Видео

Not sure I sent a thank you last time but this very tutorial got me into SD generation and.....I'm stuck in this rabbit hole. Thank you.

You are the best !

My question is why did you put the Schell and NF4 models in the checkpoints folder and not in the UNET folder?

So i followed all your step by steps to generate a generic video of a woman walking (basically in the prompt i wrote: a woman walking) as simple as that, negatives were: blurry, noise, deformed. I went with a very quick prompts just to test it out. Video came out horribly terrible, it's pretty much as if 20 buckets of paints were tossed in the air and splashed on the ground. that's the video i got. i tempered a little with the cfg etc... (You know, self exploit) but it didn't get worse , the video was still (the paint example lol) with extremely minor improvement however nowhere a very clear / detailed / high res video of a woman walking . Any tips / ideas/ or suggestions? thank you

How to bring up cpu, gpu and ram diagrams in comfyui?

This video is incredibly helpful! You’re a lifesaver!

My friend, thank you so much!

New member, I want to ask if you have a discord if there is a work flow, I want to know how to bring up a preview of the image in ksampler like that when generating something like that my ksampler does not exist and only exists in ksampler (efficient) is that the usual ksampler you use? Can give you a way how 🙏

The path does not seem to work with in a Linux environment. I've posted to the GitHub to see if they have any suggestions wonder if anyone else has had this issue

in 10:35，three icons: (from ChatGPT) 1.Triangle: Executes the group's nodes and processes the workflow inside. 2.Bypass: Skips the group's execution and directly passes input to output. 3.Mute: Executes the group's logic but blocks its output from affecting downstream nodes.

What a great tutorial 🌟

Guys please a Need help I am beginner and I dont understand how to solve this problem, please help me step by step : I have this message >>>> mat1 and mat2 shapes cannot be multiplied

A timely update and replay video. Even the icon size in the file explorer is set to the largest so that the text can be read more easily. A small but important detail. You are really good at your job and you are constantly improving yourself. Congratulations. 👏👏👏

I watched the first episodes so far and this tutorial series is awesome. I am running a PC with an AMD 6800XT GPU and started with comfy a couple of days ago. It was a bit tricky to get this running with AMD and I don't recommend it. What I like about the tutorial is the fact that you repeat certain steps throughout the videos so I don't have to memorise everything at once. Congratulations for this approach. I couldn't do it better. From what I've seen so far there's only the lora training missing, not sure if this inpainting stuff comes later. However, lora is probably a topic for more than one video (SDXL, FLUX, extern vs. inside comfy). But it would complete the tutorial, even though there are already tutorials on RUclips about lora.

ComfyUI's grouping is quite impressive, thanks for the tutorial.

There's no SVD tab in my forge UI, although I used the latest version. However, I installed reForge UI and SVD tab is here.

Great tutorial, thank you! I like your pacing.

Thank you so much for your work!

This is extremely helpful and very well explained. Thank you!!!

Thank you for your teaching, it is really comprehensive. Really includes lots of info. and worth watching it till the end of the tutorial

Great overview. Question: do you know if there's a way to use both depth and canny loras at the same time, effectively?

Excellent tutorial well calibrated for the audience. Great work!

Great content, thanks. Do you know why the previous recent videos have an audio track option, but this one doesn't?

Thank for this pixaroma! Liked and subscribed! And I'll watch the whole playlist if I can!

Thanks! I learned a lot about comfy ui in a short amount of time. Keep the good work.

Thanks. Great series.

how we can share the .gguf file for the unet nodes and Serge nodes? the require do place the files in different folders, and i think its not cool copy/paste a 14 gigabyte of flux Q8 in both folders.

AI generated voice? jiggabyte... ????

Thanks, love it.

Thank you making the journey of learning comfy so easy to understand. These tips are really useful.

Thank you bro

"I use flux because it understands longer prompts". Haha Bad. Flux is proprietary, so the tips given here are not applicable in practice. Trying to achieve similar results with less potent models will essentially mean following other tutorials.

very clear explaination for the CK, Good tutorial😁

GREAT stuff as always!

Awesome video, thank you. But the last tip ruined it. Please do not do this, folks. Learn at least basics the old school way before blindly rely on chatgpt...

Perfectly explained ! Thanks. I can at last move from Forge to Comfyui for Inpainting thanks to your tutorial and this stich and crop tool 🙂

great video!,

FWIW, unless I missed some critical changes to architecture or tooling, inpainting models should ONLY be used with a full denoise strength of 1.0. Standard inpainting workflows feed pure noise in to the masked area, and inpainting models generally do very poorly at img2img. If you want slight modifications, you will have much better luck and much more control using standard models with img2img workflows and a low denoising strength anywhere from 0.3-0.9 depending on the model and situation

I’m desperate for learning properly how to train a Lora, any chance you will do a video about it?

You’re the best

thx so much for all your work. Its helps me a lot

Thanks!

I added crystools but it’s not showing the colored progress bars even though it’s enabled. Any ideas? I’ve tried refreshing and even restarting ComfyUI. No bueno. I see the names and percentages though.

I counted 27 Tips. More than 10 are new to me. So, thank you very much! 😊 PS: I hope it is ok, if I review the video from time to time, to remember. 😄

Great tutorial, works exactly as described. As you mentioned the first few clips are a bit off and improve with further iterations. Looking forward to seeing how the technology improves! Thanks for posting.

💥💯💯💯 Thank you. Your channel is the best on the internet on this topic. And this video is very useful. Without further ado. Very informative. Thanks again and may your good intentions always succeed. 💯👍🤝

Thank You. This EP is extremly useful for me. Thank you so much.

The person who explains things in an ideal, easy, and simplified way after we've learned them from messy, random, and chaotic sources. Keep up your enjoyable lessons.

Danke!

Much helpfull as all the series. Thank you for Your time, that is much appreciated