It’s a 1st step in powerful editing tools for consumer images, harnessing on-device diffusion models.

  • IllNess@infosec.pub
    link
    fedilink
    English
    arrow-up
    4
    arrow-down
    1
    ·
    3 months ago

    Interesting how they filled in words. It looks like they spelled “Asia” wrong twice.

    Makes me wonder if they will use the geotag of an image to better guess text like this.