Live data from Hacker News

Stable-Audio-Demo

stability-ai.github.io

131–140 of 249 posts

Re: Stable-Audio-Demo

#131
post #35

Interestingly, Ed Newton-Rex, the person hired to build Stable Audio, quit shortly after it was released due to concerns around copyright and the training data being used. He’s since founded https://www.fairlytrained.org/ Reference: https://x.com/ednewtonrex

Calling him "the person hired to build Stable Audio" seems a bit misleading? He was in a executive position (VP of product for Stability's audio group). An important position, but "person hired to build" to me evokes the image of lead developer/researcher.

I think that also helps in understanding his departure, since he's a founder with a music background.

Re: Stable-Audio-Demo

#132

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…

Where this argument falls down for me is that "use" w.r.t. copyright means copying, and neither AI models nor their outputs include any material copied from the training data, in any usual sense. (Of course the inputs are copied during training, but those copies seem clearly ephemeral.)

Genuinely curious: for anyone who thinks AI obviously violates copyright, how do you resolve this? E.g. do you think the violation happens during training or inference? And is it the trained model, or the model output, that you think should be considered a derived work?

Re: Stable-Audio-Demo

#133

Earlier quoted context omitted.

> 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…

Where this argument falls down for me is that "use" w.r.t. copyright means copying, and neither AI models nor their outputs include any material copied from the training data, in any usual sense. (Of course the inputs are copied during training, but those copies seem clearly ephemeral.) Genuinely curious: for anyone who thinks AI obviously violates copyright, how do you resolve this? E.g. do you think the violation h…

Personally I think trained models are derived works of all the training data.

Just like a translation of a book is a derived works of the original. Or a binary compiled output is a derived works of some source code.

Re: Stable-Audio-Demo

#134

As with Stable Diffusion, text prompting will be the least controllable way to get useful output with this model. I can easily imagine midi being used as an input with control net to essentially get a neural synthesizer.

For music perhaps. For sound effects I think text prompting is the rather good UI.

Controlnet/img2img style where you can mimic a sound with your mouth and it then makes it realistic could also be usable.

Re: Stable-Audio-Demo

#135

Earlier quoted context omitted.

Where this argument falls down for me is that "use" w.r.t. copyright means copying, and neither AI models nor their outputs include any material copied from the training data, in any usual sense. (Of course the inputs are copied during training, but those copies seem clearly ephemeral.) Genuinely curious: for anyone who thinks AI obviously violates copyright, how do you resolve this? E.g. do you think the violation h…

Personally I think trained models are derived works of all the training data. Just like a translation of a book is a derived works of the original. Or a binary compiled output is a derived works of some source code.

Wikipedia:

> In copyright law, a derivative work is an expressive creation that includes major copyrightable elements of ... the underlying work

A trained model fails that on two counts, doesn't it? Both the "includes" part, and the fact that a model is itself not an expressive work of authorship.

Re: Stable-Audio-Demo

#136

Earlier quoted context omitted.

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…

The obvious difference is that copyleft is voluntary, while having your art style stolen isn't. If an artist approached a software developer, created a painting of them using their Mac, and said "There, I've done your job for you" you'd think they were an idiot. This is the same from the other side. The inability to understand why that's a realistic analogy does not change the fact that it is.

"> The obvious difference is that copyleft is voluntary, while having your art style stolen isn't."

This is why it is important whether you consider that infringement occurs upon ingestion or output. If it only matters for outputs, then artists have a problem, since copyright doesn't protect styles at all, see for example the entire fashion industry.

There is a saving grace though: Artists can make a case that the association of their distinctive style with their name is at least potentially a violation of trademark or trade dress, especially if that association is being used to promote the outputs to the public. This is a fairly clear case of commercial substitution in the market for creating new works in that artist's style and creating confusion concerning the origin of the resulting work.

Note that the market for creating new works in a particular artist's distinctive and named style kind of goes away upon the artist's passing. What remains is the trademark issue of whether a particular work was actually created by the artist or not, which existing trademark law is well suited to policing, as long as the trademark is defended, even past the expiration of the copyright.

Meanwhile, trademark (and copyright) also apply to the subjects of works, like Nintendo's Mario or Disney's Mickey Mouse or Marvel's Iron Man. But we don't really want models to simply be forbidden from producing them as outputs, or they become useless as tools for the purpose of parody and satire, not to mention the ability to create non-commercial fan art. The potential liability for violating these trademarks by publishing works featuring those characters rests with the users rather than the tools, though, and again existing law is fairly well suited to policing the market. Similarly, celebrities' right of publicity probably shouldn't prevent models from learning what they look like or from making images that include their likeness when prompted with their name, but users better be prepared to justify publishing those results if sued.

You can also make the (technical) argument that if you just ask for an image of Wonder Woman, and you get an image that looks like Gal Gadot as Wonder Woman, that the model is overfitting. That's also the issue with the recent spate of coverage of Midjourney producing near-verbatim screenshots from movies.

It might be appropriate though to regulate commercial generative AI services to the extent of requiring them to warn users of all the potential copyright/trademark/etc. violations, if they ask for images of Taylor Swift as Elsa, or Princess Peach, or Wonder Woman, for example.

Re: Stable-Audio-Demo

#137
post #36
post #26

I think we still need the step where the AI learns what a high quality sound library sounds like and then applies the previously learned abilities by triggering sounds of that library via MIDI. That way you'd get perfect audio quality with the creativity of a musical AI.

How would MIDI get you eg a guitar being played dirty? Or some subtle echo that comes from recording in a bathroom?

You could have AI do some postprocessing. I think a similaar approach is the future for image generation, you have a model output a 3D scene, use a classical raytracer to do rendering and then have a final model apply corrections to achieve photorealism.

Re: Stable-Audio-Demo

#138

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…

AI is a genie that you can't really stuff back into a bottle. It's out and it's global.

If the US had tighter regulations, China or someone else will take over the market. If AI is genuinely transformative for productivity, then the US would just fall behind, sooner or later.

Re: Stable-Audio-Demo

#139

"Gen AI is the only mass-adoption technology that claims it's Ok to exploit everyone's work without permission, payment, or bringing them any other benefit." Is it? What about the printing press, photography, the copier, the scanner ... Sure, if a commercial image is used in a commercial setting, there is a potential legal case that could argue about infringement. This should NOT depend on the production means, but o…

> Xerox should not be sued because you can use a copier to copy a book (trust me kids, book copying used to be very, very big).

The appropriate analogy here isn't suing Xerox, but suing Kinko's (now FedEx Office).

And it isn't just books, but other sorts of copyrighted material as well, such as photographs, which are still an issue.

Re: Stable-Audio-Demo

#140

As with Stable Diffusion, text prompting will be the least controllable way to get useful output with this model. I can easily imagine midi being used as an input with control net to essentially get a neural synthesizer.

But works great when you don’t need much control, prompt example: “Free-jazz solo by tenor saxophonist, no time signature.”
Post reply on HN