Custom Templates are not loading on Secure Cloud
I have some templates that are running without issue on Community Cloud but None of them work on Secure Cloud.
And probably Serverless is suffering with the same issue as my custom endpoint do not load.
Issue affects A5000 GPU, on Secure Cloud.
...
can’t run my own init script
Hi guys, after couple hours I give up and asking for help
I use standard runpod/pytorch image
my initial script is working in digital ocean test instances. ...
How do i create an encrypted volume programmatically?
https://blog.runpod.io/runpod-encrypted-volumes/
"If you would prefer to choose your own encryption key, you can deploy using the API."
I can't find documentation on this process anywhere, can someone please tell me where I can find the API that supports this? We are very interested in doing something like this for our future deployments....
Pod still asking to log in
Hi, I'm having an issue with the Pod still asking me to log in. When I put the credentials there it works for few minutes and then ask again. Is there a way how to repair it? It's the "ComfyUI - Jupyter" community template.
ComfyUI Manager button doesn't show
Hi, I just started my first RunPod, installed the ComfyUI from template and tried to install Manager for custom nodes, but the button doestn't appear. Even if I fully stop the Pod and launch it again. I installed the Manager using this:
cd /workspace/ComfyUI/custom_nodes git clone https://github.com/ltdrdata/ComfyUI-ManagerAny idea what to do?...
Errors while running FaceFusion 2.2.1
While trying to render a video I am running into this error repeatedly;
Solution:
This happens with large videos, ensure that you have a public IP and change the port from HTTP to TCP.
Trying to run a Fooocus Realistic Edition POD an running into errors.
Error from log; "2024-01-26T06:54:25Z error starting container: Error response from daemon: driver failed programming external connectivity on endpoint i172gyih5zhjpl-0 (9d2a2308b8ac1eeec7d93754019564939a82889f8841d2fdc7edddca81a28cb5): Error starting userland proxy: listen tcp4 0.0.0.0:40132: bind: address already in use"
Python3.8.10 and Venv
How do I start a pod where I run a specific distribution of python (3.8.10, not just the default version in apt list, 3.8.18) and create a venv on it? I've tried to do it multiple times, but every time I start a new pod, I lose access to python3.8 and pip. This is despite the fact that I am running my pods on a network volume, so I still see the venv, but the python installation seems to disappear. Would really appreciate some help on this!
Controlnets not working
Hey guys I have an issue with my control nets on img2img automatic1111,
I'm running a 30gb network volume on an a5000. This was my first time using this gpu and network volume. Usually I will just run a community cloud on 3090 and everything would work fine. So the issue is when doing img2img i enabled a couple of control nets which was fine, but after it generates it's not showing the previews of all the control nets under the new generation. Usually it does that, it leads me to believe that the control nets aren't working. Also I tried removing all the control nets and results were the exact same. And the AI styilization is barely there, with or without controlnets. When im running community cloud on a 3090 the generations are good, adding lots of styilization and also showing the previews of control nets under the new gen.
Thanks! Please feel free to ask for any extra info...
No longer able to Use Jax on H100 machines
Hello, today I am no longer able to use Jax on newly launched H100 instances (yesterday was fine). I am following the usual install instructions:
pip install --upgrade pip
pip install --upgrade "jax[cuda12_pip]" -f https://storage.googleapis.com/jax-releases/jax_cuda_releases.html
...
Detected kernel version 5.4.0, which is below the recommended minimum of 5.5.0
Hi team, am getting the following error when running my phi2 model on a 2xA100 machine:
Detected kernel version 5.4.0, which is below the recommended minimum of 5.5.0; this can cause the process to hang. It is recommended to upgrade the kernel to the minimum version or higher.
is there anything am missing?...
Could you please implement template credentials functionality for python SDK
I've faced the next issue. I want to create templates and run the pod from that template using code.
It's super useful for us and might be useful for other developers to:
- add some method to create credentials runpod.create_container_registry(name, username, password) that return container_registry_auth_id
- add method to provide container_registry_auth_id to runpod.create_template()
...
download problem
We try to download any model to work with stable-diffusion, for example specifically from this link: https://civitai.com/api/download/models/132760?type=Model&format=SafeTensor&size=pruned&fp=fp16.
In the JupyterLab explorer, a shortcut to the file we are uploading immediately appears, and a wget-log document, which instead of percentages as before, shows immediately that the file has been uploaded, although apparently this is not the case, because when working in HTTP SERVISE PORT stable-diffusion does not switch to it when selecting the uploaded file (already renamed to the .safetensors format we need).
Previously, the wget-log file showed download percentages, and after a full download up to 100%, the downloaded file would have the date of the last change changed to a month ago or two months ago. Now there are no percentages in the document, nor does the file itself change the date....
Azure speech services on runpod
Hey, I am running on /workspace a script perform speech with two options including speech services of Azure. Given that this script works correctly in ml azure and in local, the azure option does not work on runpod. I set up the same conditions (environment, same script, same inputs) to ensure that the test is not biased. NEEED HELP !!🙏
Stable Diffusion ComfyUI: Error while deserializing header: HeaderTooLarge
Hello! I get the error:
Error while deserializing header: HeaderTooLarge
This is while loading a checkpoint in ComfyUI for Stable Difusion... ...
How to run ComfyUI on RunPod?
Hi, I started with the whole Stable Diffusion recently and running ComfyUI on my M1 MacBook, which is quite slow for this use. I'd like to run the ComfyUI on RunPod, but I don't have any idea how to set it up and don't know if it's possible to download there custom nodes, my own checkpoints and loras from civit.ai etc. Could you please give me some newbie tips on how to install it there and what to do at first? Thank you a lot!
"Host is Down" error
Hey all, currently have an issue with the Ultimate Kohya Webgui Stablediffusion template. Running it as usual but the last couple of days it hangs and says
"System has not been booted as systemd (PID 1)
Host is down"
...
Automate pod&template creation
Hi, runpod.io team! I wan't to create a script that will pull my image from AWS Container Registry Service and from that template create a runpod instance.
The problem is: I'm using
aws ecr get-login-password --region eu-central-1 command to get my temporary password and not sure if my template will be available in the future. Do you have any suggestions?
Thanks...Servicio no iniciado
Hello, would anyone understand why I can't start the service? I am new to this and I can't find a way to solve it, I need to use port 5001...
