Among the many, many things for which I can give thanks this year, I want to express my still-gobsmacked appreciation of the academic & developer communities that have brought us this year’s revolution in generative imaging. One of those developers is our friend & Adobe veteran Christian Cantrell, and he continues to integrate new tech from his new company (Stability AI) into Photoshop at a breakneck pace. Here’s the latest:
Here he provides a quick comparison between results from the previous Stable Diffusion inpainting model (top) & the latest one:
In any event, wherever you are & however you celebrate (or don’t), I hope you’re well. Thanks for reading, and I wish all the best for the coming year!
Among the great pleasures of this year’s revolutions in AI imaging has been the chance to discover & connect with myriad amazing artists & technologists. I’ve admired the work of Nathan Shipley, so I was delighted to connect him with my self-described “grand-mentee” Joanne Jang, PM for DALL•E. Nathan & his team collaborated with the Dalí Museum & OpenAI to launch Dream Tapestry, a collaborative realtime art-making experience.
The Dream Tapestry allows visitors to create original, realistic Dream Paintings from a text description. Then, it stitches a visitor’s Dream Painting together with five other visitors’ paintings, filling in the spaces between them to generate one collective Dream Tapestry. The result is an ever-growing series of entirely original Dream Tapestries, exhibited on the walls of the museum.
Another day, another special-purpose variant of AI image generation.
A couple of years ago, MyHeritage struck a chord with the world via Deep Nostalgia, an online app that could animate the faces of one’s long-lost ancestors. In reality it could animate just about any face in a photo, but I give them tons of credit for framing the tech in a really emotionally resonant way. It offered not a random capability, but rather a magical window into one’s roots.
Now the company is licensing tech from Astria, which itself builds on Stable Diffusion & Google Research’s DreamBooth paper. Check it out:
Interestingly (perhaps only to me), it’s been hard for MyHeritage to sustain the kind of buzz generated by Deep Nostalgia. They later introduced the much more ambitious DeepStory, which lets you literally put words in your ancestors’ mouths. That seems not to have bent the overall needle in awareness, at least in the way that the earlier offering did. Let’s see how portrait generation fares.
Speaking of Bilawal, and in the vein of the PetPortrait.ai service I mentioned last week, here’s a fun little video in which he’s trained an AI model to create images of his mom’s dog. “Oreo lookin’ FESTIVE in that sweater, yo!” 🥰 I can only imagine that this kind of thing will become mainstream quickly.
Last year my friend Bilawal Singh Sidhu, a PM driving 3D experiences for Google Maps/Earth, created an amazing 3D render (also available in galactic core form) of me sitting atop the Trona Pinnacles. At that time he used “traditional” photogrammetry techniques (kind of a funny thing to say about an emerging field that remains new to the world), and this year he tried processing the same footage (comprised of a couple simple orbits from my drone) using new Neural Radiance Field (“NeRF”) tech:
For comparison, here’s the 3D model generated via the photogrammetry approach:
A new (to me, at least) group called Kive has just introduced AI Canvas.
Here’s a quick demo:
To my eye it’s similar to Prompt.ist, introduced a couple of weeks ago by Facet:
I’m curious: Have you checked out these tools, and do you intend to put them to use in your creative processes? I have some thoughts that I can share soon, but in the meantime it’d be great to hear yours.
I’m not sure whom to credit with this impressive work (found here), nor how exactly they made it, but—like the bespoke pet portraits site I shared yesterday—I expect to see an explosion in such purpose-oriented applications of AI imaging:
We’re at just the start of what I expect to be an explosion of hyper-specific offerings powered by AI.
For $24, PetPortrait.ai offers “40 high resolution, beautiful, one-of-a-kind portraits of your pets in a variety of styles.” They say it takes 4-6 hours and requires the following input:
~10 portrait photos of their face
~5 photos from different angles of their head and chest
~5 full-body photos
It’ll be interesting to see what kind of traction this gets. The service Turn Me Royal offers more human-made offerings in a similar vein, and we delighted our son by commissioning this doge-as-Venetian-doge portrait (via an artist on Etsy) a couple of years ago:
I had the chance to grab breakfast with Figma founder & CEO Dylan Field a couple of weeks ago, and I found him to be incredibly modest and down to earth. He reminded me of certain fellow Brown CS majors—the brilliant & gracious founding team of Adobe After Effects. I can’t wait for them all to meet someday soon.
In any case, I really enjoyed the hour-long interview Dylan did with Nilay Patel of The Verge. Here’s hoping that the Adobe deal goes through as planned & that we get to do great things together!
A few weeks ago I shared info on Google’s “Infinite Nature” tech for generating eye-popping fly-throughs from still images. Now that team has shared various interesting tech details on how it all works. And if reading all that isn’t your bag, hey, at least enjoy some beautiful results:
He notes, “Custom, fine-tuned models are absolutely game-changing, and in the future will almost certainly represent the majority of diffusion-based creativity.” 👀 Seems like a non-trivial statement coming from the new VP of product at Stability.ai.
The 3D and Immersive Design Team at Adobe is looking for a design intern who will help envision and build the future of Adobe’s 3D and MR creative tools.
With the Adobe Substance 3D Collection and Adobe Aero, we’re making big moves in 3D, but it is still early days! This is a huge opportunity space to shape the future of 3D and AR at Adobe. We believe that tools shape our world, and by building the tools that power 3D creativity we can have an outsized impact on our world.
As I may have mentioned, my 13yo son Henry—lover of all things vintage & (often) arcane—has recently taken a real interest in typography. We both enjoyed this short love letter to the craft of typesetting & printing:
Christian has trained a model on Rivians & says (ambitiously, but not without some justification) that “This is how all advertising and marketing collateral will be made sooner than most of the world realizes.”
On a related note, here’s a thread (from an engineer at Shopify) on fine-tuning models to generate images of specific products (showing strengths/limitations).
I see numerous custom models emerging that enable creation of art in the style of Spider-Man, Pixar, and more.
OMG—interactive 3D shadow casting in 2D photos FTW! 🔥
In this sneak, we re-imagine what image editing would look like if we used Adobe Sensei-powered technologies to understand the 3D space of a scene – the geometry of a road and the car on the road, and the trees surrounding, the lighting coming from the sun and the sky, the interactions between all these objects leading to occlusions and shadows – from a single 2D photograph.
One of the sleeper features that debuted at Adobe MAX is the new Create Background, found under Neural Filters. (Note that you need to be running the current public beta release of Photoshop, available via the Creative Cloud app—y’know, that little “Cc” icon dealio you ignore in your menu bar. 🙃)
As this quick vid demonstrates, the filter can not only generate backgrounds based on text, it links to a Behance gallery containing images and popular prompts. You can use these visuals as inspiration, then use the prompts to produce artwork within the plugin:
I’m really excited to learn more about this development, which I’ve been eagerly awaiting. More control + more speed will make generative imaging truly, broadly useful. I’d like to understand how it compares to techniques like prompt editing.
Motion Library allows you to easily add premade animated motions like fighting, dancing, and running to your characters. Choose from a collection of over 350 motions and watch your puppets come to life in new and exciting ways!
The Lightroom team has rolled out a ton of new functionality, from smarter selections to adaptive presets to performance improvements. You should read up on the whole shebang—but for a top-level look, spend a minute with Ben Warde:
And looking a bit more to the future, here’s a glimpse at how generative imaging (in the style of DALL•E, Stable Diffusion, et al) might come into LR. Feedback & ideas welcome!
Generative AI incorporated into Adobe Express will help less experienced creators achieve their unique goals. Rather than having to find a pre-made template to start a project with, Express users could generate a template through a prompt, and use Generative AI to add an object to the scene, or create a unique font based on their description. But they still will have full control — they can use all of the Adobe Express tools for editing images, changing colors, and adding fonts to create the flyer, poster, or social media post they imagine.
In this paper we demonstrate, for the very first time, the ability to apply complex (e.g., non-rigid) text-guided semantic edits to a single real image. For example, we can change the posture and composition of one or multiple objects inside an image, while preserving its original characteristics. Our method can make a standing dog sit down or jump, cause a bird to spread its wings, etc. — each within its single high-resolution natural image provided by the user.
Contrary to previous work, our proposed method requires only a single input image and a target text (the desired edit). It operates on real images, and does not require any additional inputs (such as image masks or additional views of the object).
Easy placement/movement of 3D primitives -> realistic/illustrative rendering has long struck me as extremely promising. Using tech like StyleGAN to render from 3D can produce interesting results, but it’s been difficult to bring the level of quality & consistency up to what Adobe users demand.
Now with Stable Diffusion (and, one hopes, other diffusion models in the future) attached to Blender (and, one hopes, other object manipulation tools), the vision is getting closer to reality:
Check out a fun historical find from Adobe evangelist Paul Trani:
The video below shipped on VHS with the very first version of Adobe Illustrator. Adobe CEO & Illustrator developer John Warnock demonstrated the new product in a single one-hour take. He was certainly qualified, being one of the four developers whose names were listed on the splash screen!
How lucky it was for the world that a brilliant graphics engineer (John) married a graphic designer (Marva Warnock) who could provide constant input as this groundbreaking app took shape.
If you’re interested in more of the app’s rich history, check out The Adobe Illustrator Story:
“My whole life has been one long ultraviolent hyperkinetic nightmare,” wrote Mark Leyner in “Et Tu, Babe?” That thought comes to mind when glimpsing this short film by Adam Chitayat, stitched together from thousands of Street View images (see Vimeo page for a list of locations).
I love the idea—indeed, back in 2014 I tried to get Google Photos to stitch together visual segues that could interconnect one’s photos—but the pacing here has my old man brain pulling the e-brake after just some short exposure. YMMV, so here ya go:
Easily my favorite thing at Google was getting to work with stone-cold geniuses like Noah Snavely (one of the minds behind Microsoft’s PhotoSynth) and Richard Tucker. Now they & their teammates have produced some jaw-dropping image synthesis tech:
And “hold onto your papers,” as here’s a look into how it all works:
With the update that starts rolling out today, you’ll see more videos — including the best snippets from your longer videos that Photos will automatically select and trim so you can relive the most meaningful moments. Even your still photos will feel more dynamic thanks to a subtle zoom that brings movement to your memories. And to bring it all together, next month we’ll start adding instrumental music to some Memories.
Happily, they’ve finally built a subset of the collage editor I spec’d out eight years ago (🧂🤷🏼).
Soon, you’ll begin to see full Cinematic Memories that transform multiple still photos into an end-to-end cinematic experience, taking you back to that moment in time. Cinematic Memories will also have music, making your photos feel a little more like a movie.
And interestingly, one need not create a complex lens in order to have it pay off:
“The research found that simple AR can be just as performant as a sophisticated, custom Lens in driving both upper and lower-funnel metrics like brand awareness and purchase intent. Brands with the resources to execute a more sophisticated Lens will see additional benefits in mid-funnel brand metrics, including favorability and consideration.”
Well… kinda? I’m feeling somewhat hoodwinked, though. The new cam promises 72-megapixel captures, compared to 18 from its predecessor. This happens via some kind of 4x upsampling, it appears, and at least right now that’s incompatible with shooting HDR images.
Thus, as you can see via the comparisons below & via these original images, I was able to capture somewhat better detail (e.g. look at text) at the cost of getting worse tonal range (e.g. see the X2 lying on top of the book).
I need to carve out time to watch the tutorial below on how to wring the best out of this new cam.
The system uses images with descriptions to learn what the world looks like and how it is often described. It also uses unlabeled videos to learn how the world moves. With this data, Make-A-Video lets you bring your imagination to life by generating whimsical, one-of-a-kind videos with just a few words or lines of text.
Whew—no more wheedling my “grand-mentee” Joanne on behalf of colleagues wanting access. 😅
Starting today, we are removing the waitlist for the DALL·E beta so users can sign up and start using it immediately. More than 1.5M users are now actively creating over 2M images a day with DALL·E—from artists and creative directors to authors and architects—with over 100K users sharing their creations and feedback in our Discord community.
We are currently testing a DALL·E API with several customers and are excited to soon offer it more broadly to developers and businesses so they can build apps on this powerful system.
It’s hard to overstate just how much this groundbreaking technology has rocked our whole industry—all since publicly debuting less than 6 months ago! Congrats to the whole team. I can’t wait to see what they’re cooking up next.
Depending on how well it works, tech like this could be the greatest unlock in 3D creation the world has ever known.
The company blog post features interesting, promising details:
Though quicker than manual methods, prior 3D generative AI models were limited in the level of detail they could produce. Even recent inverse rendering methods can only generate 3D objects based on 2D images taken from various angles, requiring developers to build one 3D shape at a time.
GET3D gets its name from its ability to Generate Explicit Textured 3D meshes — meaning that the shapes it creates are in the form of a triangle mesh, like a papier-mâché model, covered with a textured material. This lets users easily import the objects into game engines, 3D modelers and film renderers — and edit them.
The Corridor Crew has been banging on Stable Diffusion & Google’s new DreamBooth tech (see previous) that enables training the model to understand a specific concept—e.g. one person’s face. Here they’ve trained it using a few photos of team member Sam Gorski, then inserted him into various genres:
From there they trained up models for various guys at the shop, then created an illustrated fantasy narrative. Just totally incredible, and their sheer exuberance makes the making-of pretty entertaining: