Stable Audio represents the cutting-edge audio generation research by Stability AI’s generative audio research lab, Harmonai. We continue to improve our model architectures, datasets, and training procedures to improve output quality, controllability, inference speed, and output length.
  • TimeSquirrel@kbin.social
    7·
    10 months ago

    This is going to kickstart the “electronic/sequenced/programmed music isn’t music” debate all over again.

    • 9point6@lemmy.worldEnglish
      5·
      10 months ago

      I think the difference with this before was that people thought electronic musicians weren’t really doing anything and the computer just spat out music, when there was actually a load of work going into it.

      This is pretty much literally what people were saying was happening before, so the argument would probably be a bit more valid this time around.

    • MossBear@lemmy.worldEnglish
      31·
      10 months ago

      Its music, but the level of skill to make it is low, and therefore of little credit to the one who makes it.

  • peopleproblems@lemmy.worldEnglish
    4·
    10 months ago

    Ok, this is the shit I have wanted.

    I love music, I just don’t have the patience to learn modern technology. This could at least help me get ideas out of my head.

  • BrianTheeBiscuiteer@lemmy.worldEnglish
    3·
    10 months ago

    Can this kind of stuff be used for music restoration? I have a song that sounds kind of garbled and poorly balanced (it came from RealAudio over dialup) and to my knowledge it’s never been released.

    • bioemerl@kbin.social
      11·
      10 months ago

      Contrary to what the other guy is talking about, you can totally use AI for restoration, or at least upgrading the audio. At least sometimes. It depends on how this thing is programmed and if it supports something like stable diffusions control net

      • LanternEverywhere@kbin.social
        3·
        10 months ago

        Totally. AI does serious improvement to visual resolution upscaling, so it should be capable of serious audio resolution upscaling. Upscaled media never is exactly like the original, but its quality is massively improved to the way humans perceive things.

    • echo64@lemmy.worldEnglish
      510·
      10 months ago

      you can’t really use AI for restoration at all, modern AI systems are based around generating just, whatever. and the hope is that with enough training the whatever will bias towards what you want.

      this means that it can’t restore, it can’t reason about what was originally there, it can only make it’s own thing and we hope that with enough training it’ll fool humans enough not to matter.

      if all you want is something to sound “better” and don’t care about the restoration aspect then sure. if you want what was originally there, no

      • admiralteal@kbin.social
        51·
        10 months ago

        You’re making a conservation vs restoration argument here.

        Restoration is what the guy is asking about, I suspect, not conservation.

        • echo64@lemmy.worldEnglish
          31·
          10 months ago

          nah, conservation would be keeping that original recording in a way as close as possible, Restoration would be restoring what was originally there.

          What AI does is neither, it imagines details that never existed to make something new. It’s important that we don’t erode the meaning here because what AI does is cool, but it also does something new that does not care about the original thing.