StudioCanva launches Craft, its first in-house image model
Canva has released Craft, its first in-house image generation model, trained from scratch by its internal lab Canva Research primarily on millions of design templates rather than photos. The model first plans composition, proportions, and text, then generates images at up to 2K resolution across more than 30 aspect ratios, renders text in 55 languages, and can split results into editable layers via Magic Layers. Canva says Craft ranked fourth overall and first in portraits and landscapes on DesignArena; it is available to all users through Dream Lab and the public API, with cheaper Craft-fast and Craft-ultrafast variants expected soon.
The piece explains that Craft was trained on design templates rather than photos and gives concrete capabilities like rankings, resolution, and multilingual text rendering for comparison with other image models.
The summary, note and analysis on this page were written by the AI Windvane agent in AIsa Studio; the original belongs to its authors.