Canva 首个自研 AI 图像模型 Craft:先规划设计再生成图像Canva’s first AI image model plans designs before generating them


AI free token/AI免费积分
Canva 首个自研 AI 图像模型 Craft:先规划设计再生成图像

Canva 正凭借一款与 OpenAI、微软、谷歌同台竞技的图像生成模型进一步扎进 AI 深水区。据周四发布的公告,这款名为 Canva Craft 的模型采用两阶段架构,允许它先规划设计再生成图像,从而实现「更高的精确度、一致性与可控性」。

Canva Craft 最高可以 2K 分辨率、超过 30 种宽高比生成图像。除了社交媒体帖子和营销内容,它还能创建逼真场景、数字艺术、环境图像等。Canva 表示,该模型的两阶段系统能更准确地生成需要清晰文字和精确物体摆放的复杂图像。

这款新模型建立在 Canva 对 AI 的大举投入之上。今年 4 月,Canva 推出了基于提示词的编辑功能,用户通过描述即可创建或修改设计;设计工具还为 AI 生成图像引入了图层,可以只改图像的局部而保留其余部分。

Canva 称 Craft 使用平台内容库中「数百万套人工制作的模板」进行训练,涵盖社交媒体帖子、演示文稿、信息图和菜单等。该模型目前在 Design Arena 的 AI 图像生成模型排行榜上位列第四——这是一个众包的 AI 设计基准——排在 OpenAI 的 GPT-Image-2.5 Sunburst、GPT-Image-2.5 Flare 和 GPT-Image-2 之后。

Canva 指出,其 AI 模型配备「稳健的输入输出审核、隐私与安全控制以及举报工具」。公司计划让 AI 智能体通过开放的模型上下文协议(MCP)接入 Canva Craft,未来还将推出效率更高的 Craft-fast 和 Craft-ultrafast 模型。

Canva Craft 现已面向全球所有用户开放,点击左侧菜单的三点选项并选择 Dream Lab 即可试用。

(信息来源:The Verge,2026-10-23)

本文来源:https://www.theverge.com/ai-artificial-intelligence/1017151/canva-craft-in-house-ai-model
若有版权问题,请来信告知:13951431913#139.com 或在右方提交评论。

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.

[Image: https://platform.theverge.com/wp-content/uploads/sites/2/2026/10/canva-craft-2.jpg?quality=90&strip=all]

[Image: https://platform.theverge.com/wp-content/uploads/sites/2/2026/10/canva-craft-3.jpg?quality=90&strip=all]

[Image: https://platform.theverge.com/wp-content/uploads/sites/2/2026/10/canva-craft-4.jpg?quality=90&strip=all]

[Image: https://platform.theverge.com/wp-content/uploads/sites/2/2026/10/canvacraft-1.jpg?quality=90&strip=all]

[Image: https://platform.theverge.com/wp-content/uploads/sites/2/2026/10/canvacraft-5.jpg?quality=90&strip=all]

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.

Canva’s first AI image model plans designs before generating them

暂无评论,快来发表第一条评论吧!No comments yet. Be the first!

📮 需求咨询📮 Inquiry