gen‑ai.news
← Back
Image

Canva launches Craft image model with 2K output and API

Canva launches Craft image model with 2K output and API

Canva has launched Craft, an in-house image generation model that outputs images at 2K resolution - a notable step up from the lower resolutions common among many consumer-facing generative tools. The model is available through Dream Lab, Canva's existing AI image generation feature, and is also exposed via a public API for developers and teams looking to integrate it into their own products or workflows.

One of Craft's more distinctive capabilities is its handling of text. The model supports text rendering in 55 languages, which addresses one of the more persistent weaknesses of generative image models - legible, accurate text within images. For a design-focused platform like Canva, where users regularly produce materials in multiple languages, this kind of built-in multilingual support has clear practical value.

Craft also emphasizes layout awareness and editable elements, suggesting the model is built with post-generation editing in mind rather than treating the output as a finished, static image. This fits Canva's broader product philosophy, where generated content is meant to serve as a starting point that users can refine within the platform's design tools. The combination of planned layouts and editability could make Craft more useful for producing templated or structured content - such as social posts, presentations, or marketing materials - compared to more freeform generative models.

The addition of a public API broadens Craft's potential reach beyond Canva's own interface. Businesses and developers can now access the model directly, which opens up use cases in automated content pipelines, custom design tools, and enterprise workflows. Canva has been steadily building out its AI capabilities over the past couple of years, and Craft represents a shift from relying primarily on third-party models toward offering a proprietary generation engine tuned for the platform's design-oriented user base.

Read at TestingCatalog →
Share:X

Enjoy this story? Get the next one in your inbox.

Twice a week: the most important stories in generative image and video AI, distilled into a 2-minute read.

Free. Unsubscribe any time. No spam, ever.

Your next read

Photo Studios Are Closing as the Fashion Industry Embraces Generative AI
Image

Photo Studios Are Closing as the Fashion Industry Embraces Generative AI

Fashion photo studios are shutting their doors as clothing brands shift toward generative AI tools to produce product imagery, drawn largely by the cost reductions the technology offers. A Reuters report highlights the growing real-world impact this trend is having on traditional commercial photography businesses. The change marks a notable structural shift in how the fashion industry produces visual content at scale.

Canva Releases AI Image Generator That Wasn’t Trained on Photographs
Image

Canva Releases AI Image Generator That Wasn’t Trained on Photographs

Canva has launched its first in-house image generation model, with a notable distinction from most competitors: it was trained on design templates rather than photographs. The approach reflects Canva's design-first identity and sidesteps some of the copyright concerns that have surrounded photo-trained models. It positions the tool as purpose-built for graphic design output rather than photorealistic imagery.

Canva launches Craft, its first in-house image model
Image

Canva launches Craft, its first in-house image model

Canva has unveiled Craft, its first internally developed image generation model, marking a significant step away from the design platform's previous reliance on third-party AI providers. Craft is built to integrate natively with Canva's existing suite of tools, aiming to give users a more cohesive creative experience. The move signals Canva's intent to build deeper control over its AI capabilities rather than depending on outside models.