The demos are great. Could someone explain what’s in it for Meta open sourcing all these models?
Commoditize Your Complement? https://gwern.net/complement
What is it a complement to though?
Open-sourcing AudioCraft: Generative AI for audio
11–20 of 335 posts
Re: Open-sourcing AudioCraft: Generative AI for audio
#12Wonder how far off the whole "generate music based on your existing music library" thing is going to be?
That'll make musicians happy with big tech as well, just like artists are. *sigh*
Re: Open-sourcing AudioCraft: Generative AI for audio
#13> MusicGen, which was trained with Meta-owned and specifically licensed music, generates music from text-based user inputs, while AudioGen, which was trained on public sound effects, generates audio from text-based user inputs.
Meta is really clearly trying to differentiate themselves from OpenAI here. Open source + driving home "we don't use data we haven't paid for / don't own".
Re: Open-sourcing AudioCraft: Generative AI for audio
#14Here's a different question: Can you use the audio output this produces for anything else other than "research purposes"?
Re: Open-sourcing AudioCraft: Generative AI for audio
#15Wonder how far off the whole "generate music based on your existing music library" thing is going to be? That'll make musicians happy with big tech as well, just like artists are. *sigh*
Why not do generate music you like which wouldn’t need you to upload your library and would have RLHF baked in.
Re: Open-sourcing AudioCraft: Generative AI for audio
#16Is there place where I can check how it works? Like give my input and get output audio?
Re: Open-sourcing AudioCraft: Generative AI for audio
#17Wonder how far off the whole "generate music based on your existing music library" thing is going to be? That'll make musicians happy with big tech as well, just like artists are. *sigh*
The Record labels are far, far more litigious than the art community.
Re: Open-sourcing AudioCraft: Generative AI for audio
#18> MusicGen, which was trained with Meta-owned and specifically licensed music, generates music from text-based user inputs, while AudioGen, which was trained on public sound effects, generates audio from text-based user inputs. Meta is really clearly trying to differentiate themselves from OpenAI here. Open source + driving home "we don't use data we haven't paid for / don't own".
Bully "Open"AI into rebranding.
Re: Open-sourcing AudioCraft: Generative AI for audio
#19Re: Open-sourcing AudioCraft: Generative AI for audio
#20Earlier quoted context omitted.
Commoditize Your Complement? https://gwern.net/complement
What is it a complement to though?
Meta has several of the biggest UGC platforms, and in this case the complement is content itself. Reels with autogenerated (and royalty free) background music is the obvious example but I'm sure there are more. Maybe creative for ads as well?