Awesome, so glad you found it helpful :)

Sure it's definitely something I can look into :)

They probably won't ban SD because they have limits in place such as the 4 hour GPU limit per day.

Great question! Yes that's what I am working on now. Should have a video up soon. To run an API with high availability though it won't be free. Will need to pay for the GPU, although you can use a serverless GPU service like runpod to host the api

Awesome well I am looking forward to that!

Hey! I was wondering about your thoughts on this. I see jupyter notebooks docker composes out there. I wonder if this can also be an option, and somehow use a docker image to access the GPU locally and skip the whole AWS thing. It's probably not scalable but just wondering if this is something you may have tried...

​@@toshvelagawhere we found your API related video?

I got this as well. Any luck fixing it? @toshvelaga can you help please? it's possible it needs python 3.10 but sagemaker won't allow that...

yes, you need to terminate your previous ngrok connection. for some reason it did not disconnect. you can disconnect it by logging into your ngrok account and i think you can see the current session underneath Tunnels / Agents. If you terminate the active session you should be able to open up a new connection

this is what appears to me: Traceback (most recent call last): File "/home/studio-lab-user/stable-diffusion-webui/launch.py", line 48, in main() File "/home/studio-lab-user/stable-diffusion-webui/launch.py", line 44, in main start() File "/home/studio-lab-user/stable-diffusion-webui/modules/launch_utils.py", line 465, in start import webui File "/home/studio-lab-user/stable-diffusion-webui/webui.py", line 13, in initialize.imports() File "/home/studio-lab-user/stable-diffusion-webui/modules/initialize.py", line 36, in imports shared_init.initialize() File "/home/studio-lab-user/stable-diffusion-webui/modules/shared_init.py", line 40, in initialize from modules import styles File "/home/studio-lab-user/stable-diffusion-webui/modules/styles.py", line 9, in class PromptStyle(typing.NamedTuple): File "/home/studio-lab-user/stable-diffusion-webui/modules/styles.py", line 11, in PromptStyle prompt: str | None TypeError: unsupported operand type(s) for |: 'type' and 'NoneType' (studiolab) studio-lab-user@default:~/stable-diffusion-webui$

Whenevr I run this command python launch.py --listen --xformers --enable-insecure-extension-access --ngrok NGROK_AUTHTOKEN... It gives me the error python: can't open file '/home/studio-lab-user/launch.py': [Errno 2] No such file or directory

hey there thanks for the kind words and apologies for the late reply, would you be able to type the following into the terminal: ls ls will list all the files and directories. Can you check that there is a launch.py? If not you either don't have the files or are in the wrong working directory

@@toshvelaga Thanks man...... I was able to fix the issue. It was like you said I was in the wrong directory. Btw I am trying to run Comphy ui on Sagemaker Studio Labs can you please make a guide on that or guide me to some resources

​@@rishabhsingh1406 Hi. I've been getting the same error. Think you can explain the steps to work around it in laymen terms?

Hey has more than enough GB to download several models + Automatic1111. I believe there's 15 GB for free. No you won't need to restart downloading, everything is saved automatically.

Cool. Then how do I run it?

Because judging from your video, you just installed a1111 without telling us how to run it again after downloading it for the first time (like when you want to start a new session after a day or two). Would appreciate it if you made a video about it

@@nelsonaruobebh3020 Ok i see what you mean. Once you already have it downloaded, to run the web ui just run this command and replace NGROK_AUTHTOKEN with your own token from ngrok: python launch.py --listen --xformers --enable-insecure-extension-access --ngrok NGROK_AUTHTOKEN

​@@toshvelagathanks 🖤

have you got any solution??

Hey, this page might helpful has info on storage/RAM and limitations: studiolab.sagemaker.aws/faq

Thank you. I got my account and running an instance within 12 hours. Some users have reported problems getting the runtime to load, and apparently, the Captcha was to prevent bots and scripts from consuming the compute for users. There are a limited amount of computational resources available but hopefully, they will expand the free tier as more people continue to use it. @@toshvelaga

Make sure you have the automatic code downloaded from github.com/AUTOMATIC1111/stable-diffusion-webui. And then once you've downloaded it, you need to cd into the newly created folder with the automatic1111 code. If you've already downloaded the code, it's likely you are not in the directory.

Yup, everything is saved including any models you download, all you have to do is log back in and run the python command with ngrok

Thanks a lot

I believe so as long as there is a GPU. A GPU is all you need, it can be any type of notebook

It means they don't have any gpus free at the moment. You will have to try again a few times. I usually get the same message but try again every few minutes

@@toshvelaga Its working! After many attempts, it's working now! Thanks so much!

Awesome! Glad you got a GPU :)

but space is very less so delete the photos and unused models.. regularly

true, its better to put in mind the model required for the work needed to do, also the download and setup can be do in cpu saving some time@@sidheart8905

Will probably make another vid on extensions. Not familiar with roop, but it looks like there is installation instructions on the github page: github.com/s0md3v/sd-webui-roop

Same how like adding models, but in Lora folder

yeah, it's sometimes hard to get a GPU. What I usually do is just keep spamming trying to connect with the GPU runtime until i get it. If I can't connect in a few minutes, I'll just come back in an hour or so. Wish they had more GPU's available but i can't complain since its free 😅

@@toshvelaga so.. can I run webui on AWS free tier? free tier supports GPU??

yup, it should be free and you can connect with a GPU using sagemaker studio@@AfterDinnerCafe-ld4tb

Hey good question, I haven't used fooocus UI before so not sure what the exact steps would be, that being said you can still use the GPU from sagemaker studio

@@toshvelagaif you don’t mind will you be able to make a tutorial on fooocus web ui, how to use it in the Sagemaker studio lab ? I’m not a programmer I just followed your steps but automatic web ui seems complicated and need to upload lots of other things to make it work. Where as run diffusion comes with many preloaded models

Hey I think ngrok is still free, I just checked their website. Where does it say they got rid of the free tier. If they did I gotta find a new tunneling service haha :)

@@toshvelaga Since January 2024, it has a 1GB/month limit, which for me runs out after using the notebook once or twice. And then it asks you to subscribe or wait for next month to be able to keep using it for free. I heard about zrok, but have not been able to make it work, and decided to ask you (:

ahhh i see thanks for clarifying. that sucks i guess ngrok is desperately trying to make money. I havend heard of zrok before but will check it out@@gianluca-aries

Sure, I can look into it. Haven't actually used Kaggle before but will take a look

You are on the GPU runtime right?

@@toshvelaga yup

@@Messi-ny7ub so I don't know how to solve that error personally, I did find this tho: github.com/AUTOMATIC1111/stable-diffusion-webui/issues/1742 maybe try running with --skip-torch-cuda-test

@@toshvelaga thx

Actually good idea, I've seen a Google Collab notebook floating around. But will do.