OpenAI started with ChatGPT, and now it can’t stop on its way to make its AI more useful and reliable. It has come a long way in bringing you knowledge that can answer your questions in writing or generate images that you describe. Now, we know they’re working on another, more sophisticated resource: Sora, which is capable of generating videos from text alone.
This in itself seems unbelievable and elaborate, but it is true. Currently, the new AI from OpenAI is in the process of reaching the market, showing a little bit of what it can do. We will tell you everything that is known about Sora, how it works and when it will be ready for everyone to use.
How to use Sora to generate realistic videos from text
While DALL-E 3 generates images using the text you type and ChatGPT focuses on verbal responses to your texts, Sora works by generating videos. This AI uses a very similar language to the two we mentioned earlier, is part of the OpenAI project, and is actually trained to understand the common expressions we use when talking to others.
In addition, the ability to create videos as accurate as possible for our presentations will amaze the curious. Several examples are circulated on the Internet in short videos showing the results of Sora following some very descriptive questions.
From mammoths walking through a snowy landscape, to a couple walking the streets of Tokyo surrounded by cherry trees, Sora is able to respond with realistic and detailed videos. The trick with this AI is knowing how to ask for what you want as clearly as possible so that it gives you satisfactory results. Sora can understand what kind of clothing you want the main character to look like, as well as the location, the surrounding atmosphere (sun, night, rainy, etc.), the time of year, and your other additions. I’m thinking about it.
Unfortunately, Sora is currently unavailable. The only people with access to this tool are OpenAI researchers, and its capabilities are limited to generating maximum 60-second videos.
However, it is expected to be released for public use in the future; Sora is not the first AI to create videos from text, because while it is still in the oven, there are other tools that do the same and we will tell you in our article dedicated to it.
Sora, what do you think? Do you see this AI as a promising tool in the future?
