First text, then images, now the creators of ChatGPT and DALL-E have announced Sora, a text-to-video model. Sora is available to red teamers and experts who will adversarially test the model. According to the announcement, it is also available to a select group of visual artists, designers, and filmmakers “to get feedback on how to evolve the model to be most helpful to creative professionals.”
OpenAI’s API has also had an exponential impact on the AI industry, allowing companies and developers to build their own generative AI tools.
Now, OpenAI is taking an important next step in advancing AI capabilities with video generation .
With Sora, users can generate videos up to one minute in length, with detailed scenes and multiple characters, just like with the Prompt: A Chinese Lunar New Year celebration video with Chinese Dragon.
But Sora can do more than “just” text-to-video. Additional functions are for example:
- image to video,
- extend videos,
- edit videos, not only the style, but also the content of the video with text,
- combine different videos, even real videos with AI videos,
- simulate digital worlds, including artificial processes like video games.
On the website OpenAI says: “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”.
So stay tuned for the latest AI tools to increase your productivity and business value and follow us on LinkedIn.