Canva 发布首个图像生成模型 Canva Craft
原标题：Canva releases its first image generation model
AI 摘要
设计平台 Canva 发布其首个图像生成模型 Canva Craft，由内部研究团队开发，旨在与 Google、OpenAI、字节跳动和 Meta 的同类模型竞争。该模型采用两阶段生成方式，先解析提示词并规划空间关系、视觉层级等细节，再生成最高 2K 分辨率、支持 30 种宽高比的图像，并基于 Canva 模板库中的设计图而非照片训练，因此生成结果可转换为分层设计。模型已向所有用户开放，并将通过 Canva API 和 MCP 接入第三方聊天机器人，同时 Canva 正开发 Craftfast 和 Craft-ultrafast 两个低成本版本。
正文节选
Design platform Canva released its first image generation model, called Canva Craft, developed by its research team to compete with same-category models from Google, OpenAI, ByteDance, and Meta. The company said its model works in two stages. In the first stage, it interprets users’ prompts and creates a plan with details like spatial relationships of elements, relative scale, visual hierarchy, and information for text generation. In the second stage, its model generates an image of up to 2K res