RaveForce

Very interesting article and process. > "A huge part of the joy came from working in Ableton Live 12, which now feels like an extension of how I think" I feel the same way, but for Reaper Seeing the author mentions that decomposition of the snare is the hardest, and that’s what I was trying to solve in https://github.com/chaosprint/RaveForce (just an idea). Multimodality AI is much more powerful now. I wonder how helpful it would be for music and art education if AI could help us deconstruct some songs. When I was teaching kids with Glicol, I often used KraftWerk’s Das Model as an example: https://glicol.org/demo#themodel This rough midi version is very different from the original, but the kids had a lot of fun messing around with it.

I got into AI music back in 2017, kind of sparked by AlphaGo. Started by looking at machine listening stuff, like Nick Collins' work. Always been really curious about AI doing music live coding. In 2019, I built this thing called RaveForce [github.com/chaosprint/RaveForce]. It was a fun project. Back then, GANsynth was a big deal, looked amazing. But the sound quality… felt a bit lossy, you know? And MIDI generation, well, didn't really feel like "music generation" to me. Now, I'm thinking about these things differently. Maybe the sound quality thing is like MP3 at first, then it becomes "good enough" – like a "retina moment" for audio? Diffusion models seem to be pushing this idea too. And MIDI, if used the right way, could be a really powerful tool. Vocals synthesis and conversion are super cool. Feels like plugins, but next level. Real

Technically, I feel that the current diffusion angle always has to fight against sound quality. But maybe this angle can find its own "Retina" moment, and Suno's v4 is closer. But the hard flaw (almost unsolvable) of this angle is editing. I have been exploring methods based on DRL( https://github.com/chaosprint/RaveForce), but I think there is still a long way to go.

good point. few days ago I was thinking about restarting this project with Glicol https://github.com/chaosprint/RaveForce RaveForce - An OpenAI Gym style toolkit for music generation experiments. Love suno but eventually I need midi or xml or some lossless samples to work with

itneresting. I'm approaching music generation from another perspective: https://github.com/chaosprint/RaveForce RaveForce - An OpenAI Gym style toolkit for music generation experiments.

Great resources! Thank you for making this. I'm attaching here a DRL framework I made for music generation, similar to OpenAI Gym. If anyone wants to test the algorithms OP includes, you are welcome to use it. Issues and PRs are also welcome. https://github.com/chaosprint/RaveForce

Suno is great and I already shared my positive thought on its potential back in v2. I have always believed that the essence of digital music is "organized numbers". I think what needs to be thought about is how to use AI in this process. If you look at the results (numbers) generated, then we are indeed very close. But there is another future I believe: I hope AI can compose music with me, like copilot. This is why I keep working on https://glicol.org/ and the destination is: https://github.com/chaosprint/RaveForce Although my progress on AI is slow atm, I found that the copilot in VS code can already help me in live coding performances several times: https://youtu.be/xzIXzt3hSt0?si=rVihHYiKiAU5IKeI&t=389 Also want to hear your feedback.

Congratulations on your launch! I started music DRL (https://github.com/chaosprint/RaveForce) a few years ago. At that time, SOTA was still the "traditional" method of GANSynth. Later, I mainly turned to Glicol (https://glicol.org) and tried to combine it with RaveForce. There are many kinds of music generation nowadays, such as Suno AI, but I think the biggest pain point is the lack of controllability. I mean, after generation, if you can't fine-tune the parameters, it's going to be really painful. As for pro, most of the generated results are still unusable. This is why I wanted to try DRL in the first place. Also worth checking https://forum.ircam.fr/projects/detail/rave-vst/ If this is your direction, I'm wondering if you have compared the methods of generating midi? After all, the generated midi and parameters can be adjusted quickly

I have a project that aims to do the similar task but with a different approach: https://github.com/chaosprint/RaveForce not finished yet, so pr is welcomed!

interesting project! I also have a project for loop generation using DRL: https://github.com/chaosprint/RaveForce Haven't kept it up to date for a while as too many things are on my list. But if some of you find it interesting we can chat. Also if you are interested in generative music, you can't miss: https://www.riffusion.com/

https://github.com/chaosprint/RaveForce How about both symbolic and subsymbolic?