Congratulations this is an amazing application of technology and truly innovative. This could be leveraged by a wide range of applications that I hope you'll capitalize on.
Riffusion – Stable Diffusion fine-tuned to generate music
21–30 of 481 posts
Re: Riffusion – Stable Diffusion fine-tuned to generate music
#22They’ve got a looooong way to go man
Re: Riffusion – Stable Diffusion fine-tuned to generate music
#23Very cool! I was wondering why there wasnt any music diffusion apps out there, it seems more useful because music has stricter copyright and all content creators need some background music ...
Re: Riffusion – Stable Diffusion fine-tuned to generate music
#24Very impressive. I am quite confident that next years number one Christmas hit will start like "church bells to electronic beats".
Xmd5a is already a real track.
Re: Riffusion – Stable Diffusion fine-tuned to generate music
#25Earlier this year, graphic designers, last month it was software engineers, and now musicians are also feeling the effects.
Who else will AI make looking for a new job?
Re: Riffusion – Stable Diffusion fine-tuned to generate music
#26Wow, diffusion could be a game changer for audio restoration.
Re: Riffusion – Stable Diffusion fine-tuned to generate music
#27Absolutely brilliant!
Re: Riffusion – Stable Diffusion fine-tuned to generate music
#28Re: Riffusion – Stable Diffusion fine-tuned to generate music
#29Really fascinating. I'd be interested to know more about how it was trained, with what data exactly.
Re: Riffusion – Stable Diffusion fine-tuned to generate music
#30Producing images of spectrograms is a genius idea. Great implementation! A couple of ideas that come to mind: - I wonder if you could separate the audio tracks of each instrument, generate separately, and then combine them. This could give more control over the generation. Alignment might be tough, though. - If you could at least separate vocals and instrumentals, you could train a separate model for vocals (LLM for…
I think you'd have to start with separate spectrograms per instrument, then blend the complete track in "post" at the end.