I was using stable diffusion a lot previously, but haven’t really touched it in the past several months. I was wondering what interfaces people are using these days?

Automatic1111 still seems to be popular, and that’s the one I am most familiar with. I know there are some others now though, like comfy, and I guess maybe invokeAI is still going?

  • @2dollarsim
    link
    English
    11 year ago

    Haha it won’t be a joke next week when the new text-to-video model comes out

    • @[email protected]
      link
      fedilink
      English
      21 year ago

      With how unstable (lol) txt2img is, I don’t believe a stable enough for porn txt2video model is coming soon.

      • @2dollarsim
        link
        English
        11 year ago

        I would agree, but the rate of innovation in AI is so unpredictable that it could go either way.

        • @[email protected]
          link
          fedilink
          English
          11 year ago

          I don’t really agree.

          Recent AI inovations are pretty modest and use the innovation of raw fucking power to achieve goals.

          Gpt4 uses 230B parameters, whereas to run a 7B LLM you need 16gb of vram already, and llms are o(n²) in complexity in terms of parameters, I’ll let you do the maths

          Stable diffusion (latent diffusion to be more precise) is about the same, the initial training required billions of teraflop, while it was relatively cheap (100k$), it still rides on modern GPU technology .