OpenAI unveils Sora – A model that creates AI-Generated videos from a text prompt

OpenAI has unfurled a new artificial intelligence model that can turn text prompt into realistic-looking and short videos. This marks a significant step forward from the previous AI-generated video models.

Sora is an AI model created by OpenAI that can create realistic and imaginative scenes from text instructions.

As per the New York Times, this new system is capable of creating videos as if they were lifted from Hollywood movie. OpenAI calls its new system Sora after the Japanese word for sky. This name is chosen by the team behind the technology and the researchers Tim Brooks and Bill Peebles as the name epitomize the idea of limitless creative potential.

With the launch of Sora, the OpenAI said- ‘The model can generate videos up to a minute long while maintaining the quality of the visuals and adhere to the user’s prompt’.

OpenAI further emphasized that –‘Sora is capable of creating complex scenes with multiple characters, specific types of motion and apt details of the subject and background’. The company also claimed that the model the model understands how the object exists in the physical world and accurately interpret props and generate alluring characters that express vibrant emotions.

OpenAI is tagging videos produced from Sora with watermarks that that identify them as being AI generated videos. The model generates videos in response to short descriptions like ‘a gorgeously rendered papercraft world of coral reef with colorful fish and sea creatures.

Sora is engineered to create multiple shots within a single generated video that accurately persist characters and visual style.

In an interview, OpenAI said that they are not yet releasing Sora to public because the technical team is still working to understand the system’s dangers. Instead they are sharing the technology with small group of academics and other outside researchers who will look for the ways it can be misused.

Before launching Sora to the general public, OpenAI will reach out to the security experts and policy makers to try and ensure that the system does not generate misinformation, and hateful content among other things.