Better quality (claimed) than Riffusion, and lyric generation is under development.
It’s probably not too much of a stretch to suggest that AI researchers will continue improving music generation technology until anyone can create studio-quality music in any style just by describing it
If you’re curious about how all this AI stuff works, Ars has a pretty good explainer up.
Thanks. Interesting in the context of the running debate about AI from my field (visual)
Here’s an interesting clip about getting GPT 4.0 to compose music:
Hi @Bill_Janssen ,
I changed the title to make this thread a more general discussion of AI composed music. PM me if you’d like me to change it back and keep it as a discussion of MusicLM only.
In @Rugby ’s weekly zoom meeting today we discussed AI music using the linked video regarding GPT 4 above as a springboard. I mentioned that in Australia AI music would not be protected by copyright because it required a human (a qualified person) to be the author. The link below confirms that is also the position in the USA and that a consultation process is underway:
interesting read.