able to use the logs to troubleshoot, but its always one issue after another. I was eventually able to get it working with a custom model and one generic package. However some of the custom nodes (like the controlNet one that we use the most) isn't installing properly and I'm not able to know what is going on without a lot of blind attempts of fixing it... Thats why i was wondering if there was a different aproach that allowed for me to get a machine up and working, then 'snapshot it' to deploy serverless. where i would send it the json.