• Canva launched Canva Craft, a tool similar to AI image models by Google, Meta, and OpenAI.
• Surprisingly, Canva fell short on a design task but did well at generating more realistic images.
• Here is how Canva's new image generation tool stacks up against ChatGPT, Gemini, and Muse.

Canva wants a shot at winning the AI image generation race.

The design platform launched Canva Craft on Thursday, its first image-generation model, similar to those from Google, Meta, and OpenAI.

Users can access Craft through Canva’s Dream Lab, including with free accounts, though it is subject to AI usage limits. You’ll need to sign in to a Canva account to get started.

In the release announcement, Canva said the tool plans a design’s layout, proportions, and text before generating an image, an approach that aims to help it produce legible lettering and accurate details.

The company also said that the model was trained on human-designed Canva templates, including posters, menus, and presentations, rather than photographs.

To test how Canva performs, Business Insider created three image generation prompts with escalating difficulty levels — from designing a simple greeting card to creating a photorealistic image from scratch.

Here is how Canva's brand-new image generation tool stacked up against three of the most powerful models.

Canva did not respond to a request for comment.

Starting off with an illustration

We started off simple with a prompt for a birthday card.

Create a cartoon "Happy Birthday" greeting card for a friend named Jessica who has pink hair, brown eyes, likes to wear paisley, and is turning 28 years old in November.

Surprisingly, Canva, the design platform, fell short in its design of the birthday card, from the awkward font to the outsize head of the cartoon character. It didn't even bother to include any paisley.

By comparison, ChatGPT and Muse understood the assignment.

ChatGPT guessed that the recipient's favorite color might be pink, while Muse thoughtfully wove in cozy fall elements for the November birthday girl.

Meanwhile, Gemini took the request literally and produced an image of an actual card. Extra points!

Winner: Muse

Editing an image

For the second task, I tested the AI models' ability to identify an element and place it in a brand-new setting.

Edit this image of me holding a necklace pendant. Take the red garnet pendant off my hand and make it look as if it is displayed in a vitrine in a jewelry showroom.

Canva did a great job of identifying the pendant and creating an atmospheric setting, but, like Gemini, it depicted the jewelry in a way that defied physics and common sense. It would be unrealistic for a pendant to float in the air or sit propped on a metal pole.

ChatGPT and Muse once again outperformed other models in understanding how things typically look in reality. Muse, however, made some alterations to the pendant, which I didn't ask for.

Winner: ChatGPT

Creating a photorealistic image from scratch

With Halloween approaching, I asked for a realistic depiction of my favorite animal.

Generate a photorealistic image of a long-haired orange tabby cat in a Halloween costume with bat wings, perched on the edge of a gothic medieval castle under the full moon and a starless night sky.

Though the cat's fur looks a little too strandy and high-contrast in Canva's creation, no components are missing or malformed, and the image composition pretty much matches the quality of Muse and Gemini.

The clear winner for me in this round, however, would be ChatGPT.

Not only is the cat's posture majestic, but the soft glow on his left side is extremely realistic, and the white balance is well done. There are also clouds softly cradling the moon, which could be a response to my request for a starless sky.

Winner: ChatGPT

Overall, it's evident that Canva still has a lot of room to grow compared to other models, especially if graphic design is its focus. For now, I'll stick to moving components around by hand.

Nearly 60 years ago, John McPhee rafted the Colorado River with a longtime Sierra Club reader and his nemesis, taking notes as the men argued over the fate of the land, the future of Lake Powell. Today, McPhee is 95 years old and widely acknowledged as a singuler chronicler of place, people, and time. As David Schurman Wallace notes, he also has “a good chance of outlasting the lake.” In a stimulating review of Encounters with Wild America, a four-book collection by McPhee, Wallace sets a master’s time-intensive and famously lengthy projects against the contemporary attention economy and the media industry. Longform writing didn’t spring from a hashtag; it was a natural outcome of applying narrative frames to complex subjects, including nature itself. Now, writes Wallace, “this work of dedicated attention, so essential to thinking about, say, the environment, is at risk of becoming a relic.”

[McPhee’s] work is an artifact, one that aids reflection, but demands you stop first and take things slowly. It’s no accident that the books that Library of America have chosen to canonize first are about nature and the people who inhabit it. To appreciate, or even just think about an expanse—a nearly deserted forest, a glacier, a stretch of tundra—is difficult. You can look at an image, but you can just as quickly turn away or scroll past. His writing is a tool that helps us feel distance. You have to spend time on the page getting to know it, trying to imagine things you will most likely never experience yourself.

Count the verbs in Alexander Chee’s essay, note the absence of emotional language, and then thank Annie Dillard for her part. Chee, an essayist and fiction writer, revisits his undergraduate writing workshop with Dillard, the distinguished, Pulitzer Prize-winning nonfiction writer who died last week at 81. Chee’s account of their semester together is an affectionate portrait that doubles as a brisk craft talk; in it, he puts Dillard’s lessons through their paces, a fitting tribute to the teacher who borrowed cigarette drags from her students, chewed through caramel candies during class, and nurtured his own artistic evolution with her rules and exercises.

Narrative writing sets down details in an order that evokes the writer’s experience for the reader, she announced. This seemed obvious but also radical—no one had ever said it so plainly to us. She spoke often of “the job.” If you’re doing your job, the reader feels what you felt. You don’t have to tell the reader how to feel. No one likes to be told how to feel about something. And if you doubt that, just go ahead. Try and tell someone how to feel.

. . .

One afternoon, at her direction, we brought in our pages, scissors and tape, and told to bring several drafts of an essay, one that we struggled with over many versions.

Now cut out only the best sentences, she said. And tape them on a blank page. And then when you have that, write in around them, she said. Fill in what’s missing and make it reach for the best of what you’ve written thus far.

In our relentlessly optimized world, Justin Neuman calls for more nothing. More time for both adults and kids to engage in free, unstructured play. More opportunities to play games without competition or scoring. More chances to do things without needing to produce outputs or achieve goals. More “transitional spaces” through which we can practice, imagine, and think.

For years, I’ve commuted on foot from Grand Central Station to 14th Street, 30 blocks, give or take. I told myself it was exercise, or that I was saving the subway fare, or that I liked the air. But the truth is I was thinking. Or rather, I was letting thinking happen. The lecture I couldn’t outline at my desk would assemble itself somewhere around 34th Street, the important points falling into sequence with my footfalls, the argument clarifying as if the motion itself were doing the editing. I wasn’t working on the lecture. I was walking in it, the way my kids were playing in Catan.

Kevin Dupzyk’s profile of Sam Rockwell, a “legendary scene-stealer” now in his fourth decade of work, is a crisp and entertaining one-act, with journalist and actor holed up in a spare Manhattan greenroom. Dupzyk studies Rockwell while Rockwell studies the room, testing the durability of his own idiosyncratic observations—about Red Bull and loss and rain—to see what they might yield in a conversation with a stranger. Dupzyk had wanted to “gin up some action for this story,” but it’s strangely compelling to watch Rockwell’s gaze prowl the room, to see what lodges in the filter of his creative process.

Rockwell is a good tennis player. And like any good athlete, he trains. For as much as he appears to get by on natural charm and charisma, he is an actor’s actor, a true believer, in his words, an “acting nerd.” Research. Running lines. Exerci—

“Do you know what a gibbon is?” Rockwell asks.

“Like, a monkey?” I say, confused.