@olivercameron We’re reaching a future where world models will help humans live in digital fantasy worlds while simultaneously allowing robots to inhabit the real world.
Leave a generated place, then come back.
Did the same place wait—or did the model quietly replace it?
DreamX-World retrieves earlier views to preserve old places. In the authors’ return test, it led 5 of 6 measures—while longer interactions can still drift.
@seeksteve@bfl_ai Follow me and send me that robot once you're ready.
I'm trying to get my first 100 followers from the top video/world model experts on X by the end of the week.
FLUX 3 Video is #2 in the world.
To celebrate, FLUX 3 Video is free to use in our playground until Sunday 16th, 11:59pm PT (link in the thread).
This is just the beginning of what’s coming. Up next: 4K, video editing, and multiple images & videos as reference input.
A perfect dream can fail.
At τ=0.10, a controller averaged 2,086 of 2,100 steps inside its learned Doom world—but only 193 in the actual game.
Raising model temperature helped transfer, until more uncertainty hurt. From Ha & Schmidhuber’s World Models experiment.
All these new video models are going to make the next generation of gaming possible.
Video is 24 frames per second. Once we can double that and make it low-latency, your indie games are going to look just like this.
Introducing LTX’s newest open-weight model for realtime avatars - available on Reactor day 0.
We're proud to partner with @ltx_io to make it easier than ever to build lip-synced, fully-voiced AI personas at cinematic quality with our API.
Try it here: https://t.co/Kp9btWWuQm