According to the company on Thursday, Microsoft-backed OpenAI is developing software that can produce minute-long videos in response to text prompts.
According to a statement from the company, the Sora software can be used by visual artists, designers, and filmmakers to get feedback on the model, as well as red teaming, which assists in finding vulnerabilities in the AI system.
The statement added, “Sora can create multiple shots within a single video and is able to generate complex scenes with multiple characters, specific types of motion, and accurate details of the subject and background.”
According to a blog post by the company, Sora is capable of animating still images in addition to creating videos based on text prompts.
The program for creating videos comes after OpenAI’s ChatGPT chatbot, which made waves in the field of artificial intelligence (AI) by creating emails, codes, and poems when it was first released in late 2022.
Last year, the massive social media platform Meta Platforms enhanced its Emu image generation model by adding two AI-based features that allow it to edit and create videos in response to text prompts.
In the quickly evolving field of generative AI, the parent company of Facebook also hopes to compete with Microsoft, Alphabet’s Google, and Amazon.
As a work-in-progress, Sora may struggle to follow a specific camera trajectory and may get confused by the spatial details of a prompt, according to the company.
OpenAI announced that it was also creating instruments to determine whether a video was produced by Sora.
