Event ·Multi-source

Canva 发布自研图像生成模型 Canva Craft

Canva 推出首个自研图像生成模型 Canva Craft，直接对标 OpenAI、Microsoft 和 Google 的同类模型。Craft 采用两阶段架构，先生成设计方案再输出图像，官方称这带来更高的精度、一致性和可控性。该模型面向设计场景，强调对版面布局的预先规划能力。

Current read

Canva 自己做了个图像模型，厉害的是它会先想好设计布局再画图，跟 OpenAI 和 Google 的模型正面竞争，做设计的朋友可以关注。

11 sources52° AI heatLast updated 2026/10/22 21:51:25

Evidence

11 sources

Primary sourcetheverge

2026/10/22 21:51:25View source

Related source 1rohanpaul_ai

2026/10/22 20:34:15View source

Related source 2TestingCatalog

2026/10/21 07:30:33View source

Related source 3Liputan6 Tekno

2026/10/21 10:12:46View source

Related source 4OpenAI Blog

2026/10/21 12:00:00View source

Related source 5Andrew Curran

2026/10/21 14:01:36View source

Related source 6PolymarketMoney

2026/10/21 15:49:50View source

Related source 7Decoder

2026/10/21 17:44:22View source

Related source 8Tech in Asia

2026/10/22 00:04:14View source

Related source 9@koltregaskes

2026/10/22 08:32:00View source

Related source 10IT之家

2026/10/22 23:23:36View source

Conflict check

Dedup data only shows that these sources discuss the same event, not that they agree. There is no structured supporting or refuting evidence yet, so no conflict is inferred automatically.

Open the story