Canva releases its first image generation model

Canva has released Canva Craft, its first image generation model. The company says it was developed by its research team to compete with models from Google, OpenAI, ByteDance and Meta.

The model works in two stages, according to Canva. First, it interprets a prompt and plans details such as how elements relate spatially, their relative scale, visual hierarchy and text. It then generates an image at up to 2K resolution in 30 possible aspect ratios. Canva says this approach can produce accurate object details and legible text, and let users make precise edits without changing other parts of an image.

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

Canva Craft is available to all users in the Dream Lab tab and will also be offered through the Canva API. The company plans to support image generation in third-party chatbots such as ChatGPT and Gemini through Canva’s MCP. Canva says Craft gives it more control over quality and speed as well as costs. Researchers from Leonardo.ai, which Canva acquired in 2024, contributed to the model. Canva says two cost-efficient versions, Craftfast and Craft-ultrafast, are in development and will be released soon.