Sora allows you to convert text to video using AI with OpenAI

Sora allows you to convert text to video using AI with OpenAI

After announcing the arrival of a persistent memory feature on ChatGPT, OpenAI lifted the veil on a new artificial intelligence model capable of generating videos on February 15, 2024 “realistic and imaginative‘ using a simple text query: Sora.

Sam Altam’s company indicates that with the application “youcomplex scenes with multiple characters, specific motion types, and precise subject and background details”, which lasts a maximum of one minute.

Sora can create multiple recordings within a single generated video, all “while maintaining the characters and visual style”. The tool also allows you to create a video from an image or supplement an existing video.

On the page dedicated to Sora we learn that the AI ​​relies on a very advanced interpretation system to generate its videos. OpenAI says its new model can understand how objects “exist in the physical world“, “accurately interpret messages and create compelling characters that express vivid emotions”.

At this time, Sora is only available to a select group of testers. The company indicates that it works with “experts in areas such as disinformation, hate content and bias“, but also visual artists, designers and filmmakers. The goal is to gather as much external feedback as possible to refine the tool before it is deployed to the general public, either for safety or quality purposes.

OpenAI still lists some weaknesses inherent in its AI model for converting text to video: “He may have difficulty accurately simulating the physics of a complex scene and may not understand specific cases of cause and effect”.

Similar Posts

Leave a Reply

Your email address will not be published. Required fields are marked *