Canva發布圖像生成模型，與谷歌、OpenAI競爭

canva has launched canva craft, its first image generation model, which works in two stages: interpreting user prompts and generating images. the model produces images with accurate details and legible text in up to 2k resolution and 30 aspect ratios. canva craft was trained using human-designed templates from canva's library, allowing generated images to be converted into layered designs. the model is available on canva's platform and through the canva api, with plans to support image generation in third-party chatbots. canva aims to reduce api costs and improve quality and speed control with this new model.