Canva releases Craft, its first in-house image model
Original title: Canva launches Craft, its first in-house image model
Craft plans composition and text, renders up to 2K across more than 30 aspect ratios, and is in Dream Lab and a public API.
Canva released Canva Craft, which Canva Research trained from scratch mainly on millions of design templates rather than photos. The company says the model plans composition, proportions and text, then generates images at up to 2K resolution across more than 30 aspect ratios and can render text in 55 languages. Craft is available to all users through Dream Lab and a public API, with MCP integration for chatbots planned later. Canva says it ranked fourth overall on DesignArena and first in portraits and landscapes.
Unconfirmed: Quality comparisons and the DesignArena ranking are Canva's own claims, and the cheaper variants are not yet released.
- Magic Layers can split results into editable layers.
- Researchers from Leonardo.ai, acquired in 2024, contributed.
- Cheaper Craft-fast and Craft-ultrafast variants are expected soon.
- Canva says Craft can compete with models from Google, OpenAI, ByteDance and Meta.
- Vendors
- Canva
- Products
- Canva CraftDream LabMagic Layers
- Organizations
- Leonardo.aiCanva Research
- AI models
- CraftCraft-fastCraft-ultrafast
From the original article
1 min read at the-decoder.com
Design platform Canva has released Canva Craft, its first in-house image generation model. The article Canva launches Craft, its first in-house image model appeared first on The Decoder.
By Maximilian Schreiner · the-decoder.com
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.