Canva 推出首个 AI 图像模型 Craft，先规划再生成
原标题：Canva’s first AI image model plans designs before generating them
AI 摘要
Canva 发布其首个 AI 图像生成模型 Canva Craft，采用两阶段架构，先生成设计方案再生成图像，以提升精度、一致性和可控性。该模型支持最高 2K 分辨率和 30 多种宽高比，基于平台数百万人类设计模板训练，目前在设计竞技场 Design Arena 排行榜上位列第四，落后于 OpenAI 的 GPT-Image-2.5 Sunburst、GPT-Image-2.5 Flare 和 GPT-Image-2。Canva Craft 已向全球所有用户开放，公司还计划通过开放的模型上下文协议（MCP）让 AI 智能体接入，并推出更高效的 Craft-fast 和 Craft-ultrafast 版本。
正文节选
Canva is diving even deeper into AI with the launch of an image generation model that competes directly with those from OpenAI, Microsoft, and Google. The model, called Canva Craft, uses a two-stage architecture that allows it to plan a design before generating an image, allowing for “greater precision, consistency and control,” according to an announcement on Thursday. Canva’s first AI image model plans designs before generating them Canva Craft can generate images at up to 2K resolution and in