Meta just released its own text-to-video system; 'Make-A-Video'.
For Mark Zuckerberg, '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. Make-A-Video […] understand[s] motion in the physical world and [applies] it to traditional text-to-image generation.'
The new AI- fueled generator can create soundless short videos by feeding on text or synthesizing existing images and videos. The output is captioned by its respective prompt. 'Make-A-Video' can also bring motion to static images. The array of possibilities is endless as you can discover them all on the tool's website.
Meta's venture into AI content generation is undoubtedly the dawn of a new frontier despite the near-limitless hurdles.
Learn more here.