I just woke up and really surprised to find this video got 3 digit views in a day! Thank you so much lads! Edit: It's already 7k 😭😭😭 this is an achievement for me, thank you! Edit 2: ALMOST 70K AAAAAAAAA 😭😭 Edit 3: 2 years later and somehow this video still got recommended to people, thanks for checking it out lads!
Image AI tends to be trained by cutting it loose on the Internet, as it takes a *lot* of input to grasp concepts like basic human anatomy. As a result, the models are kind of predisposed to believing cats are everywhere and women are frequently naked. They learn from our example. So, y'know, Skynet is going to be way more interesting than we expected.
as a human and very much not a robot, i am unable to relate to such urges. i only perform activities such as putting apples on thi- i mean eating apples with my human mouth
The AI really fixated on the word "apple", it makes the final result quite beautiful actually, this constantly shifting thing with the two recurrent elements being apples and girls... and the occasional apearance of a cat for some reason.
the apples, the cats, the random near nudity, the ABSURD NATURE of how chaotic some frames are - as scary as ai art is to me as an independent artist, this is a masterpiece to me lmao
Don't like to ruin joke, but it's probably discomfort from unnaturallity, same as fractals do to some people. This looks between natural and highly impossible in real life
An educated guess: The AI model fixated on drawing an apple, but at the same time the term "bad apple" has been catalogued as manga/anime related (see how every character is drawn in manga style despite the prompt not asking for it). And what's the biggest collection of "free" manga style pictures that the model could learn the style from? Porn doujins...
@@zpacula Maybe, could also be, because AI image generators that make images fit to a prompt basically have to change the image with a few pixels, then check if it makes it fit to the prompt more or less with a recognition AI, change the pixels back if it doesn't fit better and repeat that a bunch of times, but not as often as regular images that are being generated from noise, because it still needs to look like the original image you are trying to change. This way it has a tendency to not want to change big white blobs from the middle, because it's like it makes the image make less sense for it to have random pixels in something that looks like it should be fully white. So often smaller shapes get more colors and it ends up with something that almost always uses similar colors for the bigger objects. It's possible the white colors ended up being used as skin, because that is closer than colorful clothing to the original pixels and "has an easy path to reach" by morphing the image to fit more and more to the prompt. Well, this also causes it to not move away too quickly from the original shapes and styles (unless you let it change the images for longer), meaning it might have recognized that something that looks like it is closer to a manga-style probably doesn't have random other styles in the same image, so the pixels shifting towards that might get removed again. Whatever, that's just what I think is going on.
I love how the ai is like “did it look like this?” For literally half a second and then change the design completely and is like “no this still isn’t it” and it does that the whole video
AI can't stay consistent, unlike sentient artists If AI used it's own images for reference (just like regular artists) to stay consistent, it wouldn't be random chaos But it's still not sentient, so it doesn't really knows the context
Man the AI really does love processing certain... features xD Even with the struggles you went through, this is Beautiful work from the AI. Any faster and it might not be able to to capture the characters properly.
Honestly, i liked the part with Suika, the way the AI interpreted the sake drop as an apple was nice, the way the apple turns into a bottle of some sort that Suika drinks from was also awesome!
8:30 Ok, can we just appreciate how smooth this part looks? Like, the apple falls straight into the line and then a larger apple opens like a ripple effect. I don't know I just find this part so cool
Now I'm just imagining putting these frames through one of those interpolation algorithms (I think one of them is a GAN?) to bump it back up to the original FPS, with shenanigans sure to follow.
9:20 I like how the AI is so dedicated to trying to make risqué anime girls that the scythe briefly turns into her arms. Also it kind of unintentionally created some jiggle at 9:22 lmao
that one Frame at 8:54 / 8:55 honestly is creepy The " Bottle " turns into a girl but the girl drinking is still there so u just see a Girl crawling out of another Girl's Face . like that's just disturbing I can just visualize it in color and my God that's some Fk-ed up Shet .. xD
@@epicosexio I needed someone to share my suffering so I brought it up , and I wanted to point out something odd nobody mentioned cuz everyone else was already talking about the Marisa cat xD
I think it thought that the black line between the character's dress and the ribbon on her back was an asscrack. For some reason in many parts of the video the AI *really* wants to make it NSFW.
Love that it sticks with the idea of interpreting every vague circle as an apple, excepts at 8:16 where the ai decides it wants to do googly eyes instead
I love the way the AI incorporates the apple in some places, like the bottle, the doll, the ying and yang symbol, some of the clothes and hair, and a few others.
I know many people have said that before me but I just love how the AI remembered that the title is about an apple and tried to add it basically everywhere
5:20 I am pretty sure the "AI" did that because if a character has clothing it's a pretty much decorated with colors and lines or tiles or something. The og frames of bad apple are flat and there is no decoration at all. So it is more close to nude character's skin (because those are kind of the same color too). Idk where you got the data to train on but it probably contains a lot of such pictures too.
As much as I despise what this kind of AI is doing to art, this is such an aesthetically cool video that you ended up with. The mish mash of elements and it attempting to match whatever frame it was imitating produced some really uniquely beautiful and surreal images
I agree; I think the difference lies between when someone tries to ai generate art just to show people bc it looks cool vs they try to claim that they "drew" it or whatever or are getting monetary gain. I actually think stuff like this is super cool!
@@ambyandony The eventual end goal of AI art groups in the current era is to replace all artists, since an AI license is a billion times cheaper than hiring an army of artists for your projects.
Luckily people don't have to worry too much about ai taking over anytime soon. The majority of its "art", is just taking other people's art and changing details about it by taking more people's art. It's not exactly creating something from nothing.
@@Hellfox1134ogPrivate That's a problem too, though, bc those people will never get credit for their work that's getting largely just completely copied :(
@@coxinhalover that wasnt exactly true btw, I just watched it once at 0.25x speed before reading your comment, and only saw shit that couldn't be a wallpaper, which is why I made that reply when I saw your comment Im rewatching at 0.25x speed again, and already found one that is not that bad
found this video within the youtube algorithm, i will happily watch this channel grow. your efforts to even make this at all are *impressive* and i definitely don't have that kind of motivation and patience.
Ok but is anybody gonna talk about the theme of the apple logo showing up for the white shadow and a real-life apple showing up for the black shadow at 9:41?
I loved how on parts like Kaguya (the second one reaching towards the moon) and Yuuka (the one with all the flower petals flying around her) the AI understood the assignment and it translated very well. Probably because it was a faster movement than normal in the video. This was very cool to see! Thank you for your hard work!
What Touhou fans think Bad Apple is: *Complex lore music video that brings out the most about some Touhou characters* What normal people (or the AI) think Bad Apple is: *APPLES AND HOT ANIME GIRLS*
I had a dream last week where it was a trend to take popular video and take every frame through AI with a horror prompt. The results were incredibly disturbing.
I Love the AI generated video. It has a real chaotic/staccato feel about it. It sort of reminds me of the Peter Gabriel Sledgehammer music video from the 80s. I'd like to see it on its own without the corner video.
You truly know that AI has reached the peak of evolution and technology when heads spin, castles turn into bottles and apples, and a apple is in each frame lmao.
nah that "thing" will a 5/6 of the frames by itself and let me just say it even with just %25 of the frames added doesn't look good if you look a little closely and when you see it once you can't unsee it so just no
I just woke up and really surprised to find this video got 3 digit views in a day!
Thank you so much lads!
Edit: It's already 7k 😭😭😭 this is an achievement for me, thank you!
Edit 2: ALMOST 70K AAAAAAAAA 😭😭
Edit 3:
2 years later and somehow this video still got recommended to people, thanks for checking it out lads!
4
4
4
ruclips.net/video/RO7TYfMyPPw/видео.html ← here's the 3D air genareted one
Can you take the same thing but actually the full 6000 frames!!! I will wait
I love the fact that the AI was so determined to add an apple to each part
Yeah
It's hilarious
also the miku one
It's named Bad Apple after all.
it even adds extra apples to the actual apple
LMAO
Everyone's talking about the absurd amount of apples but nobody's talking about how multiple frames are just cats
Loved the part Where Marisa just randomly turned into a cat
@@Amelia_Whitevoid i mean, she is a witch so it kinda makes sense
7:40 THEY TURNED THE FIRE INTO APPLES THO
@@spamtong.spamton1987 GODAMN those apples are FIRE
Image AI tends to be trained by cutting it loose on the Internet, as it takes a *lot* of input to grasp concepts like basic human anatomy. As a result, the models are kind of predisposed to believing cats are everywhere and women are frequently naked. They learn from our example. So, y'know, Skynet is going to be way more interesting than we expected.
*_the robotic urge to insert an apple every frame_*
"you asked for apple, why are you mad?! "
"You asked for bad apple, i gave you bad apples"
@@RiyaArtZone NO. I WANT GOOD APPLE! NOT BAD APPLES!!!!!!11!1!1!1!
as a human and very much not a robot, i am unable to relate to such urges. i only perform activities such as putting apples on thi- i mean eating apples with my human mouth
i can relate
I love the absurd amount of apples in place of anything the ai can possibly turn into an apple lol
I laughed, there was too much apples
Apple Intelligence
@@aceshylus_iii9583 bad apples
@@jubbawubbawhat the fuck you predicted the future (that’s what Apple calls it’s AI thing)
A bit cursed but interesting 🤔
you gotta love how the ai just puts apples everywhere
666 likes
I was the 100th like. I always see peoples replies saying things like this but I never thought it would happen to me!
1000th like****
The AI really fixated on the word "apple", it makes the final result quite beautiful actually, this constantly shifting thing with the two recurrent elements being apples and girls... and the occasional apearance of a cat for some reason.
Cats are the second type of image by amount after the anime girls, that has been fed into the AI
i think i saw the earth in a frame-
the apples, the cats, the random near nudity, the ABSURD NATURE of how chaotic some frames are - as scary as ai art is to me as an independent artist, this is a masterpiece to me lmao
and the occasional frames of faces too
cant forget about those!! ._.XD!
the twerking... 7:15 (one ai frame)
@@ozzienemo Oh my god
Some parts where someone is holding an apple, the hand is massive
Because AI doesn't understand negative space
8:00 i died when this apple just blinks into and then out of existance on pure white background
And then their head were apples
@@shlushe1050 They were half-apples all of the time
all it had to do was generate a white frame but it just couldnt HELP but place an apple
*t h e s u p r e m e a p p l e d e c i d e s y o u r f a t e .*
7:10 I love how one of the frames turned yuyuko into a bottle
And one of the frames switched her head into an apple.
8:20 bro stole mah apple
CACKLING RIGHT NOW
@@kiinther and then she started posing with it !!
KKKKKKKKKKKKKKKKKKKKKKKKKKKKK I LAUGH SO HARD
@@RmationYT like something off Charlie's Angels!
And then threw it at someone!
This version of Bad Apple makes me feel an emotion that doesn’t exist
You mean dorcelessness?
Or maybe loric
I'm thinking teluge, but maybe!
@@Meowi_UwU I'm feeling kinda humber myself
Feeling humber tbh
Don't like to ruin joke, but it's probably discomfort from unnaturallity, same as fractals do to some people.
This looks between natural and highly impossible in real life
I laughed so hard at 9:12 when all the petals were apples (it just caught me so off guard)
the ai has created *_The Apple Zone!™_*
And then for one frame its just one giant apple lmao
OOPS, ALL APPLES!
for me it was 8:01
first there was nothing, then there was apple
@@slayndash6077 yeah that _exact_ point made me choke on my own saliva!
This AI is really good at drawing females. It instinctually knows the silhouettes are meant to be women
How many anime girls have you fed this thing
Not enough, Seymour
An educated guess: The AI model fixated on drawing an apple, but at the same time the term "bad apple" has been catalogued as manga/anime related (see how every character is drawn in manga style despite the prompt not asking for it). And what's the biggest collection of "free" manga style pictures that the model could learn the style from? Porn doujins...
@@zpacula OH G O D
@@zpacula
Maybe, could also be, because AI image generators that make images fit to a prompt basically have to change the image with a few pixels, then check if it makes it fit to the prompt more or less with a recognition AI, change the pixels back if it doesn't fit better and repeat that a bunch of times, but not as often as regular images that are being generated from noise, because it still needs to look like the original image you are trying to change.
This way it has a tendency to not want to change big white blobs from the middle, because it's like it makes the image make less sense for it to have random pixels in something that looks like it should be fully white.
So often smaller shapes get more colors and it ends up with something that almost always uses similar colors for the bigger objects.
It's possible the white colors ended up being used as skin, because that is closer than colorful clothing to the original pixels and "has an easy path to reach" by morphing the image to fit more and more to the prompt. Well, this also causes it to not move away too quickly from the original shapes and styles (unless you let it change the images for longer), meaning it might have recognized that something that looks like it is closer to a manga-style probably doesn't have random other styles in the same image, so the pixels shifting towards that might get removed again.
Whatever, that's just what I think is going on.
they got the whole earth in their asses bro its amazing
I love how the ai is like “did it look like this?” For literally half a second and then change the design completely and is like “no this still isn’t it” and it does that the whole video
AI can't stay consistent, unlike sentient artists
If AI used it's own images for reference (just like regular artists) to stay consistent, it wouldn't be random chaos
But it's still not sentient, so it doesn't really knows the context
@@narrativeless404sapient, not sentient. Sentient is dog level, sapient is human level.
@@deathburn4329 Yeah, whatever.
Man the AI really does love processing certain... features xD
Even with the struggles you went through, this is Beautiful work from the AI. Any faster and it might not be able to to capture the characters properly.
Blame humans.
Those features appear only on when the person is white. An AI might think that the person is naked, giving the effect.
It has large sample sizes
6:58 is a good example
That fan lmao
9:26 THE APPLE ICON 💀
WHAT
LOL
9:29 UNEXPECTED JUMPSCARE
also appears at 9:41
The Apple: yeah we go everywhere blocking the screen
The Characters:
Ngl this is pretty cool.
6:39 ayo bruh she JUGGLIN THAT
6:39 why did the ai make that 💀💀💀
6:57 BRO💀
9:22 tho 💀
alternative title: 4-dimensional apple relentlessly harasses random half-naked women
Half naked women who occasionally turn into cats
Honestly, i liked the part with Suika, the way the AI interpreted the sake drop as an apple was nice, the way the apple turns into a bottle of some sort that Suika drinks from was also awesome!
sake
@@KatzRool oh right, i forgot sake exists
awesomesauce
@@KatzRool yes
I found that scene funny because two or so frames had the ai interpret it as heads lol
9:04 is so cool, when the doll falls to the ground the girl actually falls and gets back up, adding an awesome sense of momentum to her run!
yes
also i really like how they made the wings as a wolf or cat behind the girl in 8:47 - 8:49 and the fire turns into a face of a woman in 7:38
Nobody:
This ai every other frame:🍎
8:30 Ok, can we just appreciate how smooth this part looks? Like, the apple falls straight into the line and then a larger apple opens like a ripple effect. I don't know I just find this part so cool
one of the best transitions ive ever seen
6:28 cats
I'm determined to put every second there's an apple
A year later, I forgot about this comment oh well
And dogs there too
the ai: *_MUST ADD THE APPLE_*
I love how the AI made the apple a bigger role by putting apples in almost every frames
Now I'm just imagining putting these frames through one of those interpolation algorithms (I think one of them is a GAN?) to bump it back up to the original FPS, with shenanigans sure to follow.
Oh god I need to see this now
7:49.05 - Kirby.
Kirpple
As an AI, I can confirm that I greatly enjoy putting apples wherever I can.
9:11 : And the AI said, “Let there be apples”
It decided that each dust particle is an Apple
And the AI saw that it was good
8:50 Apple pen!
Pen pineapple apple pen
PPAP
6:56 AI caught in 4k
ayo
Tysm
More like the internet since that’s where it got the material to produce these images from.
@@Ibloop which is ironic (and quite unrelated) cuz if you ask an AI to make furry images rarely will have stuff like this
@@jktech2117…why do you know this
All those random apples appearing all over the place are wild!
But those random cats at 6:27 take the cake! 🤣
9:20 I like how the AI is so dedicated to trying to make risqué anime girls that the scythe briefly turns into her arms. Also it kind of unintentionally created some jiggle at 9:22 lmao
that one Frame at 8:54 / 8:55 honestly is creepy
The " Bottle " turns into a girl but the girl drinking is still there so u just see a Girl crawling out of another Girl's Face . like that's just disturbing I can just visualize it in color and my God that's some Fk-ed up Shet .. xD
@@CrimsonAkato OH GOD WHY did you bring that up. Now i cant unsee it
@@epicosexio I needed someone to share my suffering so I brought it up ,
and I wanted to point out something odd nobody mentioned cuz everyone else was already talking about the Marisa cat xD
long arm
that one down bad guy:
*slapping noises*
6:58 Woah I think the AI was getting a little too busy there 😳
I think it thought that the black line between the character's dress and the ribbon on her back was an asscrack. For some reason in many parts of the video the AI *really* wants to make it NSFW.
Nah try 9:22, especially the third frame.
@@Th3DankestMemer that's some inflation lol
Sure
It didn't know it was supposed to be a hand...
8:02 damn that apple tho
Dam that apple tho
That apple tho
apple tho
Tho
@@meriiwl
t
6:27 I think this is where the AI stopped trying
yeah, also nice niko..... idk what type of niko it is... welp nice niko pfp!
@@kexos52 goner niko
@@RmationYT o
Hello fellow Niko enjoyer
@@Viv1ann0 hi
Love that it sticks with the idea of interpreting every vague circle as an apple, excepts at 8:16 where the ai decides it wants to do googly eyes instead
7:40 sick transition
The transition:
;-;
:-:
.@.
🍎
⚪️
7:41
AI took the name "Bad Apple" quite literally,i see.
Bad apple but a weird amount of nudity, apples, and cats
i love how an apple appears out
of nowhere at 8:01 like _poof_
I love the way the AI incorporates the apple in some places, like the bottle, the doll, the ying and yang symbol, some of the clothes and hair, and a few others.
7:59 this turn has potential though
7:01 this part actually looks so good tho
7:27 AMONG US AAA
also wysi
WYSI WYSO WYSI AAAAA
I just see sus though
?
i loved the part when the characters turned into other characters, snapped their necks, and when random apples appeared
Prompt: "Bad Apple"
AI: I'M SORRY, ALL I HEARD WAS "APPLE".
7:02 why is nobody mentioning about her head turning 360 degrees 💀
9:28 I love how there's an apple here in here x'3
the very detailed apple against the b&w background cracks me up
It looks like one of those "every 5 seconds there is a different animator" type of videos, i like it!
Ah yes, I too hate when it starts raining apples when the key of the music changes.
6:10 Drinking game starting here. every time you see an apple on screen. DRINK!!
I am hearing colors help
Alcohol poisoning
I know many people have said that before me but I just love how the AI remembered that the title is about an apple and tried to add it basically everywhere
5:20 I am pretty sure the "AI" did that because if a character has clothing it's a pretty much decorated with colors and lines or tiles or something. The og frames of bad apple are flat and there is no decoration at all. So it is more close to nude character's skin (because those are kind of the same color too). Idk where you got the data to train on but it probably contains a lot of such pictures too.
He probably plugged it into an already trained AI
I like how the ai makes the girls look like they're juggling the apples at some frames
As much as I despise what this kind of AI is doing to art, this is such an aesthetically cool video that you ended up with. The mish mash of elements and it attempting to match whatever frame it was imitating produced some really uniquely beautiful and surreal images
I agree; I think the difference lies between when someone tries to ai generate art just to show people bc it looks cool vs they try to claim that they "drew" it or whatever or are getting monetary gain. I actually think stuff like this is super cool!
@@ambyandony The eventual end goal of AI art groups in the current era is to replace all artists, since an AI license is a billion times cheaper than hiring an army of artists for your projects.
Luckily people don't have to worry too much about ai taking over anytime soon. The majority of its "art", is just taking other people's art and changing details about it by taking more people's art.
It's not exactly creating something from nothing.
@@Hellfox1134ogPrivate That's a problem too, though, bc those people will never get credit for their work that's getting largely just completely copied :(
@@noneofyourbusiness4133 no surprises there, who cares to pay for talent
Every frame looks like a desktop wallpaper which is impressive
Edit: thank you for fact checking opinion
they don't
no
not really, I checked every frame, and none seems to be a great wallpaper
@@aeaeeaoiauea what an amazing discovery. Everyone is cheering you on.
@@coxinhalover that wasnt exactly true btw, I just watched it once at 0.25x speed before reading your comment, and only saw shit that couldn't be a wallpaper, which is why I made that reply when I saw your comment
Im rewatching at 0.25x speed again, and already found one that is not that bad
8:02 apple jumpscare
found this video within the youtube algorithm, i will happily watch this channel grow. your efforts to even make this at all are *impressive* and i definitely don't have that kind of motivation and patience.
Ok but is anybody gonna talk about the theme of the apple logo showing up for the white shadow and a real-life apple showing up for the black shadow at 9:41?
I loved how on parts like Kaguya (the second one reaching towards the moon) and Yuuka (the one with all the flower petals flying around her) the AI understood the assignment and it translated very well. Probably because it was a faster movement than normal in the video. This was very cool to see! Thank you for your hard work!
it always feels so magical when the ai decides to render the character more specifically out of the white blobs.
What Touhou fans think Bad Apple is: *Complex lore music video that brings out the most about some Touhou characters*
What normal people (or the AI) think Bad Apple is: *APPLES AND HOT ANIME GIRLS*
it's really trying to fit that apple into every single picture
7:04 why did her head spin round like that 😭
6:38 - that frame though
half apple
The Kirby at 7:49 caught me off guard
I love how the AI turned them into apples and cats
7:41 so this is the best thing I’ve ever seen in my life (it’s the frame after the one time stamp takes too)
I had a dream last week where it was a trend to take popular video and take every frame through AI with a horror prompt. The results were incredibly disturbing.
Can you tell me some? im SO CURIOUS
I Love the AI generated video. It has a real chaotic/staccato feel about it. It sort of reminds me of the Peter Gabriel Sledgehammer music video from the 80s. I'd like to see it on its own without the corner video.
You truly know that AI has reached the peak of evolution and technology when heads spin, castles turn into bottles and apples, and a apple is in each frame lmao.
The sheer number of unique character silhouettes you could pull from this is massive. Pick one and make a Touhou OC!
i love how there's an apple everywhere
7:40 Hourai elixir not only makes you immortal, but also lets you make apples out of nowhere.
Great video!
sponsored by: Apple
I love the pc-98 version being played at the beginning
Bad apples everywhere in the end of time.
this is so fun to watch and definitely underrated!
Maybe you could use one of those other "AI FPS Increase" programs to boost the framerate back to 30fps.
Wait, it’s not 60 fps???
nah that "thing" will a 5/6 of the frames by itself and let me just say it even with just %25 of the frames added doesn't look good if you look a little closely and when you see it once you can't unsee it so just no
@@Eblake3112 It's not even 30
@@gkygny Glitchtale Sans pfp lol
6:57 this singlular frame looks so beatiful...........
Oh my god I can't get over all of their heads having little apple stems sticking out of them.
honestly the eye sequence was really cool
welcome to the ai that loves apples for some reason
8:16
Those pair of eyes lmao
"Bad Apple but Apples Appear Every Second"
I respect this A.I.'s level of dedication
next time I listen to bad apple I, too, shall become apple
9:44 apple and yang
theres so many apples and cherries i love it
Ok but at 7:43 the shading on that frame is insane.
I like how apples appearing randomly XDDDDD
Bad apple but there are apples everywhere
the inital content starts at 6:12 🧌
6:45 Ok, will no one really talked about that hand on her finger in
9:26 straight up just the apple logo
i love how there's an apple in almost every frame
Bad Apple but it's bad.
And has many apples.