Google's video-synthesis model creates minute-long 1080p videos from written prompts.

On Tuesday at Google I/O 2024, Google announced Veo, a new AI video-synthesis model that can create HD videos from text, image, or video prompts, similar to OpenAI’s Sora. It can generate 1080p videos lasting over a minute and edit videos from written instructions, but it has not yet been released for broad use.

    • @mindbleach@sh.itjust.worksEnglish
      1•1 month ago

      Because it’s the obvious next step for a technology that very recently went from pure science fiction to widespread practicality?

      Because it can presumably modify human drawings instead of just generating everything from scratch, making it possible for any rando to doodle out the exact cartoon in their head?

      Because that’d also work for real video of real people, putting the CGI from billion-dollar movies into the hands of anyone with a decent PC?

      I understand why people are worried about what this will do to artists’ livelihoods, or why they don’t believe a word of hype from trend-chasing tech-bros. I do not understand why people pretend this isn’t cool as fuck.

    • @Grimy@lemmy.worldEnglish
      0•1 month ago

      Why not?

      I want to have fun generating my own shows and movies eventually. Just for my own fun. You can literally just not use it.