There’s a new paper: “Autonomous language-image generation loops converge to generic visual motifs”  — diffusion models have just 12 standard templates. [Cell; Cell, with supplements, PDF; press re…
  • fullsquare@awful.systemsEnglish
    0·
    2 days ago

    so after putting together text to image and image to text idiot boxes, there appears to be small number of approximate sort of eigenvalues in there. does that even mean anything or has any consequences?

    • David Gerard@awful.systemsOPMEnglish
      0·
      2 days ago

      as i said this is a completely unsurprising result, but it’s amusing to know what the twelve templates actually are

      I got an email from the author, he says the paper was a passing observation and he’s surprised it’s got as much attention as it has