Something something how to get a-head in generative video…? 🙂
messing around with cartoon physics in omni flash. it is just too good – the character consistency, the sound effects, all of it !! pic.twitter.com/qrlvSqijT8
Donkman Effeminate Forklifts FTW! :-p (I have no idea how she made it through this copy without completely cracking up—and per the comments, neither does she!)
Like so many folks in the extended imaging community, I was sad to hear of the passing of Jay Maisel. Though I never got to know him well, Jay was a familiar & colorful presence in the world of Photoshop and Lightroom. See some memorable recollections from Joe McNally.
Many years ago I had the chance to drop by the iconic converted bank building in the Bowery he occupied for nearly half a century. (This must’ve been before phone cameras got good, as otherwise I’d have shot the bejesus out of the place.) It was everything you’d hope it to be.
More recently, my father-in-law (having no idea about the visit) dialed up the documentary “Jay Myself” last night, and whole family (down to my then-12yo budding photographer son) loved it. I think you would, too!
Still think that AI is all about slop-machine randomness vs. artistic control? CrossViewWarp (see details & more examples) is one of many emerging technologies challenging that view:
CrossViewWarp allows you to change the camera arc of an existing video while maintaining the motion.
Wow—provided quality & resolution can be made high enough, tell me how soon tech like this can come to Photoshop & Lightroom:
Depth-aware light injection in TypeGPU
I got a 448×448 monocular depth model down to ~8 ms on my M4 Pro across ~250 dispatches, which is fast enough to use in realtime 😀 Since the inference is written directly in TypeGPU, I can just feed the depth buffer straight into the… pic.twitter.com/txDXqc88l6
My friend Dave (Adobe designer for Firefly video) brings his characteristic wit to the tribulations of just trying to “sell some junk” in the age of AI-infused design:
Given that we’re taking our eldest son to start life as a University of Colorado Buffalo tomorrow (!), it was only fitting that we communed with a few real buffs in Yellowstone over the last few days. Here’s an Insta gallery:
Bonus wildlife from the trip: in Boise we dropped by the The World Center for Birds of Prey and got to see this handsome crew in action. (Inside-baseball detail: hopefully you’d never know that I was obliged to photograph the first owl shown through a dense set of bars on his enclosure. Nano Banana in Photoshop to the rescue!)
It’s a very imperfect analogy, but I feel like as AI video fully passes the “can this pass for real” test, we’ll break into new & more interesting territory—much as painting did once photography took the “does this replicate reality” crown.
Here’s a handful of fun, beautiful animations rendered in a variety of styles. The fact of them being powered by new models is kind of incidental—as it should be: all that matters is what moves people & what helps artists do that.
Just think for a moment about the potential Seedance 2.5 has for children’s storytelling.
Bringing an animated story to life for your kids has never been easier.
Today, a solar eclipse over Poland. The first such one in 72 years. The last time people looked up at the sky like that was in 1954 – through soot-covered glass, on Constitution Square in Warsaw. I froze that moment and flew through it with a camera. All the way to the sun. Zdzisław Wdowiński / PAP, 1954
Dziś zaćmienie słońca nad Polską. Pierwsze takie od 72 lat.
Ostatni raz ludzie patrzyli tak w niebo w 1954 roku – przez zakopcone szkiełka, na Placu Konstytucji w Warszawie.
Zamroziłem tamten moment i przeleciałem przez niego kamerą. Aż do słońca.
Greetings from the midst of our bittersweet (but mostly very sweet!) roadtrip to take Finn off to college in Boulder. Me being me, I of course brought our Lego selves to use in making arguably cringey (#jeezdad) family pics. I don’t have a precise match for our newly modded van, so I brought the closest equivalent & then gave Gemini a reference image to use with Nano Banana. Not bad, robot—not bad at all:
I have no words for this kind of witchcraft. In case the embedded tweet doesn’t show up in English, here’s a translation:
Wow. Maciej Dobrodziej – a digital creator – has “brought to life” one of Warsaw’s most famous photographs. The photo of a girl running in the rain on Puławska Street was taken by Zbigniew Siemaszko in 1968. Fun fact: After many years, it was possible to find Ms. Grażyna, who is the heroine of the photo. She recognized herself upon seeing… the photograph on FB.
Wow. Maciej Dobrodziej – twórca cyfrowy „ożywił” jedno z najsłynniejszych zdjęć Warszawy. Fotografie biegnącej w deszczu dziewczyny na ulicy Puławskiej zrobił Zbigniew Siemaszko w 1968 roku.
Ciekawostka: po latach udało się odnaleźć panią Grażynę, która jest bohaterką zdjęcia.… pic.twitter.com/tvNJJjlka3
“A.I. sing of arms and the man…” Wait—that was the Aeneid, but Imma go for it.
This reimagining of The Odyssey—nailing everything from casting to an apparently generated period-accurate song that actually slaps—demonstrates my long-running contention that when things become amazing enough, we can’t even process them.
People see this and neither marvel at the incredible state of technology (which has leapt forward in just the last couple of weeks), nor point out little shortcomings here & there, nor even get into another fruitless battle about the ethics of AI. Instead, at least from where I sit, I see them simply commenting on the concept & storytelling.
It’s so fun to see work from a past life enabling whole new modes of expression!
Who knew PMF for MediaPipe hand tracking would be performance art for social media 🙂
One of the unpredictable things about vibe coding is it breathes new life into tech that’s been around for ages and gives it a new audience. Threejs is another example. pic.twitter.com/QimPPiCOj7