Scientists have built a framework that gives generative AI systems like DALL·E 3 and Stable Diffusion a major boost by condensing them into smaller models — without compromising their quality.
      • Archr@lemmy.worldEnglish
        0·
        6 months ago

        I see your InvokeAI and raise you Stability Matrix

        Edit: I wanted to edit my comment to leave some context for people.

        Stability Matrix is an app that handles installing many different stable diffusion applications. (no more messing with InvokeAI’s janky install script).

        It also integrates with CivitAI and HuggingFace to directly download models and Lora and share them between your applications, saving you lots of diskspace.

        • Black616Angel@feddit.deEnglish
          0·
          6 months ago

          … Thanks. This looks super useful.

          Edit: After posting I realized.that this sounds super sarcastic, which it wasn’t. This does look useful and I was already looking for smth. like that.

    • BrianTheeBiscuiteer@lemmy.worldEnglish
      0·
      6 months ago

      While I think the realism of some models is fantastic and the flexibility of others is great it is starting to feel like we’re reaching a plateau on quality. Most of the white papers I’ve seen posted lately are about speed or some alternate way of doing what ControlNet or inpainting can already do.

      • AggressivelyPassive@feddit.deEnglish
        0·
        6 months ago

        That’s maybe because we’ve reached the limits of what the current architecture of models can achieve on the current architecture of GPUs.

        To create significantly better models without having a fundamentally new approach, you have to increase the model size. And if all accelerators accessible to you only offer, say, 24gb, you can’t grow infinitely. At least not within a reasonable timeframe.