Artificial Intelligence: OpenAI develops AI application for video production

The US company OpenAI, developer of the chatbot ChatGPT and the image generator Dall-e, has developed an AI application for producing realistic videos. The San Francisco-based company announced this. The application called Sora can produce videos up to a minute long using a prompt, a short command in text form. The application can also turn a photo into a video or extend a short video.

At X, OpenAI boss Sam Altman announced that the model would initially be made available to selected creatives. Before the program can be used widely, experts should explore possible security risks. Politicians, teachers and artists worldwide may raise concerns.

Sora has a right-left weakness

However, Altman encouraged suggestions for videos. Sora would present “convincing results” just moments later. As an example, OpenAI showed, among other things, a video in which a creature “half duck, half dragon” flies in front of a “beautiful sunset” while carrying a “hamster in an adventure outfit” on its back.

However, Sora still has some weaknesses: For example, the AI confuses left and right. In general, errors could sometimes occur in the implementation of physical laws and continuity. For example, it could happen that someone takes a bite of a cookie in a video, but it still looks whole afterwards.

Companies such as Meta, Google or Runway AI already offer similar applications – they are either working on it or have already published versions. Such technologies could transform video production over time. At the same time, there is concern that fake videos could be created on a large scale that would be difficult to distinguish from real recordings. The developers of the technology are therefore working on ways to incorporate unique identifying features such as watermarks into the videos. Sora videos should also show that they were created by AI.

The US company OpenAI, developer of the chatbot ChatGPT and the image generator Dall-e, has developed an AI application for producing realistic videos. The San Francisco-based company announced this. The application called Sora can produce videos up to a minute long using a prompt, a short command in text form. The application can also turn a photo into a video or extend a short video.

At X, OpenAI boss Sam Altman announced that the model would initially be made available to selected creatives. Before the program can be used widely, experts should explore possible security risks. Politicians, teachers and artists worldwide may raise concerns.

SOURCE