OpenAI flags new text-to-video tool
Make us a preferred source
Make us a preferred source on Google
The news: ChatGPT owner OpenAI has unveiled a new software tool that can generate videos based on text prompts.
The numbers: The new tool, called Sora, can create videos of up to 60 seconds long based on text instructions. The model can also create videos based on a still image or expand existing footage.
The context: The Microsoft-backed artificial intelligence startup said in a blog post its latest tool can create “complex scenes with multiple characters, specific types of motion, and accurate details of the subject and background".
The Sora model is currently being tested by ‘red teamers’ to identify flaws and assess for harms and risks. Access has also been provided to some visual artists, designers, and filmmakers to gain feedback on how to advance the model to be most helpful for creative professionals.
The company said its new tool is still a work-in-progress, adding that the current model might not accurately simulate the physics of a complex scene and has difficulty in following a specific camera trajectory. It is also developing tools to detect if a video was generated by Sora.
The source: OpenAI
