DiffRhythm: Fast End-to-End Full-Length Song Generation with Latent Diffusion
1–10 of 121 posts
Re: DiffRhythm: Fast End-to-End Full-Length Song Generation with Latent Diffusion
#2Business hates creatives. They'll do anything to automate us away.
Re: DiffRhythm: Fast End-to-End Full-Length Song Generation with Latent Diffusion
#3the "prompt" is the 10 seconds original audio file + the lyrics, right?
absolutely crazy
Re: DiffRhythm: Fast End-to-End Full-Length Song Generation with Latent Diffusion
#4If I am to retain any interest as an amateur music writer without proaudio engineering skills and equipment, but with a day job, , I want tools that help me enact MY vision to reality. That means multi tracking, ability to hum or score a melody and have it transfer to musical instrument, ability to enter existing tracks, provide a temporal segment for diffusion, and ask it to 'generate a counterpoint to the melody with strings, etc. The most exciting possibilities of this is enabling talented writers with day jobs, not one click song writing.
Re: DiffRhythm: Fast End-to-End Full-Length Song Generation with Latent Diffusion
#5The style matching is interesting, but there's no song structure. There's no identifiable chorus in any of the demo songs.
Re: DiffRhythm: Fast End-to-End Full-Length Song Generation with Latent Diffusion
#6Business hates creatives. They'll do anything to automate us away.
Business doesn’t hate creatives, and is not specifically targeting creatives to automate them away. Any job that can be done as good for a lower price or better for the same price is going to be a target.
Re: DiffRhythm: Fast End-to-End Full-Length Song Generation with Latent Diffusion
#7If I am to retain any interest as an amateur music writer without proaudio engineering skills and equipment, but with a day job, , I want tools that help me enact MY vision to reality. That means multi tracking, ability to hum or score a melody and have it transfer to musical instrument, ability to enter existing tracks, provide a temporal segment for diffusion, and ask it to 'generate a counterpoint to the melody wi…
I'd be surprised if the people who are writing these understand what this means.
Re: DiffRhythm: Fast End-to-End Full-Length Song Generation with Latent Diffusion
#8This is primarily architecturally interesting in my opinion. Output songs have unusual noticeable artifacts, and I would guess they become more noticeable the more you listen.
That said, wow. An end to end FAST architecture that can infer a 4.5 minute song in 10 seconds is a compelling thing. I didn’t see if we got open weights, but my guess is that this is not crazy challenging to train, and some v2/v3 versions of this are likely to be good-to-very-good.
Re: DiffRhythm: Fast End-to-End Full-Length Song Generation with Latent Diffusion
#9Business hates creatives. They'll do anything to automate us away.
Business doesn’t hate creatives, and is not specifically targeting creatives to automate them away. Any job that can be done as good for a lower price or better for the same price is going to be a target.
That's right, they don't just hate creatives. They'll go after anyone.
I wonder what the hyper-capitalist's end game looks like. One giant company that covers everything with one man sitting at a dashboard, tweaking parameters? Is that one man even necessary?
I wonder what our plans are for when "the economy" prefers to do it's thing without us. Writing poems all day? What capitalist instrument will provide "money" for us to spend in this giant machine?
Re: DiffRhythm: Fast End-to-End Full-Length Song Generation with Latent Diffusion
#10Business hates creatives. They'll do anything to automate us away.
If I was a business I'd "hate" creatives too, and I'd also want to automate them away. The costs of producing (truly) creative works is utterly bonkers, and so are the risks associated.