Google's Project Genie Lets You Generate Your Own Interactive Worlds
- Reference: 0180692326
- News link: https://games.slashdot.org/story/26/01/29/2157233/googles-project-genie-lets-you-generate-your-own-interactive-worlds
- Source link:
> At launch, Project Genie offers three different modes of interaction: World Sketching, exploration and remixing. The first sees Google's Nano Banana Pro model generating the source image Genie 3 will use to create the world you will later explore. At this stage, you can describe your character, define the camera perspective -- be it first-person, third-person or isometric -- and how you want to explore the world Genie 3 is about to generate. Before you can jump into the model's creation, Nano Banana Pro will "sketch" what you're about to see so you can make tweaks. It's also possible to write your own prompts for worlds others have used Genie to generate.
>
> One thing to keep in mind is that Genie 3 is not a game engine. While its outputs can look game-like, and it can simulate physical interactions, there aren't traditional game mechanics here. Generations are also limited to 60 seconds, as is the presentation, which is capped at 24 frames per second and 720p.
[1] https://www.engadget.com/ai/googles-project-genie-lets-you-generate-your-own-interactive-worlds-183646186.html
[2] https://blog.google/innovation-and-ai/models-and-research/google-deepmind/project-genie/
Re: (Score:2)
If Nano Banana gets circumcised, we can call it Clippy.
Short and interactive (Score:2)
Lemme see... Yep, people will use it to generate porn. 100%
Three modes? (Score:2)
At launch, Project Genie offers three different modes of interaction: World Sketching, exploration and remixing.
That's two. Where is the third?
Re: (Score:2)
> At launch, Project Genie offers three different modes of interaction: World Sketching, exploration and remixing.
> That's two. Where is the third?
World Scetching
World Exploration
World Remixing.
Re: (Score:2)
It was lost to the missing Oxford comma.
VR? (Score:2)
Is it spatial 3D/360 interactive worlds which would be awesome for using with a VR headset.
Take my $250/month!!!! (Score:2)
LOL, kidding, you psychopaths.
Who in their right mind would pay that much for this crap?
Re: (Score:2)
> LOL, kidding, you psychopaths.
> Who in their right mind would pay that much for this crap?
Game studios who want their art directors to feed prompts to via command like to a GenAI, and iterate and refine those prompts until s/he is satisfied with the overall look, feenm and interactions on the level before showing the result of that and thelling the artists and level designers "build that on the level editor" instead of the current method which is:
Send a bunch of initial prompts via email to the level designers and artists, the level gets contructed in the level editor, the level is not to the li
is this the end of the line for individual computi (Score:2)
Once we are at the point when there is plenty of compute to generate 4k (or VR equivalent) video or interactive content based on a user's unstructured input, what else is there? If Moore's law becomes dead soon does it matter?
Re: (Score:2)
> Once we are at the point when there is plenty of compute to generate 4k (or VR equivalent) video or interactive content based on a user's unstructured input, what else is there? If Moore's law becomes dead soon does it matter?
You'll always have bitcoins to mine -- your computer will never be fast enough unless it's faster than the other guy's, and vice-versa.
Re: (Score:2)
Ah, the end of computing again.
4k is pretty shite for VR. The equivalent of my 4k monitor at a comfortable 1.5 m distance in a VR display 10 mm from my eyeball is... a lot more ks. Per eye. So that'll occupy us for a while. By then we'll probably be looking for some other senses too.
Not to mention that none of this is happening on your "individual computi" but rather on some giant pile of video cards that Google is still probably losing money renting to you for $250 a month.
The novelty factor will wear off faster than (Score:2)
the time interval between Slashdot's posting of AI stories
There's a better way to do this (Score:2)
Instead of prompt-building a world, use Second Life as the modeler.
It has a camera, geometry, and metadata to model off of, and tons of source world already built.
The hard parts; hosting, navigation, scripting, network, and money are already implemented.
Best, there's an experienced user community that gets it , and is willing to pay for it.
And no doubt... (Score:3)
they own everything you create, and you get to pay for that "privilege".
Re: And no doubt... (Score:2)
Think of it this way, it can be work, where they pay you to paint the fence or give feedback for their model training, or they can have you pay and paint the fence by giving you "exclusive access" to their ultra cutting edge stuff.
Your choice, really.