Site icon Wonderful Engineering

This New AI By Meta Can Generate Whole Videos From Just Text Prompts

In a recent development, Metaverse has welcomed a new feature in its cape that uses artificial intelligence to create different types of videos from its text prompts, ranging from “creepy to surreal and sometimes impressive.” We know that the world is nothing without AI in recent times, and companies are using it in different ways to enhance their capabilities. This new artificial intelligence system named “Make-a-video” was revealed this Thursday, in which we can generate various types of videos through mere text or captions. However, there is no word about the availability of this software to the general public, but you can take a quick look by filling out a sign-up form.

It should be noted that the software has taken into consideration the creation of only ethical videos and also embodies a watermark that “helps ensure viewers know the video was generated with AI and is not a captured video.” According to the company, “Our goal is to eventually make this technology available to the public, but for now, we will continue to analyze test, and trial Make-A-Video to ensure that each step of release is safe and intentional.”

The pictures demonstrated here are taken from the videos in which you can see that a spaceship is landing on Mars, and in the other picture, a ballerina can be seen “performing a beautiful and difficult dance on the roof of a very tall skyscraper”. The company stated, “Meta AI is committed to developing responsible AI and ensuring the safe use of this state-of-the-art video technology. Our research takes the steps to reduce the creation of harmful, biased, or misleading content. “

Not to mention, a research paper has been written by the researchers regarding the novel feature, in which they have explained the whole system. They wrote, “In all aspects, spatial and temporal resolution, faithfulness to the text, and quality, Make-A-Video sets the new state-of-the-art in text-to-video generation, as determined by both qualitative and quantitative measures.” It should be noted that all the previous systems that have been introduced prior to this did not go up to the mark and generated “strange results”.

Craiyon AI was also such a system that came up with a series of different pictures regarding what human beings would look like if they all started living in the Metaverse. Hence, this new feature “Make-a-video” has really intrigued people and also seems exciting.

Exit mobile version