This Thursday, September 29, the people of Meta took a leap in the application of AI, as they announced Make-a-Videoa new system that allows people to turn text prompts into short, high-quality video clips, something like a DALL-E multimedia.
“Generative AI research is driving creative expression by giving people tools to quickly and easily create new content. With just a few words or lines of text, Make-A-Video can bring imagination to life and create unique videos filled with vivid colors, characters, and scenery. The system can also create videos from images or take existing videos and create new ones that are similar,” says an investigation by Meta.
The folks at Meta added that, “Make-A-Video uses publicly available datasets, which adds an extra level of transparency to the investigation. We are openly sharing this research and generative AI results with the community for feedback, and will continue to use our responsible AI framework to refine and evolve our approach to this emerging technology.”
Make-a-Video also gives you the opportunity to create backgrounds for existing videos or give them more effects.
Meta maintains that the privacy of the use of videos is guaranteed:
“As a way to reduce the risk of harmful content being generated, we examine, apply, and iterate on filters to reduce the chance of harmful content appearing in videos. Since Make-A-Video can create content that looks realistic, we add a watermark to every video we make. This will help ensure viewers know the video was generated by AI and is not captured video.”