OpenAI has just announced its latest tool -- Sora -- which will generate videos from text prompts, and it has truly incredible videos out before the new tool has been officially released. Check it out:
OpenAI posted on X about Sora, teasing: "Sora can create videos of up to 60 seconds featuring highly detailed scenes, complex camera motion, and multiple characters with vibrant emotions". The new model is named "Sora" after the Japanese word for "sky" and can produce impressive video results up to 60 seconds long just from a text prompt.
OpenAI explained on its website: "We're teaching AI to understand and simulate the physical world in motion, with the goal of training models that help people solve problems that require real-world interaction".
The company has opened up access to Sora to a few video creators and researchers, while the company would "red team" the product, meaning it will test it for areas that would go around OpenAI's terms of service, something that would prohibit "extreme violence, sexual content, hateful imagery, celebrity likeness, or the IP of others" explained the AI firm on its blog post.
One of the prompts included: "A movie trailer featuring the adventures of the 30-year-old space man wearing a red wool knitted motorcycle helmet, blue sky, salt desert, cinematic style, shot on 35mm film, vivid colors" with some truly incredible results.
We don't know how much footage OpenAI used to train Sora or where the videos they trained the new AI model came from, but the company did tell The New York Times that they used videos that were both publicly available and licensed from copyright holders.
It's impressive stuff right off the bat... but does have me concerned (and excited, but more concerned) for the future of the video industry. Sora will be a game-changer for video content, now prompted through text and creating a 60-second video from a few taps of your fingers to the keyboard.
Filmmakers and VFX houses will be hurt, as visual effects in movies cost tens of millions of dollars for high-end productions, with hundreds and sometimes thousands of highly skilled people working on them. Now, their industry is completely disrupted with AI, where people can sit on their laptops and make Hollywood-grade VFX in a few minutes.
Incredible.