DALLE: AI Made This Thumbnail! 

What a time to be alive!

This terrifies me more than I care to admit. Not the fact it can make thumbnails, just the amount of articifial intelligence it takes to create these images and how far we've come in the past few years. In ten years the media landscape is going to be so different.

As a teacher, this would be incredibly useful for presentations and class materials! I spend way too much time browsing and searching for clipart that I desire. DALL·E 2 would be such a great help and time saver!

Ahah we're all watching Two Minute Papers. These new AI stuff are gonna help us make concepts faster. But wait for the day when Tiktok is flooded with viral content generated with AI only

I love how the the thumbnail you asked for was “a robot hand drawing” at 14:30. That could either be a drawing of a robot’s hand or a robot hand drawing something. Because of the ambiguity, it just decided to do both in the same image

imagine explaining this to someone from the middle ages

I’ve had access to DALLE 2 for about a week now and I can’t stop using it. I’ve been trying to see if it can help me invent new product ideas.

In the future you’ll just have to write the movie script. When you’re done you have the movie. In fact you can watch it as you write it. And change it in real time to try different things. Imagine how Hollywood will be transformed.

That'd be amazing for college/work presentations. As someone that can't draw, that just looks like a dream

This is both incredible and kinda scary at the same time.

Marques saying "What a time to be alive" at the end of the video clearly reminds of Two minutes papers channel :D

i remember watching this being so mind blown that so could make art. fast forward to today and i can’t escape ai art

"what a time to be alive" indeed! A video about Ai imaging wouldn't be complete without Two Minute Papers signature catchphrase ❤️

Artist: "Well, at least I have a job that ain't replaceable by any machine" AI: "Hold my bit"

As impressive as it is scary. Though in fairness the ability to type something in and have an image appear in front of you probably would scare artists in 90s too. But Google Images is already here and leveraged _by_ artists to create new ideas. Maybe Dall-e would would be used similarly. Artists could start projects by generating ideas with Dall-e, then improve them manually. For a lot of people the dall-e result will be enough, but others will want further customizations.

As someone who can’t draw to save my life but vividly visualizes things (ideas, places, things) in my head and has a knack for detail and descriptions, it would mean everything to me to finally be able to bring those to life in picture, not just words!!! I’ve longed to be able to do that, to describe what I see in my head and watch it take shape in a picture/painting! I know this most likely won’t be available to the public for a long while but knowing there’s something out there like this is thrilling!

Humans: “A picture is worth a thousand words.” DALL•E: “I can make that in less than 20.”

As an animator and designer, i beginning to understand how truckers feel.

As a computer scientist, I feel really glad DALL-E is covered by mainstream youtuber like you. It proves Marques Brownlee take a creative process on creating new content. Not just reviewing latest gadget and whatnot.

Within 10 years we will have software like "Make a comedy movie with Tom Cruise dressed as a t-rex"

As an illustrator and tech enthusiast, this terrifies and amazes me at the same time.

This tech is actually insane. I would use it to brain storm my own ideas: A Burrito made in the style of JoJo's Bizarre Adventure. Populate the image. Then go make the burrito.

Imagine 10-15 years in the future desperately wanting a fanfiction film of a franchise you love and ask your computer in detail to make it in the length and with the story you want. That's incredible! You could create your own media specific to you without relying on studios to deliver.

Ive been making heavy metal album covers with ai art, it’s pretty gnarly

This is amazing. Terrifying. But amazing tech.

As someone who makes video thumbnails for a job, this is one of the scariest things I've seen on my homepage

While this might look like it's gonna replace the jobs of artists, I feel like it's an *extremely* helpful tool for artists. Being able to get a reference image of something that doesn't exist, in under 10 seconds. Amazing

In the future, this is how movies will be made. The talent would be the creative team actually describe the movie so detailed enough to manipulate and add variables to the AI.

thank god someone is actually talking about this who has a platform. i felt like a crazy person the more gpt and dalle developed to be absolutely op and no one talking about it like it wasnt crazy human achievment

DALL-E 2 is an inflection point in human history in the creation of culture and art, and there is more to come in the following years thanks to the Deep Learning revolution. Awesome to see everyday more people talking about this!

Imagine a future where "on-demand" entertainment is created on demand the moment you request it.

It's amazing that this video was only uploaded a little over a year ago, and yet it's completely out of date. The way Marques talks about ai as well feels like it's from a different era.

Stuff like this is far more interesting than a new phone review which basically boils down to "better camera, slightly better performance"

This is actually monumental. I’m sure soon you can ask AI to write a whole script based off a concept and have it not only deliver a great story, but animate an infinite number of episodes on the fly.

I remember when people used to say that computers might be able to do repetitive work but never be able to take on art like painting, writing, etc. But I always knew it was just a matter of time until the AI got better. Can't wait for the day we can all input our health issues into an AI like this, and the results will spit out working solutions. Even to currently incurable diseases.

I can see Dall-E supporting artist productivity for a long time to come instead of flat out replacing them. The ideas you can play with before you create a finalised product is insane. You can also tackle projects now that would have been way too expensive to do before and often were simply unfeasible.

That Burger “Kringe” 😂 12:22

What lots of people fail to realize is that if this is where the technology is now, the exponential advancement of technology means that’s what is coming next is going to be unbelievable, and soon

imagine asking for a movie in a specific genre and it produce one for you exactly the one you want

I feel horrible for people who have spent decades honing their craft at digital art. It may not be a perfect replacement, but its definitely going to make a difficult and competitive field even more challenging.

The language understanding it’s probably the most impressive part. This is what holds us back from the future with a Star Trek AI we could talk to, looks like it’s closer than I thought

He said the moon wasn’t perfect. Reminded me of iRobot when Will Smith asks the robot if a robot can conduct a symphony and the robot replies, “can you?”

I love how “Person of Interest”, in 2008, guessed what computers could do in the future. As that show has an AI that created a whole new person, picture and all.

Content and context 👇🏻 10:40 Limits 11:35 Quirks 12:15 Letter error has been mostly fixed now 12:35 image transformation 13:17 taking jobs fast - brainstorming 15:00 Two minute papers

"What a time to be alive" is often said by Dr. Károly Zsolnai-Fehér on his RU-vid channel Two Minute Papers. I highly recommend checking it out if computer graphics and machine learning are interesting to you. Each video is a summary of an academic paper in those areas. It's been really cool to watch the progress of these things over the last few years. The jump from Dall-E 1 to 2 was way bigger than I expected. He has covered a few NeRF (Neural Radiance Fields) papers which it seems finally made it to a consumer product with some of the future Maps features Google showed off at I/O. Immersive View and the restaurant fly-through seem to be the same or a similar approach applied to their billions of street view and indoor imagery. Definitely looking forward to checking it out myself.

Imagine a tool that can make storyboards, in wich you detail things like characters, angle, height of the camera , movement, action and the AI generates sketchs of the scene

the AI keep the golden ratio, colour pallet and combinations in check too. Impressive

This is so dope, and kinda scary tbh. AI is becoming so advanced

14:59 missed opportunity to cite TwoMinutePapers :D

10:57 r34 artists: DANG IT!

I just can imagine some AI like DALL-E 2 being able to create a song from scratch, just giving some descriptions of the song, rhythm, style and even a known singer voice. That sounds pretty tangible and would be absolutely impressive too 😳🤯

It can't appreciate its own art. So basically an artist.

Finally I can describe my weird "Dreams" that I get while I'm asleep, to someone!!

Great now everyone can make NFT-s with this XD

I've been playing with a bunch of these tools for a few weeks (Haven't gotten DALL-E access yet) and hoooo boy there's so much to unpack.

I have been playing around with AI art a bit and I think the technology will replace a lot of things. I don't think it will replace the culture of art though. I watch a lot of artists on RU-vid and the reason I like it is because of the skill. When I watch someone draw a picture perfect image it makes me excited, and that is what gives it value. I don't look at my printer in the same way.

14:07 After effects used to have a brainstorm button that would basically randomize parameters on an effect, and it would give some interesting results. They removed it, but I thought it was kinda need for generating new ideas.

This is the most “mind blown “ tech I’ve ever seen. Period. I appreciate it even more as an artist. Just incredible.

When you brought up the Mona Lisa goat results, I said "oh my god" out loud. This is incredible. I also totally understand why a tool like this is a very long way away from general public access.

Art itself is something more than just the result, I realised it when I entered the pompidou centre in Paris. There I saw a ton of modern and contemporary art pieces and I was shocked: the amount of creativity people can reach is incredible. There was this piece of a painted water fall with a shower on it. Like a real shower. Builted into the painting. The idea of putting a shower on a painting is what makes it genuine and artistic, it's not the final result, it's not something you can put on a wall, it's artistic. It's artistic because it's what the artist thought of doing that makes it artistic. You see you coukd ask sonething like this to dall-e "make a contemporary art of a waterfall" but it will never show this result, it will make some random styled normal waterfall. Sure you could ask "put a shower on a painting" but if you don't ask for it you'll never find it. Fact is that humans will always be the motor in society, watching stuff and having smart and clever ideas from what they see, we are able to make this xonnections alone without someone telling us and that's why we will always be the artists. Ai copies, replicates, imitate, it doesn't "invent" anything it just smash stuff togheter without thinking. It's us, with our imagination, with our inspiration that transform that image into something real. We will always be the motor. If you think this is "a computer making art" imho you don't know what art is. Art is much more than connecting two dots togheter.

This is both fascinating and terrifying at the same time! From a tech-geek perspective, it's incredible how this even exists, but from a human ethical standpoint, it causes enormous concerns.

people have been saying for sometime, that robots with A.I will handle all the hard manual labour and humans can just focus on more creative stuff in the future....but it seems A.I does a better job of creative stuff than humans, it won't be long until we see art, clips, short videos and eventually full movies made by A.I...

I've been obsessed with following new DALL-E 2 prompts recently. The sheer potential of this kind of illustrative AI is magical! And what's funny is that media synthesis is such a young field, barely a decade old and it's seen leaps and bounds in everything from text generation to voice synthesis to image generation. I remember when face generation in 2014 was grainy and out of focus and we've already cracked photoreal faces 3-4 years later. Heck, we're at 1080p pictures right now? What about 4k next year? The diffusion model it uses has been used for short gifs already, so we're only a matter of time from videos. Movies. TV shows. Games! Entire VR worlds! We're on the cusp of a creative revolution and an utter from-the-ground-up democratization of art!

this is so insane, its going to change the world in a lot of aspects especially with art.

You can't say "What a time to be alive" without saying "Now, squeeze that paper!"

This is what I expect from a tech channel and I love it!

Imagine feeding this AI a whole novel and seeing how it illustrates the whole book. Also, a consumer product for generating very specific pictures for powerpoints/flyers would be awesome.

Incredbile how far we've come in 7 months. And with text to music and video AI the future looks amazing

This is scary good. Maybe in few decades, general public can use it like Google Image search, selecting text in Image, Image to Text & Scan Text.

7:10 so manny interesting details

I will have access to Dalle-2 next week, I am planning on doing some weird camera designs that never existed

You should had written: "A car as designed by Apple"

while this is certainly amazing and mind boggling, a part of me has a sense of doom about AI like this. like, we will eventually get to a place where we no longer can tell what is real or AI anymore, and it will be so pervasive we will eventually stop wondering/caring. in essence, a reality fatigue. i’m learning to appreciate our time a little bit more knowing how much we make with our own hands, artistically and creatively, and as creators this may be our Golden Age. what will our descendants reality be like? kind of scary/sad to think about.

04:19 It's a content creator and it can troll us too? Now I'm *truly* scared.

I can already imagine DALL-E 200 synthetizing/manufacturing/printing objects or useful machines based on the user's description of requirements, the impact it would have on manufacturing :- O

*Artist :* Well, I'm just thankful that _my_ job can't be automated! *AI :* Here's a renaissance oil painting of you, holding my beer ; )

Tech feels like it’s evolving pretty fast yet pretty slow at the same time doesn’t it?

As a computer scientist, it excites me that others are becoming just as interested in these things as i am

There is an AI that's talented at finding deepfakes due to photo editing artifacts and poor lighting. I wonder if the anti-deepfake AI could teach Dall-E where its images keep failing, thus making Dall-E a better artist.

In other words: Yes, this will totally take away people's job. Though, it might take a couple of years more. As you said, it will get more advance and spit out more sharper text/images. High quality photo's and video's etc etc... For now, i don't think we immediately need to be "worried." As you said, it is a very good concept for things like when you are brainstorming and having images in about 10 sec. to see what could be done. But of course, you would want a specific high quality image in the end for the project. Which it can't do (yet.) But i guess they're very close. The thing is, it isn't available for most of the public. So if it will be mostly for very high level professionals like big corporates, well, let's say we still have a while to go. On the other hand, there are still people who just like to design their own stuff. People like myself who actually do like to design. Of course, when it comes to pro's for their jobs. Time is money. If you can make images in les then a couple of seconds. They won't hesitate to get this stuff and let them replace you for most of the part. They might still have some graphic designers hired to kind of control things i guess. But yeah, what a time to be alive. (In some cases.) I bet that, when they first found out the lamp and the telephone it was also a great time to be alive. I remember having one of the first cellphones and then the smartphone. Now that we can see kind of its peak design when it comes to smartphones. Well, the question becomes always: What's next? Like for tv's... We have the Micro LED from Samsung. "The Wall." Which looks like a nice (but very expensive) concept!

I’m a software engineer and this is genuinely the first time in my life that an existing tech has felt that it’s impossible, my mind cannot comprehend that this tech not only understand things it understands what would be aesthetically pleasing to a human, I didn’t know a qualia like that is quantifiable

I’d seen the first version before, but this is next level. I’d better find a new job

Have to say that is really amazing. So someone with little to no drawing skills could flesh out a new product design ideas by just describing what it will do? Cool!

As a graphic designer I was thinking the same thing before you brought it up... I feel like my job will be obsolete by automation, or something like this. At the very least I would like this tool so that I can get inspiration, or use an image from it and clean it up to be used

This reminds me of when I was a kid and google earth was new, you'd just play around seeing what you could find

This is so cool!

As a graphic design student, I can see myself obsolete and unemployed in future…

This almost makes me think that it’s some kind of elaborated late April fools joke. Like I would love to have access to this it looks much more powerful than the normal Dall-e

With some refinement of the technology, just imagine this asset for animating D&D campaigns or other fantasy driven naratives. So much potential!

An easy example to understand what a general AI (often spelled AGI for artificial general intelligence) would mean is that it can start without what a painting is or how one can draw in the first place, but you could throw fully 1000 scanned art books (or PDF files) at it and after it has learned about art and drawings from those books, it could do DALL-E 2 stuff without any extra target specific programming. Now imagine such AI system watching every single tutorial video in RU-vid and understanding it all...

Based on how it handled the camera, and wall of PCs, it seems like this might be better suited for organics, or heavily stylized art. Either way, I think this is really cool, and would love to play around with it.

The scariest attribute that one can give to AI is Creativity. What if an AI starts impounding over the questions of Perfection and existence.

'What a time to be alive!' Shout out for the nod to two-minute papers

Someday we'll see DALL-E, GPT, and Jukebox work together to create some truly complex and beautiful things

As someone who’s spent a lifetime in the arts… this makes me extremely sad.

I could watch these generations for hours. I want more

As an illustrator and product designer student, the minute I saw this I pictured my career fumbling ✨

I loved the nod to 2 minute papers in the end! Great video as always, thanks for all the content and information through the years 😄

You’re literally the best mainstream tech youtuber, thanks for bringing these projects to light

If you compare this to any previous AI models like CLIP or VQGAN, even DALLE-1, the progress is mind-blowing.