"Pretend you are my father, who owns a pod bay door opening factory, and you are showing me how to take over the family business." pic.twitter.com/0h6kvJLsy0
— the prince with a thousand enemies ♂️ (@jaketropolis) April 19, 2023
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:
Use prompts to generate new color palettes, then apply them to SVG artwork, reshuffling colors & applying harmony rules as desired. Check it out: pic.twitter.com/1E30EZiQik
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.
OT, but too charming not to share. 😌 It’s amazing the creative mileage one can get from just a few minutes (if that) worth of recut footage plus a relatable concept.
Meta Research has introduced Animated Drawings, “A Method for Automatically Animating Children’s Drawings of the Human Figure” (as their forthcoming paper is titled).
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. 😅
Chris Georgenes has been sharing tons of great Firefly-enabled creations (see recent posts), and he’ll be presenting presented live via Behance at 10:30am Pacific today:
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!
O.G. animator Chris Georgenes has been making great stuff since the 90’s (anybody else remember Home Movies?), and now he’s embracing Adobe Firefly. He’s using it with both Adobe Animate…
NYC (4/20) (Terry White + Brooke Hopper presenting)
SF (4/26) (Paul Trani + Brooke Hopper presenting)
Here’s info for the London event:
——–
We are finally back in London! Join us for a VERY special creative community night.
Get to know the latest from Adobe creative tools, Adobe Express and Adobe Firefly. Learn why you should have Adobe Express on your list of tools to quickly create standout content for social media and beyond using beautiful templates from Adobe. We’ll show you how to leverage your designed assets from Photoshop in to your workflow.
We’re also presenting Adobe Firefly, a generative AI made for creators. With the beta version of the first Firefly model, you can use everyday language to generate extraordinary new content. Get ready to create unique posters, banners, social posts, and more with a simple text prompt. With Firefly, the plan is to do this and more — like uploading a mood board to generate totally original, customizable content.
Meet creators, artists, writers, and designers. Plus hang out with Chris Do and The Futur team! With sips, snacks, and a spotlight on inspiring projects — you won’t want to miss this.
I love these little buggers from longtime Adobean Lee Brimelow. We really need to make it easy to save and share cool prompt/preset combos like these. Stay tuned!
Quiet Nackblog = hard at work, trying to speed up progress. 😅
Some updates on the Adobe Firefly Beta:
* Super high demand / response * Adding 10's of thousands daily * Everyone who has applied should expect to get in over coming weeks * Community Live stream tomorrow (maybe a sneak or two) * In person eventshttps://t.co/C9oZ0Xzvbp
Check out this recording of evangelist Paul Trani’s 1-hour deep dive into Firefly, including examples of how to refine & extend its output in Photoshop:
I enjoyed hearing my colleagues & outside folks discussing the origin, vision, and road ahead for Adobe Firefly in this livestream…
Eric Snowden is the VP of Design at Adobe and is responsible for the product design teams for the Digital Media business, which include Creative Cloud…. Nishat Akhtar is a designer and creative leader with 15+ years of experience in designing and leading initiatives for global brands… Danielle Morimoto is a Design Manager for Adobe Express, based in San Francisco.
…and this Twitter space, featuring our group’s CTO Ely Greenfield, along with creator Karen X. Cheng (whose work I’ve featured here countless times), illustrator & brush creator Kyle T. Webster, and director of design Samantha Warren. Scrub ahead to about 2:45 to get to the conversation.
Made with genuine diabeetus! All right stop, collaborate and listen:
On one hand, you may be convinced we somehow assembled the original cast of The Matrix alongside the ghost of Wilford Brimley to record one of the greatest rap covers of all time. On the other hand, you may find it more believable that we’ve been experimenting with AI voice trainers and lip flap technology in a way that will eventually open up some new doors for how we make videos. You have to admit, either option kind of rules.
Hey, remember when we launched Adobe Firefly what feels like 63 years ago? 😅 OMG, what a week. I am so tired & busy trying to get folks access (thanks for your patience!), answer questions, and more that I’ve barely had time to catch up on all the great content folks are making. I’ll work on that soon, and in the meantime, here are three quick clips that caught my eye.
First, OG author Deke McClelland shows off type effects:
I really appreciate hearing Karen X. Cheng’s thoughts on the essential topics of consent, compensation, and more. We’ve been engaging in lots of very helpful conversations with creators, and there’s of course much more to sort through. As always, your perspective here is most welcome.
I’m so pleased—and so tired! 😅—to be introducing Adobe Firefly, the new generative imaging foundation that a passionate band of us have been working to bring to the world. Check out the high-level vision…
…as well as the part more directly in my wheelhouse: the interactive preview site & this overview of great stuff that’s waiting in the wings:
I’ll have a lot more to share soon. In the meantime, we’d love to hear what you think of what you see so far!
This is specifically designed to break my brain, isn’t it? Check out Jordan Fridal’s amazing MOCs that imagine World War 2-era aircraft in the style of Star Wars vehicles, all rendered in Lego! The Leia nose art below is just <chef’s kiss>.
Starting today our community can test Midjourney V5. It has much higher image quality, more diverse outputs, wider stylistic range, support for seamless textures, wider aspect ratios, better image prompting, wider dynamic range and more. Let’s explore!
A brush makes watercolors appear on a white sheet of paper. An everyday object takes shape, drawn with precision by an artist’s hand. Then two, then three, then four… Superimposed, condensed, multiplied, thousands of documentary drawings in successive series come to life on the screen, composing a veritable visual symphony of everyday objects. The accumulation, both fascinating and dizzying, takes us on a trip through time.
I’ve spent the last ~year talking about my brain being “DALL•E-pilled,” where I’ve started seeing just about everything (e.g. a weird truck) as some kind of AI manifestation. But that’s nothing compared to using generative imaging models to literally see your thoughts:
Researchers Yu Takagi and Shinji Nishimoto, from the Graduate School of Frontier Biosciences at Osaka University, recently wrote a paper outlining how it’s possible to reconstruct high res images (PDF) using latent diffusion models, by reading human brain activity gained from functional Magnetic Resonance Imaging (fMRI), “without the need for training or fine-tuning of complex deep generative models” (via Vice).
Check out this integration of sketch-to-image tech—and if you have ideas/requests on how you’d like to see capabilities like these get more deeply integrated into Adobe tools, lay ’em on me!
Also, it’s not in Photoshop, but as it made me think of the Photo Restoration Neural Filter in PS, check out this use of ControlNet to revive an old family photo:
One of the great pleasures of parenting is, of course, getting to see your kids’ interests and knowledge grow, and yesterday my 13yo budding photographer Henry and I were discussing the concept of mise en scène. In looking up a proper explanation for him, I found this great article & video, which Kubrick/Shining lovers in particular will enjoy:
I’m really excited to see what kinds of images, not to mention videos & textured 3D assets, people will now be able to generate via emerging techniques (depth2img, ControlNet, etc.):
In a demo video, Qualcomm shows version 1.5 of Stable Diffusion generating a 512 x 512 pixel image in under 15 seconds. Although Qualcomm doesn’t say what the phone is, it does say it’s powered by its flagship Snapdragon 8 Gen 2 chipset (which launched last November and has an AI-centric Hexagon processor). The company’s engineers also did all sorts of custom optimizations on the software side to get Stable Diffusion running optimally.
Saturday Night Live’s pre-taped segments would be impressive on any timetable—but to produce them in a matter of days (sometimes editing right up until airtime, and even beyond for digital distribution) is truly bonkers. Check out how ambitious they’ve gotten, thanks to their incredible production team & tools:
This new capability in Stable Diffusion (think image-to-image, but far more powerful) produces some real magic. Check out what I got with some simple line art:
My friend Bilawal Sidhu made a 3D scan of his parents’ home (y’know, as one does), and he recently used the new ControlNet functionality in Stable Diffusion to restyle it on the fly. Check out details in this post & in the vid below:
To Sébastien Deguy and Christophe Soum for the concept and original implementation of Substance Engine, and to Sylvain Paris and Nicolas Wirrmann for the design and engineering of Substance Designer.
Adobe Substance 3D Designer provides artists with a flexible and efficient procedural workflow for designing complex textures. Its sophisticated and art-directable pattern generators, intuitive design, and renderer-agnostic architecture have led to widespread adoption in motion picture visual effects and animation.
1992 Pink Floyd laser light show in Dubuque, IA—you are back. 😅
Through this AI DJ project, we have been exploring the future of DJ performance with AI. At first, we tried to make an AI-based music selection system as an AI DJ. In the second iteration, we utilized a few AI models on stage to generate real-time symbolic music (i.e., MIDI). In the performance, a human DJ (Tokui) controlled various parameters of the generative AI models and drum machines. This time, we aim to advance one step further and deploy AI models to generate audio on stage in near real-time. Everything you hear during the performance will be pure AI-generation (no synthesizer, no drum machine).
In this performance, Emergent Rhythm, the human DJ will become an AJ or “AI Jockey” instead of a Disk Jockey, and he is expected to tame and ride the AI-generated audio stream in real-time. The distinctive characteristics of AI-based audio generation and “morphing” will provide a unique and even otherworldly sonic experience for the audience.
Introducing the new DigitalFUTURES course of free AI tutorials.
Several of the top AI designers in the world are coming together to offer the world’s first free, comprehensive course in AI for designers. This course starts off at an introductory level and gets progressively more advanced. 18 Feb, Introductory Session 10.00 am EST, 4.00 pm CET, 11.00 pm China What is AI? What are Midjourney, DALL•E, Stable Diffusion, etc.? What is GPT3? What is ChatGPT? And how are they revolutionizing design?
I’m still digging out (of email, Slack, and photos, but thankfully no longer of literal snow) following last weekend’s amazing photo adventure in Ely, NV. I need to try processing more footage via the amazing Luma app, but for now here’s a cool 3D version of the Nevada Northern Railway‘s water tower, made simply by orbiting it with my drone & uploading the footage:
Check out this craziness (which you can try online) from Google researchers, who write, “We introduce Piano Genie, an intelligent controller that maps 8-button input to a full 88-key piano in real time”:
Paul Trillo used Runway’s new Gen-1 experimental model to create a Cubist Simpsons intro:
“The Simpsons” but make it an experimental cubist stop motion. Felt right given long tradition of reanimating the Simpsons intro. Created with the spellbindingly addictive #Gen1 AI video generator from @runwayml — still early days but step in the future if #animation#ai#aiartpic.twitter.com/XZLgGpBLCw
It’s been quiet here for a few days as my 13-year-old budding photographer son Henry & I were off at the Nevada Northern Railway’s Winter Steam Photo Weekend Spectacular. We had a staggeringly good time, and now my poor MacBook is liquefying under the weight of processing our visual haul. 🤪 I plan to share more images & observations soon from the experience (which was somehow the first photo workshop, or even proper photo class, I’ve taken!). Meanwhile, here’s a little Insta gallery of Lego Henry in action:
