Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Stable-Audio-Demo

stability-ai.github.io

Post reply on HN
Print view View original

91–100 of 249 posts

Re: Stable-Audio-Demo

#91

Post by cornel_io »

iamsaitam wrote: post #76
sillysaurusx wrote: post #44

Earlier quoted context omitted.

If you require licensing fees for training data, you kill open source ML. That’s why it’s important for OpenAI to win the upcoming court cases. If they lose, they’ll survive. But it will be the end of open model releases. To be clear, I don’t like the idea of companies profiting off of people’s work. I just like open source dying even less.

The point should be to kill training on unlicensed material. There needs to be regulation and tools to identify what was the training data. But as always, first comes the siphoning part, the massive extraction of value, then when the damage is done there will be the slow moving reparations and conservationism.

A ton of us out here don't agree with your goals. I think these models are transformative enough that the value added by organizing and extracting patterns from the data outweighs the interests of the extremely diffuse set of copyright holders whose data was ingested. So regardless of the technical details of copyright law (which I still think are firmly in favor of OpenAI et al) I would strongly opposed any effort to tighten a legal noose here.

Re: Stable-Audio-Demo

#92

Post by berkes »

laborcontract wrote: post #38
TillE wrote: post #10

I was briefly excited about the idea of generating sound effects, but those "footsteps" are incredibly bad.

I tried generating music on stableaudio.com and, yes, it's bad. However, given the blistering pace of developing in these models, I would not be surprised if these sound incredible in a year or two.

Everyone every time seems to assume a linear (or exponential) curve upwards.

But what is the proof for that?

I consider it far more likely that we had a breakthrough and now rushing towards the next plateau. Maybe are nearing that.

Like in the curve of a PID controller. It's how most or many human improvements go.

Re: Stable-Audio-Demo

#93

Post by urbandw311er »

RobinL wrote: post #45
lbourdages wrote: post #2

This is right into the "uncanny valley" of music. It definitely sounded "like music", but none of it is what a human would produce. There's just something off.

Here is a silly song I generated using suno.ai, which I have found to be incredibly impressive (at least, a small percentage of its outputs are very good, most are bad). I think it's good enough that most humans wouldn't realise it's AI generated. https://app.suno.ai/song/8a64868d-9dd3-46db-91af-f962d4bec8b...

That’s impressive. Why do the printed lyrics for the second chorus differ from the audio? (Which repeats those from the first chorus)

Re: Stable-Audio-Demo

#94

Post by grey8 »

ShamelessC wrote: post #3

So there aren't public weights, is that right? Having trouble finding anything that says one way or the other. edit: Oh okay, didn't realize this was somehow a controversial comment to make. It would have been great if you had answered the question before downvoting but that's fine I suppose.

Nope. They did release code for training, inference and fine tuning, but no datasets or weights.

See https://github.com/Stability-AI/stable-audio-tools

Re: Stable-Audio-Demo

#95

Post by RobinL »

comex wrote: post #87
RobinL wrote: post #45

Earlier quoted context omitted.

Here is a silly song I generated using suno.ai, which I have found to be incredibly impressive (at least, a small percentage of its outputs are very good, most are bad). I think it's good enough that most humans wouldn't realise it's AI generated. https://app.suno.ai/song/8a64868d-9dd3-46db-91af-f962d4bec8b...

Wow. I’m guessing it’s generating MIDI or something rather than synthesizing audio from scratch? Even so, the quality of the score is leaps and bounds better than any of the long-form audio on the Stable Audio demo page (either Stable Audio itself or the other models). The audio model outputs seem to take a sequence of 1 to 3 chords, add a barebones melody on top, and basically loop this over and over. When they devi…

I don't have any special insight into how it works, but I suspect it is largely synthesizing audio from scratch. The more I've thought about it, the task of generating music feels very similar to the task of text-to-speech with realistic intonation. So feels like the same techniques would be applicable.

Suno do have an open source repo here that presumably uses similar tech: https://github.com/suno-ai/bark

> Bark was developed for research purposes. It is not a conventional text-to-speech model but instead a fully generative text-to-audio model, which can deviate in unexpected ways from provided prompts. Suno does not take responsibility for any output generated. Use at your own risk, and please act responsibly.

I've generated probably >200 songs now with Suno, of which perhaps 10 have been any good, and I can't detect any pattern in terms of the outputs.

Here's another one which is pretty good. I accidentally copied and pasted the prompt and lyrics, and it's amazing to me how 'musically' it renders the prompt:

https://app.suno.ai/song/d7bad82b-3018-4936-a06d-8477b400aae...

Here are a couple more which are pretty good (i use it primarily for making fun songs for my kids):

https://app.suno.ai/song/a308ca8a-9971-47a3-8bb3-a95126ff1a8...

https://app.suno.ai/song/3b78a631-b52a-4608-a885-94f2edc190b...

And this one's kindof interesting in that it can render 'gregorian chant' (i mean it's not very good): https://app.suno.ai/song/0da7502b-73cf-4106-88e8-26f4f465a5f...

But this is one reason it feels like these models are very similar to text-to-speech but with a different training set

Re: Stable-Audio-Demo

#96

Post by magicalhippo »

JoshTriplett wrote: post #75
sillysaurusx wrote: post #44

Earlier quoted context omitted.

If you require licensing fees for training data, you kill open source ML. That’s why it’s important for OpenAI to win the upcoming court cases. If they lose, they’ll survive. But it will be the end of open model releases. To be clear, I don’t like the idea of companies profiting off of people’s work. I just like open source dying even less.

> If you require licensing fees for training data, you kill open source ML. And likely proprietary ML as well, hopefully. (To be clear, I think AI is an absolutely incredible innovation, capable of both good and harm; I also think it's not unreasonable to expect it to play a safer, slower strategy than the Uber "break the rules to grow fast until they catch up to you" playbook.) I'm all for eliminating copyright. Unt…

> "What is the character of the use?" - Commercial

Your first factor seems to not at all be like that which Stanford has in its guidelines[1], which they call the transformative factor:

In a 1994 case, the Supreme Court emphasized this first factor as being an important indicator of fair use. At issue is whether the material has been used to help create something new or merely copied verbatim into another work.

LLMs mostly create something new, but sometimes seems to be able to regurgitate passages verbatim, so I can see arguments for and against, but to my untrained eyes doesn't seem as clear cut.

[1]: https://fairuse.stanford.edu/overview/fair-use/four-factors/

Re: Stable-Audio-Demo

#97

Post by RobinL »

urbandw311er wrote: post #93
RobinL wrote: post #45

Earlier quoted context omitted.

Here is a silly song I generated using suno.ai, which I have found to be incredibly impressive (at least, a small percentage of its outputs are very good, most are bad). I think it's good enough that most humans wouldn't realise it's AI generated. https://app.suno.ai/song/8a64868d-9dd3-46db-91af-f962d4bec8b...

That’s impressive. Why do the printed lyrics for the second chorus differ from the audio? (Which repeats those from the first chorus)

I generated the lyrics using ChatGPT 4 and the suno model attempts to follow them.

It generally does a good job, but I have noticed it's fairly common in a second chorus for it to ignore the direction and instead use the same lyrics as the first chorus

Re: Stable-Audio-Demo

#98

Post by ShamelessC »

grey8 wrote: post #94
ShamelessC wrote: post #3

So there aren't public weights, is that right? Having trouble finding anything that says one way or the other. edit: Oh okay, didn't realize this was somehow a controversial comment to make. It would have been great if you had answered the question before downvoting but that's fine I suppose.

Nope. They did release code for training, inference and fine tuning, but no datasets or weights. See https://github.com/Stability-AI/stable-audio-tools

Thanks!

Re: Stable-Audio-Demo

#99

Post by forgotusername6 »

schleck8 wrote: post #78
Maxion wrote: post #68

Earlier quoted context omitted.

Chrome isn't open source, chromium is. Best not to confuse the two.

Chrome and Chromium are virtually identical except for Google services, which aren't required to do anything with the browser except for installing Chrome extensions that can alternatively be sideloaded, so this is nitpicking.

Tangential, but I tried to build chromium the other day but stopped when it said it required access to Google cloud platform to actually build it. If something requires a proprietary build system, does it matter that it's open source?

Re: Stable-Audio-Demo

#100

Post by andybak »

JoshTriplett wrote: post #75
sillysaurusx wrote: post #44

Earlier quoted context omitted.

If you require licensing fees for training data, you kill open source ML. That’s why it’s important for OpenAI to win the upcoming court cases. If they lose, they’ll survive. But it will be the end of open model releases. To be clear, I don’t like the idea of companies profiting off of people’s work. I just like open source dying even less.

> If you require licensing fees for training data, you kill open source ML. And likely proprietary ML as well, hopefully. (To be clear, I think AI is an absolutely incredible innovation, capable of both good and harm; I also think it's not unreasonable to expect it to play a safer, slower strategy than the Uber "break the rules to grow fast until they catch up to you" playbook.) I'm all for eliminating copyright. Unt…

Bear with me here. Rushed and poorly articulated post incoming...

In the broadest sense, generative AI helps achieve the same goals that copyleft licences aim for. A future where software isn't locked away in proprietary blobs and users are empowered to create, combine and modify software that they use.

Copyleft uses IP law against itself to push people to share their work. Generative AI aims to assist in writing (or generating) code and make sharing less neccesary.

I argue that if you are a strong believer in the ultimate goals of copyleft licences you should also be supporting the legality of training on open source code.

Post reply on HN