genie3

Just imagine where we'll be in another year... https://t.co/toZBOWvdKS

Video games will never be the same... https://t.co/rI1TQXT3sG

720p @ 24fps. It's over, we are living in the future. Genie3 is user motion trigger generation from a prompt. 🤯#Deepmind https://t.co/iBi4m8Zg1h

Genie 2 vs Genie 3. Just 7 months between them. The bitter lesson continues to be bitter. https://t.co/FCqG2BZ4Pw

What if you could not only watch a generated video, but explore it too? 🌐 Genie 3 is our groundbreaking world model that creates interactive, playable environments from a single text prompt. From photorealistic landscapes to fantasy realms, the possibilities are endless. 🧵

When we started working on Genie 1 three years ago, the goal was always to one day generate an endless variety of environments for training embodied AGI. I believe the capabilities of our world models are getting there now. Next step: agent self-improvement loops! https://t.co/vPuvViuOF4

Genie 3 feels like a watershed moment for world models 🌐: we can now generate multi-minute, real-time interactive simulations of any imaginable world. This could be the key missing piece for embodied AGI… and it can also create beautiful beaches with my dog, playable real time https://t.co/YSIAwV3GiS

There are many mind blowing aspects about Genie3. One of my favorite ones is how previous observations about the world remain. This is a very difficult problem that our model can address. https://t.co/yYsEOHaXnt

Actions are persistent in the world. https://t.co/Wk1mrp2LyT