The New Canva Design Model Might Give Us Editable AI Images At Last

Canva unveiled a slew of new AI products and features during its fall product launch on Thursday, but this boring, technical new release might actually be the most promising. Canva has developed a new fundamental AI model for design. And this model promises to solve one of my biggest frustrations with AI images.

Foundational models are the digital frameworks running behind the scenes to process your AI requests. Traditional diffusion models can create “flat” images and power many initial AI image generators. In recent years, these models have been upgraded to become omni LLMs: basically, they are multimodal (can handle text, images, and other inputs), have become more context-aware, and are capable of handling more complex tasks. For image generators, this meant it could process reference images, for example.

Canva’s new template works a little differently. It generates layered images while maintaining its contextual awareness. What all this means for you is that you’ll be able to select certain elements in an AI-generated image and use all of Canva’s editing tools to adjust them. You won’t need to completely regenerate an image to fix a small error, a massive quality of life improvement.

Canva has grown into a $65 billion company with the promise of making design accessible to everyone, especially those of us who aren’t Photoshop experts. AI image generators, but not without their controversies And concernsaim to achieve the same objective. I’ve used many different AI image programs, and one thing that consistently disappoints me is their post-generation editing tools. Many programs, if any, are rudimentary. Sometimes editing makes mistakes worse. So you can see why the idea of ​​editing AI images with Canva’s many one-click tools is not only appealing, but should also alert other AI image companies.

“With Canva’s foundational template, you can go from a prompt to a fully editable layered design,” Robert Kawalsky, global product manager at Canva, said in an interview. “You can use the richness of Canva’s editor to literally click on any element, any ingredient, and manipulate it, modify it just like you did before with a design that you created manually, from scratch. This is just a really fundamental change. »

Although Canva is the first major design company to offer layer-based AI image editing, it won’t be the last. Alexandru Costin, Adobe’s vice president of generative AI, told me in an interview at Adobe Max this week, the company plans to release similar capabilities in the near future. Editing capabilities overall remain a major concern for designers and illustrators using AI creative tools.

Don’t miss any of our unbiased technical content and lab reviews. Add CNET as your preferred Google source.

There’s another plus here: Canva’s internal AI image generator is great for beginners, but it wasn’t the most impressive of the bunch. This new model should bring a little more firepower.

There are many other updates, including the ability to create forms for data capture, a new Premiere Pro-style video timeline, and HTML-compatible email templates. You will also be able to copy the artistic style of an element and paste it on another object. But the only other major news actually concerns Canva’s acquisition of Affinity last year.

Canva acquired professional design program Affinity in 2024, and now Canva users will be able to use Affinity for free, with no subscription required. It’s a surprising choice and makes Affinity undeniably the most affordable choice for professional editing software, surpassing Adobe’s increasingly expensive Creative Cloud subscriptions.

Canva’s last major batch of updates was also AI-focused, aiming to help its users with STEM-oriented tasks like coding.

To learn more, see how to write the best AI image prompt and the best AI image generators.