Canva 推出首款 AI 图像模型 Canva Craft：先规划设计后生成图像
英文标题：Canva’s first AI image model plans designs before generating them
Canva 正式推出首款自研图像生成模型 Canva Craft，采用两阶段架构实现“先规划设计后生成图像”，支持最高 2K 分辨率与 30 余种画幅比例。该模型基于数百万套人工模板训练，在文本清晰度与构图定位上具备明显优势，目前在 Design Arena 评测榜位列第四，紧随 OpenAI 之后。Canva 还计划通过 Model Context Protocol（MCP）开放 AI Agent 接入并推出轻量化快速版本，展现了设计工具平台向具备底层大模型与 Agent 生态协作能力的深度演进。
30.1 KB
431.5 KB
2.9 KB
242.0 KB
114.3 KB
383.0 KB
186.4 KB
151.8 KB
99.0 KB
100.1 KB
433.6 KB
77.6 KB
161.5 KB
410.6 KB
80.2 KB
95.0 KB
336.2 KB
56.7 KB
131.9 KB
711.7 KB
中文
Canva 进一步深入 AI 领域，推出了一款直接与 OpenAI、微软和谷歌展开竞争的图像生成模型。根据周四的公告，这款名为 Canva Craft 的模型采用了两阶段架构，使其能够在生成图像前先规划设计，从而实现“更高的精准度、一致性与可控性”。
Canva Craft 最高支持生成 2K 分辨率以及超过 30 种宽高比的图像。除了生成社交媒体帖子和营销内容外，它还可用于创作写实场景、数字艺术、环境图像等。据 Canva 介绍，该模型的两阶段系统使其能够更加精准地生成需要清晰可读文本和精准物体排布的复杂图像。
这款全新的 AI 模型建立在 Canva 全面发力 AI 的基础之上。今年 4 月，Canva 推出了全新的基于提示词的编辑功能，用户只需通过语言描述即可创建或修改设计。这款设计工具还为 AI 生成的图像引入了图层功能，允许用户在保持其余部分不变的情况下针对图像局部进行修改。
Canva 表示，Craft 的训练基于其平台内容库中涵盖社交媒体帖子、演示文稿、信息图表和菜单等“数百万套人工设计的模板”。在 AI 设计众包基准平台 Design Arena 的排行榜上，该模型目前在最佳 AI 图像生成模型中排名第四，仅次于 OpenAI 的 GPT-Image-2.5 Sunburst、GPT-Image-2.5 Flare 以及 GPT-Image-2。
Canva 指出，其 AI 模型配备了“强大的输入与输出审核、隐私与安全控制以及举报工具”。该公司计划允许 AI Agent 通过开放的 Model Context Protocol 接入 Canva Craft，并将在未来推出运行效率更高的 Craft-fast 和 Craft-ultrafast 模型。
Canva Craft 现已面向全球所有用户开放。你可以通过点击 Canva 左侧菜单中的三点图标选项，然后选择 Dream Lab 进行体验。
English / 原文
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 Craft can generate images at up to 2K resolution and in more than 30 aspect ratios. In addition to generating social media posts and marketing content, it’s also supposed to create realistic scenes, digital art, environmental imagery, and more. The model’s two-stage system allows it to more accurately generate complex images that require legible text and precise object placement, according to Canva.
The new AI model builds on Canva’s big push into AI. In April, Canva launched new prompt-based editing capabilities that allow you to create or make changes to a design by describing it. The design tool also brought layers to AI-generated images, which let you make changes to part of an image while leaving the rest untouched.
Canva says it trained Craft on “millions of human-made templates” from the platform’s content library, which includes things like social media posts, presentations, infographics, and menus. The model is currently ranked fourth on Design Arena’s leaderboard for the best AI image generation models, a crowdsourced benchmark for AI designs. It sits behind OpenAI’s GPT-Image-2.5 Sunburst, GPT-Image-2.5 Flare, and GPT-Image-2.
Canva notes that its AI model comes with “robust input and output moderation, privacy and safety controls, and reporting tools.” The company plans to allow AI agents to plug into Canva Craft through the open Model Context Protocol, and will also roll out more efficient Craft-fast and Craft-ultrafast models in the future.
Canva Craft is available now to all users globally. You can try it by navigating to the three-dot option on Canva’s left-hand menu and then selecting Dream Lab.