People saying things like:
- fps is so low
- the worlds aren't playable
- some things disappear as soon as you look away
- it’s pointless
…are completely missing the point. Just like they did back when the critiques were 'not a good image' or 'too many fingers'.
EVERY pixel generated in real time, with the beginnings of in-LLM memory of the environment. That's insane. A few of us have been anticipating this since the Disco Diffusion days, when you had to wait 2 hours to generate a mediocre image… and that was only 4 years ago.
The times we're living through are absolutely unreal.
Like, do people really not have the few neurons to make the tiniest extrapolation? If we can already do this right now, what are we going to have in 10–20 years?
Everything. Literally everything. Fluid and interchangeable: novel to movie, photo to video game, all swappable, seamless, and real time from one to another.
⚡ Google Genie 3 but OPEN SOURCE
Not even 48h later and the Chinese did it again: they just dropped a free real-time playable world generator.
- LingBot-World
- Built on Alibaba's Wan2.2
- REAL-TIME interaction at 16fps
100% open source 🧵