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

Stable Audio: Fast Timing-Conditioned Latent Audio Diffusion

stability.ai

Post reply on HN
Print view View original

161–170 of 210 posts

Re: Stable Audio: Fast Timing-Conditioned Latent Audio Diffusion

#161

Post by iainctduncan »

Applejinx wrote: post #109
iainctduncan wrote: post #102

Earlier quoted context omitted.

Midi is not lossy, midi is symbolic. There's a huge difference.

No, it's lossy. It's an event model at a fixed data rate. You can only do so many things sequentially, even if you could represent any possible musical concept as a MIDI event. So even if you're not sticking to note-on, note-off, it's still extremely lossy.

well ok, you could say it's a lossy format for capturing physical movement, which it certainly is. My point is that it is not a format for capturing music any more than a score on a page is a format for capturing music. Both are instructions for a performer of music (one machine, one human), which is a very different beast.

Re: Stable Audio: Fast Timing-Conditioned Latent Audio Diffusion

#162

Post by TheActualWalko »

fnordpiglet wrote: post #74
Jeff_Brown wrote: post #67

Earlier quoted context omitted.

That raises an interesting difference between cleaning AI-generated sound and cleaning ordinary recordings. In an ordinary recording, there is an objective reality to discover -- a certain collection of voices was summed to create a signal. With (most? the best?) existing AI audio generation, the waveform is created from whole cloth, and extracting voices from it is an act of creation, not just discovery. I've come a…

Generative models can certainly create midi, but no one has done it yet. Given the technique is making video, audio, images, and language, all you need to do is train and build a model with an appropriate architecture. It’s easy to forget this is all pretty new stuff and it still costs a lot to make the base models. But the techniques are (more or less) well documented and implementable with open source tools.

We’ve done it! wavtool.com

Re: Stable Audio: Fast Timing-Conditioned Latent Audio Diffusion

#163

Post by smoldesu »

refulgentis wrote: post #139
thomashop wrote: post #128

Earlier quoted context omitted.

You are looking at a very short part of recent history. It has not been like that at all.

I'm all ears. I was "in the room" from 2019 on. Can't name one art model you could run on your GPU from a FAANG or OpenAI before SD, and can't name one LLM with public access before ChatGPT, much less weights available till LLaMA 1. But please, do share.

> Can't name one art model you could run on your GPU from a FAANG or OpenAI before SD

Google published dozens to promote Tensorflow:

https://experiments.withgoogle.com/font-map https://experiments.withgoogle.com/sketch-rnn-demo https://experiments.withgoogle.com/curator-table https://experiments.withgoogle.com/nsynth-super https://experiments.withgoogle.com/t-sne-map

The list goes on. Many are source-available with weights too.

> can't name one LLM with public access before ChatGPT, much less weights available till LLaMA 1.

Do any of these ring a bell?

- DistilBERT/MobileBERT/DeBERTa/RoBERTa/ALBERT

- FNet

- GPT2/GPT-Neo/GPT-J

- Marian

- MBart

- M2m100

- NLLB

- Electra

- T5/LongT5/T5-flan

- XLNet

- Reformer

- ProphetNet

- Pegasus

That's not comprehensive but may be enough to jog your memory.

Re: Stable Audio: Fast Timing-Conditioned Latent Audio Diffusion

#164

Post by gabereiser »

TylerE wrote: post #153
93po wrote: post #143

Earlier quoted context omitted.

he's saying the output is cheesy. it sounds like stuff you'd hear on a demo track for a kid's toy piano

It's not THAT bad, it's just that for a programming targetting jazz the playback is rather...square.

Yeah I definitely imagine certain genres sounding off due to the rhythmic nature of computer timing. Jazz doesn’t follow rules like that so good jazz has these timing idiosyncrasies that make it sound the way it sounds. That and a ridiculous obsession with adding half step and quarter tone intervals.

Re: Stable Audio: Fast Timing-Conditioned Latent Audio Diffusion

#165

Post by refulgentis »

smoldesu wrote: post #163
refulgentis wrote: post #139

Earlier quoted context omitted.

I'm all ears. I was "in the room" from 2019 on. Can't name one art model you could run on your GPU from a FAANG or OpenAI before SD, and can't name one LLM with public access before ChatGPT, much less weights available till LLaMA 1. But please, do share.

> Can't name one art model you could run on your GPU from a FAANG or OpenAI before SD Google published dozens to promote Tensorflow: https://experiments.withgoogle.com/font-map https://experiments.withgoogle.com/sketch-rnn-demo https://experiments.withgoogle.com/curator-table https://experiments.withgoogle.com/nsynth-super https://experiments.withgoogle.com/t-sne-map The list goes on. Many are source-available with w…

I understand your point.

The gap in communication is we don't mean _literally_ no one _ever_ open-sourced models. I agree, that would be absurd. [1]

Companies, quite infamously and well-understood, _did_ hold back their "real" generative models, even from being available for pay.

Take a stab at a literal definition: - post-GPT2 LLMs (ex. PALM, PALM2) - art like DaLL-E, Imagen, Parti

Loosely, we had Disco Diffusion for art, and GPT-3 for LLMs, and then Dall-E, then Midjourney. That was over an _entire year_, and the floodgates on private ones didn't open till post SD/ChatGPT.

[1] thank you for the lengths you went to highlight the best over a considered span of time, I would have just said something snarky :)

[2] I did not realize FLAN was open-sourced a month before ChatGPT, that's fascinating: we're stretching a bit, beyond that, IMHO: the BERTs aren't recognizable as LLMs.

Re: Stable Audio: Fast Timing-Conditioned Latent Audio Diffusion

#167

Post by refulgentis »

thewataccount wrote: post #160
refulgentis wrote: post #139

Earlier quoted context omitted.

I'm all ears. I was "in the room" from 2019 on. Can't name one art model you could run on your GPU from a FAANG or OpenAI before SD, and can't name one LLM with public access before ChatGPT, much less weights available till LLaMA 1. But please, do share.

Openai - GPT2 2019 - https://openai.com/research/gpt-2-1-5b-release Google - T5 - Feb 2020 - https://blog.research.google/2020/02/exploring-transfer-lear... Both of these were and still are used heavily for on-going research and T5 has been found to be decently useful when fine-tuned. Weights were available for both.

See https://news.ycombinator.com/item?id=37501964

Re: Stable Audio: Fast Timing-Conditioned Latent Audio Diffusion

#168

Post by smoldesu »

refulgentis wrote: post #165
smoldesu wrote: post #163

Earlier quoted context omitted.

> Can't name one art model you could run on your GPU from a FAANG or OpenAI before SD Google published dozens to promote Tensorflow: https://experiments.withgoogle.com/font-map https://experiments.withgoogle.com/sketch-rnn-demo https://experiments.withgoogle.com/curator-table https://experiments.withgoogle.com/nsynth-super https://experiments.withgoogle.com/t-sne-map The list goes on. Many are source-available with w…

I understand your point. The gap in communication is we don't mean _literally_ no one _ever_ open-sourced models. I agree, that would be absurd. [1] Companies, quite infamously and well-understood, _did_ hold back their "real" generative models, even from being available for pay. Take a stab at a literal definition: - post-GPT2 LLMs (ex. PALM, PALM2) - art like DaLL-E, Imagen, Parti Loosely, we had Disco Diffusion fo…

All good. I've also been working on LLMs since 2019-ish, so I wanted to toss a hat in the ring for the underrepresented transformer models. They were cool (eg. dumb), fast and worked better than they had any right to. In a lot of ways they are the ancestors of ChatGPT and Llama, so it's important to at least bring them into the discussion.

Re: Stable Audio: Fast Timing-Conditioned Latent Audio Diffusion

#169

Post by astrange »

refulgentis wrote: post #139
thomashop wrote: post #128

Earlier quoted context omitted.

You are looking at a very short part of recent history. It has not been like that at all.

I'm all ears. I was "in the room" from 2019 on. Can't name one art model you could run on your GPU from a FAANG or OpenAI before SD, and can't name one LLM with public access before ChatGPT, much less weights available till LLaMA 1. But please, do share.

> Can't name one art model you could run on your GPU from a FAANG or OpenAI before SD

CLIP could be used as an image generator, slowly.

> and can't name one LLM with public access before ChatGPT, much less weights available till LLaMA 1

InstructGPT was available on OpenAI playground for months before ChatGPT and was basically as capable as GPT3, people were really missing out. Don't know any good public models though.

Re: Stable Audio: Fast Timing-Conditioned Latent Audio Diffusion

#170

Post by astrange »

waffletower wrote: post #91
Taek wrote: post #49

Earlier quoted context omitted.

Before stable diffusion, nobody released weights at all. Meta et al only started sharing their models with the world when they realized how fast a developer ecosystem was building around the best models. Without stability, all of AI would still be closed and opaque.

In the image generation space, weights were never released for ImageGen and Dall-e, but yes you can find weights for more specialized generative models like StyleGAN (2, 3 etc). Stable Diffusion was arguably one of the most influential open model releases, and I think the substantial investment in StabilityAI is evidence of that.

There were open reproductions of DALLE1 like ruDALLE.
Post reply on HN