Canva’s first AI image model plans designs before generating them

Canva has unveiled its own image‑generation model, Canva Craft, aimed at competing with OpenAI, Microsoft, and Google’s offerings. The tool uses a two‑stage architecture: it first plans the layout and then renders the image, a process the company says improves accuracy, consistency, and control over the final result. Canva Craft can produce images up to 2,000 pixels in resolution and supports more than 30 aspect ratios, catering to a variety of content formats. In addition to social‑media graphics and marketing collateral, the model can generate realistic scenes, digital art, environmental images, and other visual types. By planning before rendering, the system seeks to reduce mistakes and give users greater customization without requiring advanced technical knowledge. This move reinforces Canva’s strategy of embedding artificial intelligence across its design platform, expanding creative options for both professionals and hobbyists. The announcement is significant because it illustrates how AI tools are becoming more democratized, enabling a wider audience to create high‑quality visual content without relying on external experts, which could reshape graphic production for businesses and personal projects.

Read the original article on The Verge AI

This summary is an informational synthesis produced by dataqbs.com. All rights to the original content belong to its author and the cited media outlet. We act solely as curators of technology news and claim no authorship.