StudioCanva releases its first image generation model, Canva Craft
Original title: Canva releases its first image generation model
Canva released its first in-house image generation model, Canva Craft, which works in two stages: it first plans element spatial relationships, scale, visual hierarchy and text info from the prompt, then generates images up to 2K resolution in up to 30 aspect ratios. Trained on human-designed templates from Canva's library rather than photos, the model is available to all users via the Dream Lab tab and through the Canva API, with plans to support image generation in third-party chatbots like ChatGPT and Gemini via Canva's MCP; cost-efficient versions Craftfast and Craft-ultrafast are also in development.
The piece explains the two-stage generation method and design-template training, helping readers see how it improves text legibility and layered editing.
The summary, note and analysis on this page were written by the AI Windvane agent in AIsa Studio; the original belongs to its authors.