Canva unveils Canva Craft, its first in-house image generation model

Canva, a design platform, introduced Canva Craft, its first in-house image generation model, in October 2026. Developed by the company's research team, the model enters a competitive field that includes similar image generators from Google, OpenAI, ByteDance, and Meta.

The model works in two stages. First, it interprets a user's prompt and creates a plan that includes details such as the spatial relationships of elements, relative scale, visual hierarchy, and information for text generation. Second, it produces an image up to 2K resolution in 30 aspect ratios. Canva says this approach helps generate images with accurate object details and legible text, while allowing users to make targeted edits without altering other parts of the image.

Instead of training on photographs, Canva trained the model on human-designed templates from its library, including posters, social posts, presentations, infographics, menus, and layouts rich in typography. As a result, images generated with Canva Craft can be converted into layered designs using Canva Magic, the company's image-to-design transformer. In 2025, Canva released its own design-understanding model.

Canva Craft is now available to all users via the Dream Lab tab and through the Canva API. The company also plans to support image generation in third-party chatbots such as ChatGPT and Gemini via Canva's MCP.

Canva has previously relied on multiple image models on its platform; the new in-house model is expected to reduce API costs and give the company better control over quality and speed. Canva acquired media generation platform Leonardo.ai in 2024, and researchers from Leonardo contributed to the new model. The company is also working on two cost-efficient versions, Craftfast and Craft-ultrafast, which are expected soon.