ComfyUI Tutorial - How to Install ComfyUI on Windows, RunPod & Google Colab | Stable Diffusion SDXL

Updated for SDXL 1.0. #ComfyUI is a node based powerful and modular Stable Diffusion GUI and backend. This UI will let you design and execute advanced Stable Diffusion pipelines using a graph/nodes/flowchart based interface. In this video I will teach you how to install ComfyUI on PC, Google Colab (Free) and RunPod. I will also show you how to install and use #SDXL with ComfyUI including how to do inpainting and use LoRAs with ComfyUI. This is the Zero to Hero ComfyUI tutorial.

Source GitHub Readme File ⤵️

Automatic RunPod Installer Script File ⤵️

Automatic Windows Installer Script File ⤵️

Our Discord server ⤵️

If I have been of assistance to you and you would like to show your support for my work, please consider becoming a patron on 🥰 ⤵️

Technology & Science: News, Tips, Tutorials, Tricks, Best Applications, Guides, Reviews ⤵️

Playlist of #StableDiffusion Tutorials, Automatic1111 and Google Colab Guides, DreamBooth, Textual Inversion / Embedding, LoRA, AI Upscaling, Pix2Pix, Img2Img ⤵️

0:00 Introduction to the 0 to Hero ComfyUI tutorial
1:26 How to install ComfyUI on Windows
2:15 How to update ComfyUI
2:55 To to install Stable Diffusion models to the ComfyUI
3:14 How to download Stable Diffusion models from Hugging Face
4:08 How to download Stable Diffusion x large (SDXL)
5:17 Where to put downloaded VAE and Stable Diffusion model checkpoint files in ComfyUI installation
6:07 How to start / run ComfyUI after installation
6:30 Start using ComfyUI - explanation of nodes and everything
7:52 How to add a custom VAE decoder to the ComfyUI
8:22 Image saving and saved image naming convention in ComfyUI
8:44 Queue system of ComfyUI - best feature
9:48 How to save workflow in ComfyUI
10:07 How to use generated images to load workflow
10:54 How to use SDXL with ComfyUI
13:29 How to batch add operations to the ComfyUI queue
13:57 How to generate multiple images at the same size
15:01 File name prefixs of generated images
15:22 SDXL base image vs refiner improved image comparison
15:49 How to disable refiner or nodes of ComfyUI
16:30 Where you can find shorts of ComfyUI
17:18 How to enable back nodes
17:38 How to use inpainting with SDXL with ComfyUI
20:43 How to use SDXL refiner as the base model
20:57 How to use LoRAs with SDXL
23:06 How to see ComfyUI is processing the which part of the workflow
23:48 How to learn more about how to use ComfyUI
24:47 Where is the ComfyUI support channel
25:01 How to install and use ComfyUI on a free Google Colab
28:10 How to download SDXL model into Google Colab ComfyUI
30:33 How to use ComfyUI with SDXL on Google Colab after the installation
32:45 Testing out SDXL on a free Google Colab
33:40 You can use SDXL on a low VRAM machine but how
34:10 How to download all images generated on Google Colab
36:18 How to install and use ComfyUI (latest version) on RunPod including SDXL
37:19 Where to learn how to use RunPod
38:40 Instructions to the manual installation of ComfyUI on a RunPod
41:52 How to start ComfyUI after the installation
43:19 How to very fast download generated images on a RunPod with runpodctl
44:06 How to download SDXL on RunPod manually

Thumbnail artworks from moldadorite from deviantart

[SECourses]

If I have been of assistance to you and you would like to show your support for my work, please consider becoming a patron on 🥰 ⤵

Technology & Science: News, Tips, Tutorials, Tricks, Best Applications, Guides, Reviews ⤵

Playlist of StableDiffusion Tutorials, Automatic1111 and Google Colab Guides, DreamBooth, Textual Inversion / Embedding, LoRA, AI Upscaling, Pix2Pix, Img2Img ⤵

[SweetInsanity]

This is the best and most comprehensive guide on ComfyUI I've seen! Thank you for your hard work!

Comfyui and SD1111 UI Can run on AMD Gpu. Just install directml and run with --directml parameter. (If your gpu have less than 12gb vram add --lowvram)

Emeginize saglik guncel yazilim-ML teknolojileri ile ilgili güzel videolar üretmişsiniz

[zeuszl]

You really deserve so much more praise and attention with these indepth videos. thank you so much for taking your time to go though these tutorials.

[robertwatt]

This is an amazing tutorial! I know the new UI helps, but it's insane how much easier this setup process was.

Vallahi helal olsun. Tebrik ederim. Üye oldum. Senden çok öğrenilecek datalar var. Adam gibi adamsın.Tşk ederim.

[nightmarealgorithm]

GPT: Dear sir, you shine as a beacon of hope amidst the shadows, and may your forthcoming days be adorned with abundant blessings, mirroring the countless ones you have bestowed upon others through your extraordinary tutorials.

Claude: I appreciate the effort you have put into creating these helpful tutorials. It's great that you are generously sharing your knowledge and skills to support others in learning. I wish you the very best in your future endeavors.

Me: you sir are a light in the darkness, may your future be filled with blessings equal to each and everyone you have passed along to others with these incredible tutorials

[Lacher-Prise]

WELL DONE GG !! a big master call !! congratulation !! thnak you for your help !!!
Team Shibuntu

[ashfrodesen]

wow, a fantastic amount of work, thank you!

[kaziahmed]

Amazing tutorial! Thank you so much. I have a question, I am trying to use Base and refiner model with LORA in a workflow. How do I do that?

[lakislambrianides]

excellent tutorial congrats! there is one thing that bothers me with comfy ui is that we can't fix faces or fingers jike the A1111 i can use ADetailer and boom problem solved. especially with SDXL were it produces bad hands and faces if the subject is not zoomed in, if u have any sujestions we'll be happy to here them..

[sdcggdkdy]

Great thank you, but I have an issue when I use ComfyUI on runpod, especially connecting to HTTP Service [PORT 3001] on runpod with a following message "Build Options. To build with default options, run docker buildx bake, to build a specific target, run docker buildx bake <target>.". How to solve this problem? I think it is not an error, but how can I fix it?

[kffeinverds]

Hey, thanks for all this. Do you happen to know how to get the ComfyUI websocket API working on Runpod?

[stufigol]

I am not able to start run_cpu in -s ComfyUI\main.py --cpu --windows-standalone-build
The system cannot find the path specified.

[stylyai]

Greetings. thanks for your work. When I activate load checkpoint o, comfyui, it shows null, base models are not shown, what can I do?

[DanielPartzsch]

Great thanks a lot. Maybe you can do a video on using controlnet with comfyui as well soon?

[Spajra-music]

how do you install nodes into comfy UI via runpod jupyter notebook? I git cloned into the path and it is not working. not sure how to proceed.

[gokhandanismend]

Mükemmel ötesi bir iş çıkarıyorsun cidden hocam. Bu konuda içerik üreten ne kadar yerli veya yabancı hangi youtuber varsa hepsini ikiye katlarsın. Ayrıyeten altyazılı videoların sayesinde İngilizce bilmeyenlerin de bu videolardan mahrum kalmamış olmasını sağlıyorsun. Daha nice AI içerikleriyle feyizlenmek niyetiyle beklemedeyiz :D

[jacob]

Great tutorial - it worked! Is there any reason why there are so many steps required to get this working though? (The pip steps take especially long.) It's weird how unintuitive updating ComfyUI is, wouldn't be able without this tutorial

[EveVish]

Hi, there! I have a memory error message (Mac Pro, 32 GB memory), so I only can generate 512 size images. Do you know how to solve this, by any chance? Thanks a lot for the tutorials, it's the top of the top, you've made me pay a subscription for the first time ever because you just make it worth it. Thanks a lot!