17 comments

[ 3.3 ms ] story [ 180 ms ] thread
I was mildly amused (but not especially surprised) to see that the "Hunter's Vale" initial image includes what's pretty clearly a partial Skyrim HUD compass at the top.
Brightvale's protagonist looks 99% like Link

Starlight Village just has Scar the lion from Lion King right there at the bottom lol

while I couldn't test it out (wait time 45min), I'm so insanely jealous. This would make one hell of an Inception style game.

The tech alone of being able to take prefabs and just prompt your way to a world is amazing. Now to get that in blender...

That is impressive. The controls are essentially unresponsive, but the fact that it starts with an image and goes from there bodes well for generative game building.

For those wanting to see it in action, the wait times are wildly inaccurate. Wait five or six minutes and you'll probably get through.

That was terrible. Controls are slow and at times unresponsive. I rode towards a hill that kept getting further away, and tried following a trail that would disappear and reappear. A horse appeared out of nowhere. The terrain detail was hallucinogenic as grass would mutate into different shapes.
Super fun to try a playable world model for the first time! I picked a random picture and got ChatGPT to write a game description, then could move within that world. Very laggy and buggy, but very fun to try!

Hackers screenshot + file system context = Ideal navigation

https://i.imgur.com/dBXdcd9.png

Will be really cool when they are ready to handle traffic.
(comment deleted)
Notes on my experience:

- Infra/systems: I was able to connect to a server within a minute or two. Once connected, the displayed RTT (roundtrip time?) was around 70ms but actual control-to-action latency was still around ~600-700ms vs the ~30ms I'd expect from an on-device model or game streaming service.

- Image-conditioning & rendering: The system did a reasonable job animating the initial (landscape photo) image I provided and extending it past the edges. However, the video rendering style drifted back to "constrast-boosted video game" within ~10s. This style drift shows up in their official examples as well (https://x.com/DynamicsLab_AI/status/1958592749378445319).

- Controls: Apart from the latency, control-following was relatively faithful once I started holding down Shift. I didn't notice any camera/character drift or spurious control issues, so I guess they are probably using fairly high-quality control labels.

- Memory: I did a bit of memory testing (basically - swinging view side to side and seeing which details got regenerated) and it looks like the model can retain maybe ~3-5s of visual memory + the prompt (but not the initial image).

Uploaded my own sci-fi art and was amazed by the result
I picked a Morrowind screenshot of Vivec city and after a few (laggy) frames, it teleported me to a lotr-looking forest and then quickly to a fallout landscape.

Might have potential, but I wasn't terribly impressed by the lack of consistency.

genrate a post punk cyber world
Create a cuberpunk animated world
Create a cuberpunk animated world
It's fun, but in the initial demo no matter how hard I am trying to make the horse go into the water, it stays on the trail.