Canva’s AI generates images with accurate details and legible text
A new tool that claims to make design work easier, but only if you're okay with letting a machine do the thinking.
The story
Canva has launched its first image generation model, Canva Craft, which uses design templates instead of photos for training and allows precise edits. It is available to all users and through APIs.
Source: techcrunch.com
Our reading
Canva Craft is designed to create images with ‘accurate details of objects and legible text,’ which is a fancy way of saying it doesn’t look like a child tried to draw a cat with a crayon. The company says it uses design templates from its library, which means the generated images can be converted into layered designs using Canva Magic. So if you’re tired of trying to make your presentation look professional, now you can just let a machine do it for you, and then pretend you did it all by yourself. The real twist is that it doesn’t use photographs for training, which means the images it generates might not look like they were taken by a human, but at least they won’t look like they were taken by a human who forgot to turn on the camera flash.
