Popular tech YouTuber Marques Brownlee shared his experience with OpenAI’s video generation model, Sora, on Friday, providing a glimpse into the capabilities and limitations of this cutting-edge AI technology.
What Happened: Brownlee took to X, formerly Twitter, to share his experience with Sora, ChatGPT-parent's text-to-video model, saying, "I got a rare opportunity to ask OpenAI’s video generation model Sora for some videos this week!"
He shared the videos Sora generated in response to his prompts and the lessons he learned from the experience.
The prompts and Brownlee’s observations were as follows:
Prompt 1: A medium-sized, friendly-looking dog walks through an industrial parking lot. The environment is foggy and cloudy. Shot on 35mm film, vivid colors.
See Also: Apple’s $3,500 Vision Pro Headset Worth The Hype? Tech YouTuber MKBHD Weighs In
Prompt 2: A timelapse closeup of a 3D printer printing a small red cube in an office with dim lighting.
Prompt 3: A young professional product reviewer in a well-lit video studio is surrounded by gadgets and technology, sitting in front of a computer with two displays. He’s holding a cinema camera as he ponders what video to make next. He is focused, while the background is slightly blurred for cinematic effect.
According to Brownlee, he learned that the AI platform sometimes struggles with physics, specifically with legs or walking. "Often in Sora-generated videos of walking, the legs cross over and merge into each other," he said.
MKBHD also said that branded items never quite match up to real life. Things like cars and cameras are never quite identifiable as a specific model.
About the third video, Brownlee praised the lighting setup. "In the third clip, it’s almost as if there’s a large soft key light just out of frame to the left, and across the board, lighting and shadows match very well."
However, he noted that the person depicted in the Sora-generated video has six fingers.
Why It Matters: Sora, OpenAI’s text-to-video model, backed by Microsoft Corporation, has been making waves in the tech industry since its launch. The AI model is designed to revolutionize content creation by generating high-quality videos from textual prompts.
It can create videos of up to one minute – from snowy Tokyo city and giant wooly mammoths to a highly detailed Sci-Fi movie trailer, with simple prompts.
Despite its groundbreaking capabilities, Sora has also faced criticism for potentially rendering video production jobs obsolete. There are also concerns about the technology being used for spreading misinformation, disinformation, and hateful content, especially in the wake of the elections.
Check out more of Benzinga’s Consumer Tech coverage by following this link.
Disclaimer: This content was partially produced with the help of Benzinga Neuro and was reviewed and published by Benzinga editors.
© 2024 Benzinga.com. Benzinga does not provide investment advice. All rights reserved.
Comments
Trade confidently with insights and alerts from analyst ratings, free reports and breaking news that affects the stocks you care about.
