IS ANYONE POD STILL UNUSABLE? IT HAS BEEN 18 HRS FOR ME
I’ll be straight — I’m brokie dawg, both in time and money, and it’s been 18 hours staring at a grey screen interface.
It began with some lag yesterday, and then suddenly everything went down. Restarting the pod doesn’t resolve the issue.
I even tried creating another pod with different GPUs and settings… same issue. Three attempts so far.
What’s going on? At the very least, could someone give me an up-to-date explanation of how this is supposed to be fixed?
22 Replies
Can you plz share logs screenshot as well?
System log:
2025-10-11T15:17:27Z create container runpod/stable-diffusion-webui:7.4.4
2025-10-11T15:17:27Z 7.4.4 Pulling from runpod/stable-diffusion-webui
2025-10-11T15:17:28Z Digest: sha256:af8c696442205e102ed00e01dab9c59a7f4bc4c9a63b5833e01fec5fd770e02f
2025-10-11T15:17:28Z Status: Image is up to date for runpod/stable-diffusion-webui:7.4.4
2025-10-11T15:17:28Z start container for runpod/stable-diffusion-webui:7.4.4: begin
Container log:
Used Template:
ULTIMATE Stable Diffusion Kohya ComfyUI InvokeAI
https://console.runpod.io/hub/template/ultimate-stable-diffusion-kohya-comfyui-invokeai?id=c3wl6sp0wd
Also (on the grey screen interface link)
From logs it seems everything is running as expected. Since there are so many ports, would you mind telling which ones are not accessible? It's not possible that all of them would be inaccessible.
Weirdly, The only thing I can open yesterday is port 2999 which is for RunPod File Uploader. But I can open other ports today, except comfyui and SD A1111. These are the ports I still can't open
Today log:
is it possible to ssh and check logs in /workspace/logs/webui.log and /workspace/logs/comfyui.log ?
hmmm strange
After restarting I can go in some extra ports but they are all corrupted
I can only go to:
9090 - invoke
7777 - Jupyter Explorer
Checking on it
this one log btw:
I will try my best digging
Webui.log:
Lol, ComfyUI and Stable Diffusion are running on ports 3021 and 3001 respectively. But these ports are not exposed in the template. The template owner might have made some changes recently post which you're facing this issue. So there is no point in waiting more and wasting money on it. Either check with template owner for a fix or while creating the pod expose ports 3001 and 3021 as well
Oh my god bro
Ok bro, I tried to snake-oil my way out of it (basically trying to logically deduce my way into making it work, since I am not a programmer) by changing the exposed ports of the pod from 8888,3000,3010,3020,6006,8000,9090,2999,7777 to 8888,3001,3011,3021,6006,8000,9090,2999,7777.
And it still doesn’t work.
Eternal Loading Screne
DAMN BUT YOU ARE RIGHT
I CAN NOW CREATE NEW WORKABLE POD WITH DIFFERENT EXPOSED PORTS
RIP old pod you will be missed
😭
Is it working now or it's still loading endlessly?
Yes new pod with different exposed ports are working fine
but old pod ... not sooo much
This used to be a problem because I can't even create another pod to work on