Creative Director Alexia Adana constantly explores new expressive tech & writes thoughtfully about her findings. I was kind of charmed to see her deploying the latest tools to form sort of a self-promotional AI herald (below), riding ahead with her tidings:
The team at BFL is celebrating some of the most interesting, creative uses of the Flux model. Having helped bring the Vanishing Point tool to Photoshop, and always having been interested in building more such tech, this one caught my eye:
Best Overall Winner
Perspective Control using Vanishing Points (jschoormans) Just like Renaissance artists who start with perspective grids, this Kontext LoRa lets you control the exact perspective point in AI-generated images. pic.twitter.com/phAY41KYdP
Back when I worked in Google Research, my teammates developed fast models divide images & video into segments (people, animals, sky, etc.). I’m delighted that they’ve now brought this tech to Snapseed:
The new Object Brush in Snapseed on iOS, accessible in the “Adjust” tool, now lets you edit objects intuitively. It allows you to simply draw a stroke on the object you want to edit and then adjust how you want it to look, separate from the rest of the image.
Check out the team blog post for lots of technical details on how the model was trained.
The underlying model powers a wide range of image editing and manipulation tasks and serves as a foundational technology for intuitive selective editing. It has also been shipped in the new Chromebook Plus 14 to power AI image editing in the Gallery app. Next, we plan to integrate it across more image and creative editing products at Google.
I was pleasantly surprised to see my old Google Photos manager David Lieb pop up in this brief clip from Y Combinator, where he now works, discussing how the current batch of AI-enabled apps somewhat resembles the original “horseless carriages.” It’s fun to contemplate what’ll come next.
“A few weeks ago,” writes John Gruber, “designer James Barnard made this TikTok video about what seemed to be a few mistakes in HBO’s logo. He got a bunch of crap from commenters arguing that they weren’t mistakes at all. Then he heard from the designer of the original version of the logo, from the 1970s.”
Check out these surprisingly interesting three minutes of logo design history:
@barnardco “Who. Cares? Unfollowed” This is how a *lot* of people responded to my post about the mistake in the HBO logo. For those that didn’t see it, the H and the B of the logo don’t line up at the top of the official vector version from the website. Not only that, but the original designer @Gerard Huerta700 got in touch! Long story short, we’re all good, and Designerrrs™ community members can watch my interview with Gerard Huerta where we talk about this and his illustrious career! #hbo#typography#logodesign#logo#designtok original sound – James Barnard
As much as one can be said to enjoy thinking through the details of how to evaluate AI (and it actually can be kinda fun!), I enjoyed this in-depth guide from Hamel Husain & Shreya Shankar.
All year I’ve been focusing pretty intently on how to tease out the details of what makes image creation & editing models “good” (e.g. spelling, human realism, prompt alignment, detail preservation, and more). This talk pops up a level, focusing more on holistic analysis of end-to-end experiences. If you’re doing that kind of work, or even if you just want to better understand the kind of thing that’s super interesting to hiring managers now, I think you’ll find watching this to be time well spent.
I’m so happy to see Adobe greatly accelerating the pace of 3p API integrations!
FLUX.1 Kontext [Pro] is now in Photoshop!
Starting today, creators worldwide can use FLUX.1 Kontext [Pro] directly inside @Photoshop – no more switching between apps or manually exporting files.
Microsoft VP Aparna Chennapragada, who recruited me to Microsoft after I reported to her at Google, recently wrote a thoughtful piece about building trust through transparency. Specifically around AI agents, we want less of this…
…and more of this:
I agree completely. Having some thoughtful back-and-forth makes me feel better understood & therefore more confident in my assistant’s work.
And feel here is a big deal. As Maya Angelou said, “People won’t remember what you said, or even what you did, but they’ll remember how you made them *feel*. Microsoft AI leader (and previously DeepMind cofounder) Mustafa Suleyman totally gets this.
Conversely, I just saw a founder advertising his product as “visual storytelling on autopilot.” I get the intent, but I find the phrasing oxymoronic: would any worthwhile “story” be generated by autopilot? Yuck.
When apps try to do too much with my sparse input, seeing the results makes me feel like Neven Mrgan did upon receiving AI-generated slop from a friend: “I was repelled, as if digital anthrax had poured out of the app.” I don’t even want to read such content, much less share it, much less be judged on it.
So yeah, apps: ditch autopilot & instead take the time to show interest & ask good questions. “Slow is smooth, and smooth is fast”—and a little thoughtfulness up front will save me time while increasing my pride of ownership.
In addition to adding support for vertical video & greater character consistency, the new Veo-powered storytelling tool now includes direct image creation & manipulation via tiny, tiny fruit:
This new feature… it’s bananas
You can now edit and refine your images directly in Flow using prompts. @NanoBanana maintains the likeness of a subject or scene across different lighting, environments, artistic styles, and more.
This paper seems really promising. From textbooks it promises to make:
— Mind maps if you think visually — Audio lessons with simulated teacher conversations — Interactive timelines — Quizzes that change based on where you’re struggling
BREAKING: Google Research just dropped the textbook killer.
Its called “Learn Your Way” and it uses LearnLM to transform any PDF into 5 personalized learning formats. Students using it scored 78% vs 67% on retention tests.
— Artificial Intelligence (AI) • ChatGPT (@chatgptricks) September 22, 2025
More details:
This is going to revolutionize education
Google just launched “Learn Your Way” that basically takes whatever boring chapter you’re supposed to read and rebuilds it around stuff you actually give a damn about.
In today’s episode Ammaar Reshi shows exactly how he uses AI to prototype ideas for the new Google AI Studio. He shares his Figma files and two example prototypes (including how he vibe-coded his own version of AI Studio in a couple of days). We also go deep into:
— 4 lessons for vibe-coding like a pro — When to rely on mockups vs. AI prototypes — Ammaar’s step-by-step process for prompting — How Ammaar thinks about the fidelity of his prototypes — a lot more
Apropos of the song featured in my previous post, in case you haven’t already beheld the ludicrous majesty of the Peacemaker Season 2 intros, well, stop cheating yourself!
Better still, here’s a peek behind the scenes of creating this inspired mayhem:
“Yes, And”: It’s the golden rule of improv comedy, and it’s the title of the paper I wrote & circulated throughout Adobe as soon as DALL•E dropped 3+ years ago: yes, we should make our own great models, and of course we should integrate the best of what the rest of the world is making! I mean, duh, why wouldn’t we??
This stuff can take time, of course (oh, so much time), but here we are: Adobe has announced that Google’s Nano Banana editing model will be coming to a Photoshop beta build near you in the immediate future.
Side note: it’s funny that in order to really upgrade Photoshop, one of the key minds behind Firefly simply needed to quit the company, move to Google, build Nano Banana, and then license it back to Adobe. Funny ol’ world…
It’s time to peel back a sneak and reveal that Nano Banana (Gemini 2.5 Flash Image) floats into Photoshop this September!
Soon you’ll be able to combine prompt-based edits with the power of Photoshop’s non-destructive tools like selections, layers, masks, and more! pic.twitter.com/CSLgJYVsHo
Check out this new work from Alex Patrascu. As generative video tools continue to improve in power & precision, what’ll be the role of traditional apps like After Effects? ¯\_(ツ)_/¯
Liquid Logos
With the right prompt, anything is possible with AI video today.
If you want to utilize the full power of Start/End frames (Kling or Hailuo), you can make the first frame empty with tour desired color and describe what happens until the last frame is revealed.
Now that Google’s Nano Banana model has dropped, I felt like revisiting the challenge, comparing results to the original plus ones from ChatGPT 4o.
As you can see in the results, 4o increases realism relative to DALL•E, but it loses a lot of expressiveness & soul. Nano Banana manages to deliver the best of both worlds.
Rob de Winter is back at it, mixing in Google’s new model alongside Flux Kontext.
Rob notes,
From my experiments so far: • Gemini shines at easy conversational prompting, character consistency, color accuracy, understanding reference images • Flux Kontext wins at relighting, blending, and atmosphere consistency
And yes, I do feel like I’m having a stroke when I type our actual phrases like that. 🙂 But putting that aside, check out the hairstyling magic that can come from pairing Google’s latest image-editing model with an image-to-video system:
Want to try a new haircut? Check out this AI workflow:
1. upload a selfie & prompt your desired haircut 2. uses Nano Banana to generate your haircut 3. then Kling 2.1 morphs from old you to new you 4. Claude helping behind the scenes with all the prompts
Nearly a decade ago now (good grief), my entree to working with the Google AI team was in collaborating with Peyman Milanfar & team to ship a cool upsampling algorithm in Google+ (double good grief) and related apps. Since then they’ve continued to redefine what’s possible, and on the latest Pixel devices, zoom now extends to an eye-popping 100x. Check out this 7-second demo:
I’d seen some eye-popping snippets of the Google XR team’s TED talk a few months back, but until now I hadn’t watched the whole thing. It’s well worth doing so, and I truly can’t process the step change in realtime perceptual capabilities that has recently arrived in Gemini:
A recent Time Magazine cover featuring Zohran Mamdani made me recall a super interesting customer visit I did years ago with photographer Gregory Heisler. Politics aside, this is a pretty cool peek behind the curtains on the making of an epic image:
As for the Mamdani shoot, it sounds quite memorable unto itself—for incredibly different reasons:
was reading the photogs substack and ive seen a lot of tricks on set but ive got to say i did not see this one coming lmfao pic.twitter.com/9pHbkIe9z0
“Coming first to Pixel 10 in the U.S., you can simply describe the edits you want to make by text or voice in Photos’ editor, and watch the changes appear. And to further improve transparency around AI edits, we’re adding support for C2PA Content Credentials in Google Photos.”
Because this is an open-ended, conversational experience, you don’t have to indicate which tools you want to use. For example, you could ask for a specific edit, like “remove the cars in the background” or something more general like “restore this old photo” and Photos will understand the changes you’re trying to make. You can even make multiple requests in a single prompt like “remove the reflections and fix the washed out colors.”
Turntable is now available in the Adobe #Illustrator Public Beta Build 29.9.14!!!
A feature that lets you “turn” your 2D artwork to view it from different angles. With just a few steps, you can generate multiple views without redrawing from scratch.
Given that I’m thinking ahead to photographing air shows this fall, here’s a short, sweet, and relevant little tutorial on creating realistic motion blur on backgrounds:
A couple of weeks ago I saw Photoshop trainer Rob de Winter experimenting with integrating ChatGPT’s image model into Photoshop, much as I’d been quietly colluding with Christian Cantrell to do three years ago using DALL•E (long before Firefly existed, when Adobe was afraid to do anything in the generative space).
I suggested that Rob try using Flux Kontext, and he promptly whipped up this free plugin. Check out the results:
From Rob’s site:
This custom-made Flux Kontext JSX-plugin lets you create context-aware AI edits directly inside Photoshop, based on your selection and a short prompt. Your selection is sent to Replicate’s Flux Kontext models (Pro or Max), and the result is placed back as a new layer with a mask, keeping lighting, shadows, and materials consistent.
Watching the face-swapping portion of Jesús’s otherwise excellent demo above made me wince: this part of Photoshop’s toolbox just hasn’t evolved in years and years. It’s especially painful for me, as I returned to Adobe in 2021 to make things like this better. Despite building some really solid tech, however, we were blocked by concerns about ethics (“What if a war criminal got access to this?”; yes, seriously). So it goes.
Maybe someday PS will update its face-related features (heck, for all I know they’re integrating a new API now!). In the meantime, here’s a nice 4-minute tour of how to do this (for free!) in Ideogram:
Wow—well, you sure can’t fault these guys for beating around the bush: video creator Higgsfield has introduced a browser extension that lets you click any image, then convert it to video & create related images. For better or worse, here’s how it works (additional details in thread):
this should be banned..
AI now can clone any ad, change the actor, keep the brand and make it yours
Jesús Ramirez is a master Photoshop compositor, so it’s especially helpful to see his exploration of some of the new tool’s strengths & weaknesses (e.g. limited resolution)—including ways to work around them.
The AI generator—of which I’ve been a longtime fan—has introduced the ability to upload a single image of a person (or cat!), then use it in creating images. It’s hard to overstate just how long people have wanted this kind of control & simplicity.
For a deeper look, here’s a quick demo from the team:
The app promises to let you turn static images into short videos and transform them into fun art styles, plus explore a new creation hub.
I’m excited to try it out, but despite the iOS app having been just updated, it’s not yet available—at least for me. Meanwhile, although I just bit the bullet & signed up for the $20/mo. plan, the three video attempts that Gemini allowed me today all failed. ¯\_(ツ)_/¯
