Comfyui not using GPU, how to fix this?
We are running in instance of Comfyui and it's using CPU and not GPU, using a 4090. How can this be fixed?
What are the rules that RunPod follows to cache DockerHub images?
I did some more testing today and it seems like RunPod sometimes holds a copy of my docker image, which leads to the fast load I'm looking for. Is there any predictability to this? Like, is it cached for a specified amount of time?
Can I cache my DockerHub image in RunPod storage?
My image is 5.8GB in DockerHub. This includes a 2.5GB folder of assets I need for my workload and the rest is just packages. I timed it and it took about 2 minutes to download into my RunPod container. Is there a way to cache my Docker image so that I can reduce this download speed?
Is there a way to add storage volume to a pod after creation?
Hi, I have worked on this pod for a while but I did not add the pod under a volume to increase the storage space. Is there a way to add it now?
Solution:
No neither a way to remove it from a pod too
how to remove network volume from pod
hey how can i remove the network volume from a pod. I cant delete it without removing it but i dont see any options in the ui. how to do it?
Solution:
You cant like disconnect the network volume from a pod
Pod seems to behave like 'Spot' even though it's configured for 'On Demand'
I'm using the stable diffusion template, and haven't had any issues for a few days. Now image generation is taking up to 3 mins before it even starts to generate. Nothing in the logs suggests any sort of error or unusual behavior. How can I diagnose what's wrong? I don't want to terminate and try a new pod because I'll have to redownload all my models and loras.
Different user of same team see different ComfyUI workflow on same pod
Hey,
I have an issue with my team sharing our comfyUI in runpod. We have a team space with 1 pod and each team member see a different comfyUI setup when launching the port url... Do you know why?...
How to add start command via python
I was not able to find a parameter related to it, please assist.
Solution:
```python
Create a new pod configuration
config = runpod.PodConfiguration(
name="my-app-container",
imageName="nginx:latest",...
Comfyui Model and Node problem
1. When trying to save work in a pod in ComfyUI if I stop the pod then I lose certain nodes that have been installed and they stay red.
2. When I try to install them via Git URL it's saying that the security level configuration is incorrect, even though it's worked previously. I had everything working and then when I clicked to stop the pod it broke parts of it. How do I stop this from happening?
3. I've uploaded checkpoint models where the default ones exist but aren't appearing in the comfyui interface. Also Ipadapter isn't importing correctly. Even models that I install through the comfy Manager interface aren't registering. Please advise....
ComfyUI idle to running red box issue
So Iβve installed a workflow in runpod and I install all the nodes and I have it working. However when I go to switch the runpod to idle and then switch it back to running it gives me red box errors and if I try to either fix them or uninstall and then reinstall they stay broken. Is there anyway to fix this?
Node packs that break are impact, WAS, sipherxyz comfyui-art-venture...
Attempting to open a pod when an email is received.
I'm using Make.com to open a pod when emails are received by a certain account (open to solutions other than make.com but its the service I went with). I am unsure of how to set up the API. Currently I have a http widget set up to make a request to runpod but I think I'm simply sending the wrong request. The way I have it set now is:
Method: POST
URL: https://api.runpod.io/graphql
Headers:...
Getting data in/out of a community cloud pod
For Secure Cloud pods, you're able to dump to a Network Volume, and either manually download that or sync it out to a cloud provider
For community pods which don't have network volumes, what's the alternative solution? Is there any way to pipe it's content's directly to a cloud service?
Similarly, is there a way to have a community pod pull contents from a cloud service?...
Solution:
Yeah sure, i think there is try to browse around
When does IP of pod change?
When does the IP of the pod changes? Does it change when we restart/pause the pod or only when we delete and create the new pod?
Is there any option to get a static IP for the pod?
We are planning to deploy an inference API on pod on a trial basis....
possible to take image from dockerhub
Hi I want to be able to pull an image from dockerhub and use on my 100gb network volume storage
0 GPU pod makes no sense
I have network storage attached to my pods. I don't care if a GPU gets taken from me, but it's very inconvenient that I have to spinup a completely new pod when it does. I am automating runpod via the CLI, and at the moment I dont see any way to deploy a fresh instance and GET the ssh endpoint. I think just slapping on a warning saying you have to start fresh when a GPU gets taken and finding the next available one makes so much more sense, especially when using network storage.
A4000 - 50GB , BUT ONLY GETTING 16 GB BASED ON nvidia-smi
Hello, not sure if I am doing something wrong, but I purchased a pod using A4000 50GB, but when I run nvidia-smi I only see 16GB. I am not sure why ? I see after purchase that this is 9cpu, so not sure what is going on , since even 9x16 = 144, so why is this advertised as 50GB ? Any clarifications or settings please do advise, it is not obvious.
Why the available GPUs are only 1?
I want to run my pod with at least 2 gpus.
My pod is A5000.
Now available gpus are ony 2.
what happened?...