Using AI this way seems like the equivalent of inventing spam for music to me. It's interesting, but basically we've figured enough out about the entropy and shape of an honest signal that we can automatically produce noise against it that cancels meaning, or subverts it.<p>The difference between simulating music and using formalisms to make discoveries about it seems like a matter of intent. As in, what's the difference between a horizon, a window viewing one, and a picture of one? The existence of an observer makes them related, and the position of the observer makes them different. That difference is probably analogous to what simulated music is to intentional music.
The existence of a listener makes it music, and the relationship of the listener makes it different.<p>These AI generated images are like cancelling-noise to images we already associate meaning with. Which is seems analogous to 1/f fractal or Perlin noise at a certain level of abstraction. Not to dismiss or attempt to trivialize the accomplishment at all, but when people create tech that is overwhelming to the senses like that, sometimes a new frame of reference can help.
The syncing of the visuals to the music brings to mind
the video for The Chemical Brothers’ Star Guitar: <a href="https://www.youtube.com/watch?v=0S43IwBF0uM" rel="nofollow">https://www.youtube.com/watch?v=0S43IwBF0uM</a>
Edit: Its using OpenAI Jukebox (<a href="https://openai.com/blog/jukebox/" rel="nofollow">https://openai.com/blog/jukebox/</a>) which claims to actually produce good music.<p>Ive heard music synthesized by neural nets made by different people, this doesn't sound like that. It may be over-fitting.<p>Also, watching multiple videos, all the music is similar. There is this one tune thats in every single one of them.
I really like it, altough the music seems to be always the 2 same songs with some alterations<p>- Dancer In The Dark <a href="https://www.youtube.com/watch?v=XnGv2gwk8As" rel="nofollow">https://www.youtube.com/watch?v=XnGv2gwk8As</a><p>- Cigarettes After Sex <a href="https://www.youtube.com/watch?v=KIKTnnsL9CU" rel="nofollow">https://www.youtube.com/watch?v=KIKTnnsL9CU</a>
This is scary and what I feared would eventually happen. How long before AI is better than every music producer, trained on all of music how likeable something is? How long before fake influencers on IG and TikTok completely dominate by having more addictive personalities and videos to follow than real people?
It's actually good music. The visual parts match the music pretty well, too (though it makes me anxious if I look at it longer than 3 seconds).<p>I do wonder, though, whether it's just over-fits, and takes the original music with some minor tweaks.<p>Another interesting point would be to know if this music could be sold cheaply without legal troubles (or even distributed royalty free). Most of the music I heard is pretty neat, I could image using them in YouTube videos, or as podcast jingles.
Can someone explain why this is impressive? Seems easy to correlate music features to visuals. It's been done for decades. What's special about this one?
I was dissapointed to see that while the videos are hosted on YouTube, all videos on the channel are unlisted.<p>Luckily the video IDs can be found at <a href="https://www.thismusicvideodoesnotexist.com/assets/urls.json" rel="nofollow">https://www.thismusicvideodoesnotexist.com/assets/urls.json</a><p>List of videos:<p><pre><code> https://youtube.com/watch?v=Spu3eiOEJ-M
https://youtube.com/watch?v=BE2lZ-Ti1Wc
https://youtube.com/watch?v=lHpcYPfjiLs
https://youtube.com/watch?v=6w2WXRFJpAE
https://youtube.com/watch?v=jPBgu-IO6TI
https://youtube.com/watch?v=g4px8cFR3gc
https://youtube.com/watch?v=whD78YCQXoo
https://youtube.com/watch?v=4iN9738uASY
https://youtube.com/watch?v=2tSa701EftM
https://youtube.com/watch?v=hjinBNYEkb8
https://youtube.com/watch?v=jckJS8RNMbw
https://youtube.com/watch?v=gq5EQtSiJiE
https://youtube.com/watch?v=zhV3ecScgrA
https://youtube.com/watch?v=wVnt_CX0C64</code></pre>
I see heavy influences from the video for Take On Me by a-ha (except that was in black and white) <a href="https://youtu.be/djV11Xbc914" rel="nofollow">https://youtu.be/djV11Xbc914</a>
I would love to see this used with music that's already extremely "algorithmic" and aesthetically lends itself to a computer-created process... IDM stuff like Access to Arasaka[0], Autechre[1], Qebrus[2] etc. Can I just take an artist's entire discography (or that of a few artists) and generate comparable material? Ahhhh can I have "more music" from my favorite artists!??! hehehe :)<p>[0] <a href="https://tympanikaudio.bandcamp.com/track/nypox" rel="nofollow">https://tympanikaudio.bandcamp.com/track/nypox</a><p>[1] <a href="https://autechre.bandcamp.com/track/acroyearii" rel="nofollow">https://autechre.bandcamp.com/track/acroyearii</a><p>[2] <a href="https://exophobiaorgqebrus.bandcamp.com/track/hmn-fshn" rel="nofollow">https://exophobiaorgqebrus.bandcamp.com/track/hmn-fshn</a>
This makes me uncomfortable, but also very intrigued. Something about the visuals "tickles the brain" but not in any particular way I can reason about. Cool!
What is a good start to learn about generative art with neural nets? Using tools which work on OSX preferably.<p>Lets say I want to train the AI on classical art pictures and see what it can generate by itself.
Shameless plug:
You can create one of these yourself using <a href="https://wzrd.ai" rel="nofollow">https://wzrd.ai</a> , with any audio you want.
Is there an explanation of how it works aside from just "It's a GAN"?<p>I'm guessing it's generating a GAN on frames, and navigating around it (at random?) synchronized to the music, like the transition animations at <a href="https://www.thisfuckeduphomerdoesnotexist.com/" rel="nofollow">https://www.thisfuckeduphomerdoesnotexist.com/</a> , I'm curious if there's something else to it
I think the model is plagiarizing somewhat. Both <a href="https://www.youtube.com/watch?v=zhV3ecScgrA" rel="nofollow">https://www.youtube.com/watch?v=zhV3ecScgrA</a> and <a href="https://www.youtube.com/watch?v=hjinBNYEkb8" rel="nofollow">https://www.youtube.com/watch?v=hjinBNYEkb8</a> contain the part of the melody from Take on Me by a-ha.
It started with just noise, but a bit later there was actual music which was very impressive if indeed synthesized out of 'nothing' by a neural network. Chord progression which was something like I-V-IV-vi, a simple melody based on the same progression, a simple baseline...
I had lots of fun taking images from <a href="https://thispersondoesnotexist.com/" rel="nofollow">https://thispersondoesnotexist.com/</a> and feeding that to wombo.ai (converts static images of people to them singing a song)
It would be cool if videos like these can be generated in realtime to replace music visualizers like waveform or spectrograms. Even if it has no utility as a real visualizer, it is still nice to watch!
Those visuals are badass. I know the nn was trying to replicate “realistic” images, but this semi-organic nonsense vibe would actually be awesome at a concert.
Does anyone know what this is? I see a lot of people jumping to a lot of conclusions, but no explanation on the site.<p>EDIT: Ok, there's text at the bottom that I missed, with some cursory information and a link to <a href="http://taggartbonham.me/" rel="nofollow">http://taggartbonham.me/</a> . It says:<p>Built with OpenAI's Jukebox and NVIDIA's StyleGAN2.<p>Watch another or contact me
Similar
<a href="https://TheseLyricsDoNotExist.com" rel="nofollow">https://TheseLyricsDoNotExist.com</a><p>Complete list
<a href="https://thisxdoesnotexist.com/" rel="nofollow">https://thisxdoesnotexist.com/</a>
Beautiful, almost every frame is a perfectly plausible and very tasteful abstract painting. But it seems a bit obsessed with cars, not a very meaningful image. Would it be possible to nudge the net to other concepts?
Reminds me of Cuttlefish changing their camouflage.<p><a href="https://youtu.be/pgDE2DOICuc" rel="nofollow">https://youtu.be/pgDE2DOICuc</a>
It looks like this has involved uploading tens of thousands of videos to youtube... (guessing by the video names).<p>All unlisted and without ads... Presumably uploaded with the API...<p>Thats tens of TB's of free storage provided by Youtube there... With no ads... Do you not run a risk of a ban for that?