Материал на языке оригинала: English.
Video generation models as world simulators
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
15 февраля 2024 г. · Источник: OpenAI news
Полный текст доступен у источника.