riffusion-inference VS spleeter

Just put the generated image into the seeds folder on the inference server, replace it with one of them on the seed_images folder: https://github.com/hmartiro/riffusion-inference/tree/main/seed_images

I think so. This is the specific code they say they use to do the image>audio conversion

I'm still reading, but it looks like they're doing some extra pre and post processing: https://github.com/hmartiro/riffusion-inference

Yes from https://huggingface.co/runwayml/stable-diffusion-v1-5. Our checkpoint works with automatic1111, and if you'd like to make an extension to decode to audio, it should be pretty straightforward: https://github.com/hmartiro/riffusion-inference/blob/main/ri...

virtual dj and others stem separator is shrinked model of this https://github.com/deezer/spleeter you will get better results downloading original + their large model.

I have used multiple tools at this point. It depends on the scene. I use https://ultimatevocalremover.com/, https://github.com/deezer/spleeter/, iZotope RX. There are also multiple options online, I would personally recommend https://vocalremover.org/.

I tried to use it but I had some issues as others in the thread.

I have tried many sources and method over the years and settled on spleeter [0]. Works well even for 10+ minute songs, varying styles from flamenco to heavy metal.

[0] https://github.com/deezer/spleeter

Spleeter is pretty good https://github.com/deezer/spleeter. Apparently it is used in some dj applications

Haha GitHub and command lines and all can be confusing, but it’s certainly worth the effort because it lets you do everything for free.. here’s the online tutorial: https://github.com/deezer/spleeter/wiki/1.-Installation

Chopped from their website Simple Stems is a quick and easy way to decompose any audio into it’s constituent parts. The plugin uses the well established Spleeter algorithm by Deezer to deconstruct songs into 2, 4 or 5 stems. The results are stunning, though more complicated mixes and live recordings are not always perfectly decomposed.

I was going to post basic pitch from Spotify but it looks like billconan beat me to it. That said I can give you a bit more advice. The Spotify basic pitch model isn't too good at multi-track input. It's capable of it, but you may actually get better results if you separate out the tracks first and then run them individually through the basic pitch model.

In order to do this you can use a source/stem separation model like spleeter (https://github.com/deezer/spleeter) and then run the basic pitch model (or any other midi transcription model). There's other you can try which may yield better results, for example: (https://github.com/Music-and-Culture-Technology-Lab/omnizart)

Either way the key words you want to be looking for are "midi transcription" and "stem separation", should help you find more models to try for both steps. Good luck! :)