Category Archives: GPT-4o

Krea introduces “GPT Paint”

Continuing their excellent work to offer more artistic control over image creation, the fast-moving crew at Krea has introduced GPT Paint—essentially a simple canvas for composing image references to guide the generative process. You can directly sketch, and/or position reference images, then combine the input with prompts & style references to fine-tune compositions:

Historically, approaches like this have sounded great but—at least in my experience—have fallen short.

Think about what you’d get from just saying “draw a photorealistic beautiful red Ferrari” vs. feeing in a crude sketch + the same prompt.

In my quick tests here, however, providing a simple reference sketch seems helpful—maybe because GPT-4o is smart enough to say, “Okay, make a duck with this rough pose/position—but don’t worry about exactly matching the finger-painted brushstrokes.” The increased sense of intentionality & creative ownership feels very cool. Here’s a quick test:

I’m not quite sure where the spooky skull and, um, lightning-infused martini came from. 🙂

GPT-4o image creation is coming to Designer!

Having created 200+ images in just the last month via this still-new image model (see new blog category that gathers some of them), I’m delighted to say that my team is working to bring it to Microsoft Designer, Copilot, and beyond. From the boss himself:

Fun recent GPT-4o explorations

Just sharing a few things I’ve been trying.
For Easter, my cousin’s sweet pup as sweet treats:

Bespoke felt ornaments FTW:


Creating cozy slippers from an A-10 Warthog:

That Happy Meal feel

Sure, the environmental impact of this silliness isn’t great, but it’s probably still healthier than actually eating McDonald’s. :-p

Tangentially, I continue to have way too much fun applying different genres to amigos:

Rustlin’ up some Russells

2025 marks an unheard-of 40th year in Adobe creative director Russell Brown’s remarkable tenure at the company. I remember first encountering him via the Out Of Office message marking his 15-year (!) sabbatical (off to Burning Man with Rick Smolan, if I recall correctly). If it weren’t for Russell’s last-minute intervention back in 2002, when I was living out my last hours before being laid off from Adobe (interviewing at Microsoft, lol), I’d never have had the career I did, and you wouldn’t be reading this now.

In any event, early in the pandemic Russell kept himself busy & entertained by taking a wild series of self portraits. Having done some 3D printing with him (the output of which still forms my Twitter avatar!), I thought, “Hmm, what would those personas look like as plastic action figures? Let’s see what ChatGPT thinks.” And voila, here they are.

Click through the tweet below if you’re curious about the making-of process (e.g. the app starting to render him very faithfully, then freaking out midway through & insisting on delivering a more stylized, less specific rendition). But forget that—how insane is it that any of this is possible??

Severance, through the animated lens of ChatGPT

People can talk all the smack they want about “AI slop”—and to be sure, there’s tons of soulless slop going around—but good luck convincing me that there’s no creativity in remixing visual idioms, and in reskinning the world in never-before-possible ways. We’re just now dipping a toe into this new ocean.

See the whole thread for a range of fun examples:

Virtual product photography in ChatGPT

Seeing this, I truly hope that Adobe isn’t as missing in action as they seem to be; fingers crossed.

In the meantime, simply uploading a pair of images & a simple prompt is more than enough to get some compelling results. See subsequent posts in the thread for details, including notes on some shortcomings I observed.

See also (one of a million tests being done in parallel, I’m sure):

ChatGPT reimagines family photos

“Dress Your Family in Corduroy and Denim” — David Sedaris
“Turn your fam into Minecraft & GTA” — Bilawal Sidhu

And meanwhile, on the server side: