Canva Releases First Image Generation Model, Canva Craft

The company said Canva Craft works in two stages. First, it interprets a user’s prompt and creates a plan that includes spatial relationships among elements, relative scale, visual hierarchy and information for text generation. Second, the model produces an image at up to 2K resolution in up to 30 aspect ratios for different platforms.

Canva said this approach lets the model generate images with accurate object details and legible text, and allows users to make precise edits without changing other parts of the image.

Instead of photographs, Canva trained the model on design, using human-designed templates from its library, including posters, social posts, presentations, infographics, menus and typography-rich layouts. The company said images generated with Canva Craft can be converted into layered designs using Canva Magic, its image-to-design transformer. Canva released a model last year that understands designs and layers.

Canva Craft is available on Canva’s platform to all users through the Dream Lab tab, and it will also be available through the Canva API. Canva plans to support image generation in third-party chatbots such as ChatGPT and Gemini through Canva’s MCP.

Canva has used several image models on its platform. TechCrunch reported that the new model is likely to help Canva save API costs, and Canva said that beyond costs, the model gives the platform better control over quality and speed.

Canva acquired media generation platform Leonardo.ai in 2024, and it said researchers from Leonardo contributed to the new image model. Canva said it is developing two cost-efficient versions, Craftfast and Craft-ultrafast, which will be released soon.

According to TechCrunch, Canva was on track for $4 billion in revenue last year, but it cut its growth forecast for 2026. External analysts reportedly said its valuation fell from $42 billion to $35 billion.