back to article Text-to-image models are so last month, text-to-video is here

AI progresses rapidly. Just months after the release of the most advanced text-to-image models, developers are showing off text-to-video systems.  Meta announced a multimodal algorithm named Make-A-Video that allows its users to type a text description of a scene as input and get a short computer-generated animated clip as …

  1. demon driver

    Willis: not "for any future movies", only for that one ad

    Seems that was false news; the deal with Deepcake was only about that one video.

    1. Neil Barnes Silver badge

      Re: Willis: not "for any future movies", only for that one ad

      And anyway... how do we know whether Willis signed the deal, or if the entire deal was a product of deep fake technology?

      It's getting to the stage when we're going to have to authorise things with something like our DNA!

      1. Pascal Monett Silver badge

        And when that gets hacked, what do you do ?

        1. Neil Barnes Silver badge

          We're already doomed...

        2. Fred Flintstone Gold badge

          I think we'll end up with the bum print authentication as premiered in Monsters vs Aliens.

          As a matter of fact, the whole scene is shockingly close to reality :).

      2. doublelayer Silver badge

        Re: Willis: not "for any future movies", only for that one ad

        It's not a great idea to use anything you leave behind as authentication for critical things. That includes your fingerprints and your DNA. If I can get a copy of those by being near you for an hour or so and monitoring what you've touched, it's not good for proving your identity for a one-time thing. It works a bit better for something where you provide new samples each time. For example, using a fingerprint to unlock a door or device makes more sense than using one to sign a contract, but there's a risk for both so if it's really important, don't even use it for the door.

    2. Jan K.

      Re: Willis: not "for any future movies", only for that one ad

      Bruce Willi's agent denies the story

      A spokesperson for the actor told the BBC that he had "no partnership or agreement" with the company.

      And a representative of Deepcake said only Willis had the rights to his face.

      Deepcake fake...

  2. An_Old_Dog Silver badge

    "Using NLP to crackdown on paper mills"

    When I read the title, I first thought it was some sort of pollution-detector device which analyzed smoke from paper-manufacturing facilities.

    1. Michael Wojcik Silver badge

      Re: "Using NLP to crackdown on paper mills"

      Since NLP is poised to replace paper mills with machine-written papers, this is a nicely symmetric development in this particular arms race.

      I'll also note it's one I predicted in a post to one of the rhetoric mailing lists about a dozen years ago, but since it's an obvious development anyone paying attention ought to have seen it coming. It hasn't been a technical problem for a long time – just a question of economics. Existing paper mills enjoy cheap labor1 and an established network of customers2, which makes them harder to displace by automation. But not immune to it.

      1Mostly unemployed and underemployed people with advanced degrees, according to research I've seen. There was a long piece by a former paper-writer in ... Harper's, maybe? ... some years back that supports this.

      2In the US, this includes fraternities and sororities, and organizations that "support" student athletes.

  3. An_Old_Dog Silver badge

    Plagiarism & Shadow-Authoring

    If the the NLP program shouts, "J'accuse!" at a paper, how can the authors effectively defend against erroneous accusation? Does the program give an itemized listing of things it thinks are "too similar" to other published texts? Do publishers blindly accept this programs results simply because, "The computer said so"?

    1. Michael Wojcik Silver badge

      Re: Plagiarism & Shadow-Authoring

      Presumably it will work just like other ML-based judging systems (e.g. systems for assigning sentencing factors in criminal cases): as a black box with no real provision for appeal, because fuck you.

  4. Pascal Monett Silver badge

    "type a text description of a scene as input"

    Oh dear God, that is so going to turn into flying penises.

    1. Joe W Silver badge

      Re: "type a text description of a scene as input"

      As long as this happens on ThirdLife, sorry, "Metaverse", I could not object....

      1. Anonymous Coward
        Anonymous Coward

        Re: "type a text description of a scene as input"

        Was that not TurdLife, or was that just the accent?


    2. GruntyMcPugh Silver badge

      Re: "type a text description of a scene as input"

      Righty, I know what I'm doing at lunchtime now,... : -)

  5. yetanotheraoc Silver badge

    lots of opportunities for AI

    Have it analyze business emails and based on the content decide if the sender is full of bs. That one would be really useful.

  6. Michael Wojcik Silver badge

    Stay out of the Uncanny Valley

    Text-to-video will be a lot more palatable, and less resource-intensive, when it stays comfortably far from photorealism. Text-to-cartoon running on moderate resources would probably be very popular with kids, "creatives", and people who are just interested in doing it for a hobby or the occasional lark.

    Primitive versions of that are already available, but an improved version, perhaps coupled to a streaming service like Steam for backend processing, might actually be commercially viable. It offers some of the same creative opportunity as, say, Minecraft.

POST COMMENT House rules

Not a member of The Register? Create a new account here.

  • Enter your comment

  • Add an icon

Anonymous cowards cannot choose their icon

Other stories you might like