Ever wonder what MP Kristyn Wong-Tam would look like next to a capybara? What about what Doug Ford might look like if he appeared in the 2019 horror film “Midsommar?”
A hilarious internet tool can show you … kind of. It’s still learning.
A new AI model which generates artwork from human-inputted text is garnering attention across the internet and filling up our social media feeds.
Users are prompted to type in a phrase describing their desired art, and a grid of nine images is offered up for your consideration.
According to a paper by Dall-E creator Boris Dayma, the model learns “by looking at millions of images from the internet with their associated captions.” The model retains some memory — individual images and search terms — but it continues to learn when faced with unique inputs like, for instance, “Doug Ford drinking bubble tea.”
Over time, the AI model will continue to improve, creating more accurate images from text-based prompts.
The generator’s name is a reference to the surrealist artist Salvador Dali and cartoon robot WALL-E.
Who did we miss? Click here to send us your best AI art.
Here are some of our favorite images we’ve created using this model at the Star:
JOIN THE CONVERSATION