Over time, AI technology has developed in new, efficient ways and among a variety of its forms, AI art has recently become popular. Creators including artists have used the technology to generate unique digital art pieces.
Of course Meta being a leading digital technology-driven company decided to take AI art to the next level. As part of its Generative AI research, Meta has launched a new AI system that uses machine learning to generate high-quality videos from text prompts, as claimed by the company.
We’re pleased to introduce Make-A-Video, our latest in #GenerativeAI research! With just a few words, this state-of-the-art AI system generates high-quality videos from text prompts.— Meta AI (@MetaAI) September 29, 2022
Have an idea you want to see? Reply w/ your prompt using #MetaAI and we’ll share more results. pic.twitter.com/q8zjiwLBjb
The technology, which is called Make-A-Video, allows people to create videos, simply by providing a few words or lines of text. In Meta’s words, “Make-A-Video uses images with descriptions to learn what the world looks like and how it is often described.” Via this system, you can also produce variations of existing video clips or add motion to static images.
Although the video results appear a bit odd, the technology has brought a distinct element to the process of video creation using AI. Since the system is still in its initial stages of development, we could expect Meta to bring changes and improvements to it over time.
Maybe my favorite AI generated video so far. Prompt: "A fluffy baby sloth with an orange knitted hat trying to figure out a laptop, close up, highly detailed, studio lighting, screen reflecting in its eye.mp4"— Mike Schroepfer (@schrep) September 29, 2022
killer work @MetaAI !! pic.twitter.com/Lvlrl3rWdG
Meta has not yet launched Make-A-Video publicly, although that is what it intends to do later. “For now, we will continue to analyze, test, and trial Make-A-Video to ensure that each step of release is safe and intentional,” explains the company.