YuE2 · Frontier Music with Symbolic Planning

sexy_seedbox

With this local audio model, I can finally make proper covers in different genres and change lyrics. Previously: https://news.ycombinator.com/item?id=46641627

philip-b

That example "Comedy" sounds like the most soulless synthetic example of "music" ever. Like the music analogue of a PR-speak article of a big corpo generated by an LLM. It's still technically impressive but it's 0/10, absolutely empty of soul.

quaverquaver

I guess it could be neat to play 100 of these at the same tempo at once but otherwise I'm having trouble coming up a use case for this...

corysama

BTW: https://github.com/ScryptHunter/ComfyUI-YuE2

stevage

It's really depressing that I have gotten into music composition right when this is happening. All of these projects are basically just destroying entire fields of human creativity. It doesn't seem so bad at first when the quality is mediocre, but as soon as they get good, then any human composition will be completely devalued, despite the enormous amount of knowledge, skill and effort that goes into producing one. A composer who writes a piece of music themselves, instead of being recognised and admired basically becomes the equivalent of someone who bakes their own sourdough instead of going to the supermarket: a curiosity, someone who does things the hard way for their own amusement. Graphic artists and bloggers were the first to suffer this, but it feels like it's just going to happen to basically every type of creative expression that can be represented digitally. It's just a question of how many months until that happens.

dr_kiszonka

The vocals in the few songs I listened to are so very clearly AI. I find Suno's much more credible in many genres. If anyone has tried Suno's Studio 2, I would love to hear your take on it. At $24-30/month, it's approaching Ableton Live 12 Suite rent-to-own territory, without the "own" part.

hypersoar

I mentioned this in another comment thread, recently, but I value art, including music, for the fact that another human being(s) created it to express something. I have zero interest in it if it's AI-generated. The thought of endless content created from the void for me to gorge on like oreos fills me with nothing but despair.

E-Reverance

I really want to like ai music but none of them seem to be trained on reward models that reward "ambiance" or any sort of interesting sound design (which this paper obviously doesn't even concern), which might be reflective of the people training them not having niche music tastes

yellowapple

It's interesting that the “Classical Music” sample ended up with a style prompt of “Contemporary Christian”. It's even more interesting that the “Contemporary Christian” music it generated was specifically Mormon music (specifically about the exile of Lehi and his family from Jerusalem into the wilderness, during which they reach the ocean, build a boat, and sail to the Americas), but in the style of contemporary Christian rock.

bit-rot

The majority of people, I think, don't want to listen to AI music or view AI art. Systems like this will produce muzak for ubers, cafes, phone queues, advertisements. Some artists will make hyperreal work by sampling it. But to listen to these "songs" willingly is not something I expect most people will choose to do.

artmanja111

I say this as someone with no skin in the game, but I don’t think it’s necessary for AI to replace human creativity in music. Instead, it can be a tool for augmentation. There has almost always been backlash against new technologies in music. Ultimately, musicians adopted those technologies and continued producing great works. I recently dug some 20-year-old CDs out from storage that were full of riffs and chord progressions for songs I never got around to completing. I fed them to Suno as a sort of “what might these have sounded like if I’d finished them?” experiment. I found the results quite impressive and plan to publish them some time in the near future. None of the tracks sound like marketable products to me, and I certainly don't think AI is going to generate the next Bohemian Rhapsody -- but it definitely could be a great thing for curing writer's block.

golem14

apt reference: https://electricliterature.com/wp-content/uploads/2017/11/Tr... "The Petty and the Small; Are overcome with gall ; When Genius, having faltered, fails to fall. Klapaucius too, I ween, Will turn the deepest green To hear such flawless verse from Trurl's machine."

tom_vidal

We are creating animated corpses out of our culture. The point of art isn’t to generate beautiful patterns. It’s to create meaning. And you can’t have that without human care and intent. Furthermore, that care needs to be intrinsically interwoven into the patterns that comprise the work. That’s what craft is. The mastery to generate exquisite patterns, and the care to infuse them with meaning at every level. Without care, in a Heideggerian sense, we are left with something which tastes sweet but is completely hollow, perhaps even illusional.

dcw303

I'm not species-ist. If a digital sentient being has something to say and they can express it through music, I'm more than willing to listen. But listening to these samples, it's obvious that, while technically proficient, they have no voice. Funnily enough, neither does most of the human produced music slop that existed before gen AI. All it exposes is that most people have no taste. This is as good as shuffling through popular songs on Spotify.

dcsommer

For an informed take (from a professional musician, composer, and arranger) on where this is going for musicians and the music industry, I really recommend Adam Neely's video essay "Suno, AI Music, and the Bad Future": https://www.youtube.com/watch?v=U8dcFhF0Dlk

euleriancon

I've been waiting for symbolic music generators for ages. This is so nice for musicians. Being able to intelligently translate parts, generate additional parts, generate sheet music from audio, generate variations on pieces, making pieces easier or harder. So many possibilities.

vunderba

This seems to be one of the few open-weight models that isn't just another "text to audio" generator. You can take existing sheet music, convert it to ABC notation, and then experiment with various covers. I don't have a ton of time right now to really mess around with it, but I took 15 minutes to run it on my Mac M1 with an old melody I wrote back in high school for an RPG I was writing in VB6 ( dating myself a bit here ). If anyone wants to hear what it sounds like: https://mordenstar.com/other/yue2-tests

rbtprograms

all of these fall very flat, many of them sound like generic commercial tunes at their worst. there is obviously melody and structure but none of it sounds good.

Tsarp

I wish folks spend more time on agentic music genertion instead of a single black box prompt to music. Similar to coding, where you are have a bunch of tools that can do the drudge work for you (the mundane things in mixing mastering for example), but still retain full creative freedom and expression. I am not articulating this well, but basically transitioning from IDE->Coding harnesses what is the DAW-> ??

pdntspa

Is there some way to get this to output just the vocals? Without running a stem splitter? It would be useful to be able to generate backing vocals/hums/melismas and whatnot, that could be plugged into a DAW.