By submitting a text description of the intended scene, the 'Make-A-Video' artificial intelligence technology from Meta will enable users to create quick video clips. The company's recent developments in generative technology research, which aims to give creators more creative control over artificial intelligence-based image generation, led to the announcement. With the announcement, Meta advanced the technology by adding text-to-video creation capabilities in addition to text-to-image capabilities. The business has not, however, given people access to the model.

Videos created in response to prompts would be no longer than five seconds and without audio. However, Meta asserts that the paradigm supports a variety of prompts.

In a blog post announcing the news, Meta said that as part of its commitment to 'open science,' it would share information about the research that went into the development of the most recent generation of artificial intelligence technology. Meta also confirmed that it would soon be making a demo experience available to users.

By providing people with tools to rapidly and easily produce new content, generative AI research is advancing creative expression, according to Meta in a blog post announcing the work. The parent firm added to Facebook and Instagram, 'With just a few words or lines of text, Make-A-Video can bring creativity to life and produce one-of-a-kind videos full of bright colours and landscapes.

The company notes that the 'Make-A-Video' demo model uses pairs of images, captions, and unlabeled video footage sourced from the WebVid-10M and HD-VILA-100M datasets, which include stock video footage produced by websites like Shutterstock and scraped from the web and total hundreds of thousands of hours of footage.

'It's much harder to generate video than photos, because beyond correctly generating each pixel, the system also has to predict how they'll change over time,' said Mark Zuckerberg, CEO of Meta, in a post to Facebook.

As seen in the case of AI image generative systems and deepfakes, there have been some troubling questions raised about AI generative media, with some suggesting that it could result in an increase in misinformation, propaganda, and non-consensual pornography.

According to Meta, it intends to restrict access to such generative models because it wants to be 'thoughtful' about how they are created. It is yet unclear when the demo experience will take place and exactly how access will be restricted.