China News Service, February 16th: Recently, the American artificial intelligence research company OpenAI launched a video generation model "Sora".
According to OpenAI's official website, this model can be used to generate one-minute videos from text. The videos can have complex scenes such as multiple characters, specific types of movement, precise themes and background details.
A video model created using the video generation model "Sora". Image source: OpenAI official website
The company said it developed the model to teach artificial intelligence to understand and simulate the physical world in motion and train it to help people solve problems that require real-world interaction.
CNN quoted Hayden, a senior analyst at market research company ABI research, as saying that "Sora" may have a significant impact on the digital entertainment market as new personalized content will be spread across various channels.
In the introduction to "Sora", OpenAI also pointed out that the current model has weaknesses. It may be difficult to accurately simulate the physical performance of complex scenes, and it may not be able to understand specific instances of cause and effect. For example, a video is likely to appear After a person takes a bite of a biscuit, there are no bite marks on the biscuit.
At the same time, the model can also confuse spatial details such as left and right.
OpenAI said it plans to work with a team of experts to test its latest models and keep a close eye on various areas including misinformation, hateful content and bias.