To better understand the emerging capabilities of GAIA-1, it is helpful to see it in action.
GAIA-1 can predict up to several minutes into the future based on a few seconds of video. When we generate driving scenes that far into the future, what happens in the first few seconds of the initial video prompt becomes less important to what it generates next. This shows that GAIA-1 understands the rules that underpin the world we inhabit.
(video) Wayve GAIA-1 Generated driving in London
