I felt a great disturbance in the Force, as though all the music licensing lawyers in the USA all cried out at once.
Stable-Audio-Demo
11–20 of 249 posts
Re: Stable-Audio-Demo
#12[flagged]
Re: Stable-Audio-Demo
#13So 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.
[flagged]
Re: Stable-Audio-Demo
#14[flagged]
I know right, what year is this?
Re: Stable-Audio-Demo
#15wake me up when it can write a fugue
Re: Stable-Audio-Demo
#16This is incredibly good compared to SOTA music models (MusicGen, MusicLM). It looks like there's also a product page where you can subscribe to use it, similar to Midjourney: https://www.stableaudio.com/ Sadly it's not open-weight and it doesn't look like there's an API (again like Midjourney): you subscribe monthly to generate audio in their UI, rather than having something developers can integrate or wrap.
Thankfully you can train it at home, the bigger question is a data.
Re: Stable-Audio-Demo
#17[flagged]
Worked fine in Firefox.
Re: Stable-Audio-Demo
#18[flagged]
What’s your preferred browser?
Re: Stable-Audio-Demo
#19this can produce some pretty disturbing, but interesting music using the prompt "energetic music, violin, voice, orchestra, piano, minimalism, john adams, nixon in china": https://www.stableaudio.com/1/share/953f079e-d704-4138-904c-...
Re: Stable-Audio-Demo
#20This 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.
AI pictures are the same. We are more tolerant of six fingered-pictures with missing limbs, for some reason.