OpenAI launches ‘Sora’: the AI text-to-video tool

OpenAI, renowned for its widely used ChatGPT, has recently unveiled a cutting-edge video generation model named Sora.

With this innovative tool, users have the ability to describe the video they desire, and AI takes care of the entire creation process. While the feature is not yet publicly accessible, OpenAI CEO Sam Altman has showcased imperfect videos, likely attributed to the early stages of the technology. Some videos possess a video game aesthetic, while others exhibit a more realistic quality—a common occurrence when dealing with new technologies.

OpenAI’s history of evolution and adaptation with user interaction suggests a similar trajectory for Sora.

What are Sora’s capabilities?

Video Extension

Sora can generate complete videos in a single pass or elongate existing ones while maintaining visual quality and adhering to user prompts, producing videos of up to one minute in length.

Real-world Understanding

The model not only comprehends user prompts but also possesses a deep understanding of how elements exist in the physical world. This linguistic proficiency enables Sora to accurately interpret cues and create characters that convey vivid emotions.

What improvements are needed?

However, Altman openly acknowledged some challenges faced by Sora during its announcement on ‘X’ (formerly Twitter).

It may struggle with accurately simulating the physics of a complex scene and may not understand specific instances of cause and effect. For example, a person might take a bite out of a cookie, but afterward, the cookie may not have a bite mark. The model may also confuse spatial details of a prompt, for example, mixing up left and right, and may struggle with precise descriptions of events that take place over time, like following a specific camera trajectory.”

Before Sora becomes publicly available, OpenAI is committed to implementing safety measures. They plan to develop tools to identify misleading content and engage with global policymakers, educators, and artists to address concerns. The company anticipates that future use of Sora could revolutionize video production, but potential misuse akin to some instances with ChatGPT is also a consideration.

Future use

We are curious about the potential impact of this new innovation on video production—whether it will enhance the quality or face misuse by users. Nevertheless, we eagerly anticipate testing it ourselves once it is released!

If you’re interested in hearing more about AI, Automation, and emerging technology, then check out our blog.