It’s never been easier to create photos from scratch.
GauGAN technology from Nvidia has previously demonstrated its capabilities by transforming simple doodles into photorealistic photos. Since then, we’ve seen it used in Nvidia Canvas, but it appears that the GPU giant is taking AI to new heights, announcing a new version capable of converting words into graphics.
Nvidia initially demonstrated its GauGAN technology in 2019, but it wasn’t until recently that we saw it in a product that was available to the general public. This piece of software, dubbed Canvas, can be a lot of fun to use because it allows users to generate spectacular photo-like images from simple sketches.
A few months have passed since Canvas’ announcement, but work on GauGAN has continued and it’s now hitting version 2.0. The technology has become even more impressive, as it’s now capable of turning words into photorealistic images, providing a similar result to the one we get from using the draw-to-image feature.
As seen in the video above, write something on the text box, and an image will be generated immediately based on your words. Add an adjective or replace a noun in the phrase, and the image will change accordingly.
Users can combine text and draw-to-image tools for enhanced customisation. You can adjust the shape, size, and texture of any object within the image by using written words as the base and drawings to detail the image.
Nvidia’s GauGAN 2 text-to-image feature achieves these results by combining segmentation mapping, inpainting, and text-to-image generation in a generative adversarial network-based AI model. This model was built using 10 million landscape pictures, so whatever you throw at it should be no problem (or not).
You may check it out in your web browser using Nvidia’s AI interactive demo for GauGAN 2. To use it, you must first agree to the terms and conditions set forth by Nvidia (check the box at the bottom of the page).