Video generation models as world simulators
Article Link : openai.com/res...
OPEN AI SORA
openai.com/sora
GOOGLE lumiere
lumiere-video....
Google Labs
labs.google/
Open Ai explore large-scale training of generative models on video data. Specifically, we train text-conditional diffusion models jointly on videos and images of variable durations, resolutions and aspect ratios. We leverage a transformer architecture that operates on spacetime patches of video and image latent codes. Our largest model, Sora, is capable of generating a minute of high fidelity video. Our results suggest that scaling video generation models is a promising path towards building general purpose simulators of the physical world.
17 сен 2024
