OpenAI ↗ · 2024-02-15 16:00 · UTC+8
Video generation models as world simulators
Company news OpenAI Source language: English
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.
Excerpt
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.
Short excerpt from the source — open the original for the full text.