AI art, explained
How programmers turned the internet into a paintbrush. DALL-E 2, Midjourney, Imagen, explained.
Subscribe and turn on notifications 🔔 so you don't miss any videos: goo.gl/0bsAjO
Beginning in January 2021, advances in AI research have produced a plethora of deep-learning models capable of generating original images from simple text prompts, effectively extending the human imagination. Researchers at OpenAI, Google, Facebook, and others have developed text-to-image tools that they have not yet released to the public, and similar models have proliferated online in the open-source arena and at smaller companies like Midjourney.
These tools represent a massive cultural shift because they remove the requirement for technical labor from the process of image-making. Instead, they select for creative ideation, skillful use of language, and curatorial taste. The ultimate consequences are difficult to predict, but - like the invention of the camera, and the digital camera thereafter - these algorithms herald a new, democratized form of expression that will commence another explosion in the volume of imagery produced by humans. But, like other automated systems trained on historical data and internet images, they also come with risks that have not been resolved.
The video above is a primer on how we got here, how this technology works, and some of the implications. And for an extended discussion about what this means for human artists, designers, and illustrators, check out this bonus video: • Bonus video: What AI a...
Midjourney: www.midjourney.com
List of free AI Art tools: pharmapsychotic.com/tools.html
Sources:
arxiv.org/abs/1511.02793
arnicas.substack.com/p/titaa-...
/ copyright-storm-author...
tedunderwood.com/2021/10/21/l...
/ a-journey-through-mult...
jxmo.notion.site/The-Weird-an...
ml.berkeley.edu/blog/posts/cl...
multimodal.art/
openai.com/blog/dall-e/
openai.com/blog/clip/
openai.com/dall-e-2/
laion.ai/laion-5b-a-new-era-o...
arxiv.org/abs/2110.01963
Make sure you never miss behind the scenes content in the Vox Video newsletter, sign up here: vox.com/video-newsletter
Vox.com is a news website that helps you cut through the noise and understand what's really driving the events in the headlines. Check out www.vox.com
Support Vox's reporting with a one-time or recurring contribution: vox.com/contribute-now
Shop the Vox merch store: vox.com/store
Watch our full video catalog: goo.gl/IZONyE
Follow Vox on Facebook: / vox
Follow Vox on Twitter: / voxdotcom
Follow Vox on TikTok: / voxdotcom
Thanks for watching! The video above is a primer on how we got here, how this technology works, and some of the implications. And for an extended discussion about what this means for human artists, designers, and illustrators, check out this bonus video: kzhead.info/sun/pqp7ltaSZIBpemw/bejne.html
first
xd
Sorry
❤️👍🏻👍🏻👍🏻
👁🌸👁
This is so scary, it’s only a matter of time before AI can generate videos and then whole movies with complete soundtracks, characters and a plot
And we won’t need artist, graphic designers, just to name a few.
@@gilberttorres8 We need those to get there
@@Ghreinos not if the machine already has enough data to recreate nearly everything we can think of.
Well, Hollywood doesn't do well with people making movies, maybe it's time to let computers take the helm.
That has been done already years ago
As a researcher working on generative models, this is one of the best, clean and concise explanations for the tech! Kudos to the Vox team! :')
do you know a good text to image sight?
Same. Great job by Vox. Also working on Generative models in the industry
@@bigdelicious8006 Not sure if any text to image models are available for free. You'll need some credits to start
@@bigdelicious8006 maybe starry ai
@@ananthasrao7600 No, they do have great free colab notebooks.
I feel discouraged from studying art. There's a feeling of satisfaction that comes from conquering something so difficult, from sitting back and seeing the fruits of my efforts grow. I'm afraid of becoming obsolete in a way that's difficult to articulate.
I'm just some random guy, but it's hard for me to see how this could invalidate human art. It will have a huge effect on where images come from, but a computer can't express YOU. There's something alien about what computers are creating, it will likely fade with time, but I think people will always care about that difference. Also, perhaps the art education you're getting isn't that great. There's a lot of bad art education and educators out there.
@@Vinemaple Thank you. I needed to hear that.
@@Babyrobot444 You're welcome. I struggle to find the courage to create, but that's not the reason I decided not to get a 4 year degree in an artistic major.
@@Vinemaple I sense a story.
@@Vinemaple IMO computers will be head to head with real artists. Just constant fight. Now it looks like hand-made is the way.
As an ML researcher, this was the best 'public facing' explanation of latent space I've ever seen. Good job Vox team.
This is the best explanation of the tech I’ve seen so far. Would love to see a follow up video on this for animations. I believe this is a game changer for music videos.
hmm i wonder why you think it would be a game changer for music videos surely nobody has done that before
@@piggywink333boyfriend6 music generative models are not that good
wild DoodleChaos spotted
@@glock7061 the sarcasm lies in the second line of my message
You don't need LSD when you even have this AI
As a digital artist and graphic designer, this is ridiculously fascinating and scary🤯 I've been watching every videos of Dall-E on the internet...
I understand your fear because it could take your job away
You are not supposed to be drawing people. That goes against Islam.
@@canaryinacoalmine7267 yes but what about background artists they could lsoe their job
@@canaryinacoalmine7267 what does this have to do with Islam?
@@canaryinacoalmine7267 Muslim on Internet said AI is not haram?
I'm doing a research project in machine learning, and I've seen various KZheadrs getting things wrong in their explanation of AI. But you guys completely nailed the concept of latent space. I guess you left out how exactly the encoder and decoder works, but this video is targeted at the general public, so fair enough.
hey, is your project research available somewhere ? I'm sort of interested !
i would love to see the research project!
Have you heard the whispers about VideoGPT? It's the not-so-secret weapon of top-tier video creators.
The quality with which Vox is able to simplify hard things is amazing
Joss is amazing. This is truly the pinnacle of tech journalism.
It’s the pace and articulation of complex subjects for me
I hope tech journalism will replace by AI.
Seeing AI unfold in real time over the years is so satisfying and also a bit terrifying.
I remember when Cleverbot was the extent of AI intelligence. That was only about a decade ago. Pretty wild.
Lol I don't see what's so terrifying about it honestly. I just find it fascinating
@@averythesuperhero you can watch conference "Global Crisis. This already affects everyone" And other "Global crises" conferences and forums for better understanding of situation in which we are all now. It's about AI crisis and climatic, ecological and social crises. It's not like United Nations conferences where they talk about what gives them money, these conferences are organized by really caring people, volunteers from 180 countries on a platform of Creative society project, and they are for people to understand our problems and real solutions and implement them now.
@@averythesuperhero AI is just an instrument. And as it is fascinating when used for everyone's good, it is also just as terrifying when misused. To see it just think about it a bit, analyse, predict possible scenarios.
@@ilove-jesus I don't think I'm gonna sit through 11+ hours of information that I don't even know to be reputable lol and talking about it analyzing and predicting possible scenarios is not only vague but kind of underwhelming in the way you described it. That's something that computers have been doing long before AI started getting developed, and it's something that humans have done and continue to do forever
As an artist this scares and impresses me. Its scaring me cause of even the artistic field being overrun by ai in the future but impresses me cause it is just, impressive
In 3 weeks there will be a robot to mix the paint pick the canvas and create the best masterpiece ever in the combined styles of every great master in 5mins. There's a 3d printer in 6 days that will replace sculptures. And a musical version to replace musicians I'm a builder so won't be replaced until November
Maybe that’s how portrait painters felt when photography was created. There is sure going to be a revolutionary change in art making. AI won’t stop people from making art - nothing will stop human from doing so - we would just have a new way of thinking about and creating art. And I’m all for that
@@banisterman6083 And?
@@azukib2230 photography didn't take the stylization away from art, it just takes the realism away. AI on the other hand, takes away the style and illustrative side of art, while using data from real art. It creates its own art, not capture reality. That's why it's different, but yeah I think a revolutionary change is inevitable at this point
Art was supposed to be the last frontier of AI. It was supposed to be the most "human" thing there was. This is terrifying.
I used to daydream about computers being able to create a virtual reality version of a book. Looks like that’s on the way. It will probably be even better than that, with the simulation being customized for each user’s specific interests. The future is nuts.
reading the hitchhiker's guide to the galaxy with this would be fun!
Re-arranging a _whole_ constellation into a peen constellation is surely fun!
This is especially important to me because of Aphantasia, which means I see NOTHING in my head when I read a book.
🤯
I got plans already
you can’t just hit me with the fact that 2015 was 7 years ago so early in the morning
A little lead-up would've helped
8… 😵💫
I remember a teacher from my childhood once she said to me "your drawings will get you knowhere, they will save you from nothing", while embarassing me in front of everyone and ripping appart my drawing, and now, having battled heavy depression for many years and trying my best for working in the future in something that has to do with drawings or illustrations... AI came in, "learning" so extremely fast that in a handful of years they will totally outclass artists I mean, ofc I can draw just as a hobby, but a hobby would not give me enough money to pay my bills if the ones who would pay me look for a faster and cheaper option, I guess my teacher (and my father) were right all along
Don't give up on your dreams. This is still in its infancy and nowhere near perfected yet, and I think its going to end up being a tool for artist more than a replacement. For right now, there are still opportunities for illustrators, concepts artists, etc. in the traditional sense. AI will have a massive impact on arts and entertainment, but I doubt AI is going to make you and other artists irrelevant (at least, not in the ways you think it might). Some jobs will disappear, but some jobs will just change. Also, we have no idea what new types of opportunities this is going to create.
You just have to adapt. You can use AI, it will not replace you if you are its employer. You will probably have to change your medium, dont just draw pictures. Make a whole comic book. If you are an artist its a given that you are a creative person, that means you definitely can think of stories to tell. You can focus on the important details while AI can do the boring and mundane tasks that would take up your time like unimportant backgrounds. And thats just one example. There's animations, 3d art. Drawing has a lot of applications that AI cant completely take over, and never will.
@@thunderwatch8463if an artist uses Ai to make the thing for them, they are not an artist. Ai is not art. Someone who uses the Ai is not an artist, they are commissioning the Ai to “make” it for them.
@@SkygerbyGameplaysusing Ai to do a major part of something for you is lazy and soulless. If someone is at the point where an Ai does the whole thing for them, they aren’t an artist.
Reminds me of that one scene in I, Robot: Will Smith: "Can a robot paint a masterpiece?" Robot: "Can _you_ ?" At this point it can now be rewritten as: Will Smith: "Can a robot paint a masterpiece?" Robot: " *Yes.* Can _you_ ?"
Surprised you have 2 reply man
They still can't paint masterpieces.
@@Pantano63 Some are pretty close. Just 3 years from a program that fills in blanks on a spreadsheet to a program that can create basically anything in seconds at a quality that rivals a human. Give it 20 years and the world will be filled with 'masterpieces' created by this type of 'AI'. There's nothing stopping this from being applied to Film/Video, Games, Music.
@@joepopplewell680 It's already been applied for creating terrain in video games. But it's a far cry from doing menial tasks to creating actual masterpieces.
@@Pantano63 Don't worry, the AIs aren't coming for your job yet.
Challenge, having done a Computer Ethics and Law Course were we covered some of the topic, is as follows When looking at sites like Facebook, Twitter, DeviantArt, or any other website that will host art content is that the individual artist or creator is not paying for the server space. Server space being what the buzz word is of "Cloud" which is owned by another company or individual. As such, the issue being that Meta (Formerly Facebook), and others own what ever a person posts to the social media platforms as it is on the company servers...that does not mean the creator does not have copyright to the creation, but that is the sticky situation when artists post works online period and can be found with a simple google search...the most similar form to understand is owning a physical copy of a movie, the person does not really own the movie and is not legally allowed to alter the movie from what the creator intended (though this too is being fought in the courts with companies like VidAngel trying to make even rated R films family friendly through editing like a non-movie channel can through a cable or satellite tv service can...through contracts that allow such actions). As the professor instructed, in the Computer Ethics and Law Class, to help protect images from being used for AI or even just being used without consent of the original creator...use Watermarks all over the image, as the AI and Machine Learning will not be able to get passed all of the watermarks to generate the clear images...also as stated in the class, instead of posting to Social Media on server space you are not in control of (as Facebook and them own it) everyone has three viable options with the last one being the worst of the three to show art works or any other creations that are the best protections from a simple google search that is helping to feed the AI generation of projects. Option 1: Host a personal server with your own personal images, and pay for a domain to show images you want, and due to SEO (Search Engine Optimization) understand you still will need to use watermarks on the posted images and then have a link or email where people can contact to ask for proper permission to use the art created without watermarks, but make sure to get a signed agreement that the person will not use it for personal monetary gain (similar to an NDA) Option 2: As most people can not get the licensing to host a personal server that is publicly available go through a website hosting company to host your personal website (NOT for FREE), pay for a URL, and follow the rest of option 1 Option 3: Use Social Media like Facebook, DeviantART, Twitter, etc...but make sure you keep original copies of the work...and only post once a large portion of the work has water markings to make it much harder for the work to be used by AI and ML when it comes to AI art.
As musician I'm excited and afraid in a same time knowing this will certainly come too for my art. What a time to be alive!
I think this was bound to happen. I tried using one of these programs and it's actually cool. I think that having ways of giving credit to artists that are used for these programs would be a good step. I can see AI art being a great source of inspiration and ideas to use and plan out different types of art. For a novice like me, it can actually be a good learning tool over how to produce different types of art. This won't be an easy transition, but I think it's a necessary one that we need to hammer out the legal and ethical details now rather than waiting for them to haphazardly come together.
Let us still not forget the fact that the generated images are derived from hundreds or thousands of creative artworks by us, humans. It is like the arts of different artist all come together to form an unimaginable piece we do not expect. It is still incomparable to an art piece that has the soul and passion of an artist.
I felt better after realizing the computer didn't create the art from within, it had to pull from humans. If AI replaces us artists, then it was our own work that became our end. I mean humans created the AI in the first place but I digress.
Photobashes already exist, this just automate sit into mundaness. Boring and soulless, lacking semiosis and cultural purpose. This might appeal to hollywood and braindead american consumerists but not to the artistic subcultures who actually support artists and have a basic sense of artistic merit and know "how to read art".
We do the exact same thing. Our art style comes from the combination of things we were influenced by. Sadly I feel that it will take over because the artwork is actually really good
@@ayanari3531 > *Photobashes already exist* Though that is something different from how things like stable diffusion works.
@@202cardline Show me a single human artist that wasn't inspired or learned from the works of other artists.
This video is mindblowing and awe inspiring. Such simple and effective descriptions of the processes, along with original art created by the models!
As an artist who dabbles in the Arts as a photographer who dabbles in photography for a decade as a filmmaker who has dabbled in filmmaking for over a decade I am very excited for this new technology I think we should always embrace the future
Same🙌
That's because you're skillless, why else would you need a computer to do it for you. People likeminded will do the same as you, pushing you further down the skillless well. AI will be generating films, next.
@@ayanari3531 skillless? I am contracted to many large companies and businesses and paid very well for my work I doubt they would keep me if I was that skillless
As a science fiction fan, I always assumed that the time when AI technology advanced to the point of artistic expression would be after my lifetime. Yet, here it is in a rapid breakthrough when I'm only 60.
Incredible how this is progressing it's shocking what the researchers have done.
They just added more layers and more data
@@user-pe1ek5vz6q thanks for explaining progress
@@user-pe1ek5vz6q I wish I could add more brain to my brain.
@@zubinkynto You can collaborate with other peoples
When thinking of professions that could be phased out by AI, artists never came across my mind. The future really is scary.
Wait till you realize AI is writing AI code
Creativity... they say that is one trait AI will never replicate. That's what I'm told anyways.
Artists are still less likely to be phased out by AI. I mean, AI used those artists' style in the first place and not the other way around. There will always be an infinite number of art styles that our brain hasn't thought of yet and when there's no source of info, the AI won't have a set of examples to copy with. One thing that AI doesn't have is human capabilities in art to create something out of nothing through consciousness, at least for now.
Technology had always helped humans to create art. Filippo Brunelleschi in Florence invented a tool to draw geometrically perfect prospective with a single vanishing point. Artists will change as they always have done.
@@s_ame1135 as an artist my self i agree
The quality of VOX's non-political content is BONKERS. So amazing.
ye
Agreed.
I can't remember the last time I was truly mind-blown like this.. Really feels we're at the frontier for a new approach to creative arts, the ramifications are awe inspiring and a little terrifying. Also poses the question; how does this change how we feel about existing art, when you can create new masterpieces in an instant..
Mind blown 🤯
speaking of being mind blown...
Can’t wait until this tech is applied to video game development. Imagine hopping online with your buddies on some FPS game, typing in a prompt about what kind of map you want to play, then having a completely unique and interactive map to play on.
thats kinda what new flight simulator did actually. They have made possible to generate the whole world as a game map using AI
@@burakkan6264 Minecraft also did what you're describing but Pfann is saying if you could make an entirely new map that has to do with a personal prompt and is unique and not some completely random terrain
@@Mufraan Correction, Minecraft does not use AI to generate its worlds. It uses Procedural World Generation, wherein the programmer defines a couple of variables(Land, Water, Specific Structures et cetera) and their rarities(For example, Woodland Mansions are rarer to find in close proximity as compared to villages) and then the program based on their rarities, randomly generates these structures infinitely.
@@Mufraan mincraft uses procedural generation algorithms, there's no deep learning involved.
TF2?
We humans derive meaning, satisfaction, hope and even therapy from conjuring up our own images. There is so much mystery within the frontier of our own minds but ultimately, it is limited. We do not want to find the limitations of our own psyches by watching AI outstrip and outperform what should be a human frontier. AI acceleration is dwarfing its own creations - never mind how small, mundane, and slow it could render human art. I’m a big fan of technology, but I’m a bigger fan of art.
Ultimately AI created art is still made by humans, it just uses clever tools in the process. The artist in this case are the clever humans who wrote the code.
@@samik83 this thread sounds so wise it makes me proud
There will always be a place for real art. Every human is technically an AI of its own and these small variations are what makes it possible to have such different creations all of which are an expression of the unique configuration of each human. The AI is not really doing anything different from a commissioned artist is it? It's just really fast. You could do the exact same thing but you would need to do a bit of research and then spend a lot of time making it. It's the speed that's the real concern here however what's interesting is that if I tell you to create something whose concepts you have a decent understanding of you too could mentally generate it even faster than an AI....we just can't convert these into reality.
@@samik83 Wrote the code, but didn't make the picture. You're not the one making the marks, you are not part of the experience, there is no direct human element in it, and it's an entirely different skill. You do not know the fundamentals of drawing and painting, so how can you take credit for such a thing? You cannot even project the exact image you have in your mind unto a canvas. It's soulless and disgusting.
@@crepooscul And yet, theres a pretty picture
"The field of AI is highly interdisciplinary & evolutionary. The more AI penetrates our life and environment, the more comprehensive the points we have to consider and adapt. Technological developments are far ahead of ethical & philosophical interpretations. This fact is disturbing. We need to close this gap as soon as possible." ~ Murat Durmus (THE AI THOUGHT BOOK)
can you explain this in fortnite term??!
Well said. Sadly this is the area that bothers the beneficiaries the least. In a just world, that's something that would've been resolved before giving this much power to the public for free.
Morality is meaningless. We should only concern ourselves with one question: *What works?* (and *What works best?* ). Every problem is simply a goal, and every goal has a (theoretically) optimal solution. Concerning yourself with "Is that a good idea, guys!? Isn't that going to hurt their feelings - wait is that MORAL, guys? No, no! That's not ETHICAL - we shouldn't do it!" is a huge waste of time.
You "philosophers" haven't even decided on whether you _exist_ or not. Keep coming up with questions (that you never solve), and we'll come up with solutions that work well.
this is another way of preventing creative blocks. imagine you're stuck in a scene you're creating for a chapter for a fiction book you're writing, and you're stuck with only a bunch of words to describe it. putting those words as prompts in a dall-e based image production system can help even writers visualize the scene better and even come up with distinct personalities for the characters they's like to have for that particular scene. and that's just one way of using it in a manner that could help expand creative horizons. film makers and musicians can benefit from this too.
You've done a really great job here. The context & framing, the explanations, and your overall take, focused on the artistic outcomes that have already been happening in the short time since the release of these models, all A+. Motivating multiple dimensional representations with your balloon/banana classifier, and explaining latent space as a natural outcome of making progress on that task, I will definitely use that. And tying it all together with the cheeky "multi-dimensional latent space" Midjourney prompt 👏
This just made me realize again how much more terrifying technology keeps getting
It also made me realize how beautiful it can be.
I dont think this is terrifying, just impressive and beautiful really
Peak 2022 comment, I guess you are an antivax and a climate change denier too right?
@@hsrocha2479 It's not terrifying; the concept of unlimited pictures and end of art as we know it may be overwhelming for lots of people
@@stanislawignacywe won't be needing artist, we won't be needing designers, we won't need any talent to accomplish everything Its terrifying ok? Maybe one day technology will replace all humans job
One of the best Vox reportings I've ever seen. Not even Tech KZheadrs are bringing up the potential consequences of this technology and you guys touched on it beautifully. Well done, very excited and scared for the future of this technology!
The question regarding the copyright of images generated by trained models is absolutely resolved! The precedent comes from a case called Naruto v. Slater which ruled that only a human can create art that is copyrightable. No one can own the rights to an image generated by an AI because they are uncopyrightable.
So did the ruling also say how many pixel I as a human have to change to make it copyrightable again? Also that ruling only applies in the USA, other country might decide quite differently.
@@tristanwegner But the question here is "By how much does one have to change an existing artwork in order to create a new, seperate artwork?" and not "Who has the copyright of the original artwork?" The second question is definetly resolved (at least in the US, as you rightfully pointed out). And surely there allready exists an answer to the first question, as it is far older than AI image generation.
This is gonna be so extremely subjective. It will get more and more impossible to even know if AI created it or not
that is not yet 'resolved'
@@Leviweyhrich Well, you can prove that it's human made by showing parts of the drawing process.
6:38-9:49 That was by far the best explanation of deep learning I've ever heard. Also it gives you a sense of why mathematicians care about higher dimensions; their results are useful even if these higher dimensions don't physically exist.
I won't last half that long before I inevitably say "vector" and lose everyone's attention
As a Computer Science (AI) student from the University of Toronto (where the paper in 00:26 came from), I'm truly amazed by how well this video is structured and how you intuitively explain the concepts of features, data, dimensions, latent space with such clarity! 👍 Thank you @Vox @Joss Fong!
Yeah, vox video are more interesting (and probably more effective) than 90% of the lectures I attend XD Lol
12:57 "my 5 year old drew war" is something.
Thank you for creating this video in such objective tone. I think this is a great starting point for anyone who wants to understand what's going on, whether they're in favor or not towards the use of this technology.
I guess, once this model is perfected, the definition of a human artist changes to something completely different from what it used to mean.
Writers will become a painting artist too. Imagine a whole movie made out of text-to-image from a book.
What?
the same thing happened in the past when photos were invented, it makes art more accessible
@@Jeyblox ??? Art is not suppose to be "accessible". It's not water and it's not a just another product. It's a skill and it use to be uniquely human, it was a human endeavor, a human expression, it was humans putting our unique voices and insights and ideas into the world, it was humans speaking to humans about what it was to be human. This isn't like the camera, this is a conceptual feature that mechanizes deep creativity en masse. If all we need to do now is put a "I want this combo of these things" into a data-base and walk away with something unique... we ALL lose the ability to make those creative decisions on our own - we just CONSUME. We are letting computers and robots take away all of our human abilities. In 3 generations we will have very little left that isn't done FOR us and we will have no idea how that happens or how to do anything ourselves or have any REASON to do anything ourselves. I don't know where this is taking us but it certainly doesn't look promising.
@@mattwood1323 you don't "lose" anything. Wanna draw? Draw then.
So cool, so scary, so real. The biases, the creative possibilities, the 500 variables humans can even name. The fact that we can relate to the images and have such a clear process, can help us learn about our own creative process.
and it hints at the nature of the human mind as well
@@daviga1 not necessarily, depends what you mean
Wonder where AI will go from here.
@@aixart1719 Trust me you don't want to know where this technology is heading.
It's exciting yes, but there is already a huge problem with plagiarism in Art. With the rise of NFT's many have taken artists work or even made an AI data set of the artists style to sell online.
I really hope NFT would fall into obscurity
Just not talk about how NFT artists have made hundreds of thousands of dollars off of stolen artwork?
As a digital collage maker, this is great for us as a never ending resource for material to use
Or for your consumers. Will the freelance industry exist in the future? I think it will be scarce. Goodluck
@@AlbertKimMusic consumers?
I wish you guys showcased DALLE 2 more, it's leaps ahead of Midjourney, although what they've been able to accomplish so quickly is amazing.
It's hard because there's a very limited waitlist for DALLE 2
Dalle 2 is really good compared to others. It paints my prompts more accurately than ever before. The only issue is the credit system, so it's not free anymore after you used up all of your credits.
Are we lose the meaning behind the work? The meaning of the process of making art.
1:23 It's been quite dramatic how the community of AI generated imagery has evolved since the release of this video
I'm so envious of my nephew, he'd be my age when these have matured
As an artist this is just incredibly scary.
Lean in fellow artist. You got this.
Get a job and continue doing your passion.
Just watched this today while trying to learn a way to explain this tech to non technical people I know and I am really impressed. Excellent work with a great breakdown with some awesome visuals.
Coming from a computer engineer: you all explained this so well. This is amazing!
Couldn’t agree more.
“Oh, yeah. Oooh, ahhh, that’s how it always starts. Then later there’s running and screaming.” Dr. Ian Malcom
This channel is always so well thought-out and explained, it’s awesome.
Couldn’t agree more.
OMG the best part is the reveal of Joss ! No AI can come up with such a beautiful image
I think this video explains most fundamental steps of the learning and creation, not only one specific part like 'the diffusion model' like in many other videos. Great work.
Best simplified explanation of deep learning I've ever seen... well done!
I feel bad for human creators that don't want their work used by the algorithm. There's no way to prove that it was their creation(s) that was used to make the image. The problem is compounded when you add in that every image generated is a true "1 of 1. Still the technology is truly fascinating.
The last couple of days I have been creating images with chatgpt4+dalle3 and watching this video now I realize that even though it's only one year ago. Dalle 2 was the wright brothers airplane. While chatgpt4+dalle3 is a space shuttle. That is how astonishingly fast the evolution is going. The S curve is going bananas. How long will we improve at exponential speeds? Nobody knows. What will the cutting edge AI technology be when the S curves starts slowing? Nobody knows. For now, enjoy the ride before all the negative aspects of this will hit you like a crippling anxiety.
Watching this video 10 months after it was released feels like watching a documentary from tens of years ago.
As someone working with ML, I've gotta pay my respects to this video. Clearly explained and beautifully produced.
The explanation for latent space and deep learning was really well made imo!
"i asked AI to make a Music Video... the results are trippy"
i gotta appreciate how this video hits the sweet spot of being informative but also simple. it's not so complex that it's hard to understand, but it's not so simple that it becomes misinformation either
This is an amazing resource for artists. You can generate an image to use as a reference for an abstract idea you have, and no one will ever get the same image due to randomness in the code.
The more you remove the human element, the more the experience cheapens.
This is really well researched and love how many Interviews y’all did!
My simple mind cannot even comprehend how cool it is. Thank you Vox for explaining it so simply😘 Maybe in future, you can write and create a whole movie
As a visual artist, thinking about the infinite possibilities for reference choices is very fascinating to me. But as a black woman who creates majority of my art around this subject, I am slightly worried about some biases in AI and how useful some of the generated images will be for me.
Of course make it a race issue then we can cancel AI for being racist :)
you can include the subject in your prompt
Fascinating... and terrifying and the same time. It also reminds me of a movie from 1956 -- The forbidden planet -- where a machine was capable of creating everything the inhabitants of such planet could imagine.
I'm currently studying digital art and I'm scared for my life.
same :(
all I can say is learn how to use these models
I dont think you intended to make latent space sound scary, but it definitely is an amazing thing to grasp on a philosophical level.
when you noclip out of the backrooms you end up in the latent space
give anyone who is responsible with this explanation a raise, you successfully explaining nth dimension that is easy to digest!
Midjourney is still blowing my mind on a daily basis. And it's improved massively over the last month, the top images are incredible, way better than they were a month ago. And it's ability to replicate artist's style is amazing. This thing is going to put concept artists out of work.
No. Computers are not creative.
@@Potato-pn8sg Call it what you want. They'll still put concept artists out of work. Humans can't do what AI is doing right now. Just wait 5 or 10 years.
@@groob33 your right
They can't think for themselves, they just replicate what humans do and modify it.
@@groob33 all the most unique and interesting work I've seen has been done by people, the best a program can do is impressive only in a way you would be impressed by a toddler drawing a tree.
about 10 years ago, I was talking to a friend of mine and I was saying that if there is any technology that could turn thoughts into arts, designs, and music, I would become a great artist. But I had this thought more than 10 years ago! and now they are about to bring this tech to the real world!? That's so cool! Hats off buddies!
So will everyone else. Art is dead.
So basically make art without any effort? It's going to be worthless and saturate the medium, a big part of a fantastic painting is appreciating the human mind that projected that unto a canvas on their own, with the skills they've gathered over decades of experience. Scarcity makes things valuable and that's a fact.
@@crepooscul That's true. But what I thought or still think, is not like that exactly. I believe, the most powerful thing of an art is the imagination behind that art. In fact, imagination is the most important thing. So, the skill of drawing is a tool just. Yes, it surely requires great talent and effort but, there are lots of people who can draw better yet cannot imagine something creative or unique to put that on a physical canvas. On the other hand, there are people who ain't skilled enough to draw yet can use their imagination and if, they could turn that imagination into a drawing, it might become a wonderful masterpiece. Turning texts into A.I. generated art is just a beginning. Yes, there r so many matters to think about. Like, the uniqueness of an individual Artist. But apart from that, what's exciting to me is, soon it would be possible to convert the imagination into art. Someone's own creation, own style and uniqueness. That's what I think..
@@thisisnahian6753 Having a good imagination isn't an impressive skill. Anyone can do it with little to no training. Most people who draw regularly are in fact far more skilled in this than those who do not draw, due to their vast visual library that they've accumulated over the years. The skill of drawing is not "just a tool". A tool is a pencil, or any other mark making object. The skill of drawing represents the years of experience that artist has gathered. It's a showcase of their effort and achievements. Also, it will be impossible even for someone with great imagination to put on a canvas something through AI. The AI will be able to give you "suggestions" but it will never accurately transcribe what you're thinking. For some that will be "just enough", but it will never be ideal. And honestly the lack of skill cheapens the entire project massively. Anyone can imagine anything, bar some kind of cognitive issues. Here are some of the questions draughtsmen and painters get asked all the time: what medium did you use? how long did this piece take you? What are you going to answer? "DALEE"? I'll be like "oh, well my son who is in kindergarten can do that too, big deal."
@@crepooscul I agree with u on this. The difference is I'm just a bit open minded about technology in this case I'd say. That's why I think, the conversion of one's imagination into something tangible or viewable on 100% scale would be possible one day (Not today, maybe not by even Dall.E). That's it.. Otherwise all other things u say, I'm totally agreeing with u. 🤝
The tune at 1:20 sounds like a remix of Toccata and Fugue in D-minor.
Absolutely amazing video, from the investigation to illustration and the clarity of ideas, everything is perfect from this. I will say both congratulations and thanks for such content.
Thanks Vox, loved learning the science behind it! For dalle 2, i believe mkbhd did a video on it
I just realized something really disturbing. If AI can match an image to a word, how are those "prove you're not a robot" tests going to work now? If AI can figure out what a tree is, "click all the tiles with trees" no longer works.
Captchas have been obsolete big time. All you're doing when filling captchas is captioning data sets that are to be eventually fed to such models.
This reminds me of the nascent days of Photoshop and digital editing. This is going to bring on a whole new level of interesting stuff.
one of the best videos I've come across on KZhead, thank you to all involved, AI is progressing alot faster than I expected or times moving fast hehe.. amazing 👏
Yeah, it's a bit of a problem that the images of artists are used without consent by for-profit companies... Aside from that cool technology, it's gonna replace a lot of art but, at first, most probably, only lower-grade art. The interesting thing is that even if an artist's art is of higher quality, it will be overshadowed by the millions of images AI can generate specifically for a consumer in a blink of an eye. So, our art will become irrelevant for most viewers. But still, it's exciting to see how it develops!
I’m pretty sure ai art is transformative as it creates new and reasonably differing images from the data it’s given
Just look at legal eagles video about it
@@JustChillinxd well it's been a while )) sorry fot the late reply) actually yes it does create new images but doesn't have the creativity for now. Within these 11 months I haven't seen a single impressive artwork made by AI, mostly only "Marvell" level creations. Copy of a copy. The thing is that even if the images are different from the training data, usually materials used by for-profit companies should be licensed. Since they used it to create a product and sell it. It's just the law still isn't there. Maybe it's good since these technologies were created faster but maybe bad since there are other AI models based only on contibutions and licensed stuff
James Gurney’s point of the artist being able to opt out of having their art as an input is totally fair. But I think this is really beautiful and cool. I also think it’s really good. I think giving everyone the ability to realize the contents of their imagination is really positive.
As Steve said, keeping your paintings away from this is impossible. Also, someone else can just copy your style and put that in the training data.
This isn’t positive it’s satanic. Honing your craft as an artist is a rewarding, life affirming act. Technology like this not only means you no longer need to do this, it makes the peoples who do’s effort meaningless. Tech people need to be put in ovens before this gets worse.
@@cretaceoussteve3527 the AI should only be allowed to be used as a tool for artists/creatives; not to make art as a final piece. The artist isn’t the person typing an input; it’s the AI. The job of artists isn’t to input text; it’s creating and transforming; like transforming the output image of the AI. AI art shouldn’t be posted as art that someone made; it should only be known as “art that this algorithm made”. Because it takes images and styles and copies them. and the person “making” it by typing a prompt is a client not an artist.
The level of anxiety for tech vs art is not new, a similar existential crisis took the hearts of some painters with photography. I'll not go to say it's the same, the speed of the revolution is so fast that will be more traumatic but at the end we'll find new ways of sharing our obsessions
Another excellent piece by Vox. And so much has changed in the last eight months, with AI, since this video was posted. Thank you for explaining to me how the back end works. Talk about complexity. And yes, like one of the gentleman‘s concluding words stated, “It will bring a lot of good and a lot of bad.“ Just like the Internet. But I think at a whole new level. Example: AI is generating photorealistic people (soon to come videos). Imagine AI generated deep fakes. Add to that the epidemic we have now of sophisticated hacking. Add it all to a pot, stir together and you have the potential for unprecedented social chaos.
Would be cool to see this in music application. Ideating motifs in reference to what has just been written or played into the progression and its velocity and mpe data as well. Could be sweet.
yeah it could be a further extend of the emotions and ideas of music pieces
How about arts-to-text so the teachers won't ask anymore why the curtains are blue.
They are also working on this right now
This would be an easy way to find painting ideas when I need inspiration but it also scares me that this could potentially decrease painters bc ppl would instead be reliant on ai in terms of making art :/
And the Ai go nuts and people still left...
From a defendant's point of view, one argument could be that the use of a dataset of images to train a text-to-image model does not constitute copyright infringement because it is a transformative use of the original images. The purpose of the text-to-image model is not to copy or replicate the original images, but rather to learn from them in order to generate new and unique images. Additionally, the text-to-image model does not create exact copies of the original images, but rather creates new images that are influenced by the style of the original images but are not identical to them. Another argument could be that the use of a dataset of images to train a machine learning model falls under the fair use doctrine of copyright law. Fair use allows for the use of copyrighted material without permission for certain purposes, such as for the purpose of commentary, criticism, news reporting, teaching, scholarship, or research. As for the copyright laws in a class-action suit, the plaintiffs would have to prove that the defendant's use of their images in the dataset that was used to train the text-to-image model was not fair use. They would also have to prove that the text-to-image model created images that were substantially similar to their original images, and that this similarity caused them significant economic harm. It's also important to note that copyright laws differ from country to country and it's important to consult with a legal expert in your specific jurisdiction.
This is the best generative AI text-to-image explanation I've seen. All the designers should watch this.
This is genuinely amazing, hope to use it one day.
Your videos are always the best💯 I do receive a notification each time you post a new video.. We'll have regrets for things we did not participate in...Investment should always be on any creative man's heart for success in life.
Nice content mate! So happy to announce that I have gained financial freedom by investing in digital currency. Now I know that multi creation of various streams of income is the ideal Principle for financial sustainability.
I wanted to invest more in crypto, but the fluctuations in crypto value discouraged me into dumping.
@@vaztrevorknox4203 Crypto trading is the best investment anyone could get into. As it could make you rich in a blink of an eye, trading with an expert is the only key to successful trading
@@leither-truth4414 Exactly which is why I will always recommend Expert Arjun B Jagat to all Newbies/greenhorn interested in making bigger profits on crypto. He is reliable and profitable
I have heard a lot about investments with Mr Arjun B Jagat and how good is he, please how safe are the profits?
Really good video. One small thing: diffusion happens in latent space. Mapping to pixels happens at a later stage, which in Stable Diffusion, for example, is in the variational autoencoder (VAE). But this is as close as I've seen a pop-culture video get to describing latent space, so that's just a small nit.
Took an intro course on AI in college and loved how this video explained machine learning. That bit on the ‘Latent space’, 🤌🏾
Until today I didn't realize a computer only sees numerical data on images instead of an actual, visible image that a biological eye can see. Truly remarkable how machines process data!
yea, it's the best explanation a non-tech channel has given of deep learning rather than treating it as something completely mysterious.
Surprised that latent space was mentioned. Fantastic addition! That part where it was talking about balloon vs banana classification was amazing too
You did such a great job. What a great overview. I particularly love your explanation of latent space. Very economical. Very clear.
What I really want is a way to automatically generate movies, so I can finally get that sequel I've always wanted.
Just make it yourself. You'd have to get the copyright for the material anyway.
It's coming. It'll be trippy and weird but you can already see the seeds sprouting. AIs are writing scripts, having conversations, generating art, making animations, writing music...the hard part will be writing a prompt specific enough and having enough of a data set available. I don't think they're feeding these models star wars for example, and I wonder if they'd be allowed?
I have to say that the lighting and composition of the frame in interview of the person at 10:02 was beautiful. Something about the out of focus background, the zoomed in shot, the shadows cast by the trees on their face, and the color of the scene just all work together.
I agree
Amazing. Thought of this before as I tinker IBM Image recognition, but they made it possible. The artists were stunned to speak.
A great explanation of the latent space, much better than some vague "probability distribution"
What an excellent video. The technology is accurately and clearly explained. Truly impressive. Thanks!
I kinda feel bad for artists and photographers who tried their best to make the same results
I dont
AI is always limited by human training data like the example of a dancing taco on a beach wasn't pictured right. The program is basically the perfect sequel maker but it can never create new things.
Those artists you're talking about are also copying other artists in some way and just tag it as an "inspiration". The AI technically does the same thing as human artists been doing since it's basically creating its own unique art based off a set of requirements and not just a rag-tag copy-pasting of existing arts.
🎯 Key Takeaways for quick navigation: 00:00 🤖 *Introduction to AI art and image captioning* - AI development in image captioning. - The curiosity to generate images from text prompts. - Early challenges and experiments in generating novel scenes. 01:04 🎨 *Advancements in AI-generated art* - Progress in AI-generated art from 2015 to 2021. - The introduction of DALL-E and DALLE-2 by OpenAI. - The emergence of open-source developers creating text-to-image generators. 04:14 💬 *Prompt engineering and creative interaction with AI models* - The concept of "prompt engineering" in communicating with AI models. - Experimenting with various prompts and creative possibilities. - The ease of accessibility and use of AI-generated art tools. 06:24 🧠 *Understanding how AI models learn and create images* - Explaining how deep learning models learn and recognize images. - Introduction to the latent space and its role in generating images. - The generative process called diffusion in creating images from latent space. 08:27 🌌 *Exploring the multidimensional latent space* - The complexity of multidimensional latent spaces. - How latent space captures different variables and concepts. - The idea that any point in latent space represents a recipe for an image. 10:06 🎨 *Artistic implications and ethical considerations* - How AI can mimic artists' styles through prompts. - The need for transparency in disclosing the use of AI in art creation. - Copyright and ethical concerns related to AI-generated content. 11:36 🌐 *Societal impact and biases in AI-generated content* - Recognizing biases and limitations in AI models. - The diversity and representation issues in AI datasets. - The uncharted territory of AI-generated content's impact on society. 12:36 🚀 *The transformative potential of AI in creativity* - The broader implications of AI in human creativity. - The removal of barriers between ideas and visual content. - The unpredictable long-term consequences of AI in culture and communication. Made with HARPA AI
This is an amazing piece of journalism! Thanks for a succinct and well-laid-out explainer on the latest in ML art tech.
In terms of how generated images would affect artists, I feel like it might be similar to industrialization and mass production. There will always be a demand for real people's work. It won't replace artists just because it can generate anything you can think of. It can't think of its own, it just takes what has already been done and combines it. It doesn't know how to make a new art style, but real artists can.
That's pretty much what human beings do anyway - all artists are inspired by what's come before them.
But it does make the stock photo industry boom lol
This technology is useful when someone doesn't need something specific. Album covers, editorial illustration etc. But if you're working on a Film or video game and you want a very specific arrangement of elements in a shot because it tells a story. Like all the pieces in an environment someone might arrange to show a murder has taken place, and exactly how it happened. Or if you're designing a product that has to be used and handled by humans. Like a coffee maker, or a user interface for a car. There's a degree of understanding that's needed. To arrange the controls for something in a way that a human hand can use. it helps to have an understanding of what it is to have hands. And the way humans think. What would be more interesting to me as a designer would be an AI that doesn't use words as prompts but uses simple line sketches. It would be amazing if it could turn a line drawing that takes 5 minutes into a completed iteration, rendered in the material and color I choose at the push of a button.
Right but just like industrialization and automation the problem really comes back to who benefits the most from this and who is hurt the most. These AIs essentially learn by using real-world artists artwork without their permissions, and can then spit out new art that than benefits someone else entirely. That is a direct threat to artists who's livelihoods depends on their creative skills. Its not unreasonable to conclude that these AIs and whoever owns/profits from them are essentially stealing from artists. Its an incredibly awesome tool that has the potential to do great harm.
@@Darius-scifieart There already are tools that transform sketches into more complex images, look them up. It's still in its early days, but it's being worked on.
As an artist, I wanted to give my opinion about it. But because you made a bonus vid. with opinions from artists, I 'll wait and see what they have to say about it. But one thing I've to say about it. The artwork A.I. made isn't art, but the birth of A.I., that is actually the artwork!! In short: A.I. is the artwork, but artwork the A.I. made, isn't. No matter how beautiful it is. But that, that's just my opinion. ツ
Programming is an art, yes, but just as with Microsoft Word and Adobe Photoshop, the company that owns the software can't take ownership of what is produced by it. Similarly, software generating the results isn't the same as art, art is a practice, artwork can't be detached from the artworkers and AI users have no sense of how something in an image could be achieved. So you can't claim a painting, for example, is your painting, without knowing how it was painted, therefore calling yourself an artist for using it is a falsehood as artists can explain their artistry.