Way Better Then Dreambooth! Custom AI Models Based on Your Photos!

Рет қаралды 17,828

Күн бұрын

Perfusion lets you customize AI image generation with your own concepts using compact model updates! See how locking attention keys and training latent values enable quality text-to-image personalization.
▼ Link(s) From Today’s Video:
✩ Nvidia's Paper: arxiv.org/pdf/2305.01644.pdf
► MattVidPro Discord: / discord
► Follow Me on Twitter: / mattvidpro
-------------------------------------------------
▼ Extra Links of Interest:
✩ AI LINKS MASTER LIST: www.futurepedia.io/
✩ General AI Playlist: • General MattVidPro AI ...
✩ AI I use to edit videos: www.descript.com/?lmref=nA4fDg
✩ Second Channel: / @matt_pie
-------------------------------------------------
Thanks for watching Matt Video Productions! I make all sorts of videos here on KZfaq! Technology, Tutorials, and Reviews! Enjoy Your stay here, and subscribe!
All Suggestions, Thoughts And Comments Are Greatly Appreciated… Because I Actually Read Them.
-------------------------------------------------
► Business Contact: MattVidProSecond@gmail.com

Пікірлер: 69

@alpineswiftai 10 ай бұрын

Ah, the 'it exists but you can't use it,' genre of AI news. The corner stone of frustration.

@virgilxavier1 10 ай бұрын

I only really call bs when it's Google though.

@alpineswiftai 10 ай бұрын

@@virgilxavier1 omg those guys. They told us for years,”You don’t deserve this”

@timmygilbert4102 10 ай бұрын

As long as they explained how it's done so we can replicate

@alpineswiftai 10 ай бұрын

@@timmygilbert4102 ahhh great point

@thursdaybrothers7964 9 ай бұрын

I wish people would say that up front. This video is a waste of time

@Musicman3832 10 ай бұрын

This is some cool stuff man. Always excited to see your videos in my notifications inbox.

@garjog1 10 ай бұрын

Agreed. Matt is the best. Always entertaining.

@realcinnamongold 10 ай бұрын

This reminds a lot of the character ai website, but with images. Can't wait for this model to be usable (and hopefully it's free)

@virgilxavier1 10 ай бұрын

I feel like this is the biggest AI development in months. AI takes mountains to get a single concept. A human can see a single picture and learn the concepts from it based on inferences from their life experience. To create such a small file on a concept from a single example means AI is getting smart-scary smart.

@TheHolyEagle33 10 ай бұрын

They do have their database to combine/ train with the pictures.

@allielynmorg1861 10 ай бұрын

dude i remember playing with you and dirtbike and rcsandy (or something like that) wayyy back in the day, youre channel has grown so much! you might remember me, i was AkayAllie

@Dr.BestBuy 10 ай бұрын

Clean Cut Matt

@RandumbThings 10 ай бұрын

I am genuinely confused why they don't just release this already?

@David.Alberg 10 ай бұрын

Why should they? Don't think they let people like us profit from that. They first are going to make tons of money with most of their Technology ofc. It's like people saying people using AI will replace other people but no that's very wrong. People owning the AI will replace people who don't own one 😂

@RandumbThings 10 ай бұрын

@@David.Alberg I get that for things like language models, but i don't really get how not releasing this could be beneficial.

@David.Alberg 10 ай бұрын

@@RandumbThings it's all about capitalism and competition. The world runs on money ofc. I really hope that in the next 5 years we are not dependent on money and everything will be much better.

@Gerlaffy 10 ай бұрын

Because it's not 2030/40 yet. Around that time it'll be less about money and more about status

@David.Alberg 10 ай бұрын

@@Gerlaffy you are right but I guess you are underestimating exponential growth so it will be probably earlier

@FRareDom 10 ай бұрын

damn, cant wait for the model to release

@sazarod 10 ай бұрын

Hold onto your papers, fellow scholars...

@noobethgamingtonthethird 10 ай бұрын

real

@zeddpilsner4 10 ай бұрын

Hey Chat GPT is the title of this video gramatically correct? No, the sentence "Way Better Then Dreambooth! Custom AI Models Based on Your Photos!" is not grammatically correct. The word "then" should be "than" when making comparisons. The corrected sentence would be: "Way Better Than Dreambooth! Custom AI Models Based on Your Photos!"

@BeginningInfluence55 10 ай бұрын

You really need ChatGPT for that? Damn humanity is doomed

@MobileJeremie 5 ай бұрын

is this available yet? and or is there something else out there now?

@Queenbeez786 8 ай бұрын

oh god cant wait

@Blastmaster321 10 ай бұрын

Very nice

@lollihonk 2 ай бұрын

Any update on this?

@-You-Tube- 10 ай бұрын

3:36 Gotcha, Matt!!

@saymydomain9504 10 ай бұрын

What will Matts next video might be hmm🤔? Oh i think it will be on "FullJourney" am i right???😄

@robd7724 10 ай бұрын

FYI there's a typo in your description, it says "then" instead of "than" 👍

10 ай бұрын

At least we know he isnt using ai to generate his titles 😅

@tombradford7035 10 ай бұрын

Just release the thing and Matt can put the link up!

@starwarsnuggets 10 ай бұрын

make a video on firefly generative font styles

@Raulikien 10 ай бұрын

How is it different than LoRAs, just smaller size?

@meijiishin5650 10 ай бұрын

filesize is one thing, but it seems like the big perk is being able to use a ton of these fine-tuned model extensions together and also that they are much more coherent than LoRA. In my experience, LoRA does great for styles and pretty good on characters, but when you throw in a new concept they don't often play nice with each other. This new technique seems like it can keep things much more coherent if you're pumping a ton of concepts, styles, and characters into the model.

@realcinnamongold 10 ай бұрын

GRAMMAR ALERT!!! YOU PUT THEN, NOT THAN!!! pls fix ty :)

@woszkar 10 ай бұрын

Wish we can use this one day!

@LouisGedo 10 ай бұрын

So the most important question is.......when will the public get access to NVidia's model?

@nedo68 10 ай бұрын

never, but we have free AI models, SD1.5 or the new SDXL, that's all you really need.

@eatmybutt42069 10 ай бұрын

Stable diffusion textual inversions do pretty much the same thing and are small in file size.

@edd9581 10 ай бұрын

But they are not as coherent as this method. Textual inversion is more a concept of styles than subjects

@nickiesnook 10 ай бұрын

based

@ZacharyRodriguezVlogs 10 ай бұрын

I like your shirt.

@RedRisotto 10 ай бұрын

Assuming that the chosen examples shown are NOT cherry-picked is incredibly naïve.

@wakariah 10 ай бұрын

gotta wait for someone smart to make it into an a1111 extension

@andrewxzvxcud2 10 ай бұрын

3:36 😂

@fossil98 10 ай бұрын

Damn its like textual inversion on crack

@tanksten7549 10 ай бұрын

*than

@Yozo_official 10 ай бұрын

1h 137 likes 207k suns

@gorsignups 6 ай бұрын

it's "than", not "then"

@devfromthefuture506 10 ай бұрын

Create a new pink Floyd music with AI please

@Drugs543 10 ай бұрын

@methaneconan 10 ай бұрын

the

@realcinnamongold 10 ай бұрын

fox

@realcinnamongold 10 ай бұрын

jumps

@realcinnamongold 10 ай бұрын

over

@realcinnamongold 10 ай бұрын

the

@realcinnamongold 10 ай бұрын

lazy

@tonebonetones 10 ай бұрын

'Super impressive stuff". Really? Its hardly any better in the examples you illustrate.