Srikanth
Meta has introduced a new artificial intelligence (AI) system called ‘Make-A-Video.’ This AI system is going to allow users to generate short video clips by entering a text description of the desired scene. The introduced announcement is seen as an advancement in generative technology research, which seeks to provide the creators more creative control over artificially intelligent image generation. With the help of this new invention, Meta has taken the technology a step ahead by including text-to-video generation capabilities apart from text-to-image. However, the company has not yet revealed the access to users for the model.
The prompt-generated videos are five seconds or shorter and would contain no audio. However, Meta has made a promise regarding the wide range of prompts which is supported by the model.
By the medium of the blog post, the company has mentioned that in a commitment to ‘open science,’ it will be sharing details of the research behind the latest artificial intelligence generative technology. The company has various plans on the list; the major plan is to release a demo experience for users.
Generative AI research is promoting creative expression forward by facilitating the tools to the people so that they can quickly and easily create new content.” “With just a few words or a few texts, Make-A-Video tool can bring imagination to reality and create one-of-a-kind videos which can be full of vivid colors and landscapes,” as per the mention of the Meta.
In the research paper describing the model at work, the company remarked that the ‘Make-A-Video’ demo model utilizes pairs of images, captions, and unlabeled video footage sourced from WebVid-10M and HD-VILA-100M datasets. This also includes stock video footage created by sites like Shutterstock and scraped from the web that together spans hundreds of thousands of hours of footage.
The CEO of Meta, Mark Zuckerberg, took the example of Facebook to describe the work as “amazing progress.” He also mentioned that it’s much harder to create video than images because, along with the collection of each and every pixel, the system also has to determine how they are going to change over time.
However, there have been concerning issues raised around AI generative media; there are some of the suggestions received that could lead to a rise in misinformation, propaganda, and non-consensual pornography. The same has been seen in the case of AI image generative systems and deep fakes. The company wants to be more thoughtful about how they can build such generative models and hence plans to limit access to them. However, a timeline on the demo experience and clarity on how access would be limited is yet to be known.
