• dandi8@fedia.io
    link
    fedilink
    arrow-up
    1
    ·
    3 days ago

    So you agree, then, that comparing the two is like comparing apples to oranges?

      • dandi8@fedia.io
        link
        fedilink
        arrow-up
        1
        ·
        2 days ago

        Per the original reply to your top comment:

        Are you seriously comparing using generative diffusion models to applying a chroma key in video editing?

        • CovfefeKills@lemmy.world
          link
          fedilink
          English
          arrow-up
          1
          ·
          2 days ago

          Are you not aware of the AI assisted greenscreen tools? No well they are helpful and make the job faster.

          I am referring to generative models trained to take an image and output a chromakey’d image with some minor hair and transparency improvements. The lines are kinda blurred between classified and generated here but it is “generative AI”.

          I think we just all agree text-to-image/video is bad and not creative at all. I just have this strong feeling that these directors have access to real experts and tools so I give them the benefit of the doubt rather than fediverse members, by a huge fucking margin.

          https://youtu.be/3Ploi723hg4?t=1291