Open Al is working on a software that can generate minute long videos based on text prompts.
Sam Altman, the CEO of Open AI took to his X account to introduce Sora, the company’s video generation model. Altman went on to share videos on his profile to showcase the efficiency of the new AI model.
According to him, the software called Sora is a text to video model that generates one minute long videos.
Open AI says that Sora is capable of generating complex scenes with multiple characters, specific types of motion and accurate details of the subject and background.
The company says Sora is a diffusion model that is capable of generating entire videos all at once or extending generated videos to make them longer. Apart from generating videos from prompts in natural language, the model is also capable of taking an existing image and generating a video from it.
“The software is a work in progress, Sora may also confuse spatial details in a prompt and may struggle with precise descriptions of events that take place overtime” the company says.
Open AI says it is also developing tools, such as detection classifiers, to identify misleading content and determine if a video was generated by Sora.
