Now this is exactly the kind of thing I want to help bring into the world—not just because it’s delightful unto itself, but because it shows how AI-enabled tools can make the impossible possible, rather than displacing or diminishing artists’ work. It’s not like in some earlier world a talented team would’ve made this all by hand: 99% likely, it simply wouldn’t exist at all.
The 1% exception is exemplified by SNL’s brilliant Anderson parody from a few years back—all written, scouted, shot, and edited in ~3 days, but all requiring the intensive efforts of an incredibly skilled crew. (Oh, and it too features a terrific Owen Wilson spoof.)
My Adobe Research teammates & their collaborators at Berkeley have devised an interesting way to represent objects in scenes—not via sharply defined segments, but via more diffuse blobs. This enables some trippy editing techniques and results. Check it out in action:
I always love a good dive into learning not just the what and the how of how things—in this case materials from the US federal government—was designed, but why things were done that way.
This video’s all about the briefly groovy period in which Federal designers let it all hang out. From the NASA Worm, to the EPA’s funkadelic graphics, to, heck, the Department of Labor acting like it just took mushrooms, this was an unquestionably adventurous period. And then it stopped. What went wrong?
The Federal Graphics Improvement Program was an NEA initiative started under Richard Nixon, and its brief reign inspired design conventions, logo revamps, and graphics standards manuals. But it was also just a cash infusion rather than a bureaucratic overhaul. And as a result, we only remember toasty Federal Graphic Design, rather than enjoy its enduring legacy.
And for a deeper dive, check out his 20-minute version:
Meanwhile my color-loving colleague Hep (who also manages the venerable color.adobe.com) joined me for a live stream on Discord last Friday. It’s fun to see her spin on how best to apply various color harmonies and other techniques, including to her own beautiful illustrations:
I had a ball presenting Firefly during this past week’s Adobe Live session. I showed off the new Recolor Vectors feature, and my teammate Samantha showed how to put it to practical use (along with image generation) as part of a moodboarding exercise. I think you’d dig the whole session, if you’ve got time.
The highlight for me was the chance to give an early preview of the 3D-to-image creation module we have in development:
Today, Adobe is unveiling new AI innovations in the Lightroom ecosystem — Lightroom, Lightroom Classic, Lightroom Mobile and Web — that make it easy to edit photos like a pro, so everyone can bring their creative visions to life wherever inspiration strikes. New Adobe Sensei AI-powered features empower intuitive editing and seamless workflows. Expanded adaptive presets and Masking categories for Select People make it easy to adjust fine details from the color of the sky to the texture of a person’s beard with a single click. Additionally, new features including Denoise and Curves in masking help you do more with less to save time and focus on getting the perfect shot.
To start, we’re exploring a range of concepts, including:
Text to color enhancements: Change color schemes, time of day, or even the seasons in already-recorded videos, instantly altering the mood and setting to evoke a specific tone and feel. With a simple prompt like “Make this scene feel warm and inviting,” the time between imagination and final product can all but disappear.
Advanced music and sound eﬀects: Creators can easily generate royalty-free custom sounds and music to reflect a certain feeling or scene for both temporary and final tracks.
Stunning fonts, text effects, graphics, and logos: With a few simple words and in a matter of minutes, creators can generate subtitles, logos and title cards and custom contextual animations.
Powerful script and B-roll capabilities: Creators can dramatically accelerate pre-production, production and post-production workflows using AI analysis of script to text to automatically create storyboards and previsualizations, as well as recommending b-roll clips for rough or final cuts.
Creative assistants and co-pilots: With personalized generative AI-powered “how-tos,” users can master new skills and accelerate processes from initial vision to creation and editing.
Adobe prototyper Lee Brimelow has been happily distracting himself by creating delightful little creatures using Firefly, like this:
Today he joined us for a live stream on Discord (below), sharing details about his explorations so far. He also shared a Google Doc that contains details, including a number of links you can click in order to kick off the creation process. Enjoy, and please let me know what kinds of things you’d like to see us cover in future sessions.
Terry White vanquished a chronic photographic bummer—the blank or boring sky—by asking Firefly to generate a very specific asset (namely, an evening sky at the exact site of the shoot), then using Photoshop’s sky replacement feature to enhance the original. Check it out:
On Thursday I had the chance to talk with folks via a Discord livestream, demoing vector recoloring enhancements (not yet shipping, but getting close), talking about how we evaluate feature requests, showing some early thinking about saving presets, talking about “FM technology” (F’ing Magic), and more. Check it out if you’re interested:
I promise I don’t have this stupid look on my face all the time. 😅
Wouldn’t it be amazing to make and composite things like this right in Photoshop? I can’t speak for that team, of course, but it’s easy to imagine ways that one might put the proverbial chocolate into the peanut butter.
A couple of weeks ago I got the chance to attend Runway’s inaugural AI Film Fest in San Francisco, from which the team has now posted the winners. Numerous entries are well worth a look, and I thought I’d highlight a couple of my favorites here (with perhaps more to come later).
“Checkpoint,” below, offers a concise & stylish intro to the emerging domain of AI-assisted storytelling. I particularly like the new-to-me phrase “cultural ratcheting”:
I also vibed out with the sheer propulsive, explosive energy of “Generation”:
And if you want a deeper dive into What This All Might Mean, check out a recording of the panel discussion that accompanied the debut session in New York:
Yikes—my ability to post got knocked out nearly a week ago due to a WordPress update gone awry. Hopefully things are now back to normal & I can resume sharing bits of the non-stop 5-alarm torrent of rad AI-related developments that land every day. Stay tuned!