Sora: Creating video from text – OpenAI

Sora: Creating video from text - OpenAI

OpenAI released its premier AI text-to-video generator Sora.

What is Sora?

Sora is an AI model that can create realistic and imaginative scenes from text instructions. Sora can produce videos up to a minute long in a range of artistic genres, including incredibly lifelike human faces, according to OpenAI’s website. According to its capabilities, the model can produce “complex scenes with multiple characters, specific types of motion, and accurate details of the subject and background.” Additionally, Sora may create a movie from an image or take an already-existing film and add more frames or text to it.

Sora: Creating video from text - OpenAI

Image source:

Sora can create intricate scenes with several actors, distinct motion styles, and precise background and subject details. In addition to comprehending the user’s request in the prompt, the model also knows how those items actually exist in the real world.

According to OpenAI, the model’s shortcomings include its inability to accurately replicate the physics of intricate scenes, its incomplete comprehension of cause and effect, and its tendency to misinterpret spatial cues in prompts, such as left and right. For example, you might want to try creating the video again if it shows a jogger jogging backwards. Moreover, the model is unable to produce audio to go with a video.

“Visual artists, designers, and filmmakers” are among the “limited number of creators” who will get a first pass at Sora; they will provide comments to improve the model’s usefulness for creative professionals. The model will also be available to AI researchers for redteaming, a procedure wherein teams identify the model’s shortcomings and mistakes in order to make improvements.


Sora can create full videos all at once or can add more time to generated videos to make them longer. The difficult task of ensuring that a subject remains unchanged even when it momentarily disappears from view has been resolved by providing the model with many frames’ worth of foresight at once.

Without a doubt, Sora creates amazing videos. A genuine film crew or animator would have needed hours to create these videos. The film industry will probably be disrupted by Sora in a similar manner to how the editorial and design worlds were jolted by ChatGPT and AI-image generators. This is a technology that, in terms of video makers’ job security, is both amazing and terrifying.


Last Updated on 24 February 2024 by Tuomas Data