Canva Launches Its First In-House Image Generation Model, Canva Craft

Canva released its first proprietary image generation model, called Canva Craft, in October 2026, making it available to all users on its design platform. The model was developed by Canva’s research team, with contributions from researchers at Leonardo.ai, the media generation platform Canva acquired in 2024.

Canva Craft operates in two stages. First, it interprets a user’s prompt and builds a plan covering spatial relationships, relative scale, visual hierarchy, and text generation details. Second, it produces images at up to 2K resolution across 30 different aspect ratios suited to various platforms. Canva says this approach enables accurate object detail, legible text within images, and precise edits that leave the rest of the image unchanged.

A notable distinction in the model’s development is its training data: rather than photographs, Canva used human-designed templates from its own library, including posters, social posts, presentations, infographics, menus, and typography-rich layouts. This means images generated with Canva Craft can be converted into editable, layered designs using Canva Magic, the company’s image-to-design tool.

Users can access Canva Craft through the Dream Lab tab on Canva’s platform. The model will also be available via the Canva API, and the company plans to support image generation in third-party chatbots such as ChatGPT and Gemini through Canva’s MCP. Two faster, cost-efficient variants — Craftfast and Craft-ultrafast — are in development and expected to launch soon.

Canva cited reduced API costs, improved quality, and greater speed control as reasons for building the model in-house. The company, which was on track for $4 billion in revenue last year, has seen its valuation reportedly fall from $42 billion to $35 billion after cutting its 2026 growth forecast, according to external analysts.