วีดีโอ

Great content, as always! I need some advice: My OKX wallet holds some USDT, and I have the seed phrase. (alarm fetch churn bridge exercise tape speak race clerk couch crater letter). How should I go about transferring them to Binance?

You’re a phenomenal teacher thank you so much. I would really like to see content that covers video and animation.

Thank you for bringing the theory. I've been dying for content of this nature. Amazing work.

for users of comfyui: Your bundle of models and loras strike me as the perfect complement to YanWenKun's version of ComfyUI Portable with preinstalled nodes. The 3 part zip file on YanWenKun's github gives me portable comfy with insightface etc. etc. installed, resolved depencies - without the models. Your IP Adapter bundle supplies all the relevant and up to date IP Adapter models, which are a pain to sort out.

"(Part 3 of 3)" ---> Sniff. I have really enjoyed your videos so far - you sure there is no way we can bribe you to keep on going? Though I'm sure you have your reasons. Making these videos is very time consuming, and there has to be some pay-off on the horizon. Then again - if ComfUI should pull it off to become the Blender of AI image and video generation, investing into the tedious and painfully SLOW process of increasing follower numbers now might pay off in the future, "the first ones become the big ones". Easy for me to say, since I don't have to put in the work :)

"I have deliberately left putting output nodes into the workflow, because you can use it to control how far the workflow gets executed." (paraphrasing) --> So obvious now that I heard you spell it out - and yet, I hadn't thought about that before

what is the minimum GPU VRAMs required to run ComfyUI bro ?

Since there is so much to learn, I feel like I am kind of swimming, in so many respects. I kind of improvise my way through. I had noticed that comfy and forge produce different images, but I had no idea why. I have no idea where comfy actually gets its images from, when using the standard "Load image" node. (With "load image from path", it is clear.) For example, when I use images as reference, like when using controlnet - ideally, I would want to be able to reproduce the exact same output I got, just by throwing in the generated image. Somehow, at the moment, it seems to have no trouble finding those images. If you asked me now, how it does this, and what I would need to do to make sure it will still be able to this a year from now, I would have to say "I have no idea". The list goes on and on, I can use Comfy, and I absolutely love using it, but there are so many fundamental questions I don't know the answer to.

Your videos are so refreshingly... different. Introductory AND deep, at the same time Both videos that I watched so far gave me answer to a number of questions that have been lingering in the back of my mind for quite some time. great stuff, I'm hooked!

Segs education had me dying LOL.

Ha. I found it. In the tidying up sped up part you connected the inpainting pipe to the K Sampler for the impainting. I connected the first pipe further...This is what I wrote first:(It is funny how I get a different image than you after the inpainting into the outpainted image. My new part of the kitchen looks very different from yours. Strange.) A very good tutorial.

I didn't expect that song at the end. Nice!

Your videos are amazing Prof. I just subscribed. Thanks for this.

This looks like a very down to earth educational channel with great approach to teaching. Subscribed! :)

I am #300 sub! I learned a lot, and I been trying to get good with CompfyUI for a few weeks, thank you.

Out of over 40 (often very good) videos using ComfyUI I’ve watched this is by far the best introduction by combining an excellent overview with varied practical examples and useful tips and tricks. All in a brief and well structured format. Excellent work. Looking forward to more from you.

I absolutely loved watching this, so much valuable information in one swift "painless" go :) Now I know how to do outpainting and inpainting! I know about the ToBasicPipe node, and I know how to increase the number of suggestions when dropping a cable into the empty canvas. No time wasted, super useful stuff, presented in a super clear, easy to understand way. Thanks!

fantastic thank you

One thing to keep in mind, even if you think someone else explains a topic better than you, just be aware, to the watching individual, you might make more sense. Happens for me all the time. Love your take on topics. Thanks for posting!

Nice. Thank you.

You flip the slides to fast

Thx for the summary.

as a self-proclaimed pun aficianado, all good choices, why choose when you have the undead academic angle cornered?

THANK YOU - straightforward explanations, lighthearted and informative style, logical progression of concepts and clear, no-nonsense examples that don't insult my intelligence or flash by in a cloud of jargon or tangents. It's unfortunate it has taken me this long to find anything remotely resembling a non-biased, non-clickbait, non"hey look at me and the cool dumb thing I did" take on all this because I think it is valuable information that artist and non-artists alike just want to have to explore and learn like with anything else. TYTYTYTYTY....Please keep posting content!

The hideous, obviously AI-generated thumbnail...bleh.

1:54 The problem is that human language implies human's body experience. LLM does not and cannot have such experience, all it has is a mishmash of dictionary index on top of picture's library, therefore all efforts to explain to the machine the difference between these two pictures are futile.

I have followed everything and triple checked, but when i try to open SD through the shortcut i get "No Python at '"C:\Users\...\AppData\Local\Programs\Python\Python310\python.exe'" I installed anaconda and SD in different drives, could that be causing the issue?

Ohh here it is, time to grab a tea

still waiting for new videos my friend, flux is amazing. i would love to understand how it works and what you can do with it. comfy ui is getting amazing updates too.

excellent! :) Being able to write, even simple, nodes for Comfyui could be really useful!

Hello sir Is it possible to create a UI based on a custom comfyUI workflow? I mean is it possible to do this = 1. create and test comfyui workflow A (this workflow will run custom nodes to remove background from an image) 2. an executable in Linux, mac, or Windows (would still work even when no ComfyUI installed) when this run it will have UI like in this example a button when pressed it will remove background of images in a specified folder. or... rather than individual executable what about remotely trigger ComfyUI workflow A in CLI from client computer to a ComfyUI server? git clone remoteComfyUI sh ./remoteComfrUI. sh -d "~/Pictures/removeBackroungs" -server 192.168.255.255 -verbose 192.168.0.88 ~/Pictures/removeBackroungs/testimg1.jpeg sent 192.168.0.88 ~/Pictures/removeBackroungs/testimg2.jpeg sent 192.168.0.88 ~/Pictures/removeBackroungs/testimg1.png sent 192.168.0.88 ~/Pictures/removeBackroungs/testvid.mp4 sent 192.168.255.255 processing ~/Pictures/removeBackroungs/testimg1.jpeg success 192.168.255.255 processing ~/Pictures/removeBackroungs/testimg2.jpeg success 192.168.255.255 processing ~/Pictures/removeBackroungs/testimg1.png success 192.168.255.255 processing ~/Pictures/removeBackroungs/testvid.mp4 failed (not an image) saved into "~/Pictures/removeBackroungs/output" the idea was to help folks at home and maybe neighbor who wants just do 1 or 2 specific thing with their pictures... or... they can just keep using subscription based of canva 🙃

Great videos, great quality content! I was wondering if it is possible to create a custom node that uses code with a different python version? I want to create a cool node and I have working python codes already but it only works on python 3.7 because it needs tensorflow 1.5. Is this even possible to accomplish in comfy UI, maybe by using code in the custom node that creates a virtual environment?

awesome work! its the kind of content i hoped it would be, looking forward to the next video!

有人能确认这是否正确吗： Automatic1111: 稳定扩散网页用户界面 ComfyUI: kāng fēi yōu ài (康菲优爱)

If you have a deep understanding and can go beyond the surface and explain to people how things work below the surface to give them a deeper understanding people will listen, to many click this button tutorials. Comfy desperatly needs people that explain whats actualy going on not just click this button, for the average user to understand, so that people can then use it the way they want and might get a grasp of its capabilities. The best channel I've seen so far that does this really well is LatentVision but I wish he had the time to go even more in depth and make more videos. Thanks for what your doing, I hope this will always stay free and open for everyone to see.

looking forward to learning from you Mr. Lich!

Shoutout to the Lich family! Keep the lectures rolling man <3

10:39 I misspoke at this point: *Models (not molecules)

Excellent tutorials. I enjoyed them very much. But how do we get the skull (or any) icon in our category? Apologies if you explained and I missed that :) Please keep up the good work, and I will keep watching even though TH-cam wants to feed me Chinese content now rofl

Clearly structured and well done! Thank you for your excurse into history! 😊

Thanks, I think I'll have to go back to beginning

omg thank you for the Tuple information i never was understood what that's mean !

thank you so much, as a begginer it's hard to find some information and you are so clear and precise ! more more more plz !

Chandrasekhar was another brilliant mind India gave us (offtopic, but I will put it here). He has shown that electron degeneracy pressure is not sufficient to prevent the collapse of stars beyond a certain mass. This implied that such stars would continue to collapse into more compact objects (neutron degeneracy was not yet discovered, or fully developed at the time, I believe). His ideas caused quite an uproar, he was publicly ridiculed even...

Looking forward to your next lecture, with or without pineapple😂

I guess it is quite challinging to teach ComfyUI specialities combined with basic python. You are on the right track, your style is improving and everybody who is following your explanations, improves too! ;-)

Good job! The translation is basically available. But there are Chinese, Cantonese and English in this video, especially if you're speaking very fast. And the pronunciation and intonation are a little weird. Maybe Chinese subtitle is a better idea for Chinese speakers.

I followed your video and now I can’t even open stable difussion. I’m furious!! Why would you put information that doesn’t work. It was working perfectly until I tried this and now it doesn’t open. Whoever is watching this. Do not try this. It took me days to even download stable difussion and I had so many things added to it already. Honestly this is horrible. Do not try this video.

Hi, Bro! Please correct the link to GitHub in the description. Thanks for the content

Thank you so much for taking the time to make this video. Just one suggestion, the border and style of the background is distracting. Code can be visually confusing, adding detailed graphic elements around it can be counterproductive. Also, having a huge border around everything reduces the scale and legibility of the screenshots. I only give these suggestions in hopes that your videos attract more viewers. I really appreciate how you explain things and your step by step approach, very helpful for non-coders. 🙏