Good news! You too can capture footage exactly like this. You just need a $100,000 Phantom Flex 4K with a Canon 50-1000mm lensâoh, and you need to be hanging out the side of a Black Hawk helicopter:
We’ve released the code for LegoGPT. This autoregressive model generates physically stable and buildable designs from text prompts, by integrating physics laws and assembly constraints into LLM training and inference.
I have to admit, I don’t know Erwitt’s photography nearly as well as I know his name, but this largely humorous new collection makes me want to change that:
Continuing their excellent work to offer more artistic control over image creation, the fast-moving crew at Krea has introduced GPT Paintâessentially 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:
introducing GPT Paint.
now you can prompt ChatGPT visually through edit marks, basic shapes, notes, and reference images.
Historically, approaches like this have sounded great butâat least in my experienceâhave 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 helpfulâmaybe because GPT-4o is smart enough to say, “Okay, make a duck with this rough pose/positionâbut 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. đ
Director John Likens and FX Supervisor Tomas Slancik dissect existential collapse in Your Friends & Neighborsâ haunting opener, blending Jon Hammâs live-action gravitas with a symphony of digital decay. […]
Shot across two days and polished by world-class VFX artists, the title sequence mirrors Hammâs crumbling protagonist, juxtaposing his stoic performance against hyper-detailed destruction.
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:
5/ Create: This one is fun. Turn a PowerPoint into an explainer video, or generate an image from a prompt in Copilot with just a few clicks.
Weâve also added new features to make Copilot even more personalized to you, plus a redesigned app built for human-agent collaboration. pic.twitter.com/m1oTf53aai
âYouâre now the proud owner of the most dangerously cozy footwear in the sky. Plush, cartoon A-10 Warthogs with big doe eyes and turbine engines ready to warm your toes and deliver cuddly close air support. Let me know if you want tiny GAU-8 Gatling gun detailing on the front.â⌠pic.twitter.com/lKLRJGALaw
Back at Adobe we introduced Firefly text-to-vector creation, but behind the scenes it was really text-to-image-to-tracing. That could be fine, actually, provided that the conversion process did some smart things around segmenting the image, moving objects onto their own layers, filling holes, and then harmoniously vectorizing the results. I’m not sure whether Adobe actually got around to shipping that support.
In any event, StarVector promises actual, direct creation of SVG. The results look simple enough that it hasn’t yet piqued my interest enough to spend my time with it, but I’m glad that folks are trying.
I really hope that the makers of traditional vector-editing apps are paying attention to rich, modern, GPU-friendly techniques like this one. (If notâand I somewhat cynically expect that it’s notâit won’t be for my lack of trying to put it onto their radar. ÂŻ\_(ă)_/ÂŻ)
Introducing Vector Feathering â a new way to create vector glow and shadow effects. Vector Feathering is a technique we invented at Rive that can soften the edge of vector paths without the typical performance impact of traditional blur effects. (Audio on) pic.twitter.com/39kfjmFsTJ
I know only what you see below, but Magic Animator (how was that domain name available?) promises to “Animate your designs in seconds with AI,” which sounds right up my alley, and I’ve signed up for their waitlist.
Three years ago (seems like an eternity), I remarked regarding generative imaging.,
The disruption always makes me think of The Onionâs classic âDolphins Evolve Opposable Thumbsâ: âHoly f*ck, thatâs it for us monkeys.â My new friend August replied with the armed dolphin below.
I’m reminded of this seeing Google’s latest AI-powered translation (?!) work. Just don’t tell them about abacuses!
Meet DolphinGemma, an AI helping us dive deeper into the world of dolphin communication. pic.twitter.com/2wYiSSXMnn
Wait, first, WTF is MCP? Check out my old friend (and former Illustrator PM) Mordy’s quick & approachable breakdown of Model Context Protocol and why it promises to be interesting to us (e.g. connecting Claude to the images on one’s hard drive).
The team showed of good new stuff, includingâOMGâshowing how to use Photoshop! (On an extremely personal level, “This is what it’s like when worlds colliiiide!!”)
As it marks its 50th anniversary, Microsoft is updating Copilot with a host of new features that bring it in line with other AI systems like ChatGPT or Claude. We got a look at them during the tech giantâs 50th anniversary event today, including new search capabilities, Copilot Vision which will be able to analyze real-time video from a mobile camera. Copilot will also now be able to use the web on your behalf. Hereâs everything you missed.
WowâI marvel at the insane, loving attention to detail in this shot-for-shot re-creation of a scene from Interstellar:
The creator writes,
I started working on this project in mid-2023, and it has been an incredible challenge, from modeling and animation to rendering and post-production. Every detail, from the explosive detachment of the Ranger to the rotation of the Endurance, the space suits of the minifigures, the insides of the Lander, and even the planet in the background, was carefully recreated in 3D.
Interstellar is one of the films that has moved me the most. Its story, visuals, and soundtrack left a lasting impact on me, and this video is my personal love letter to the movieâand to cinema in general. I wanted to capture the intensity and emotion of this scene in LEGO form, as a tribute to the power of storytelling through film.
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 thatâhow insane is it that any of this is possible??
Can you show ChatGPT 5 portraits of legendary Adobe creative director Russell Brown and get a whole set of action figures? Yep! pic.twitter.com/gLTIcGqLJ0
It’s pretty stunning what a single creator can now create in a matter of days! Check out this sequence & accompanying explanation (click on the post) from Martin Gent:
I tried to make this title sequence six months ago, but the AI tools just werenât up to it. Today itâs a different story. Sound on!
Since the launch of ChatGPTâs 4o image generator last week, Iâve been testing a new workflow to bring my characters – Riley Harper and her dog,⌠pic.twitter.com/SMgjDnJWH1
People can talk all the smack they want about “AI slop”âand to be sure, there’s tons of soulless slop going aroundâbut 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.
ChatGPT 4o’s new image gen is insane. Here’s what Severance would look like in 8 famous animation styles
1/8: Rankin/Bass â That nostalgic stop-motion look like Rudolph the Red-Nosed Reindeer. Cozy and janky. pic.twitter.com/5rFL8SGttS
It’s worth noting that creative synthesis like this doesn’t “just happen,” much less in some way that replaces or devalues the human perspective & taste at the heart of the process: everything still hinges on having an artistic eye, a wealth of long-cultivated taste, and the willpower to make one’s vision real. It’s just that the distance between that vision & reality is now radically shorter than it’s ever been.
It’s funny to think of anyone & anything as being an “O.G.” in the generative spaceâbut having been around for the last several years, Runway has as solid a claim as anyone. They’ve just dropped their Gen-4 model. Check out some amazing examples of character consistency & camera control:
Today we’re introducing Gen-4, our new series of state-of-the-art AI models for media generation and world consistency. Gen-4 is a significant step forward for fidelity, dynamic motion and controllability in generative media.
First impressions: I am very impressed! 10 second generations, and this is the only model that could do falling backwards off a cliff. Love it! pic.twitter.com/GZS1B7Wpq0
Currently asking ChatGPT for faux-German words like Ăberintelligenzchatbotrichtigkeitsahnungsscham:
“The bizarre cocktail of joy, panic, and existential dread a product manager experiences when an AI answers a tough product question better than they could.” pic.twitter.com/yVZVdoKZi9
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.
A quick test of ChatGPT virtual product photography, combining real shoes with a quick render from @krea_ai/@bfl_ml Flux: “Please put these shoes into the image of the basketball court, held aloft in the foreground by a man’s hand.” pic.twitter.com/k1AhTdHFcs
We’re speed-running our way through the novelty->saturation->nausea cycle of Studio Ghibli-style meme creation, but I find this idea fresher: turn Ghibli characters into Dorothea Lange-style photos:
In the first three workdays of this week, we saw three new text-to-image models arrive! And now that it’s Thursday, I’m like, “WTF, no new Flux/Runway/etc.?” đ
For the last half-year or so, Ideogram has been my go-to model (see some of my more interesting creations), so I’m naturally delighted to see them moving things forward with the new 3.0 model:
I don’t yet quite understand the details of how their style-reference feature will work, but I’m excited to dig in.
Meanwhile, here’s a thread of some really impressive initial creations from the community:
We launched Ideogram 3.0 just three hours ago, and we’ve already seen an incredible wave of striking images. Here are 16 of our favorites so far:
Oh man, this vid from Aaron Draplinâstalwart hoarder of obsolete removable mediaâgave me all the feels, and if you’re a creative of a certain age, it might give you them, too:
Nearly twenty years ago (!), I wrote here about how The Killing’s Gotta Stopâironically, perhaps, about then-new Microsoft apps competing with Adobe. I rejected false, zero-sum framing then, and I reject it now.
Having said that, my buddy Bilawal’s provocative framing in this video gets at something important: if Adobe doesn’t get on its game, actually delivering the conversational editing capabilities we publicly previewed 2+ years ago, things are gonna get bad. I’m reminded of the axiom that “AI will not replace you, but someone using AI just might.” The same goes for venerable old Photoshop competing against AI-infused & AI-first tools.
In any case, if you’re interested in the current state of the art around conversational editing (due to be different within weeks, of course!), I think you’ll enjoy this deep dive into what isâand isn’tâpossible via Gemini:
Specific topic sections, if you want to jump right to ’em:
00:00 Conversational Editing with Google’s Multimodal AI
The old (hah! but it seems that way) gal turns two today.
The ride has been… interesting, hasn’t it? I remain eager to see what all the smart folks at Adobe have been cooking up. As a user of Photoshop et al. for the last 30+ years, I selfishly hope it’s great!
In the meantime, I’ll admit that watching the video aboveâwhich I wrote & then made with the help of Davis Brown (son of Russell)âmakes me kinda blue. Everything it depicts was based on real code we had working at the time. (I insisted that we not show anything that we didn’t think we could have shipping within three months’ time.) How much of that has ever gotten into users’ hands?
Yeah.
But as I say, I’m hoping and rooting for the best. My loyalty has never been to Adobe or to any other made-up entity, but rather to the spirit & practice of human creativity. Always will be, until they drag me off this rock. Rock the F on.
Man, I’m old enough to remember writing a doc called “Yes, And…” immediately upon the launch of DALLâ˘E in 2022, arguing that of course Adobe should develop its own generative models and of course it should also offer customers a choice of great third-party modelsâbecause of course no single model would be the best for every user in every situation.
And I’m old enough to remember being derided for just not Getting It⢠about how selling per-use access to Firefly was going to be a goldmine, so of course we wouldn’t offer users a choice. ÂŻ\_(ă)_/ÂŻ
Here’s a little holiday-appropriate experiment featuring a shot of my dad & me (in Lego form, naturally) at my grandmother’s family farm in County Mayo. SlĂĄinte!
Speaking of reskinning imagery (see last several posts), check out what’s now possible via Google’s Gemini model, below. I’ve been putting it to the test & will share results shortly.
Alright, Google really killed it here.
You can easily swap your garment just by uploading the pieces to Gemini Flash 2.0 and telling it what to do. pic.twitter.com/pNPBkIdRqy