A few weeks ago, Dall.E’s artificial intelligence gained a lot of attention because of its ability to produce images from text entered by users. Meta AI announced they also have artificial intelligence with the same capability with the addition of the feature of producing images also from user -generated sketches.
Make-A-Scene’s artificial intelligence has the ability to produce images with 99.54% accuracy when receiving text input and sketches compared to 66.3% with text input only. At this time Make-A-Scene has been used by artists to realize what is thought to the head into an image. It becomes a rectangular image equal to a resolution of 2048 x 2048 pixels.
Meta AI sees Make-A-Scene can be used to produce 3D images from 2D sketches in the future. Its capabilities are similar to the Bot Builder shown in metamesta which generates 3D models based on user voice commands.
Tags
CYBER LIFE