Since I made this video I added a "precise style transfer" node to the IPAdapter. You can use that instead of fiddling with the Mad Scientist. It also works with SD1.5 (to some extent). Also since I've been asked quite a few times now... sorry, we do not have exact data of what each block does. 3 and 6 are pretty strong so it was easy but other layers have also some impact on both the composition and the style. Some seems to effect text, others background, others age. But at the moment it doesn't seem there is a "definitive guide". I would have told you otherwise 😅

This guy is literally equivalent to what Piximperfect is to Photoshop. I doubt even the people who worked on SDXL had any idea that this much stuff and control can be gained over the models. Like seriously, wtf ???? Amazing work.

Best Comfyui channel on KZfaq.

Matteo, your work is amazing! You are our Dr. Brown. Our mad scientist who will give 1.21 Gigawatts to the AI to take us to the future. We love you!!! 😄😄😄

As always amazing work Matt3o! For those interested in the Crossattention codes this is what they target: 1) General Structure 2) Color Scheme 3) Composition 4) Lighting and Shadow 5) Texture and Detail 6) Style 7) Depth and Perspective 8) Background and Environment 9) Object Features 10) Motion and Dynamics 11) Emotions and Expressions 12) Contextual Consistency

when it comes to teaching and concise explaining, you are the GOAT!!!! Thank you so much, please keep doing this. Thank you!

Great work as usual, M! I am happy to see that the group experimentation with the UNET layers has led to the development of a node that will give us more control over our generations. Thank you for your continued efforts in this field!

Matteo sei davvero incredibile con il tuo lavoro... 🎉

Love what you're doing for the community - thank you for your time and for sharing :D

You are a mad scientist haha thank you so much Matteo

"While keeping up with the influx of new features is important, I'm reminded again of the value of in-depth understanding of a single function. Thank you as always."

Just found the node today and was wondering about its use - thanks for sharing the knowledge!

Incredible Content ! your work is undoubted the best !

Thanks a thousand Matteo. Your last statement is something I tell time and time again, we only use so little potential in what's already out there. Brilliantly proving that point.

I love the idea of target conditioning various layers and being able to direct the layer with this kind of control in the cross attention. Thank you Matteo for you continued work and expertise. You give us a lot to play with and work with. The implications of the kind of control we can have in image creation and manipulation will last for years. Continued blessing to and appreciation to you good sir. 🙏🏾👍🏾

Thanks a lot for this new node, really appreciate it.

Your work is amazing!

Absolutely amazing 😮

This is so incredibly cool! Thank you very much. I can't even imagine how nerve-wracking and exciting the coding was for this. :)

it was amazing ,thank you for the work you have done for the community, i really appreciate it

Thank you. Exactly, we become conditioned to chase the new shiny toy rather that fully learning and enjoying the old ones. So much can be done with this, looking forward to...

God of IPAdapter

Always waiting for your greate video, that help me alot! Thanks

Great node, thanks a lot 😁

Again, blowing minds !!!!

Image gen is a tech that seemed science fiction a couple years ago, but to have refined it to the point people in their homes can casually do generations like 7:19 is nothing short of outstanding. Thanks as always.

love love love this, going MAD!!!!

Thanks Matteo, this is so good!

Thanks that's cool, amazing findings that will help the comunity

Insanely cool, also just realized, you are italian as well😂🔥

genius hacking of cross attention and perfect explanation of the indexing.

Very cool! Would love to see some coding sessions. Maybe you could explain your code a bit. More info about the vector sizes, layers etc :)

This is awesome! ty!

so cool and you are our mad scientist

Keep up the good work man

Thank you again, my lord

Thank you!

Very cool, I need to play with IPAdapter more often, but I am often too busy just improving prompts and upscale workflows!

this is awesome thank you

This builds on your previous experimental node where you asked for some help from the community. Glad to see they helped you decipher the layers

Awesome, Bro

Cos-XL is so tight, I'm a huge fan

GENIUS

Thank you so much!

Thanks you dr.Matteo. I think i need one of your pills to make my days shine. Again an extraodinary work.

amazing, thanks a lots

Amazing video. You do a great job at explaining complex ideas. I've learned so much from your videos.

W O W!!! AMAZING!

Until I use this a *lot*, I will have no idea what the different UNet blocks do. Maybe you could put a Note node in the pack that contains an estimation of the relative contribution of each block to style, composition, and anything else that might be useful. A++ work as always. Best SD channel around.

My understanding is that Precise generally weakened the weights of more layers, but style has always been a mystery to neural networks, although you have done so well already. I hope you can bring us more surprises, thank you for your contributions! The name 'Mad Scientist' is simply fantastic

Nice work! ❤It's awesome to see real progress on the U-net layer. But having too many parameters can make it tough to get started, even for someone like me who's been at it for over a year. It's just too challenging for ordinary people. If we change the filling parameter to four simple options like ABCD, it might be easier to promote. Ordinary people aren't into the process; they're all about the end result.

I'll take the blue pill!! 😁 Thanks so much for this one!! 💊

7:20 my jaw literally drop

Impeccable naming, we're all a little mad by now 🤣

you're the man, thanks for all this tutorials!

Matteo, thank you for bringing us IPAdapter, which provides a solid ground for us to combat the uncertainty generated by large models. I personally like your explanation of basic theories. Although your course is less than 10 minutes, I have studied it repeatedly for several hours. If you have time to explain in detail the specific functions and applications of the 12 layers of the cross nerve, thank you very much for your efforts, thank you!

Nice❤❤

Awesome work! Do you have the info on the other 10 control index points?

you have so many secrets matteo :D

HOLY SHIT, this is powerful!

This is awesome! Are you planning on making a version that works with embeds?

07:20 quella roba è fucking insane.

Hey Matteo, Just finished your ComfyUI tutorial - seriously impressive stuff! 👍❤ Your breakdown of advanced features with practical examples is super motivating. I'm excited to put these into action and unlock the full potential of ComfyUI. Thanks for sharing your knowledge!

You called that node based on yourself right? You're truly a mad scientist bringing us the best discoveries! Thank you Mateo

How about a widget setting in the IpAdapter node, to set the strength of each layer with a short lable of its function?

Unbelievable.

This is pretty awesome. Great work! I have a question about the cross attention indexes. Are they tied to output or input blocks in terms of merging? I am wondering if this could help to find the best blocks to merge to for more precision.

Very good as always Matteo. Can you explain all the index please? I've noticed only 3: 3: Reference image 5: Composition 6: Style

Great video. Top notch content, as always

Is there any similar way to apply Lora style to only specific layer? Maybe we can apply negative weight for composition layer (e.g. layer 3) and positive weight for style layer (e.g. layer 6)?

Great video, thank you! Where can we find this node?

Wow... You should make the layers as weight handles and call the layers for what they are :D

And one more question. Where can I find an explanation of the index/Cross Attention?

Mateo, This is amazing work with the mad scientist node - My only question (not criticism) is if you plan to convert the index:weight string into widgets for ease of use or is there something that prevents that?

🤯

🤩🤩

🙏

UPDATE ALL THE NODES!!!! thanks Matteo

One proposal and one remark: You should name it "clever" instead of mad!^^ Your last words are very well spoken. I have problems to keep track of all the new nodes and developments regarding time and depth of understanding and using. There isn't even enough time to carefully read through manuals, test nodes, combine new workflows based on what we already have. The big players are on the run, too. See all these new announcements what their model brings for the benefit of the world (and for their pockets). [irony off]. Nevertheless, interesting, but challenging times ! And thank you for your contributions, Matteo, always appreciated!

incredible. Apart from style and composition, has the community found consensus on what specific qualities of the image other indexes affect?

Amazing and insightful work! Question wrt to sponsorship, do you have a preference between github vs patreon? I'm getting so much value here that I want to meaningfully support you and will default to github support if there's no preference

Your 666th like is from me. I don't know what I'd do without your brilliant work. Thank you.

"We fail to understand what we already have" - cries in GLIGEN conditioning

Damn that's impressive. Could the same logic be applied to a Lora node in the future ?

Did anyone ever figure out what each block of the Unet does? When I was obsessively trying to understand how stable diffusion work, I went deep into it but could never get a straight answer. Also what processes are involved in each block? If I remember correctly each block has layers within it, with ResNets and other things above my pay grade. If anyone can point to a resource I’d appreciate 🙏

Woooow, wow 🎉 you are amazing. This is just soooo cool. Why the negative prompt doesn't go with minus? It would be 3:-2.5, 6:1, and this way all the sintaxis could be consistent everywhere. And people would be able to pass positive and negative as much as they want.

Hello man, thanks for sharing this amazing improvement on control! Did something change between the style transfer and composition from 2 days ago to this release? I cant seem to reproduce same results :( Or, is there a way to reproduce the exact same layer weights of that previous release within the mad scientist node?

a newbie question (maybe), index 3 is composition and 6 is style, what are the others? I don't remember if you have already talked about them in your other ipadapters videos

amazing work, anyone test mad scientist in SD1.5? how is the specific block to inject attn work?

Thanks, that's really cool 🙏🙏. but Is this just for me? I found almost everything too advanced and couldn't understand what's going on, but I would really love to understand it in depth so that I can add my own to it and share. I do have some knowledge on comfyui but this is...

hi thanks for this great tutorial. im getting error while executing the code is "" ipadapter object has no attributee 'apply_ipadapter" i tried to using sd15 checkpoints as well sdxl. but getting same.

I will say this again, you are simply amazing Matteo! "Shut Up and Take My Money!"💰

@latentvision Is it possible to combine the image to image workflow along with even more control to resemble the input? Aka, control net type of options.

dying to know what the other index blocks are!

please is the prompt injection node out yet???

Mateo hi and thank you. I'm using the Mad Scientist node. Thanks for the clarification. I've become more aware of how to use it. I also have one question about the "IPAdapter Encoder" node, it has an input for a mask? The point is that both input image and mask should be connected to this node. When using only the input image in the "IPAdapter Encoder" node, the output image adopts the style/whatever. But when I also connect an input mask (I tried just a colored map, image, half painted image), the IPAdapter Encoder node has no effect on the generated image at all. Could you please explain how to use the mask in the "IPAdapter Encoder" node?

Do you have a list of what the other index layers are? We are experimenting with this now

Hi, thanks, wonderful! I just don't understand the point of this custom node having "weight_type" field if we modify the layers' weights in the bottom input field? Is "weight_type" overriden by the values in the input field?

... It feels like SD3 is going to have a very hard time