วีดีโอ

Is it possible to do it on video too?

can you plug this differential diffusion node into any impainting solution? Combined with COntrolNet for example. Edit: yes it does. Just plug in the Differential Diffusion node and you're good to go. Just that little node changes everything. What a discovery, wow

Underrated! You deserve more.

2:28 if you're using like an RTX gpu it shouldn't strain it for recording since it should use the Tensor Cores for the AI generation which wouldn't affect the processes used for encoding video

How can I restart the server once closed?

i love your speed. but i think, it is only good, if u provide the workflow - sadly i cant find it here. for your next upscaling video: if u show results, dont show them as thumbnails ;)

no viable description in reply, try regenerating }

great work

Thank you for sharing this info! Perfect install and fully up and running. I'm more impressed by the side panel customization. :) Trying to figure out that now. Def joining the Discord. Cheers!

Can you make a tutorial on inpainting with mask and IP adaptor V2 to swap a reference cloth image to a model

Thannk you verry much for your best tutorial 😍😍, what is the minimum requirement for pc to run the ComfyUI

how did you get the CivitAI option on the left? iam not having that

Üstad, ne yaptıysam comfyui içine InstandID yi yükleyemedim, fix error yazıyor ve sorunu düzeltemedim eğer eposta adresiniz yazarsanız hata görselini gönderebilirim. Yardımcı olursanız sevinitim teşekkürler.

please, slow down your videos, so talking and skipping topics, so i don't have to constantly stop and replay them countless times, going to other streams to undersatnd what you were saying, until i can finish and then listen to your next topic, followed by the same. Please, if making a tutorial, expect that people have no clue as to what you are talking about. That's what I've had to learn the hard way. So, keep your videos to the point, but, give more information as to where and how the files can be obtained as well as a guide how to do that. Just FYI. Thank you for your Videos!

Tried to join the Discord group, inside the own Discord, but I couldn't. Error, link expired. I'd like to join :/

@Aris_28 Does elevenlabs have access to the conversations; and further, what are the privacy limitations of this setup?

where is Workflow download link?

do you have a workflow where I can upload an image to be upscaled in comfy instead of relying on a prompt to generate an image from scratch?

you should consider posting a link to the workflow

Hi I am new and followed your video. I m trying to install Iterative Upscale, and click that link but not sure how to do it. Its a bit not clear. Thx

is there just a simple video upscaler

Excellent video , I have a question when I already upscale thr pic 2.5 it's original size and it's a close up portrait usually skip this part of my workflow in the console it say it's enough big or the scale and it's not possible to detect any face . What parameters should I move to bbox ans sam detect the face?

You mention Differential Diffusion but you do not explain what it is, how it works, or why we should use it.

How do you add loras in this. Also how do you control the weight of loras in this detailer node.

Bro how i use meta sam2 in ComfyUI for retopo in After Effects

Thank you so much for the tutorial 🤩 I have an error when I start I have this message : ENOENT: no such file or directory, stat 'c:\ai\pinokio\api\comfy.git\{{input.event[0]}}' Do you think I need to download something in the folder « comfy.git »? Thank you 🙏

Explaining how to actually create the character would be useful. I don't even have the "character" tab under "Parameters" and I'm guessing is because there are missing configurations that are not explained in the video. Edit: Found it, it was inside "parameters", "chat", and then the "character" tab appears. It seems to be a difference due to the version, not due to a missing step.

Thank you so much for the tutorial! Learnt a lot. Is there any way to do this programmatically? Thanks!

Can we use the same setting for video?

custom_nodes\ComfyUI-Impact-Pack\modules\impact\impact_pack.py", line 496, in enhance_face segs = bbox_detector.detect(image, bbox_threshold, bbox_dilation, bbox_crop_factor, drop_size, detailer_hook=detailer_hook)

Excellent workflow!

i see no difference between nodes, am i?

how do i just load an image...i dont find this easy at all lol

Any way to get the workflow file ?

how to prevent face detailer from changing the eye color

Nice thanks

guess its a nice HowTo - but much to fast when you combines the nodes - unfortunately not useful for me :/ anyway - thank you!

you worked hard. but your comparison method is really useless. you are upscaling and showing is passport size photo. you shoul show "actual size" comparision right ?

I'm new to this but shouldnt the Gaussian Blur Mask output be connected to the InpaintModelConditioning Input? It seems to work better this way for me at least.. Anyway thank you for the tutorial!

looking forward ComfyUI Inpainting Tutorial Part 2

Hi, I`ve noticed that I don`t have an ultralyticsDetector Provider after installing Impact Pack

Fantastic ComfyUI Tutorial you have a new SUB.👍😁

🎉🎉🎉🎉🎉senks ! You best ! Go go go ! Sorry my Englishs very bad)) I love you video 😄 Go next workflow GIF animation img.

I'm back! After a short break, I'm returning with lots of new content. Get ready for weekly videos packed with fresh ComfyUI techniques and AI art tutorials. Stay tuned for regular uploads to help you master AI-generated artwork!

I felt like a tool being intimately familiar with nodes in DaVinci, and clueless here. And none of the other 20 videos I tried explained it from the beginning. Thank you for doing so! Cheers

Great. It would be very great if you could make a video about the animate diff stuff and other movie nodes. Thanks in advance.

Pinokio failed to install because of a Java Script error. Can't seem to find any solution to it.

Wow, I hope you are a teacher, you explain this so well without taking up 2 hours in a video. Thanks so much.

I really didn't see any difference for any of them.

amazing, i thinking if it is possible by changing some weights to get a result that is a bit different from the input, for example turning an enscape raw render into a more professional one, enhancing materials and people