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

The link has been changed! Please, we need another video.

When i get to the part where you're supposed to put in the endpoint/password, I copy it directly from what the notebook creates and it tells me its the wrong password. Any idea why this would happen?

Would you ever consider doing a tutorial specifically on running Warpfusion or Animatediff on Runpod?

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!

Why do i need token when i use colab version? it works without it

Hello, I installed ComfyUI through Runpod. I was able to get into ComfyUI. However when I click Queue Prompt I get an error. it says KSampler Error. What can I do to fix this issue?

Merhaba, ComfyUi ' da Animatediff Google Collab ile kullanılabiliyor mu, bununla ilgili bir video çekebilir misiniz

Hi there

Can I just use the Confyui template on runpod instead and skip the last steps ?

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

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

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

So when I starting SDXL 1 using Googel drive I created, how do I reopen the comfyUi using Google drive. What file should I run?

I installed ComfyUI on Colab.
But how do I update it when they apply updates?

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

Where do I find the test9.safetensor (Lora) you use to generate an image of yourself in a colliseum with an armor on ?

Fantastic amount of work. Thanks for sharing. Wondering, in runpod, I would like to load a custom workspace but when I click load it points to my actual local computer and not the pod. I would like to open a file on /workspace/ComfyUI/custom_nodes
Is there a workaround? Thanks again.

I see the is a vae file sd_xl_base_1.0_0.9vae.safetensors is there any advantage in downloading that one ?

question - is there a way to export to code the comfyUI pipeline/workflow and productionise? E.g. if I build an app and want to save a workflow for users to interact with

you are a fucking gangsta this is so lit

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

Thanks this was really useful

wow, a fantastic amount of work, thank you!

Thank you for sharing the SDXL_1 workflow. Being able to generate images with just one click through the base and refiner models is amazing. I wanted to modify the batch size to generate multiple images at once, but the modification doesn't seem to work. Each queue still only gets one image. Why is that?

i can not believe how this guy cons people into paying for stuff that is free and open source..

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

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?

Is it possible to use SD Ultimate uspcale, HiRefix and Lora n ComfyUI? at the same time.

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

You made a 47 minute tutorial for "Download the model and put it into the folder"

Hello Sir. I need your Help please I am despairing. Sorry for the comment but i dont know how i can contact you. Everything works fine but inpaint i cant get to work. always the same "Runtime Error: Sizes of tensors must match except in dimension 1. Expected size 1 but got size 2 for tensor number 1 in the list.". i tried really everything but i am not so confident with python to edit the half of the code how someone suggested to me on py.torch forum. Size with an multiply of 64 is all known to me and wasnt a solution. also i have no unresolved dependencies, on this site everythig is fine. Ive got a 3090 OC and i9-12900k. Best Thanks in advance

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

sicko

Lve your videos, wanted to let you know that the word "queue" is pronounced just like the letter "Q" (i.e. kyoo).

Dear ser, thank u for these tutorial

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.

Like i always say to you. Great job!!
You could teach how to use RVC (Retrieval-based-Voice-Conversion) or other audio "clone".

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..

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

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

i just want to ask as someone who has 2070s 8gb vram. should i wait for optimizations? i want to train my face in xl too.