I'm so proud to have made it work. Thanks for your instructions!

As always, I love your videos for the extra comments and help that you provide. Most of the time those small hints go a long way for me. Best wishes

As a novice in all this, you would think with ALL of these downloads and distribution requirements that 'they' would have a simple batch file to download all of the packages and give them the right names. I don't understand how there can so much work put into development, yet for someone that knows what they are doing would take them 10 mins to write a batch script. Just think everyone that wants to use this IPadapter Version 2, every single person has to follow this monotonous process (and this is the EASY install guide!)

@Utoko

14 күн бұрын

You say that, but it is still work. You have to write different script for different OS. You have to adjust it each time you make changes on your project. You have to respond to issues people have with it. You have to test the script... Timesinks add up, this IPAdapter is just from one person. but you know what, GPT4 and Claude Opus exist. So you could do it too with trial and error and share it with the community.

A1111 homies leaving the chat

@AlgorithmInstituteofBR

Ай бұрын

we have been forgotten. especially on this channel.

@gicknardner

Ай бұрын

@@AlgorithmInstituteofBRnooo the free tutorial is using the wrong free software!

@ratside9485

Ай бұрын

I think we have to accept that auto1111 always lags a little behind because it is not so flexible.

@JustFeral

Ай бұрын

​​@@AlgorithmInstituteofBRlol the developer of the plugin made it for comfyui. Not his fault that the dev prefers comfyui.

@wykydytron

Ай бұрын

It's because SD people bought comfy and made it official SD app. Still, a1111 gets more stuff from community as it's more popular and bilion times easier to use.

Thank you! I had to create the ipadapter folder. It was driving me crazy

thank'you for this full tutorial for installation ❤

Basically the midjourney consistent face feature, but it's: 1. Free. 2. Open-Source. 3. Without restrictions. 4. Arguably looks better. 5. More freedom with the models/styles you can choose from. That's great!!

@OlivioSarikas

Ай бұрын

well, the model is from a company with a lot of restrictions and pretty strict licencing rules as far as i know. So not that. But for private purposes it is very powerful and fun

@undergroundxp

Ай бұрын

Aahh I see, cheers for the info! Appreciate your videos as always!@@OlivioSarikas

@karenreddy

Ай бұрын

SD has had IP adapter for a while now.

@JustFeral

Ай бұрын

​@@karenreddythe old version. Not the better v2 version the creator literally just created. Basically rewrote it .

@latentvision

Ай бұрын

@@OlivioSarikas Only the FaceID models are restricted by the InsightFace license (basically if you use any of the FaceID nodes)

Thanks Olivio, you rock, as always!

@OlivioSarikas

Ай бұрын

Thank you!

Awesome video Olivio!

thank you so much!!!

Thanks man!

The creator of this gave a warning you should have mentioned. This will BREAK existing workflows because the nodes are different.

@OlivioSarikas

Ай бұрын

good point!

@whizadree

Ай бұрын

@@OlivioSarikas create a new message and pin that info

@hoodooguru1450

Ай бұрын

It is not hard to fix existing workflows to use the V2 IPAdapter. Once you upgrade ComfyUI with the new nodes, you just need to load the older workflow, delete the IPAdapter nodes and replace them with the new nodes, then refresh ComfyUI and reload the browser window and the node should run as usual.

@KINGLIFERISM

Ай бұрын

@@hoodooguru1450 Problem is IF you do not know the worflow you will have no idea what the settings were. That is the only real issue.

@hoodooguru1450

Ай бұрын

@@KINGLIFERISM You should write down the settings before you delete the old nodes. Not an issue then.

감사합니다~!! ❤

Awesome! 😁🤌

me, technical guy for 30+ yrs, just now learning about right-click-copy-as-path, wondering how long that's been there 🤦‍♂thank you olivio 🤘😅

Thanks bro

Great video as always, Olivio. Even though I catch AI news here and there, I'm completely lost these days. The last thing I was familiar with was Stable Diffusion 1.5 and A1111. But now I come across this video mentioning ComfyUI and other strange things I don't understand - where did those come from and when? As a suggestion to help newcomers break into learning these technologies, it would be helpful to have a summary video every 6 months or so covering the current general use tools. Everything is moving so quickly that I no longer know where we're at. Thanks. Liked and shared.

any luck on getting insightface installed properly on a mac?

Nice video bro❤❤❤🎉…

Is faceid better than giving an already cut face to ipadapter ? I have an entire workflow to manage gender detection in an image with 2 faces to process in 2 different reactors (reactor gender detection is bad) and after that I am using ipadapters to make the faces less cartoonesque.using the faces segs and masks I got during gender detection I never redetect faces in a large image so it is faster. Is the quality the same ?

Hi Olivio, do Ksampler node and Ksampler Efficient function differently? I made the same initial workflow / settings using Ksampler efficient, but not getting the same output as you have shown

@OlivioSarikas

Ай бұрын

yes, because Ksampler Efficient often does bad results where ksampler gives the correct output. in most cases don't use Ksampler Efficient

@deyakash2504

Ай бұрын

@@OlivioSarikas Was just studying this more, do you think there may also be an issue with Efficient Loader node? I don’t think the prompt gets transferred to the Ksampler the same way as it would through clip text encode > K sampler +ve conditioning

@OlivioSarikas

Ай бұрын

@@deyakash2504 it's best if you ask people in my discord. I have a room just for comfyui

@deyakash2504

Ай бұрын

@@OlivioSarikas Oh nice, I think your discord details should be somewhere on your profile.. Will join right away, thanks!

all I had to do was make 2 new folders called ipadapter and insightface in the comfyui/models folder and I just put the models in them and it works

Is OOTD the same as this or better?

Hey olive, can you also show how to do the same on runpod

Agreed on pain to install! But very interesting so far...

How to see your posts on discod. How much do I need to upgrade?

also for A1111 ???

I think this is a happy case scenario . Have you tried with something more tight to her like jeans and smaller size blouse ?

@OlivioSarikas

Ай бұрын

yes, i have and i made a 30 minute video for my patreon supporteres with different cloths styles and also with background combinations www.patreon.com/posts/ipadapter-v2-101309573

thanks u

Is there any way of locking the update of a single extension in comfyui? This update seems nice, but I'd rather not break some of my workflows.

@justinwhite2725

Ай бұрын

You can go into the manger and update them one by one as you did before. Though if you are worried about yourworkflows, the iP adapter itself is different enough that your exising ip adapter workflows own't work after updating it

Hey, where I can get the workflow for this?

IP Adapter v2 will arrive for Forge | Automatic1111? Or should I get depressed from now on?

Beware that the automatic update of the manager sometimes doesn't work and you may need to upgrade manually. This is NOT an addition but a complete replacement of all files

Why there are using the .bin not safetensor file type ?

Will it work with clothing that has a print on it, or will it distort it?

@OlivioSarikas

Ай бұрын

it will create a different print that looks somewhat similar. this really works best with clothing items with simple or no patterns.

painful to install but the reward is huge my friends - read carefully the doc

The "Weight_type" in "IPAdapterAdvanced" does not have "style transfer(SDXL)" and "compostion(SDXL)".Other functions are working fine, but there is no "style transfer(SDXL)" and "compostion(SDXL)", I would like to have a separate reference for styles, but I can't get it to work. How to solve this problem?

Comfy is just SO HARD to use. It feels more like coding with having to permaneently connect and deconnect multiple nodes to just upscale and use a fkin controlnet… but it seems to be the most optimized one though. I’ve tried a1111 swarm and forge and only comfyui is able to run lightning models on my poor 2060 the others just crash….

I am already running IPAdapter workflows... if i update, will i have to download the models again ? or will the update automatically reference them into the new nodes ?

@JavierPortillo1

Ай бұрын

No, just make sure they are named as shown in the video

I've had IP adapter plus for months. Is there a difference? If so, what can it do that the old one couldn't?

@PretendBreadBoy

Ай бұрын

Just a cleaned up script and new more simplified way of doing it. It's not any better as far as quality of the face though.

@JavierPortillo1

Ай бұрын

No, it has a couple new settings that affect how IPA is applied. I've gotten better results with the old full-face models on stubborn anime models that didn't work before, I haven't tested other models yet but it is a big improvement. That's on the advanced node.

it's easier instsalling the clip vision models VIT-H and VIT-G with the manager.

Will this work on a MAC.

Olvio with another banger! Can't wait to enjoy this one

Hello. Can we do this with stable diffusion or Fooocus?

@OlivioSarikas

Ай бұрын

technically it should work the same way with IPAdapter in these tools

I don't like comfyUI anymore! I would like you to explain using forge or webUI (;_;)

@AB-wf8ek

Ай бұрын

He hasn't covered webui in months. There are plenty of IPAdapter videos for Automatic 1111 if you do a search. I don't get why everyone keeps complaining about ComfyUI, it would be like going on a Houdini tutorial and complaining that they're not using Blender when there are hundreds of videos on it already.

@Your-Stranger

Ай бұрын

@@AB-wf8ek This is simply because there are so many errors that it is unusable. I'd rather learn how to resolve errors than how to create videos.

@wykydytron

Ай бұрын

Because comfy is over hyped overcomplicated garbage. Only con of comfy over a1111 is that it turns on faster. A1111 is billion times easier to use and gives exactly same results. Comfy was better when it was new as it was faster but now it's not the case.

@AB-wf8ek

Ай бұрын

Then use Auto1111/Forge, why would you bother watching a channel that covers ComfyUI just to complain about it?

@jellymage7469

15 күн бұрын

@@wykydytron You're right, A1111 is more intuitive.

I tried for several days... but it breaks everytime with layer diffusion... and i use transparent images a lot. 😢

Please cover how to use ipadapter in A1111 as well. I just can't get into the mindset needed for ComfyUI.

Can we link together a FaceID IPAdapter and a regular IPAdapter into one Apply IPAdapter node?

@hoodooguru1450

Ай бұрын

Yes they can be linked together. Both the Unified Model Loader and The Unified Model FaceID Loaders have an IPAdapter Input and Output on them.

@97BuckeyeGuy

Ай бұрын

So, if the image I'm using has both a style AND a face I want to reproduce, I should just run the two loaders into each other and then run the second one into the Unified Loader?

I did everything you said, put everything in the correct folders, installed everything, got no errors and still can't see the IP nodes in comfy and I don't know why 😔

Note: if yours was working and now isn't working its likely because you deleted, moved or changed where the original file was you downloaded in this process olivio shows. Most of these issues can just be solved by leaving the file where it was originally downloaded lol

Maaan, you are the BEST! I f*ck*ng love you! I hit 'Enter' and receive an error, but it's only because the path contains spaces instead of underscores

I have all the new nodes except there is no "IPadapter" node?

made an update through the Manager (Update All), got an error "When loading the graph, the following node types were not found: IPAdapterAp" Does not help "Install Missing Custom Nodes"

@hoodooguru1450

Ай бұрын

You have to delete the old node from the workflow, replace it with the appropriate new node of the V2 IPAdapter, then refresh (and or Restart) ComfyUI, and reload the browser window once it restarts and the node should run as usual.

@samon29

Ай бұрын

@@hoodooguru1450 thank you there is no way to go back

Right click, install. I miss those days 😂

@UmbrellaTrick

Ай бұрын

pain of installation is your last layer of protection. Because when its gone, everyone will have AI in their phones. And noone gona need you anymore :) So enjoy current days while you can !

@theh1ve

Ай бұрын

Need me for what? Install the software lol

Isn't there an AGI agent that could build an AIO installer ;)

Anyone not able to find the IPAdapter node to connect to the unified loader?

@juncando

Ай бұрын

You do not need the IPAdapter or Clip Vision if you are using the unified loader. Just need to connect the model and choose PLUS(high strength)

someone throw me a bone.. his directions go off the screen at 6:00. spaxes \ between insight face and location?

it doesnt work. it breaks at the image blend mode

@godorox

Ай бұрын

The same here.

Extremely Inconvenient. I will refer to this tutorial when I innocently update my ComfyUI and discover that all of my workflows are broken 😃. May solve a lot of frustration in future! - (Thank you in advance) Which real usage issues was this total rewrite meant to actually solve? - Had no issues with IP adapter usage whatsoever. - Not complaining ofc.. Just that, as you said 'it's a pain'.

@149315Nico

Ай бұрын

1. speed improvements 2. fixed all directml issues 3. easier use bc you won’t have to remember and connect the right clipvision and ip adapter combos and weither it’s a plus and or v2 model. 4. being able to use non-square inputs. Clipvision only understands squares, the new ip-adapter tiled automatically crops the image and generates according masks. That’s about it for problems, everything else is extra features, like optional negative image in, being able to select the mathematical approach of how multiple images get mushed together and weight types (slowly fading in/out the ip adapters influence over time thereby giving more control over it than just start and end time). Also you can now use masks for the embed loader, not an attention mask , but a regular mask for what part of your reference images should be considered by the ipadapter. It’s especially strong with rembg, be it objects, animals, people, clothes, removing the background removes its unwanted influence on the output. So overall a Game changing Update if you wanna explore the advanced new features, if you just need the basics tho it gotten kinda more complicated if used to the old way but I can imagine it being more beginner friendly as people won’t have to hassle with all the different possible model and setting combinations. On the other hand, there’s even more possible settings now if you wanna fiddle with different weight types and embedding combinations

@liialuuna

Ай бұрын

it's very easy to update your old workflows with the new nodes.

I love controlnet but someone needs to rename all of the various gizmos so their names are more intuitive lol

it seems time to move to comfyui

I'm going to make a glove with extra fingers. It looks like a messed up AI hand. Then photo evidence can never be used against me. 🤔

@OlivioSarikas

Ай бұрын

and a teeth model with extra teeth ;)

not in automatic 1111 yet i presume?

@PretendBreadBoy

Ай бұрын

Ipadapter is in automatic 1111 and is easier to use, its in the control net section.

@149315Nico

Ай бұрын

Easier but less capable ;) That’s the tradeoff with auto/forge. IPA has been working in a11 for a long time, but the new update is comfy exclusive yet and I don’t see Matteo spending his little spare time to go horrendous efforts in making it work with auto, if anything it’ll be on forge first as that Plattform is much better at allowing devs to easily implement their new ideas. Auto is lacking the different weighting’s, the negative image input, the different choices of how embeds get calculated and the flexibility of comfy. There’s a new inofficial ip-adapter for composition, its not implemented in any gui, so I added like 4 Lines of code to the ip-adapter-plus comfy custom nodes and now I can use it with the unified loader and it automatically selects the right Clipvision model. If you don’t get the benefits of comfy you probably won’t benefit from it as its admittedly more difficult to start with, but it opens up endless possibilities if you are open to learning a bit of logic and like following a linear path of execution

Many might ask what IPAdapter actually does and unfortunately this was not addressed in this video. The IPAdapter are very powerful models for image-to-image conditioning. The subject or even just the style of the reference image can be applied to a generation. Think of it as a 1-image lora.

@BlackDragonBE

Ай бұрын

Thanks for the explanation, I was wondering why there wasn't any info on it in the video.

@OlivioSarikas

Ай бұрын

I show in two speperate examples what it does. Unless people have never seen what AI is, they will get what i am doing

@MikevomMars

Ай бұрын

@@OlivioSarikas It doesn't work if you show the results at the end of the video - most people won't watch the entire video when they aren't sure what it is about in the first 5-10 seconds.

mateo rules

@OlivioSarikas

Ай бұрын

yes, he is awesome!

5:00 you should REALLY not do that... Unless your machine is fully dedicated to comfy you are asking for troubles (that's why we have venv)

@stranostrani9212

Ай бұрын

Why? You can always delete them if you don't need them. They are just paths that are more easily accessible anywhere from your PC

@workflowinmind

Ай бұрын

@@stranostrani9212 Many reasons... Python is not meant to be used globally unless you know what you are doing. By making PATH collide like this you will introduce hard to debug issues. Most tools just take the first matching python it can find in PATH, wheels might install into the global path but using this local version etc etc... Just type "why use a virtualenv" in google if you want to know more

IP Adapter should have auto download like several other Nodes I use.

@OlivioSarikas

Ай бұрын

yes, agreed

why everything has to be so stupidly dificult just tu run some nodes. i'm a photographer and i really need to use these tools for my job and clients but i don't know how to code. hope some day someone will come up with an easy solution to use these tools...

HAHAHA great intro.

not working for me .... have the same settings as you have... only differnece is that I am using a lightning model... but all I get is a deformed winter jacket .... no woman.... or any subject

@OlivioSarikas

Ай бұрын

adjust the weight of the IPAdapter and see what you get. Try values between 0.4 and 0.8 and see what you get

@SasukeGER

Ай бұрын

still not correct.... 0.4 or above... always getting a deformed clothes but no people@@OlivioSarikas

We need a Olivio rock theme

You're pretty much the only AI youtuber who is consistently staying on top of everything at this point. Thank you for keeping us up with the new developments🙏👏👍

@OlivioSarikas

Ай бұрын

Thank you, that means a lot

@olivere5497

Ай бұрын

It is hard to keep up. Im 9 months out of date and feel lost.

@AIFuzz59

Ай бұрын

I am trying 😜

haha, its working with pink puffy coat, but i loaded different clothes and comfyui generated with 0,8 same clothes without woman )

@OlivioSarikas

Ай бұрын

The experiment more and adjust the settings. AI requires some learning and all of this is still in early development

Side note, I think you're using the wrong version of the IP Adapter (you're using the IP Adapter Plus node which Mateo deprecated in the latest update, it's only IP Adapter Advanced node now)

@Havic22123

Ай бұрын

this explains the issue I'm facing. thanks for commenting this.

@OlivioSarikas

Ай бұрын

I'm not using the IP Adapter Plus node, the Nodes Pack is called "IPAdapter Plus" - As far as i can see i use the same nodes that Matteo uses in this Video and he also links to the IPAdapter Plus node Pack: kzread.info/dash/bejne/kX6upsWge8rNmLw.html

@GrocksterRox

Ай бұрын

@@OlivioSarikas OK I may be wrong, but if you use ComfyUI Manager and update the IP Adapater node pack, see if you can add a regular "IP Adapter node" to your workflow. I only see "IP Adapter Advanced" but again apologies if I'm mistaken

@OlivioSarikas

Ай бұрын

@@GrocksterRox the IPAdapter Node is still there and if you watch the video from Matteo he also uses the IPAdapter node at 2:59, not the Advanced node

@KonoShunkan

Ай бұрын

@@GrocksterRox I had the problem with not seeing the plain IPAdapter node, but Matteo explained that you need to delete the "IPAdapter-ComfUI" folder under custom_nodes (not "ComfyUI_IPAdapter_plus", of course!). This was by a previous developer and is deprecated, with relevant code moved to ComfyUI_IPAdapter_plus. After deleting this and restarting ComyUI I could find the regular node.

Epic walkthrough! You made navigating the IP adapter version two feel like spreading butter on warm toast - smooth and satisfying. Eager to dive into the unified loader's buttery goodness. But really, who's truly prepared for the sheer, unadulterated power of Olivio Butter? It's like the secret boss level of kitchen spreads! 😂🧈

👋

I want automatic 1111 💔

Slowly AI art practitioners are adopting Python

This is all such a hassle for something that you can't even use commercially.

but its confyui and they just broke a ton of configs. ew

@2PeteShakur

Ай бұрын

works fine for me even on old workflows, easy peasy! ;)

every time you make a video, I never see you hit generate as if you want people to buy in to your patreon... This is the second tutorial of yours that has come across my recommended feed that didn't work... I don't know how you got this subscriber count but I'm done with the video baits you do. I am not interested in this channel going forward!

SKIP.. this is insane...........