ComfyUI - Vast.ai: tutorial - how to rent cheap high VRAM GPUs for your AI art

Рет қаралды 6,404

Күн бұрын

If you do not have a powerful GPU, you can use ComfyUI (node based GUI for Stable Diffusion) by renting a virtual GPU machine in Vast.ai.
Vast AI: tinyurl.com/5n972ran
With this method, you can create your AI art without purchasing a powerful computer, and without subscribing to expensive services. You can do it yourself, by renting a GPU and paying for the time you use it. No more, no less.
============================================================
💪 Support this channel with a Super Thanks or a ko-fi! ko-fi.com/koalanation
☕ Amazing ComfyUI workflows: tinyurl.com/y9v2776r
🚨 Use Runpod and access powerful GPUs for best ComfyUI experience at a fraction of the price. tinyurl.com/58x2bpp5 🤗
☁️ Starting in ComfyUI? Run it on the cloud without installation, very easy! ☁️
👉 RunDiffusion: tinyurl.com/ypp84xjp 👉15% off first month with code 'koala15'
👉 ThinkDiffusion: tinyurl.com/4nh2yyen
🤑🤑🤑 FREE! Check my runnable workflows in OpenArt.ai: tinyurl.com/2twcmvya
============================================================
00:00 Introduction
00:37 Table of contents
00:55 Sign up and login into Vast.ai
01:14 Select docker template for ComfyUI
02:01 Filter and select rental GPUs at Vast.ai
04:54 Installation of ComfyUI and models in Vast.ai instance
07:07 Run ComfyUI and use ComfyUI Manager
09:16 Outro
Scripts of the video:
pastebin.com/V2Un0cYW
Vast AI:
tinyurl.com/5n972ran
ComfyUI:
tinyurl.com/24srsvb3
ComfyUI Manager:
tinyurl.com/ycvm4e29
Make sure to subscribe to Koala Nation Channel:
cutt.ly/OZF0UhT
AI videos and animations
Released: 4 September 2023
© 2023 Koala Nation
#comfyui #stablediffusion #vast

Пікірлер: 40

@brgtubedev001 5 ай бұрын

Thank you for showing us how to set up this method of cloud computing. You have an excellent way of explaining the method. Good luck to you and your channel!

@koalanation 5 ай бұрын

Thanks to you for watching!

@TheFusssi Ай бұрын

Thank you :) I got it working with the pytorch version!

@koalanation Ай бұрын

Excellent! Have fun

@TheFusssi Ай бұрын

@@koalanation short catch-up -> used it multiple times now + adapted your script and it works like a charm. Thank you very much for the video, as without it I would either have spended way more time setting it up or even have given it up before getting it to work.

@koalanation Ай бұрын

@@TheFusssi good to hear!

@MusikMozaiK 10 ай бұрын

owesome :)

@koalanation 10 ай бұрын

Thanks! I am glad you liked it

@victorrochin2616 6 ай бұрын

Just what I needed! Once that I need to delete my instance and pick up my work the next day, is there a way of saving my data and pick up where I left later in another instance?

@koalanation 6 ай бұрын

You need to synchronise with Dropbox or Blackblaze. Last time I checked with Google Drive did not work. You can always stop the instance, but you have to pay full price, unfortunately. Alternatively, you can transfer files from a local computer via SSH or use another cheaper instance for storage, but then you depend on the owner of the instance.

@momoe7563 9 ай бұрын

Great tutorial, do you think it's possible to edit the template for it to automatically install comfyui with the user going into Jupiter?

@koalanation 9 ай бұрын

Thanks! I think it should be possible to make a jupyter notebook from the script. I tried at some moment but I had some issues and decided it was faster to directly just copy and paste the script in the terminal. I have the code in a Google Docs document, which I use every time I want to use vast.ai

@alexlindgren1 9 ай бұрын

Thanks for this! I want to set up a ComfyUI API instead, so I can send a request from another server and retrieve the generated images, how would you recommend me doing this?

@koalanation 9 ай бұрын

This is a little beyond my expertise. I have seen a tutorial for stable diffusion A1111 with endpoints for runpod. Maybe you want to look at it to get some ideas how to do it for comfyui.

@CristGhazarian Күн бұрын

hi, do you still recommend to use it now?

@koalanation 23 сағат бұрын

Hi! Nowadays, I normally use runpod with network storage. I do not need to reinstall nodes and models every tme. Installation in runpod is almost identical. However, I still use vast to test some new or experimental custom nodes, or for training. It is still cheaper, so I prefer long sessions with vast.

@prasanthrajappan4401 10 ай бұрын

how can i have an api to this set up to access it externally

@koalanation 10 ай бұрын

Hi! I am not a technical person, not sure of what your question is. In vast.ai there is some documentation about API. I understand access to the VM can be done via SSH/SCP but I just simply download the requirements via git clone and wget, and use jupyterlab to upload/download from my local machine . Access to Google/drive and Dropbox is possible, but I have not used it. Sorry I cannot help more.

@Vinesh1010 8 ай бұрын

Stable diffusion fast is missing from the template

@koalanation 8 ай бұрын

Try with the pytorch template.

@AIWarper 9 ай бұрын

Do you have to do this literally every time you launch? Also, there is no "fast" template anymore

@koalanation 9 ай бұрын

If you destroy your instance at the end of the work to keep the costs low, yes. Alternatives are to using your cloud storage or to create your own docker container with the basic models and nodes you normally use. Instead of the fast template, you can use the pytorch template.

@AIWarper 9 ай бұрын

@@koalanation how would I go about the latter (creating the docker)?

@koalanation 9 ай бұрын

@@AIWarper if you are using a 'base' of models and nodes and not changing many things, I think it should not be very difficult to create an image, if you know how to use docker. I have not done it myself, though. If you like to try things and you have good reference workflows, I think the fastest is to only install ComfyUI and ComfyUI manager, then use the install missing nodes feature from the manager, and install the models with the manager too. But yes, the cheapest solution may not be optimal if you want not to run these scripts anytime.

@Mindset2Work 8 ай бұрын

Is the choise of the preprocessor / cpu important?

@koalanation 8 ай бұрын

To be frank, I am not sure. I try to use what is available and so far my needs are covered

@yasinaydn763 4 ай бұрын

can you share scripts again? pastebin is not working.

@koalanation 4 ай бұрын

Hi! It works for me...🤔 Anyways, I think I may need to update it. To begin, you can use more general templates, new versions of pytorch, etc...I think it is also valuable to connect to have the models/files in backblaze and sync it, instead of downloading everything every time. Takes the same time, but at least you keep the work....

@2DPTuts 3 ай бұрын

i wonder if its possible to get this to run on krita

@koalanation 3 ай бұрын

There is a guide with a Krita template for runpod or vast.ai: github.com/Acly/krita-ai-diffusion/wiki/Cloud-GPU Never tried, though

@Scramit 8 ай бұрын

why i don't have manager in your interface?

@koalanation 8 ай бұрын

In the script the manager should be installed. Anyway, follow the instructions in the GitHub: From the ComfyUI folder 1- cd custom_nodes 2- git clone github.com/ltdrdata/ComfyUI-Manager.git 3- Restart ComfyUI