Research

Video generation models as world simulators

Source: OpenAI News 15 Feb 2024

Listen to Brief

AI audio in English, based on the NadiAI brief and original source.

Brief

We 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.

Why It Matters

Kemajuan ini menunjukkan potensi model video berskala besar untuk membina simulator dunia fizikal yang lebih umum, dengan implikasi untuk penyelidikan dan aplikasi simulasi.

Keep Reading on NadiAI

Selected Related Articles