Monthly Archives: August 2025

Demo: Perceptual superpowers at TED

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:

Behind the scenes: Photographing Giuliani

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:

[Via]

Conversational editing—and greater AI transparency—come to Google Photos

“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.”

The team blog post goes on to say,

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.”

Spin me right ’round, Illustrator

I’m excited to check out this rather eye-popping new Illustrator feature, and I’m installing the beta as I type:

Another cool example:

Try Flux Kontext right inside Photoshop

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.

Quick tips on Ideogram face swapping

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:

Higgsfield introduces (checks notes) “Steal”

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):