Generative AI for Design

The problem

Starting a design is the hardest part—especially starting from a blank page.
 

The solution

Magic Design allows users to create any template design they need—by uploading an image and generating a design to match, or describing what they want and seeing a unique design created for them.

The Process

User research (and personal experience) had long shown us that starting a design is the hardest part. It’s why we created our template library—but we also knew users wanted more:
 

I hypothesised that advancements in ML technology could provide a solution. I pitched a hackathon project, and working with David Fankhauser of Kaleido, created a proof of concept that generated editable Canva designs via AI. The results were promising enough to get company investment in the concept.

YUK VS YUM

Our next step was to explore how users might want to use the technology inside Canva to get their job done.
 
With our researcher, Annabel Blake, we ran two in-person generative research workshops with kids and adults, to find out how they’d be excited to use AI technology when they design.

Three key insights emerged:

Prototyping and testing

Using these insights, we worked with our ML engineers and Creative Technologist to propose and build a prototype. We settled on a concept which showed inspiration up front to educate the user on the tool’s capabilities.
 

But… users said they’d probably ignore the feature

The prototype testing results were actually pretty crushing. While users said they were excited about generating designs via AI, in practice we faced three significant problems:

Try it 10 more times?

But despite the setback, we were really encouraged by how excited users were when they saw the media upload feature, and they realised how simple it would make it for them to design. So we tore our designs apart and built them again via 10 rounds of design, testing, and implementation.

 
We set ourselves two goals from the testing:

Beta launch

Our beta launch thankfully went a little better.
 
Rather than asking users to prompt in a text box, we changed the entry point to our Search box and filters. When a user searches, we display our personalised, generated Magic Designs at the top of the results. Users discovered the feature without having to prompt or even think about AI creation. This removed the sense of creative block and fear from prompting, and once users discovered the feature they realised it was easy to ask for what they wanted in the familiar search environment.
 
It also allowed us to only feature AI designs prominently in results when we detected a search query long or unique enough to generate good quality designs.

We made it simpler to discover that you could design with media—both videos and images. We added the media upload feature to all our Create and Search flows for more discoverability.

We included simple, visual drop-downs above all our search results, to encourage users to play with any of our templates using AI, by uploading their own media, or changing the topic, type, or style of the templates.

We provided a space that allowed users to effortlessly create a range of ideas via AI, and have control over how much of the refinement work the tool did for them. We also made it easy to describe the design they wanted, suggesting styles, topics or design types from visual drop-downs.

REFINE AND REFINE AGAIN

From the Beta launch, we refined the functionality to make Magic Design even easier to use—adding Magic Design inside our design editor as well as in Search, refining our filtering approach to be easier to use, and adding autocomplete suggestions to guide users to input longer queries for better AI results.

Including the ability for users to add their own media and brand to their designs from the editor.

This is only the beginning for Magic Design—and we’re incredibly excited to continue developing it into the future.
 
Try Magic Design