Ferniclestix

Пікірлер

@AndroKarpo 6 күн бұрын

Does not work CLIPSeg: Input image size (352*352) doesn't match model (224*224)

@antimczenko 9 күн бұрын

first. the video is great. second. can you explain the purpose of prompt module? cause for me it looks like excessive complication. i mean... instead of just write some stuff in the negative/positive field you should create the bunch of nodes, that generate the same thing, but with selectors you can't choose, and just...why? or i didn't understand something?

@djroastbeef1 9 күн бұрын

These videos have been amazing for learning comfy! I was always curious but avoided it because of how complex it is. I've finally been able to progress with it and it's been a lot of fun. Thanks so much for making this and the other series!

@The-Retoucher-Studio 9 күн бұрын

Hey Fern, thank you for the amazing tutorials. What do you think about converting the start at steps to inputs this way it's easier to modify them when modifying the switch source?

@The-Retoucher-Studio 10 күн бұрын

Thank you for the detailed tutorials. Question, how did you learn to do all that? What are you references? Are there any blogs or books that someone can refer to?

@artgainz 12 күн бұрын

Help! I am at a loss how to find the lora you're using! I can find other loras, just not that one.

@artgainz 11 күн бұрын

I got this working for me with the "get photoshop" node instead of that screen capture thing. Also could not find that lora. That thing where the teeth appear in the clouds also did not happen for me.

@kira7x2 20 күн бұрын

thanks a lot friend that exactly what i needed

@1lllllllll1 26 күн бұрын

0:42 finally a genu8nely skilled author! This is the first tut I’ve seen on the topic that clarifies on the outset that this is much more efficient in a trad editor, and really makes only sense to do in comfy if you need automation.

@ChuckPalomo 8 күн бұрын

I mean, automation is like the whole point of AI.

@DarthAlex666 Ай бұрын

@ 12:57 , what do you mean, "You people?"

@Ozstudiosio Ай бұрын

your are unique in videos subjects you did

@ddenizc Ай бұрын

wow man you are a work of art yourself.

@PhantasyAI0 Ай бұрын

Thanks man been searching everywhere for this!

@MegaGovert 2 ай бұрын

Tank you, for the tutorial and also for including the workflow, that´s so handy.

@eltalismandelafe7531 3 ай бұрын

I hope your health improves. Thank you for coming back and sharing your wisdom and generosity. We missed you

@CsokaErno 3 ай бұрын

Hello there. I have just found your channel with a lots of Comfy tutorial. Do you have any advice which order I should go through your lessons? Thank you.

@jorvax3744 3 ай бұрын

You are the savior of saviors, you know how much i've been searching for a GOOD workflow of character consistency, 2 WHOLE MONTHS, and you just were the key to that problem, tysm you can't know how much you helped an unknown fella btw do you have a flux version of this same workflow?

@ferniclestix 3 ай бұрын

check out grocksters channel, he recently did a control net flux workflow, unfortunately I don't have a good enough graphics card to make use of flux control net, it requires too much ram.

@davidvce5035 3 ай бұрын

integer and text box missing nodes

@TohkaTakushi 3 ай бұрын

I was watching this wanting to learn more about the actual components and found all your clean lines connecting modules so satisfying. Thanks for the video tutorial.

@kusacubari1867 4 ай бұрын

no comfy workflow video Ive seen yet (and Ive seen a few) gave me so many rewarding tips and insights, and best of all clean fast optimised workflow. What a gem this video is. Hope you do more like this, great work sir!

@ferniclestix 3 ай бұрын

happy to help :D

@ahmedsheeraz 4 ай бұрын

very nice tips thank you

@1lllllllll1 4 ай бұрын

Big thanks for this video! It really showcases the serious limitations of comfy as an interface for artists. It’s great tech, but it’s super limited. Thankfully, enterprising developers are building bridges to photoshop, so we can quickly build the composition then run the generation on the composition.

@ferniclestix 3 ай бұрын

yah, once you sort out integration into an art program things become much more useful. unfortunately there is still a huge lack of control on the users part.

@1lllllllll1 4 ай бұрын

I love that your insomnia is my learning benefit, lol. 4am 🕓

@ferniclestix 3 ай бұрын

:P im one of those weird people who is more active at night.

@TUYGVISUALCREATIVES 4 ай бұрын

your tutorials are awesome! thanks

@ferniclestix 3 ай бұрын

happy to help :D

@bakablitz6591 4 ай бұрын

underrated tutorials! hope your better now

@ferniclestix 3 ай бұрын

unfortunately my health issues are the kind that end in transplants and lots of visits to hospitals. not to be depressive. Happy I can be of help tho! :D

@cives 3 ай бұрын

Hi, I was in the same situation and now I have a nice normal life after the transplant. I will be deepening my recent acquaintance with the AI and ComfyUI thanks to your excellent tutorials and workflows. Keep the good job! ¡Y mucho ánimo!

@mat5844 4 ай бұрын

Really appreciate your videos. This spanish-speaking youtuber love your videos a lot too lol kzbin.info/www/bejne/jJioamynjpeJia8

@ThePetroale 4 ай бұрын

Hi there, this is old enough but I hope someone will point me in the right direction. When I try to use UltralitycsDetectorProvider I get a red cross of the SEGM detector. Can somebody help me with that?! Thanks a lot!

@ferniclestix 3 ай бұрын

unfortunately as comfyUI updates many issues have cropped up in different custom nodes. many of my older videos have nodes that are broken. That said, there are other similar methods available using different nodes. unfortunately tho face restoration stuff is largely pretty bad due to some copyright issues and broken dependancies.

@wellshotproductions6541 5 ай бұрын

@Ferniclestix: RE: IPAdapters/Clip vision. The current version of IPAdapterPlus by Cubiq (Matt3o/Latent Vision) has a "Ipadapter Uniified Loader" node that takes the guesswork out of finding the right IPAdapter-ClipVision pairing.

@ferniclestix 5 ай бұрын

huh, well that would have been good to know XD thanks so hard to keep track of all the things.

@wellshotproductions6541 5 ай бұрын

So wonderful to see you back and sounding well!

@hylian_otaku 5 ай бұрын

My images come out as grey squares, I've completely followed your setup so I'm not sure what the issue is?

@defidigest9 4 ай бұрын

checkpoint/vae issue

@ferniclestix 3 ай бұрын

gonna add that yeah, sounds like a vae or a low denoise setting on your initial sampler

@heinlatt9530 5 ай бұрын

Hello Welcome back, one question What if we can control the character pose? by the way we are wishing you fully recover.

@ferniclestix 5 ай бұрын

caracter poses and full characters are possible but multiple character source images might be needed, you would want to create a full body character from a portrait, then use the full body charcter for full body poses. It takes more work but easy enough once you have the source images you need.

@pika9985 5 ай бұрын

Consistent Characters is impossible till now using sd , all it weak tricks . might be soon who can developing real ipadapter for character likness and share them , otherwise atm all txt2img,img2img,cotrolnets scene has nothing call Consistent Characters , it's a single lie from many. keep the good work

@ferniclestix 5 ай бұрын

yeah, I agree, this method is about as close as you can get using current tech. There are ways of improving even this but its more about building a big reference library of characters and poses to get the job done. lots of work.

@velRic 5 ай бұрын

@@ferniclestix still sounds great. Are you going to do a tutorial how you do it?

@ferniclestix 3 ай бұрын

maybe, im currently working on a tutorial where I do direct painting and show how to use it with both sdxl and flux. The idea is to show how you can use an external program and a few tricks to turn bad sketches into better art and in the process teach yourself how to actually draw better as I'm well aware lots of AI art people don't have the kinds of skills or even tools that let them leverage the power of digital art programs

@EntaFahemGhalat 5 ай бұрын

Welcome back .. i missed you❤❤ and your deep tutorials . Keep going

@MicheleBrugiolo 5 ай бұрын

welcome back maestro!

@yiluwididreaming6732 5 ай бұрын

GoodOnyaMate. Take care of ya self. 💜

@DaVasQ 5 ай бұрын

Awesome video as always, glad you could make that one. Always a pleasure to get your approach around things like that. I hope you'll get better quickly ! Thanks too for the shout out on ComfyUI_MaraScott_Nodes - AnyBus :)

@generalawareness101 5 ай бұрын

Welcome back.

@BadLuckBinks 5 ай бұрын

first, and also very useful as always! algorithm

@ferniclestix 5 ай бұрын

@FranckSitbon 6 ай бұрын

nice tutorial thank you

@Rachelcenter1 6 ай бұрын

It would be helpful if you immediately showed the end product in the intro of your video so viewers can know if this is the tutorial theyre looking for. and find out of this covers video and not just stills.

@ferniclestix 3 ай бұрын

not a bad idea, I've changed it up a little now by explaining roughly what we will do before proceeding to the rest of it in a few vids.

@Rachelcenter1 3 ай бұрын

@@ferniclestix the explainer isnt enough for me personally. people want to see a visual of the end product first. to make sure they arent wasting their time watching a 47 min tutorial that doesnt cover what they're looking to accomplish.

@kptnix 6 ай бұрын

I'm new to ComfyUI. I noticed that your KSampler & Main widget shows a live preview of each step of the image generation as it generates. How do I enable this?

@kptnix 6 ай бұрын

To future readers: I figured it out. It's called "ComfyUI Manager" and is easy to install by git cloning the repo into the right directory. Guide is in the github repo page

@ferniclestix 3 ай бұрын

yah, its in the settings comfyUI manager has a little option to choose the prieview method, you can choose from a few different versions which are varying degrees of speed or acuracy. (generally renders are slower with it on)

@someguy1428 6 ай бұрын

his mouse cursor be like 🔄🔄🔄🔄🔄

@59Marcel 6 ай бұрын

Enjoyed the video. I think we all go through the same frustration with these programs. I was watching a similar Lora stacker tutorial and they used a CR apply lora stack node to connect all the bits. But I could not find it. You may have better luck. Here's the KZbin video. video kzbin.info/www/bejne/sGW4enl5g7iSfKs. It looks really good. But where's the CR apply lora stack node? It did not show up when I searched for it. Thanks for your video.

@ferniclestix 3 ай бұрын

pretty sure thats in the comfyroll suite.

@silkypixel 6 ай бұрын

Thank you so much!!

@ferniclestix 3 ай бұрын

and thanks for watching :D

@3dpixelhouse 6 ай бұрын

im in love with the music in the speedup part! It is AI generated? Sounds like Aladin

@ferniclestix 3 ай бұрын

Its a royalty free song from Kevin Mcleod who is a very prolific musician who makes stuff for both film and television but he also provides a huge list of freely available works that people who make stuff on youtube can make use of. there is a link in the details section