Happy Halloween, y’all!
Monthly Archives: October 2024
Stop-motion M4 Mac mini ad
You know I love some stop-motion animation, and the vibe & copywriting here are more cheeky & charming than just about anything I’ve seen in a while:
1980s Reimagined Logos of Popular Brands
Heh—charming vaporwave & chiptune:
Peeps of a certain age & demographic see these & get immediate PBS/WGBH vibes:
Thunder & The Deep Blue Sea
Everybody needs a good wingman, and when it comes to celebrating the beauty of aviation, I’ve got a great one in my son Henry. Much as we’ve done the last couple of years, this month we first took in the air show in Salinas, featuring the USAF Thunderbirds…
…followed by the Blue Angels buzzing Alcatraz & the Golden Gate at Fleet Week in San Francisco.
In both cases we were treated to some jaw-dropping performances—from a hovering F-35 to choreographed walls of fire—from some of the best aviators in the world. Check ’em out:
And thanks for the nice shootin’, MiniMe!
Stop-Motion: Will Smith vs. Pumpkin
Who needs AI Will gobbling spaghetti (which has somehow become the Utah Teapot of generative video!) when you’ve got this tiny, meticulous excellence?
More relighting goodness
DifFRelight can change flat-lit facial captures into high-quality images and dynamic sequences with complex lighting!
It uses a diffusion-based model for precise lighting control, accurately showing effects like eye reflections and skin texture.https://t.co/iXZjpVOxFx pic.twitter.com/Rwj7jTBnRd
— Dreaming Tulpa (@dreamingtulpa) October 23, 2024
Relighting via Midjourney
Check out this impressive use of the new “retexture” feature, which enables image-to-image transformations:
Wow!
Midjourney’s edit and retexture features are incredible!
I retextured my profile image using some of my sref codes and animated it with LumaLabs.
The new images are stunning, and the animated video looks even better.
You can apply this to any image in no time!
Prompt… pic.twitter.com/TYhD7VzZAS
— Umesh (@umesh_ai) October 24, 2024
Here’s a bit more on how the new editing features work:
We’re testing two new features today: our image editor for uploaded images and image re-texturing for exploring materials, surfacing, and lighting. Everything works with all our advanced features, such as style references, character references, and personalized models pic.twitter.com/jl3a1ZDKNg
— Midjourney (@midjourney) October 23, 2024
Ideogram Canvas arrives
I’ve become an Ideogram superfan, using it to create imagery daily, so I’m excited to kick the tires on this new interactive tool—especially around its ability to synthesize new text in the style of a visual reference.
Today, we’re introducing Ideogram Canvas, an infinite creative board for organizing, generating, editing, and combining images.
Bring your face or brand visuals to Ideogram Canvas and use industry-leading Magic Fill and Extend to blend them with creative, AI-generated content. pic.twitter.com/m2yjulvmE2
— Ideogram (@ideogram_ai) October 22, 2024
You can upload your own images or generate new ones within Canvas, then seamlessly edit, extend, or combine them using industry-leading Magic Fill (inpainting) and Extend (outpainting) tools. Use Magic Fill and Extend to bring your face or brand visuals to Ideogram Canvas and blend them with creative, AI-generated elements. Perfect for graphic design, Ideogram Canvas offers advanced text rendering and precise prompt adherence, allowing you to bring your vision to life through a flexible, iterative process.
“Big alpha channel energy”
The hilariously nerdy Elle Cordova (of “Fonts Hanging Out” fame) is back, this time as some of our favorite (and least favorite) file formats.
San Jose derails through the power of AI
Filmmaker & Pika Labs creative director Matan Cohen Grumi makes this town look way more dynamic than usual (than ever?) through the power of his team’s tech:
Took @pika_labs AI effects to the streets of San Jose. It’s crazy what you can create with just a phone, Pika and some basic edits #pikaffects pic.twitter.com/uzN2KyLHnh
— Matan Cohen-Grumi (@MatanCohenGrumi) October 19, 2024
Doom scrolling, the SNL way
Oh man, what a mixture of tiny, relatable jokes (“STOP”) with absolutely incomprehensible gibberish—i.e., TikTok in a nutshell. I think you’ll dig it:
Project Turntable spins me right ’round
Adobe’s new generative 3D/vector tech is a real head-turner. I’m impressed that the results look like clean, handmade paths, with colors that match the original—and not like automatic tracing of crummy text-to-3D output. I can’t wait to take it for a… oh man, don’t say it don’t say it… spin.
Project Perfect Blend promises game-changing compositing in Photoshop
Oh man, for years we wanted to build this feature into Photoshop—years! We tried many times (e.g. I wanted this + scribble selection to be the marquee features in Photoshop Touch back in 2011), but the tech just wasn’t ready. But now, maybe, the magic is real—or at least tantalizingly close!
Being a huge nerd, I wonder about how the tech works, and whether it’s substantially the same as what Magnific has been offering (including via a Photoshop panel) for the last several months. Here’s how I used that on my pooch:
But even if it’s all the same, who cares?
Being useful to people right where they live & work, with zero friction, is tremendous. Generative Fill is a perfect example: similar (if lower quality) inpainting was available from DALL•E for a year+ before we shipped GenFill in Photoshop, but the latter has quietly become an indispensible, game-changing piece of the imaging puzzle for millions of people. I’d love to see compositing improvements go the same way.
The ceiling can’t hold us stuffed animals
As I drove the Micronaxx to preschool back in 2013, Macklemore’s “Can’t Hold Us” hit the radio & the boys flipped out, making their stuffed buddies Leo & Ollie go nuts dancing to the tune. I remember musing with Dave Werner (a fellow dad to young kids) about being able to animate said buddies.
Fast forward a decade+, and now Dave is using Adobe’s recently unveiled Firefly Video model to do what we could only dimly imagine back then:
Bringing stuffed animals to life with Adobe Firefly Generate Video. pic.twitter.com/XSbQxaIDiD
— Dave Werner (@okaysamurai) October 16, 2024
Time to unearth Leo & get him on stage at last. :->
Extremely metal “I Voted” sticker
Aw hell yeah, 12yo illustrator Jane!
IM FUCKING CRYING pic.twitter.com/fsSqPxsHhQ
— Casey Shea Enthusiast (@csheaenthusiast) October 3, 2024
AI-flavored vacation pix: Delightful nightmare fuel
Enjoy the latest from Magnific impresario Javi Lopez!
PART 3: Handed my vacation videos to an AI for auto editing, and now I’m pretty sure I’ll have nightmares for life pic.twitter.com/jYX1TZ4rMX
— Javi Lopez (@javilopen) October 12, 2024
Striking visualizations of a storm surge
Amazing, and literally immersive, work by artists at The Weather Channel. Yikes—stay safe out there, everybody.
The 3D artists at the weather channel deserve a raise for this insane visual
Now watch this, and then realize forecasts are now predicting up to 15 ft of storm surge in certain areas on the western coast of Florida pic.twitter.com/HHrCVWNgpg
— wave (@0xWave) October 8, 2024
Flair AI promises brand-consistent video creation
As soon as Google dropped DreamBooth back in 2022, people have been trying—generally without much success—to train generative models that can incorporate the fine details of specific products. Thus far it just hasn’t been possible to meet most brands’ demanding requirements for fidelity.
Now tiny startup Flair AI promises to do just that—and to pair the object definitions with custom styling and even video. Check it out:
You can now generate brand-consistent video advertisements for your products on @flairAI_
1. Train a model on your brand’s aesthetic
2. Train a model on your clothing or product
3. Combine both models in one prompt
4. Animate✨In beta – comment/RT for access and free credits pic.twitter.com/88NYLVOFSQ
— Mickey Friedman (@mickeyxfriedman) October 7, 2024
In search of The Something Else
Late last night my wife & I found ourselves in the depths of the Sunday Evening Blues—staring out towards the expanse of yet another week of work & school, without much differentiation from most of those before & after it. I’m keenly aware of the following fact, of course:
And yet, oof… it’s okay to acknowledge the petty creeping of tomorrow & tomorrow & tomorrow. The ennui will pass—as everything always does—but it’s real.
This reminded me of the penguin heroine in what was one of our favorite books to read to the Micronaxx back when they were actually micro, A Penguin Story by Antoinette Portis. Ol’ Edna is always searching for The Something Else—and she finds it! I came across this charming little narration of the story, and just in case you too might need a little avian encouragement—well, enjoy:
Meta AI introduces conversational editing
I was super hyped last year when Meta announced “Emu Edit” tech for selectively editing images using just language:
Now you can try the tech via Meta.ai and in various apps:
Meta has casually released the best AI image editor
You can upload your image to Meta AI and just write the edits you want to make.
Accessible for free in WhatsApp, Instagram, Messenger, Facebook, etc. pic.twitter.com/jJEhMdJadT
— Paul Couvert (@itsPaulAi) October 2, 2024
In my limited experience so far, it’s cool but highly unpredictable. I’ll test it further, and I’d love to know how it works for you. Meanwhile you can try similar techniques via https://playground.com/:
Welcome to the new Playground
Use AI to design logos, t-shirts, social media posts, and more by just texting it like a person.
Watch: pic.twitter.com/eSwJcJUxtB
— Playground (@playground_ai) September 3, 2024