OpenAI has introduced a tool that can generate videos from text tags. This is stated in the company's blog, reports UNN.
Details
The new model, nicknamed Sora after the Japanese word for sky, can create realistic shots lasting up to a minute, which users can set both in terms of subject matter and style.
According to the company's blog post, the model is also capable of creating videos based on a still image or supplementing existing footage with new material.
We teach AI to understand and model the physical world in motion in order to train models that will help people solve problems that require interaction in the real world
The company announced that it has opened access to Sora to several researchers and video creators.
OpenAI creates new team for child safety: research and protection08.02.24, 10:04