OpenAI’s Sora Transforms Text into Realistic Videos of Puppies
Over the past two years, AI has made significant progress on various fronts, including pioneers like OpenAI and the steadily advancing Google, which has established itself as an AI powerhouse. As we enter 2024, tech companies are ramping up their efforts to capitalize on this momentum. In particular, Google has garnered attention with the release of Gemini 1.5, while OpenAI has also announced Sora, its latest text-to-video AI model.
As the name suggests, OpenAI’s Sora has the ability to bring text-based prompts to life by creating lifelike scenes. Imagine yourself writing an imaginary scenario, like a cat dancing on top of a spaceship. Sora excels at translating these prompts into detailed and realistic videos, as evidenced by the company’s disclosures.
“We teach 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,” OpenAI said.
It added that Sora can create videos up to a minute long and maintain the visual quality according to the user’s prompt.
If you visit Sora’s homepage, you will see countless results posted by Sora. One particular example of a drone shot where waves can be seen crashing at Big Sur’s Garay Point Beach is as realistic as it gets. First of all, I can’t tell the difference. If you gave me this material without telling me it was AI, I wouldn’t know.
OpenAI claims that Sora can create complex scenes with multiple characters, specific movements, and precise details of the subject and background.
The company also claims that “the model understands not only what the user has asked for in the prompt, but also how these things exist in the physical world.”
A scary future?
As dystopian as it may seem, OpenAI says it’s taking big steps to improve deployment security. The company works with experts to prevent misinformation, hateful content and bias. In addition, it aims to detect misleading content and the ability to tell that the video was created by Sora. In addition, the safety technologies used in DALL-E 3 also apply to Sora.