Microsoft Built an AI That Draws What You Tell It To

Researchers at Microsoft are working on a new artificial intelligence system that’s capable of drawing images based on text descriptions. The new AI, simply called the drawing bot, is based on a technology called a Generative Adversarial Network (GAN), which consists of two different machine learning models.

The first one is used to actually generate the images from text descriptions — while the other, known as the discriminator, is used to score the authenticity of the generated image. These two models work together in order to achieve the best possible accuracy possible in the final drawing.

Windows Intelligence In Your Inbox

Sign up for our new free newsletter to get three time-saving tips each Friday — and get free copies of Paul Thurrott's Windows 11 and Windows 10 Field Guides (normally $9.99) as a special welcome gift!

"*" indicates required fields

This field is for validation purposes and should be left unchanged.

Microsoft’s drawing bot doesn’t actually use a basic GAN — instead, the company’s researcher designed a new system called the Attentional GAN, or AttnGAN which is capable of perfecting the drawing using the provided description. Microsoft says the regular GAN would not be able to draw pixel-perfect or sharp images based on descriptions where there are a variety of different colours, so the AttnGAN is being used in order to tackle the problem by effectively picking out the key variables from the provided description and matching them against the drawing.

Microsoft’s AttnGAN isn’t just only about improving the accuracy, and it also has the basic common sense of humans. Like every other AI systems, Microsoft used a lot of training data in order to train the models required by the AttnGAN, allowing the system to pick up important details that will be useful when drawing images. “Since many images of birds in the training data show birds sitting on tree branches, the AttnGAN usually draws birds sitting on branches unless the text specifies otherwise,” Microsoft said in a blog post.

Microsoft says the drawing bot could one day be used as sketch assistants to painters, or even help filmmakers save time and money by drawing animation scenes based on the screenplay. For now though, it’s still a work in progress.

Tagged with

Share post

Please check our Community Guidelines before commenting

Conversation 4 comments

  • Bats

    18 January, 2018 - 3:12 pm

    <p>Wait… I am confused! Did Microsoft already build this, as the title suggests, or are they still trying to build it, as indicated in the first sentence?</p>

    • Chris_Kez

      Premium Member
      19 January, 2018 - 9:19 am

      <blockquote><a href="#238840"><em>In reply to Bats:</em></a></blockquote><p>They have already built this, but it is an ongoing research project.</p>

  • Mark from CO

    18 January, 2018 - 4:01 pm

    <p>Mehedi:</p><p><br></p><p>As a fanboy, these wonderful and magical demonstrations used to wow me. But with too many demos not seeing the light of day, or when they do arrive, seeing the competition already into version 2.0 of the same thing, please wake me when this actually hits the market.</p><p><br></p><p>Mark from CO</p>

  • AnOldAmigaUser

    Premium Member
    18 January, 2018 - 4:26 pm

    <p><em style="color: rgb(0, 0, 0); background-color: transparent;">"…it also has the basic common sense of humans."</em></p><p><br></p><p><span style="color: rgb(0, 0, 0); background-color: transparent;">They will have to do better than that if they are trying to make it intelligent.</span></p>

Windows Intelligence In Your Inbox

Sign up for our new free newsletter to get three time-saving tips each Friday

"*" indicates required fields

This field is for validation purposes and should be left unchanged.

Thurrott © 2024 Thurrott LLC