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.

  • RubberDuckEnglish
    6•1 month ago

    Until they sunset it. No use getting invested in new Google products anyway.

      • JackGreenEarthEnglish
        2•1 month ago

        That means not open, right? I’m only interested once the first good opens Circe video generator is released, more closed source ones aren’t interesting, once I heard about the first.

  • @deathmetal27@lemmy.worldEnglish
    4•1 month ago

    After reading the wheresyouredat article I don’t have much faith in this one either for any serious work. It’s a curiosity at best.

  • AutoTL;DRBEnglish
    2•1 month ago

    This is the best summary I could come up with:

    Veo’s example videos include a cowboy riding a horse, a fast-tracking shot down a suburban street, kebabs roasting on a grill, a time-lapse of a sunflower opening, and more.

    Conspicuously absent are any detailed depictions of humans, which have historically been tricky for AI image and video models to generate without obvious deformations.

    Google says that Veo builds upon the company’s previous video-generation models, including Generative Query Network (GQN), DVD-GAN, Imagen-Video, Phenaki, WALT, VideoPoet, and Lumiere.

    While the demos seem impressive at first glance (especially compared to Will Smith eating spaghetti), Google acknowledges AI video-generation is difficult.

    But the company is confident enough in the model that it is working with actor Donald Glover and his studio, Gilga, to create an AI-generated demonstration film that will debut soon.

    Initially, Veo will be accessible to select creators through VideoFX, a new experimental tool available on Google’s AI Test Kitchen website, labs.google.

    The original article contains 701 words, the summary contains 150 words. Saved 79%. I’m a bot and I’m open source!