New NVIDIA AI technology transforms words into realistic images

NVIDIA GauGAN technology He has already shown what he is capable of, turning simple sketches into photorealistic images. And now the GPU giant is aiming higher with its AI, launching a new version capable of turning words into images.

NVIDIA showed its GauGAN technology for the first time in 2019, but just a few months ago we saw it presented in a product available to the general public. Called Canvas, this software can be a lot of fun to use as it allows users to create amazing photo-like images with basic sketches.

It has been a few months since the Canvas announcement, but work on GauGAN has continued and is now reaching version 2.0. The technology has become even more impressive as it is now capable of turning words into photorealistic images.

As seen in the video above, when we type something in the text box, an image will be generated immediately based on those words. If we add an adjective or replace a noun in the sentence, the image will change accordingly.

Converting words to images has never been easier

For further customization, users can combine text and picture-to-picture functions. Using written words to generate the base and drawings to detail the image, you can change the shape, size, and textures of any object within the image.

To achieve these results, the text-to-image function, NVIDIA uses a generative network-based AI model that “combines segmentation mapping, painting and the generation of text to image ”. This model was trained using 10 million landscape images, so it should be well prepared for whatever we write to it (or not).

You can try the NVIDIA AI interactive demo for GauGAN 2 using your web browser. To play it, you must first agree to NVIDIA’s terms and conditions.