Style and Composition with IPAdapter and ComfyUI

Рет қаралды 25,129

Күн бұрын

IPAdapter Extension: github.com/cubiq/ComfyUI_IPAd...
Github sponsorship: github.com/sponsors/cubiq
Paypal: www.paypal.me/matt3o
Discord server: / discord
00:00 Intro
00:26 Style Transfer
03:05 Composition Transfer
04:56 Style and Composition
07:42 Improve the composition
08:40 Outro

Пікірлер: 248

@Billybuckets 2 ай бұрын

No hype. No BS gimmicks. You are the golden god of AI generation tutorials. Plus you make a damned fine node or two.

@latentvision 2 ай бұрын

thanks! The difference is that I'm not a youtuber, youtube for me is a hosting platform not a job... that and the fact that I hate "this will change everything..." kind of videos

@HiProfileAI 2 ай бұрын

@@latentvisionthe fact is this is GAME CHANGING. I've been struggling with art direction for images for client requests for artwork. This is game changing making it very easy to get desired outputs with styles and compositions. Looking forward to see how this works out with image posing references for composition. Thanks much appreciated

@zGenMedia 2 ай бұрын

Incase anyone is wondering... the art work used (First crayon skull) is from Jean-Michel Basquiat. An amazing artist.

@lefourbe5596 2 ай бұрын

thanks for saying it 👌. it's true it should be credited. we don't want to destroy the people despite the look of it. we just like to make stuff like everyone else.

2 ай бұрын

You added value to our lives. Thank you..

@latentvision 2 ай бұрын

I'm doing my part!

@GabrielRosenthal 2 ай бұрын

Wow, this is realy the last missing piece I needed to use Stable Diffusion in proper client work. I already tested it and am super impressed by the performance of style transfer!! Thank you so much for making all of this possible open source! ❤ This new features will change entire industries!

@urbanthem 2 ай бұрын

Literally grabbing pop corn and smiling at all your videos. The goat. Thank you for all!!

@Mr.Sinister_666 2 ай бұрын

What you do here is incredibly helpful on all ends. Helpful is a bad word. Game changing is better but that is two words. Honestly whatever you release is gold. I look forward to every video and release man. Thank you so very, very much for your hard work!

@razvanmatt 2 ай бұрын

Thank you once again for doing all of this!

@GoblinWar 2 ай бұрын

I remember when I was a research assistant my professor told me to look into this "GAN-style transfer" thing and report back to him. For the time it was super impressive but it's cool to see what ~7 years can do, this is astounding compared to back then

@Paulo-ut1li 2 ай бұрын

That's wonderful! That combined composition and style node is game changer! I added visual style prompt to some generations it seems to give that final touch to style transfer. Thank you!

@TheGalacticIndian 2 ай бұрын

God bless you, Matteo! This makes me fall in love with generative AI again😍AMAZING!

@latentvision 2 ай бұрын

IKR?! me too!

@denisquarte7177 2 ай бұрын

This is massive, something I was hoping to achieve when I started using sd and you made it possible

@latentvision 2 ай бұрын

if I understand SD3 architecture, it should be totally possible

@sorijin 2 ай бұрын

Thank you for your hard work, I have a workflow im constantly updating with your ipadapter tech, these new capabilties are awesome!

@flisbonwlove 2 ай бұрын

Great work Matteo 👏👏✨❤️

@reapicus557 Ай бұрын

I am so grateful that you take the time to make these videos. Your nodes are so powerful and efficient, and I am able to use them with confidence right from the start given these wonderful expositions. :)

@AnotherPlace 2 ай бұрын

OMG, just this small short vid gives a lot of important information and update to my knowledge.... THANK YOU MATEO!!

@latentvision 2 ай бұрын

just doing my part

@AdamDesrosiers 2 ай бұрын

Elegant and powerful workflow - this is absolutely fantastic stuff

@DanielPartzsch 2 ай бұрын

Just when you think it can't get any better you always proof us wrong and surprise is with new tools and smarter as well as more efficient ways to get to certain results. Thank you so much.

@NotThatOlivia 2 ай бұрын

OMG!!! 👏👏👏

@MarkScorelle 7 күн бұрын

Wow great presentation, the only time I could follow Comfy presentation without programming problems and these new features are so amazing and add so much to AI art. Thanks

@andykoala3010 2 ай бұрын

you are a genius, sir!

@latentvision 2 ай бұрын

only by chance

@orion4d727 2 ай бұрын

👍Excellent work

@PulpoPaul28 2 ай бұрын

you are the best, number 1, the greatest channel in youtube. I love you, Mateo.

@latentvision 2 ай бұрын

thanks! I'm not worth it :)

@prasanthchowhan 2 ай бұрын

Thank you Matteo and the unnamed heroes (sponsers) who are responsible for this incredible thing🎉

@ranks6670 2 ай бұрын

You always make my day ❤

@mmxyt 2 ай бұрын

I haven't had so much fun with SD in a while, thanks so much for all you do!

@latentvision 2 ай бұрын

IKR?! same here!

@petertjie4128 2 ай бұрын

fantastic work Mateo, Thank You!

@erikdias9604 2 ай бұрын

This is what we imagined KZfaq to be used for when it happened. More practical than the forums and newsgroups of the time. Excellent work. it's simple and effective, it opens the way to a lot of exploration and testing (I added lora to see what it gives and... at 5 a.m. I looked up from the screen: oops 😅

@DarkGrayFantasy 2 ай бұрын

Matt3o this is amazing! I can tell you I'm going to have a blast experimenting with the nodes, keep up the amazing work!

@latentvision 2 ай бұрын

IKR?! Stable Diffusion is fun again 😄

@aamir3d 2 ай бұрын

Incredible stuff, thank you Matteo!

@ivanyang2022 2 ай бұрын

you did wonder to the community ! thank you so much!

@marjolein_pas 2 ай бұрын

amazing, thank you very much for making these and your easy to understand explanation and workflow!

@Some1uNo 2 ай бұрын

This information is gold. Thank you

@amineroula 2 ай бұрын

I am going to try this as soon as i get home 😮❤

@Skydam33hoezee 2 ай бұрын

Absolutely brilliant! Already having so much fun with this.

@ttul 2 ай бұрын

Lovely work, Matteo! I can’t wait to play with this.

@remmo123 2 ай бұрын

This is amazing. Thank you for great work.

@Showdonttell-hq1dk Ай бұрын

That's just fantastic, thank you!

@kallamamran 2 ай бұрын

Amaaaaazing video! Your work is fantastic :D

@piemoul 2 ай бұрын

I’ve been missing your live stream and you gave us this? Impressive

@3dpixelhouse 2 ай бұрын

I love it! for me, it works like a charme. thanks for your engagement and time

@latent-broadcasting 2 ай бұрын

This is exactly what I needed! Thanks so much

@jibcot8541 Ай бұрын

This is increadible, great job.

@ZhuYuxiang 2 ай бұрын

Very good video, thank you, it helped me a lot

@renegat552 2 ай бұрын

This is absolutely amazing!

@mhfx Ай бұрын

ok wow amazing update. Thank you for your hard work

@optimbro 2 ай бұрын

I have been away from all AI stuff due to my work, just wanted to thank you for this. It means a lot

@latentvision 2 ай бұрын

you are welcome! have fun (and profit) with it

@optimbro 2 ай бұрын

@@latentvision

@jccluaviz Ай бұрын

Amazing again. Really nice work

@faxuancai 2 ай бұрын

Fantastic work! Thank you, Matteo!

@user-fe3pi9rc9b 5 сағат бұрын

love you😭

@caseyj789456 2 ай бұрын

Mamamia ! Gracia Mateo ❤

@Rammahkhalid 2 ай бұрын

Great update as usual

@hmmrm 2 ай бұрын

woow thats cool

@DataMysterium 2 ай бұрын

mamma Mia, this is incredible! Thank you for making this a open-source project

@autonomousreviews2521 Ай бұрын

Thank you for this excellent tutorial :)

@kittikajorns1811 2 ай бұрын

Great work as always.

@paulotarso4483 2 ай бұрын

Insane, you're the goat!

@banzai316 2 ай бұрын

Fantastic!! As always 👏

@sanchitwadehra 2 ай бұрын

Dhanyavad

@AnthonyDev 2 ай бұрын

Amazing. Ipadapter and comfyui = 😍

@no-handles 2 ай бұрын

Amazing work!

@eddiemauro.design 2 ай бұрын

Thank you for everything. I supported you in paypal :)

@latentvision 2 ай бұрын

thanks!

@sachacarletti6533 2 ай бұрын

amazing!! thank you Matteo!

@Cyalithe 2 ай бұрын

This is absolutely amazing. You are one of the few people I watch every single piece of content from. Unfortunately, I don't have the VRam to run SDXL models. Any chance of this functionality coming to 1.5?

@latentvision 2 ай бұрын

unfortunately I don't think that would be possible, but I will try

@Cyalithe 2 ай бұрын

@@latentvision Awesome if you can, but it's all appreciated no matter what =)

@user-cp8vm5ef2l 2 ай бұрын

Thank you!

@hamidmohamadzade1920 2 ай бұрын

you really unlocked the power of image generation

@pandalayreal 2 ай бұрын

So good!

@alanhk147 2 ай бұрын

You are the best !

@KriGeta 2 ай бұрын

Waiting for the day when changing complex anime or real images to manga type sketches would be possible 😅

@Injaznito1 2 ай бұрын

Just finished updating my IPAdapter and it wasn't too painful. I did had to use ComfyUI manager to download the new models but other than that I didn't hit any walls. Thanx for the tutorial!

@electrolab2624 2 ай бұрын

ooh - I want to update too! - did you use a tutorial to do that? - So you just update the IP Adapter nodes (using manager) and download some new models? - I am a bit confused 😬

@electrolab2624 2 ай бұрын

Managed! - Using the 'IPAdapter Style & Composition SDXL' now - it's awesome! THX much much - @Matteo! 🤗

@35wangfeng 2 ай бұрын

awesome!!!

@pk.9436 2 ай бұрын

great work

@xellostube 2 ай бұрын

Interesting behaviour: I've just discovered that if I mask the image leaving the center of the image out of the mask, whatever generation will be ifluenced by the image but no in the center Interesting results. (workflow at 9:21)

@MrMartinBoo 2 ай бұрын

IPAdapter is just mesmerizing...

@RodrigoNishino 2 ай бұрын

Very interesting surely gonna try it. Thx!

@RodrigoNishino 2 ай бұрын

Cant seem to find StyleAndComposition node .. .am I missing something?

@afaridoon1104 2 ай бұрын

🤯amazing

@dan323609 2 ай бұрын

How to use a multiple ref images? It is possible?

@ashokp9260 2 ай бұрын

this is crazy good..

@liialuuna 2 ай бұрын

great nodes! 🍒🍒🍒

@juanchogarzonmiranda 2 ай бұрын

Thanks Matteo!!

@BobDoyleMedia 2 ай бұрын

GREAT!

@hayateltelbany 24 күн бұрын

that is crazy xD I love it

@aviator4922 2 ай бұрын

awesome man

@AdwinWijaya 2 ай бұрын

nice one... i am looking for this feature in stablediffusion and just found it on your video. nice one ...

@alessandrorusso583 2 ай бұрын

Thank you for the time you dedicate to the community, my thanks unfortunately are not much, I was only able to offer you a coffee, but I hope that others will do the same to be able to support your time. 😊 I gave you something using the youtube thank you button.

@latentvision 2 ай бұрын

thank you, it would be great if companies that are actually making a lot of money out of this technology would chime in

@alessandrorusso583 2 ай бұрын

@@latentvision Can you mix multiple styles? And does it also work with image to image?

@latentvision 2 ай бұрын

@@alessandrorusso583 yes and yes-ish. img2img works but the denoise needs to be pretty high. depends on the result you are after

@RodgerE2472 2 ай бұрын

Amazing! Go support Matt if you can afford it!!!

@ceegeevibes1335 2 ай бұрын

amazing!

@dashx3465 2 ай бұрын

Thank you! I think this will be way better than controlnet for me. Give the AI a base to follow but have way more freedom than controlnet gives. I could never get the SDXL controlnets to work too well.

@haljordan1575 2 ай бұрын

Since you build these, you're the perfect person to ask. Would it ever be possible to combine your previous workflow "character stability and repeatability" with something like composition adapter or multi area composition, where you'd feed separately stable and posed characters into one image to generate a final singular artwork where they interact?

@yvann.mp4 2 ай бұрын

thanks so much

@alessandrorusso583 2 ай бұрын

Grazie.

@david_ce 2 ай бұрын

I love this guy so much Great video and thank you for your service When’s the next comfy to hero video coming out?

@latentvision 2 ай бұрын

I'm prepping it... not sure when but it's in the pipeline

@sb6934 17 күн бұрын

Thanks!

@the_neural_network 2 ай бұрын

bravo Matteo 💪💪💪💪 ora so che esiste anche il LeoneMedusa, farò un documentario 🤣

@Injaznito1 2 ай бұрын

I'm guessing this only works with SDXL and not 1.5?

@Shisgara77 2 ай бұрын

ФАНТАСТИКА 😍❤

@flamingwoodz 2 ай бұрын

These updates are great! How do you recommend composition for SD1.5 models currently?

@Darkwing8707 2 ай бұрын

Since 1.5 models don't have a composition unet, tools like attention/latent couple and regional prompter might be your best bet.

@pfbeast 2 ай бұрын

👌👌👌❤❤❤ very nice & high quality video. Really your new node give lots more option😀. I am sorry for my comments on your last video due to change your node structure. Salut 🫡 your thought about open source in this video last part.

@rsunghun 2 ай бұрын

Holy magical heaven

@burdenedbyhope 2 ай бұрын

awesome work!!! btw, can you suggest a workflow for using the new composition transfer with subjects from other IPAdpater (like how we use attention masks to achieve before)

@latentvision 2 ай бұрын

I really just released the feature I still need to play with it. I'll post more in the coming weeks

@burdenedbyhope 2 ай бұрын

@@latentvision you’re the best