DALL·E 3 understands significantly more nuance and detail than our previous systems, allowing you to easily translate your ideas into exceptionally accurate images.

  • antlion@lemmy.dbzer0.com
    link
    fedilink
    English
    arrow-up
    11
    ·
    1 year ago

    Amazing. I wonder how well it could work in reverse: generating an accurate caption for any image, including graphs and charts. Could be useful for visually impaired and accessibility.

    • regbin_@lemmy.world
      link
      fedilink
      English
      arrow-up
      4
      ·
      1 year ago

      I’ve seen people say that even if DALL-E images aren’t as good, the images it produce adhere to your prompt much better than SD(XL).