Microsoft recently introduced a new artificial intelligence (AI) software – “Drawing Bot”. Drawing Bot is an artist, able to draw variety of things and turn something from text description to vivid images. It is able to convert text details into lifelike images, showing that AI itself has some imaginative power, says Microsoft.
“If you go to Bing and you search for a bird, you get a bird picture. But here, the pictures are created by the computer, pixel by pixel, from scratch,” explained Xiaodong He, principal researcher and research manager in the Deep Learning Technology Center at Microsoft’s research lab in Redmond, Washington. “These birds may not exist in the real world — they are just an aspect of our computer’s imagination of birds.”
The software has a well developed dataset which enables it to pair up descriptions and images, Microsoft explained. For example, when the drawing bot is told to draw a bird in text, it pictures how a bird should look like.
Two machine learning models are incorporated into the drawing bot. One is for translating text descriptions into images, and one for determining the reliability of the produced images. The producer tries to get rid of fake images and put two compatible models together in order to deliver better and higher quality images.
According to recent research, this new bot is almost three times better in generating quality images than past past technology.
Microsoft’s AI drawing bot is not the first software to integrate with art. Google, Facebook and some leading big brands are also adopting AI to help with drawing and producing images.
The AI bot could be a useful tool in different job areas, such as animation. It can down on manual labor in the production of animated movies. However, this technology still requires time to continue developing.