Popular content creation platform Canva has integrated Stable Diffusion's text-to-image model and will now enable users to generate images by typing text-based commands. Canva's text-to-image tool works in a manner that asks users to describe the image they want to see with prompts.
We tried creating some photos with Canva's text-to-image tool, and the results were impressive. The image showcased above is what the platform generated upon typing "dog riding a cycle." The feature is under development. Hence, users can expect the results to get better with time.
The new Text-to-Image will be available to Canva's over 100 million users, allowing them to convert their imagination into images as they type a text-based description of their images. To try it, users should open Canva’s website, create a design, and click on more in the menu towards their left. Then, they should locate the Text-to-Image tool and start by typing in the description of their image and selecting the type of image they wish to generate.
While Canva allows users to generate new images using text-to-speech AI developed by Stable Diffusion, it also enables users to report images that might contain violence, hate speech, nudity or other inappropriate content.
For instance, a sample prompt on the platform reads, "a light watercolour painting of koi fish in a pond." Additionally, users can choose from various styles, including photo, drawing, 3D, painting and pattern. With the tool, Canva will offer users 100 images per day.
In an interview with The Verge, Canva's co-founder and chief product officer Cameron Adams said, "we're treating this as very much a learning experience for our community." Adding to it, Adams mentions that "we're keen to get this technology in front of them because it's an emergent field, and the exact way it works and how customers will interact with it is still being developed."
For more such insightful technology news, product reviews, sci-tech features and updates, keep reading Digit.in.