News for hackers. Stuff that matters.
Re:NeuralSVG: An Implicit Representation for Text-to-Vector ... by janalsncm on Wednesday January 08, 2025 @02:17PM (#42637481)
I am a huge fan of this type of incremental generative approach. Language isn’t precise enough to describe a final product, so generating intermediate steps is very powerful.

I’d also like to see this in music generation. Tools like Suno are cool but I would much rather have something that generates MIDIs and instrument configurations instead.

Maybe this is a good lesson for generative tools. It’s possible to generate something that’s a good starting point. But what people actually want is long tail, so including the capability of precision modification is the difference between a canned demo and a powerful tool.

> Code coming soon

The examples are quite nice but I have no idea how reproducible they are.

Re:NeuralSVG: An Implicit Representation for Text-to-Vector ... by kadushka on Wednesday January 08, 2025 @03:23PM (#42638069)
I’d also like to see this in music generation. Tools like Suno are cool but I would much rather have something that generates MIDIs and instrument configurations instead.

Sounds like you're looking for something like https://www.aiva.ai

Re:NeuralSVG: An Implicit Representation for Text-to-Vector ... by janalsncm on Wednesday January 08, 2025 @04:30PM (#42638657)
Honestly that site feels like they have a database of midis tagged by genre and pick them out randomly. It’s totally different from their demo song.

I guess I’m hoping for something better. It’s also closed source, the web ui doesn’t have editing functionality, and the output is pretty disjointed. Maybe if I messed around with it enough the result would be decent.

Re:NeuralSVG: An Implicit Representation for Text-to-Vector ... by kadushka on Wednesday January 08, 2025 @08:32PM (#42640609)
Fair enough. Still, for what you’ve described, Aiva is the best tool available.
Re:NeuralSVG: An Implicit Representation for Text-to-Vector ... by bufferoverflow on Wednesday January 08, 2025 @04:12PM (#42638497)
MIDI isn't enough. I want MIDI + filters, plus separate voice and custom sounds tracks.
Re:NeuralSVG: An Implicit Representation for Text-to-Vector ... by gexaha on Wednesday January 08, 2025 @04:14PM (#42638520)
microtonal midi would be super awesome
Re:NeuralSVG: An Implicit Representation for Text-to-Vector ... by chaosprint on Thursday January 09, 2025 @06:20PM (#42650859)
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