Canva 发布首个自研图像模型 Canva Craft，DesignArena 排名第二

AI 导读

Canva 发布首个自研图像模型 Canva Craft，在 DesignArena 图像生成榜单中位列第二，仅次于 OpenAI。Canva Craft 由规划模型和渲染模型组成，前者先读取提示词并确定构图、元素位置、大小、强调重点与文字，后者按计划以最高 2K 分辨率、覆盖 30 多种宽高比生成图像。规划结果在修改阶段可复用，修改一个元素时其余内容保持不变。

正文 · 原文

Canva has entered the frontier AI model race, and its first model is already near the top.

It's first in-house image model made it the second-best (on DesignArena) lab in image generation, with only OpenAI ahead of it.

Canva Craft has a planner that reads the prompt and writes out the composition before any pixels exist: which elements appear, where each one sits, how large it is, what carries the emphasis, and the exact words to display.

A second model, the renderer, paints that plan at up to 2K across more than 30 aspect ratios.

So layout is no more something that the model has to get right inside a single pass. It becomes an explicit intermediate object.

Spelling gets settled before rendering starts. The renderer’s job is to draw words it was already given, in a spot it was already assigned.

The plan pays off a second time during revision. Change one element and only that element changes, so fixing a subhead leaves the product shot next to it alone.