Take a minute to look at the complexity of this 20 second video that was created with a single prompt.
Prompt: The camera rotates around a large stack of vintage televisions all showing different programs — 1950s sci-fi movies, horror movies, news, static, a 1970s sitcom, etc, set inside a large New York museum gallery.
I don't know about you, but this blows my mind! With the unveiling of Sora, Open AI's next generation video model, video creation has reached a whole new level. So lets take a look at what it can actually do. Prepare to be impressed!
OpenAI's Sora: A Revolutionary Text-to-Video AI Model with Advanced Capabilities
Sora can create realistic and imaginative scenes from text instructions. It's capable of generating videos up to a minute long, maintaining visual quality and adherence to the user's prompt.
It can create complex scenes with multiple characters, specific types of motion, and accurate details of the subject and background. Sora understands not only the content of the prompt but also how those things exist in the physical world.
It's capabilities include image animation, video extension, video-to-video editing, and seamless video connection. The model can also simulate digital worlds, such as games like Minecraft, by determining the physics of each object in an environment and rendering a photo or video based on these calculations.
It's a multimodular model, meaning it allows users to upload a still image and animate its contents with attention to small details. It can also take an existing video and extend it or fill in missing frames. Sora's deep understanding of language enables it to accurately interpret prompts and generate compelling characters that express vibrant emotions.
However, Sora is not perfect, and it may struggle with accurately simulating the physics of a complex scene, confuse spatial details, or misunderstand specific instances of cause and effect. Having said that, it's still in the early stages and improvements are happening quickly. I'm interested to see if it's capable of character consistency for longer creations for long form storytelling because that would be a gamechanger!
While Sora is not yet available to the public, it is being shared with third-party safety testers and a select group of video makers and artists to gather feedback. The company is also collaborating with experts to test Sora for its potential to cause harm via misinformation, hateful content, and bias. Despite its impressive capabilities, OpenAI is taking a cautious approach to the deployment of Sora, emphasising the importance of safety and responsible use.
When it does get released it's going unleash a whole new world of creativity! Can't wait!