for anyone unfamiliar- first frame is a photograph called "View from the Window at Le Gras," which is the earliest known surviving photograph taken all the way back in 1826
typical depictions of molecules are super simple, just some spheres and sticks. I'd guess that whenever it sees some spheres it just gravitates towards that sort of pattern.
What amazes me is how it uses the SAME material (sort of smooth specular plastic using some very basic light representation) than we use when we model vulgarized molecules ! It nails it perfectly.
There’s something so calming about seeing art that isn’t trying to tell you anything. There’s no bias or ego attached. Like someone else said, it’s just a stream of consciousness from something that can quantify “thinking”.
It can't get back. It really never gets back to any style it explored. The latent space for those images has more than 2 dimensions, therefore a random walk in this space has a 0 probability to go back to where it started. It's a real thing.
@@wolfgangouille a discrete random walk in 3 dimensions has a strictly positive probability of returning to where it started. (But the probability that it will eventually do so tends to decrease quickly over time) Or, in any finite number of dimensions. I think you’re thinking of the fact that the probability it eventually does so in 1D (or in 2D? Idr for 2) dimensions, is 1, while for number of dimensions more than 2 (Idr the probability in 2D) is less than 1? But maybe you are referring to some result that I’m not familiar with or aware of and which is about continuous random walk and getting close to the starting point, instead of discrete random walk and returning to it exactly? I’m pretty sure people have studied that question but idk what they found. Well, I guess I know that for a 1D continuous random motion , that uh, it is a Wiener process and that it crosses the origin infinitely many times, and... uh... I think the crossing points have like, accumulation points actually? Something weird. I vaguely remember that maybe these sets were mentioned on Wikipedia as having a fractal dimension (in terms of like, covering them with balls) Idr.
This one is just as good as the first! I could watch these all day. "stream of consciousness animation" is an excellent term for these, used in this way Dall-e really does feel like dipping into the internet's subconscious.
@@NewtonPL actually, it's a model that uses images it saw to generate new ones. Dall-e-2 learns properties of images and associates them with words, and generates unique new images. It's not hard recall (replaying the exact same training images) but generating its own
Now I can't help but think how much this would have cost under OpenAi's 'price-per-prompt' pricing model and why charging per prompt is a terrible and limiting idea.
@@DoctorNemmo the model is likely made of terabytes of data stored across dozens of not hundreds of servers. Gonna be hard to run that on your local machine.
It seems like only recently we had Google’s AI that could “dream,” and now we have DALL-E 2 able to produce what feels much more like dreaming than anything before it.
Yes this is what I feel like our thoughts would look like projected on screen, a tangent within another tangent, which turns into another tangent and so on
dalle 2 is a being whos entire world consists of smooth, flat, surfaces. gradients and gentle curves. plastic, reflective objects--spheres and tubes and cylinders.
the more abstract scenes have lighting and shapes that are in some odd way reminiscent of psychedelic closed eye visuals, at least those in my experience. which my best guess it that its two systems attempting to find underlying patterns in very little, they come to similar conclusions. just an interesting observation
Technically all this is really doing is industrial scale reminiscing. It would be sensible to assume that this AI would only ever return imagery that we recognise.
An interesting observation I've made with this AI is that a lot of the images are very dream-like. I used to practice lucid dreaming and studying dreaming and it's very interesting just how similar some of the images are to the otherworldly appearance of things you'd see in your dreams
This is so mesmerizing, combined with the sound design its such a treat to watch. Reminds me when I tried making an "animation" by copying a drawing repeatedly, copying the previous iteration over and over again until the result is indistinguishable from the beginning frame. I'd imagine some time in the future when AI image generation can work in real-time that a pretty dope screensaver would be made using such "stream of consciousness".
Youre one of the first people Ive ever seen do something interesting with multiple different prompts, this is very cool! Its hard to tell when a new prompt begins, it all has amazing cohesion, thanks lynksboy :D youre an inspiration to all of us as a truly innovative filmmaker
I really really love how natural this is, while at the same time being chaotic. Every transition is amazing, but the sequence from 1:45 to 2:05 was just…WOW. Please make more of these!!!
I'm assuming you made the backing soundtrack to this video? The sound describes these feelings so well, there were a few moments that gave me cathartic chills
@@RedaFL Did it? No wonder it sounds strange, cause in all the music I've listened to from various Artist, and what not , not even Aphex twin could make something like this.
This is exactly how my brain operates on low oxygen, but a decent deal faster. When I close my eyes, sleep deprived, low (asthmatic) on oxygen, and clear of thoughts, my mind creates images precisely like the ones in this video. Nearly every image in this video is akin to what I see when I'm having my... Hallucinations? I guess? It's eerily similar in many respects.
i'm so ready for this type of content to become more of a thing and get better with a smooth framerate and just be abstract scenes that morph into each other created by an AI
I hate how OpenAI still call themselves open, yet were the ones to start the dark age of ML research by not sharing the models due to "AI safety" bs, only to repackage it into a SaS product.
@@SiamHossain7 I'm not so sure, Siam. I've used GPT-3 to make a lot of my work easier whenever I've had the opportunity. I'm working on an indie game, and the applications of the text-generating AI are endless. I've used it to amend scripts (indeed, the AI can program!), to write different statistics for characters, to write backstories for characters, and to improve the general plot. That's just text generation - I imagine DALL-E 2 could be used for something like creating sprites for the game. And those are only the things _I'd_ use it for! Imagine the diverse range of people who'd use these models to improve the quality and quantity of their work. Sure, there are bound to be malicious users - there always are - but there are absolutely things that machine learning would make easier. I've burned through 4 phone numbers for OpenAI accounts, and I'm always trying to hustle more free credit. A day when I can run the model on my own hardware is a day I rejoice.
@@SiamHossain7 Releasing the model would help researchers develop tools to detect generated text. If every dangerous invention was to be kept as a secret and perpetually rented to anyone at a price, it's unlikely we'll any get closer to a better world.
Hmm. A porthole to another world? A one-sided conversation with an omnipotent being? Perhaps the dreams of a vast sleeping God? I'm not completely sold on AI as art, but I truly believe something excellent could be made from these images. There's an odd story being told
As an artist myself, *this is exactly how the art brain thinks* while it works, when I let the medium tell me what it wants to become. I would say, I would love to see finer interpolation between each image, or more iterations or steps performed.
They say that if you noclip out of reality in the wrong place, you'll end up in the Backrooms. However, if a cameraman- I mean camera-carrying wanderer manages to noclip out of reality in the correct place, they might end up in some unchartable region of the metaquantum trans-Hilbert hyperspacetimelike manifoldoid superstructure where any picture they take would look really cool on an album cover. Certain simulation hypothesizers would suggest it's some sort of sophisticated screensaver used by so-called SimOps to synthesize our imagination and procedurally generate our dreams for us. The Snapchat ghost notwithstanding, the entities shown here could be Olympic mascots or Google spokesfolk one day.
can someone explain to me how it renders the 3d shapes so well? if there post production? cuz its amazing. please explain it to me if yk because I can think of a million uses for ai assisted shading or rendering
This is a case were we have to acknowledge something. Deep learning AI models are for the most part black box's. The AI just knows, how? We don't know, the assumption is that it's seen enough that it's model is able to reasonably predict shading and rendering. This black box issue is a big deal in science as AI becomes an evermore important tool. Some progress has been made in decoding deep learning systems but the issue seems to be yet resolved.
Oooh, I notice how it falls back into similar patterns as in the first variant animations. Not as many interesting designs here, but I absolutely adored how much it seemed to animate over itself? (Rocket into space, 3D gallery piece grows and expands). If that's something you thought about when choosing which pictures for it to iterate over, then this is a fantastic display of AI imagry as a creative tool.
I find it interesting how it starts off with a colourless photo of multiple buildings but just after 5 seconds, all the way till the end of the video it’s filled with colour, yet uses very simplistic shapes and patterns.
My human brain is just trying to make sense of all the visuals, trying to find things that are recognisable, for some patterns I can hold onto, but it's like a fever dream
for anyone unfamiliar- first frame is a photograph called "View from the Window at Le Gras," which is the earliest known surviving photograph taken all the way back in 1826
@@chucklebutt4470 Yeah theyd have to have a life and not spend hours wikipediang useless shit like me and you.
@@chucklebutt4470 I didn't know but I am smelly. But I am not mixed up I'm completely separate.
@@chucklebutt4470 I guess am smelly
@@Theoneaboveitall6537 you either a smart fella or a fart smella
I knew it was familiar too me but I forgot where it came from
It's really interesting how good Dall-e is at making logos and commercial icons.
Dall-e 2*
Dalle 1 is ass at what u just said
Yes, Dall-e definitely knows pop culture.
graphic designers btfo
especially at 0:04 fr it looks like eateot
It's interesting to me how in both of these, it's made models of molecules a few times.
typical depictions of molecules are super simple, just some spheres and sticks. I'd guess that whenever it sees some spheres it just gravitates towards that sort of pattern.
What amazes me is how it uses the SAME material (sort of smooth specular plastic using some very basic light representation) than we use when we model vulgarized molecules ! It nails it perfectly.
Russian design studio ArtLebedev already using the AI called "Nikolai Ironov" to make logos. And the results are mind-blowing
@@Lyzrinn Er, yeh, because that was part of it's reference material.
@@Haze1434 I know how an AI works and learns, but it doesn't make it less amazing when you see it.
Man, the animation itself is cool but the sound design takes it to a different level. Like it's almost meditative.
sound design might be anxiety inducing
For real, I wanna know how it was made!
I could be watching for hours
I'm watching this at 11at night and its the opposite of relaxing I'm terrified
It sounded like it was made by ai, but idk it just so terrifying to hear
almost every frame from this would make a great screensaver or album cover
it's harder to find something that wouldn't make a great album cover
@@LarsWilms like 1:49?
@@Bob78 This looks like a 3D animation you would see on a 2000's PC
@@Bob78 Kids channel cover.
0:38 is... hell
It's like when you close your eyes and start to see things that then start mending into even more random things
It's so surreal
yea exactly
also when next duping vid?
man it's so weird seeing creators you like enjoying videos you like alongside you
ok how did you frind this but i like you content
Oh hi there
There’s something so calming about seeing art that isn’t trying to tell you anything. There’s no bias or ego attached. Like someone else said, it’s just a stream of consciousness from something that can quantify “thinking”.
Interesting that it never gets back to the gritty grainy start. It has such a natural leaning towards “graphic” art
It can't get back. It really never gets back to any style it explored. The latent space for those images has more than 2 dimensions, therefore a random walk in this space has a 0 probability to go back to where it started. It's a real thing.
i mean if you give it enough time eventually it'll go back
@@yungquagton Unless the random walk is bounded no it will never get back.
@@wolfgangouille yes it will give it a few millenia
@@wolfgangouille a discrete random walk in 3 dimensions has a strictly positive probability of returning to where it started. (But the probability that it will eventually do so tends to decrease quickly over time) Or, in any finite number of dimensions.
I think you’re thinking of the fact that the probability it eventually does so in 1D (or in 2D? Idr for 2) dimensions, is 1, while for number of dimensions more than 2 (Idr the probability in 2D) is less than 1?
But maybe you are referring to some result that I’m not familiar with or aware of and which is about continuous random walk and getting close to the starting point, instead of discrete random walk and returning to it exactly? I’m pretty sure people have studied that question but idk what they found.
Well, I guess I know that for a 1D continuous random motion , that uh, it is a Wiener process and that it crosses the origin infinitely many times, and... uh... I think the crossing points have like, accumulation points actually? Something weird. I vaguely remember that maybe these sets were mentioned on Wikipedia as having a fractal dimension (in terms of like, covering them with balls)
Idr.
This one is just as good as the first! I could watch these all day. "stream of consciousness animation" is an excellent term for these, used in this way Dall-e really does feel like dipping into the internet's subconscious.
You have no idea how it works
@@multiply67 he is right, dall-e is an AI model trained on data from the internet, so it can only come up with things it saw
@@NewtonPL actually, it's a model that uses images it saw to generate new ones. Dall-e-2 learns properties of images and associates them with words, and generates unique new images.
It's not hard recall (replaying the exact same training images) but generating its own
So where's the porn?
Now I can't help but think how much this would have cost under OpenAi's 'price-per-prompt' pricing model and why charging per prompt is a terrible and limiting idea.
Only paying for what you actually use seems pretty fair to me?
It's computing power. Someone's computer working at the other side of the world.
What we need are open source models that we can run by ourselves.
Everything should be free I agree. They're just out for your money.
@@krunkle5136 dude calm down if they hadn't money there wouldn't be any dalle2 in the first place
@@DoctorNemmo the model is likely made of terabytes of data stored across dozens of not hundreds of servers. Gonna be hard to run that on your local machine.
This really feels like some hypnagogic imagery. Incredible piece of art.
This is such a cool idea, just letting the Ai dream almost by endlessly producing a variant of the previous image
It seems like only recently we had Google’s AI that could “dream,” and now we have DALL-E 2 able to produce what feels much more like dreaming than anything before it.
Of all the things people are pulled out of this tool yours are my favourite. Love it
Putting it on fullscreen and just staring at it feels like scratching an itch deep in your brain; pure unfiltered stimulation of the mind. Cool video.
Because you’re watching another brain’s imagination.
Yes this is what I feel like our thoughts would look like projected on screen, a tangent within another tangent, which turns into another tangent and so on
I'd love to be accepted into the program
same, I signed up maybe a month ago and haven't heard anything yet. I'll bet they've gotten lots of requests
You wouldn't contribute. So no, I hope you don't
@@azca. what's your problem?
@@theoroinvictus I want to use it for alternatives in engine design and mathematical optimisation of aerodynamics in automotives
@@user-un9ej7th6j could AI imagery really be used for that kind of work? that's interesting!
magnificent!!!!! I couldn't keep my eyes off it
There's just something about the background music and the occasional clattering that makes this video so unsettling and so real at the same time
Audibly gasped when I got this notification. I'll always love content from Alan, good stuff.
i like that it just makes an app icon for a little while
this has become one of my favorite short films ever. this hits one of those indescribable feelings that alan has mastered.
The idea of exploring the latent space using this technique is really really cool. Loving these animations, want to see more of them!
1:50 my favourite instrument - the clusterfuck
It's learning how to depict where we all started, in spirit. The symbols and visions are so abstract yet so profoundly clear
This smokes out the deepest parts of my mind, I could watch it forever thank you
dalle 2 is a being whos entire world consists of smooth, flat, surfaces. gradients and gentle curves. plastic, reflective objects--spheres and tubes and cylinders.
the more abstract scenes have lighting and shapes that are in some odd way reminiscent of psychedelic closed eye visuals, at least those in my experience. which my best guess it that its two systems attempting to find underlying patterns in very little, they come to similar conclusions. just an interesting observation
Technically all this is really doing is industrial scale reminiscing. It would be sensible to assume that this AI would only ever return imagery that we recognise.
@@whirled_peas yeah true!
An interesting observation I've made with this AI is that a lot of the images are very dream-like. I used to practice lucid dreaming and studying dreaming and it's very interesting just how similar some of the images are to the otherworldly appearance of things you'd see in your dreams
@@ADreamingTraveler agreed!! its really cool to see
Well there's the system that creates the image and then there's the system that understands the image
loved your work in Coreys
This is so mesmerizing, combined with the sound design its such a treat to watch. Reminds me when I tried making an "animation" by copying a drawing repeatedly, copying the previous iteration over and over again until the result is indistinguishable from the beginning frame.
I'd imagine some time in the future when AI image generation can work in real-time that a pretty dope screensaver would be made using such "stream of consciousness".
hey youre the minecraft guy
its like being trapped in the logos before the film starts
Youre one of the first people Ive ever seen do something interesting with multiple different prompts, this is very cool! Its hard to tell when a new prompt begins, it all has amazing cohesion, thanks lynksboy :D youre an inspiration to all of us as a truly innovative filmmaker
there was only one prompt I believe
it looks to me like every picture just takes the previous picture and tries to draw a variation on what it thinks it is, like an AI game of telephone
@@dopaminecloud yeah, Ive read the description now lmao sorry, this is still pretty cool and impressive
I love the music so much, it fits perfectly
I really really love how natural this is, while at the same time being chaotic. Every transition is amazing, but the sequence from 1:45 to 2:05 was just…WOW.
Please make more of these!!!
It reminded me of the Art Attack opening.
its natural for neural networks to see neural networks' creations as natural :)
it really went from london to ghosts to molecules to youtuber logos
I'm glad we're not the only beings in this universe able to recognize smiling faces in everything we see.
Is there a way in the current API to get the textual CLIP representations behind the generated images?
this isn’t a being. this is a program. it doesn’t feel anything.
@@mrman24 Yet... It somehow developed Paraidolia...
@@itryen7632 That's because it's based on human data lol, love me some faces.
It's a computer running an advanced model.
this is like when you are close to falling asleep and you focus on your vision
amazing work. always a creative mastermind. it's so suggestive and feels so topical. i love it
This is absolutely mind blowingly incredible. I'm literally speechless
thank you alan very cool
Watching this right before i go to sleep is a very good idea. Thank you Alan!
The audio is perfect
Incredible Alan. You are truly a genius.
Immediately subscribed for the waiting list. I have so many concepts popping up now!
Great job. I liked the molecules. So cool.
The eclipse type pictures at around 1:15 are amazing
I'm assuming you made the backing soundtrack to this video? The sound describes these feelings so well, there were a few moments that gave me cathartic chills
No he didn't
the robot did
@@RedaFL Did it? No wonder it sounds strange, cause in all the music I've listened to from various Artist, and what not , not even Aphex twin could make something like this.
Reminded me of the wall pink floyd on the run
@@bluenightfury4365 dalle doesn't make music. This is most likely made by a person.
'you are schizophrenic' The 4mm fletchette pellet coming from my modified 12 gauge shotgun:
This is exactly how my brain operates on low oxygen, but a decent deal faster. When I close my eyes, sleep deprived, low (asthmatic) on oxygen, and clear of thoughts, my mind creates images precisely like the ones in this video. Nearly every image in this video is akin to what I see when I'm having my... Hallucinations? I guess? It's eerily similar in many respects.
Ok
hypnagogia
Hey alright
@@weasel6843 Hypnogogic hallucinations are related to hearing music. Not really what OP experiences.
@@Defirence Auditory hallucinations are one among many potential hypnogogic hallucinations. It's not specific to music
I love how concepts phase in and out of existence in these
This is literally what you see when you close your eyes and start imagining things and then transforming them into other things
Artificial intelligence slowly forgets what a photograph from 1826 looks like and ends up constructing a new universe in the process.
Sounds fun!
i'm so ready for this type of content to become more of a thing and get better with a smooth framerate and just be abstract scenes that morph into each other created by an AI
This was one of the best videos I’ve ever seen, I’m so stunned
...damn. DALL•E truly has a passion for graphic design.
...I wish OpenAI wasn't behind it, though.
I hate how OpenAI still call themselves open, yet were the ones to start the dark age of ML research by not sharing the models due to "AI safety" bs, only to repackage it into a SaS product.
@@rkvkydqf I dream of a day when all of these models are public.
@@daniel-andersson it will definitely be used for nefarious and disgusting reasons more than anything else
@@SiamHossain7 I'm not so sure, Siam. I've used GPT-3 to make a lot of my work easier whenever I've had the opportunity. I'm working on an indie game, and the applications of the text-generating AI are endless. I've used it to amend scripts (indeed, the AI can program!), to write different statistics for characters, to write backstories for characters, and to improve the general plot.
That's just text generation - I imagine DALL-E 2 could be used for something like creating sprites for the game. And those are only the things _I'd_ use it for! Imagine the diverse range of people who'd use these models to improve the quality and quantity of their work. Sure, there are bound to be malicious users - there always are - but there are absolutely things that machine learning would make easier. I've burned through 4 phone numbers for OpenAI accounts, and I'm always trying to hustle more free credit. A day when I can run the model on my own hardware is a day I rejoice.
@@SiamHossain7 Releasing the model would help researchers develop tools to detect generated text. If every dangerous invention was to be kept as a secret and perpetually rented to anyone at a price, it's unlikely we'll any get closer to a better world.
Goddamn i've been following dalle 2 stuff for a while I had no idea you were into it alan thats hella cool
0:48 when you need an app for finding ghosts
I need to get engaged with one y'know
Ghost Instagram
This thing just invented like 6 different types of brass instruments in a couple seconds. That’s insane
Please understand that you are respected and admired a great deal, Mr. Resnick. ✨
This stuff scares the shit out of me. Especially the saxophone/instruments/looks-familiar-but-dont-know-what-to-make-of-it part
I'm really quite OK with this.
Hmm. A porthole to another world? A one-sided conversation with an omnipotent being? Perhaps the dreams of a vast sleeping God? I'm not completely sold on AI as art, but I truly believe something excellent could be made from these images. There's an odd story being told
What does it mean "to be sold on AI art"?
I can see why each and every frame was your favorite, sir resnick!
Amazing! Your first variant animation inspired me to sign up and do the same... But it got stuck in a loop generating Simpsons characters. :/
How difficult was it to get access to DALL-E 2?
@@lysikasaito I got an invite about 2 weeks after applying. Providing social links to any art accounts you own probably helps.
Lol
I loved the video with all my heart, then I read how it's all cascading from the first image which is well dear to me, and... mind blown. Amazing!!!!
As an artist myself, *this is exactly how the art brain thinks* while it works, when I let the medium tell me what it wants to become. I would say, I would love to see finer interpolation between each image, or more iterations or steps performed.
You mean like smooth transitions?
@@julianemery718 smooth in more than a visual sense, in a conceptual sense
@@whirled_peas What should that mean?
@@fuji_films it means smother transition as well as a visual representation for what influenced the direction of said tradition.
Agreed, this is eerily similar to the creative process
I'm asuming you did the sound. And great job. It really adds to it.
They say that if you noclip out of reality in the wrong place, you'll end up in the Backrooms. However, if a cameraman- I mean camera-carrying wanderer manages to noclip out of reality in the correct place, they might end up in some unchartable region of the metaquantum trans-Hilbert hyperspacetimelike manifoldoid superstructure where any picture they take would look really cool on an album cover. Certain simulation hypothesizers would suggest it's some sort of sophisticated screensaver used by so-called SimOps to synthesize our imagination and procedurally generate our dreams for us. The Snapchat ghost notwithstanding, the entities shown here could be Olympic mascots or Google spokesfolk one day.
ok
Crazy how it starts from one image and then it transforms into a completely new set of images.
can someone explain to me how it renders the 3d shapes so well? if there post production? cuz its amazing. please explain it to me if yk because I can think of a million uses for ai assisted shading or rendering
This is a case were we have to acknowledge something. Deep learning AI models are for the most part black box's. The AI just knows, how? We don't know, the assumption is that it's seen enough that it's model is able to reasonably predict shading and rendering. This black box issue is a big deal in science as AI becomes an evermore important tool. Some progress has been made in decoding deep learning systems but the issue seems to be yet resolved.
Each of these images could make an interesting music album cover.
Oooh, I notice how it falls back into similar patterns as in the first variant animations. Not as many interesting designs here, but I absolutely adored how much it seemed to animate over itself? (Rocket into space, 3D gallery piece grows and expands). If that's something you thought about when choosing which pictures for it to iterate over, then this is a fantastic display of AI imagry as a creative tool.
wdym not interesting designs? I think they were all pretty cool
@@NGC-qm1so Oh for sure! I liked them too, I think I just meant in comparison to his first animation. Just an opinion I had at first watch is all :)
This was genuinely one of the coolest things I've seen on youtube
1:15 I have seen this movie
7 days
@@grandeTO9Arrival
This was like watching Lucy without characters and trippy. Thanks for sharing this with us.
Everyone gangsta until ai starts to build an atom
This is like the inside of my brain 24/7 not kidding, god damn it took me on a nostalgia trip i didn't know was possible!
On a weed trip.*
Got kind of spooky there for a second! And beautiful choice of a starting image!
The amount of iterrations it went through is beautiful
The sound on this my man! you did a fantastic job mate
I find it interesting how it starts off with a colourless photo of multiple buildings but just after 5 seconds, all the way till the end of the video it’s filled with colour, yet uses very simplistic shapes and patterns.
This is pretty much what it feels like to have a continuous train of thought that just goes wherever.
This is absolutely amazing, both the capabilities of AI, and the presentation of the images
now just imagine combining this with an ai that transitioned between 2 frames as smoothly and naturally as possible
Man this is so amazing, thanks for putting this together! 👍👍👍
I love how at some point it had a striking resemblance to the default wallpaper that cake with my phone
WAIT!! ALAN?? I can’t believe I’ve randomly stumbled across your channel again, I really loved this video
Wow this actually very interesting, it feels that video somehow captures creative process, itself.
Oh dang, this is actually beautiful.
this is the most amazing thing I've ever seen I love dalle 2
Sweet.
New Kirby antagonist just dropped. :0
Man I fucking love everything ur brain produces into art forms and how u play w so many layered concepts thank u alan
This is generated by an ai
Yes the ai created the images thank u but Alan thought abt this idea and composed this video
Is curious how similar to a DMT trip this actually was, to the point taht I had numerous flashbacks.... so, dall-e... gotta get into it
this is absolutely amazing
y'know, this felt rather theraputic for me, the sound kinda helped me get tired before bed and idk why
Didn't realize I was going to watch the coolest video I've ever seen 🤯
Truly a masterpiece Alan-- I mean, Dall-E...
0:34 these little faces remind me of lsd dream emulator
I love how a bunch of molecules randomly becomes a SpaceX rocket lunching
My human brain is just trying to make sense of all the visuals, trying to find things that are recognisable, for some patterns I can hold onto, but it's like a fever dream
I love this! Absolutely amazing!
Add in some weird Earthbound music, and then this is gold