Technologies

Here’s What I Learned Testing Photoshop’s New Generative AI Tool

Adobe’s Firefly AI feature brings new fun and fakery to photos. It’s a profound change for image editing, though far from perfect.

Adobe has bulit generative AI abilities into its flagship image-editing software, releasing a Photoshop beta version Tuesday that dramatically expands what artists and photo editors can do. The move promises to release a new torrent of creativity even as it gives us all a new reason to pause and wonder if that sensational, scary or inspirational photo you see on the internet is actually real.

In my tests, detailed below, I found the tool impressive but imperfect. Adding it directly to Photoshop is a big deal, letting creators experiment within the software tool they’re likely already using without excursions to Midjourney, Stability AI’s Stable Diffusion or other outside generative AI tools.

With Adobe’s Firefly family of generative AI technologies arriving in Photoshop, you’ll be able to let the AI fill a selected part of the image with whatever it thinks most fitting – for example, replacing road cracks with smooth pavement. You can also specify the imagery you’d like with a text prompt, such as adding a double yellow line to the road.

Firefly in Photoshop also can also expand an image, adding new scenery beyond the frame based on what’s already in the frame or what you suggest with text. Want more sky and mountains in your landscape photo? A bigger crowd at the rock concert? Photoshop will oblige, without today’s difficulties of finding source material and splicing it in.

The feature, called generative fill and scheduled to emerge from beta testing in the second half of 2023, can be powerful. In Adobe’s live demo, the tool was often able to match a photo’s tones, blend in AI-generated imagery seamlessly, infer the geometric details of perspective even in reflections and extrapolate the position of the sun from shadows and sky haze.

Such technologies have been emerging over the last year as Stable Diffusion, Midjourney and OpenAI’s Dall-Ecaptured the imaginations of artists and creative pros. Now it’s built directly into the software they’re most likely to already be using, streamlining what can be a cumbersome editing process.

«It really puts the power and control of generative AI into the hands of the creator,» said Maria Yap, Adobe’s vice president of digital imaging. «You can just really have some fun. You can explore some ideas. You can ideate. You can create without ever necessarily getting into the deep tools of the product, very quickly.»

But you can’t sell anything yet. With Firefly technology, including what’s produced by Photoshop’s generative fill, «you may not use the output for any commercial purpose,» Adobe’s generative AI beta rules state.

Photoshop’s Firefly AI imperfect but useful

In my testing, I frequently ran into problems, many of them likely stemming from the limited range of the training imagery. When I tried to insert a fish on a bicycle to an image, Firefly only added the bicycle. I couldn’t get Firefly to add a kraken to emerge from San Francisco Bay. A musk ox looked like a panda-moose hybrid.

Less fanciful material also presents problems. Text looks like an alien race’s script. Shadows, lighting, perspective and geometry weren’t always right.

People are hard, too. On close inspection, their faces were distorted in weird ways. Humans added into shots could be positioned too high in the frame or in otherwise unconvincingly blended in.

Still, Firefly is remarkable for what it can accomplish, particularly with landscape shots. I could add mountains, oceans, skies and hills to landscapes. A white delivery van in a night scene was appropriately yellowish to match the sodium vapor streetlights in the scene. If you don’t like the trio of results Firefly presents, you can click the «generate» button to get another batch.

Given the pace of AI developments, I expect Firefly in Photoshop will improve.

It’s hard and expensive to retrain big AI models, requiring a data center packed with expensive hardware to churn through data, sometimes taking weeks for the largest models. But Adobe plans relatively frequent updates to Firefly. «Expect [about] monthly updates for general improvements and retraining every few months in all likelihood,» Adobe product chief Scott Belsky tweeted Tuesday.

Automating image manipulation

For years, «Photoshop» hasn’t just referred to Adobe’s software. It’s also used as a verb signifying photo manipulations like slimming supermodels’ waists or hiding missile launch failures. AI tools automate not just fun and flights of fancy, but also fake images like an alleged explosion at the Pentagon or a convincingly real photo of the pope in a puffy jacket, to pick two recent examples.

With AI, expect editing techniques far more subtle than the extra smoke easily recognized as digitally added to photos of an Israeli attack on Lebanon in 2006.

It’s a reflection of the double-edged sword that is generative AI. The technology is undeniably useful in many situations but also blurs the line between what is true and what is merely plausible.

For its part, Adobe tries to curtail problems. It doesn’t permit prompts to create images of many political figures and blocks you for «safety issues» if you try to create an image of black smoke in front of the White House. And its AI usage guidelines prohibit imagery involving violence, pornography and «misleading, fraudulent, or deceptive content that could lead to real-world harm,» among other categories. «We disable accounts that engage in behavior that is deceptive or harmful.»

Firefly also is designed to skip over styling prompts like that have provoked serious complaints from artists displeased to see their type of art reproduced by a data center. And it supports the Content Authenticity Initiative‘s content credentials technology that can be used to label an image as having been generated by AI.

Today, generative AI imagery made with Adobe’s Firefly website add content credentials by default along with a visual watermark. When the Photoshop feature exists beta testing and ships later this year, imagery will include content credentials automatically, Adobe said.

People trying to fake images can sidestep that technology. But in the long run, it’ll become part of how we all evaluate images, Adobe believes.

«Content credentials give people who want to be trusted a way to be trusted. This is an open-source technology that lets everyone attach metadata to their images to show that they created an image, when and where it was created, and what changes were made to it along the way,» Adobe said. «Once it becomes the norm that important news comes with content credentials, people will then be skeptical when they see images that don’t.»

Generative AI for photos

Adobe’s Firefly family of generative AI tools began with a website that turns a text prompt like «modern chair made up of old tires» into an image. It’s added a couple other options since, and Creative Cloud subscribers will also be able to try a lightweight version of the Photoshop interface on the Firefly site.

When OpenAI’s Dall-E brought that technology to anyone who signed up for it in 2022, it helped push generative artificial intelligence from a technological curiosity toward mainstream awareness. Now there’s plenty of worry along with the excitement as even AI creators fret about what the technology will bring now and in the more distant future.

Generative AI is a relatively new form of artificial intelligence technology. AI models can be trained to recognize patterns in vast amounts of data – in this case labeled images from Adobe’s stock art business and other licensed sources – and then to create new imagery based on that source data.

Generative AI has surged to mainstream awareness with language models used in tools like OpenAI’s ChatGPT chatbot, Google’s Gmail and Google Docs, and Microsoft’s Bing search engine. When it comes to generating images, Adobe employs an AI image generation technique called diffusion that’s also behind Dall-E, Stable Diffusion, Midjourney and Google’s Imagen.

Adobe calls Firefly for Photoshop a «co-pilot» technology, positioning it as a creative aid, not a replacement for humans. Yap acknowledges that some creators are nervous about being replaced by AI. Adobe prefers to see it as a technology that can amplify and speed up the creative process, spreading creative tools to a broader population.

«I think the democratization we’ve been going through, and having more creativity, is a positive thing for all of us,» Yap said. «This is the future of Photoshop.»

Editors’ note: CNET is using an AI engine to create some personal finance explainers that are edited and fact-checked by our editors. For more, see this post.

Technologies

Today’s NYT Mini Crossword Answers for Monday, May 19

Here are the answers for The New York Times Mini Crossword for May 19.

Looking for the most recent Mini Crossword answer? Click here for today’s Mini Crossword hints, as well as our daily answers and hints for The New York Times Wordle, Strands, Connections and Connections: Sports Edition puzzles.

Today’s NYT Mini Crossword is pretty easy. 5-Across, «one for whom every day is Boxing Day,» stumped me because I really wanted the answer to have something to do with cats. (Spoiler: It did not.) Need some help with today’s Mini Crossword? Read on. And if you could use some hints and guidance for daily solving, check out our Mini Crossword tips.

The Mini Crossword is just one of many games in the Times’ games collection. If you’re looking for today’s Wordle, Connections, Connections: Sports Edition and Strands answers, you can visit CNET’s NYT puzzle hints page.

Read more: Tips and Tricks for Solving The New York Times Mini Crossword

Let’s get at those Mini Crossword clues and answers.

Mini across clues and answers

1A clue: Network satirized on «30 Rock,» for short
Answer: NBC

4A clue: Sport played on horseback
Answer: POLO

5A clue: One for whom every day is Boxing Day?
Answer: MOVED

6A clue: Like correct letters in Wordle
Answer: GREEN

7A clue: Blend together
Answer: MELD

Mini down clues and answers

1D clue: «Invisible Man» or «Little Women»
Answer: NOVEL

2D clue: Run in the wash
Answer: BLEED

3D clue: What bourbon whiskey is primarily made from
Answer: CORN

4D clue: Tiny hole in the skin
Answer: PORE

5D clue: Longtime movie studio acquired by Amazon in 2022
Answer: MGM

How to play more Mini Crosswords

The New York Times Games section offers a large number of online games, but only some of them are free for all to play. You can play the current day’s Mini Crossword for free, but you’ll need a subscription to the Times Games section to play older puzzles from the archives.

Technologies

Today’s NYT Connections: Sports Edition Hints and Answers for May 19, #238

Hints and answers for the NYT Connections: Sports Edition puzzle, No. 238, for May 19.

Looking for the most recent regular Connections answers? Click here for today’s Connections hints, as well as our daily answers and hints for The New York Times Mini Crossword, Wordle and Strands puzzles.

Connections: Sports Edition might be tough today if, like me, you don’t know what «loge» means. Read on for hints and the answers.

Connections: Sports Edition is out of beta now, making its debut on Super Bowl Sunday, Feb. 9. That’s a sign that the game has earned enough loyal players that The Athletic, the subscription-based sports journalism site owned by the Times, will continue to publish it. It doesn’t show up in the NYT Games app but now appears in The Athletic’s own app. Or you can continue to play it free online.

Read more: NYT Connections: Sports Edition Puzzle Comes Out of Beta

Hints for today’s Connections: Sports Edition groups

Here are four hints for the groupings in today’s Connections: Sports Edition puzzle, ranked from the easiest yellow group to the tough (and sometimes bizarre) purple group.

Yellow group hint: Brag.

Green group hint: Where’s my seat?

Blue group hint: City that never sleeps.

Purple group hint: Opposite of go.

Answers for today’s Connections: Sports Edition groups

Yellow group: Boast

Green group: Stadium seating sections

Blue group: New York Knicks

Purple group: ____ stop

Read more: Wordle Cheat Sheet: Here Are the Most Popular Letters Used in English Words

What are today’s Connections: Sports Edition answers?

The yellow words in today’s Connections

The theme is boast. The four answers are crow, gloat, grandstand and showboat.

The green words in today’s Connections

The theme is stadium seating sections. The four answers are bleacher, loge, suites and upper deck.

The blue words in today’s Connections

The theme is New York Knicks. The four answers are Bridges, Hart, McBride and Towns.

The purple words in today’s Connections

The theme is ____ stop. The four answers are back, jump, pit and short.

Technologies

Blade Runner: 18-Rotor «Volocopter» Moving from Concept to Prototype

It may look "nutty" and like a "blender," but the designers say the craft could challenge helicopters

Inventor and physicist Thomas Senkel created an Internet sensation with the October 2011 video of his maiden—and only—test flight of a spidery proof-of-concept 16-rotor helicopter dubbed Multicopter 1. Now the maker of the experimental personal aviation craft, the European start-up e-volo, is back with a revised «volocopter» design that adds two more rotors, a serial hybrid drive and long-term plans for going to 100 percent battery power.

The new design calls for 1.8-meter, 0.5-kilogram carbon-fiber blades, each paired with a motor. They are arrayed around a hub in two concentric circles over a boxy one- or two-person cockpit.

After awarding the volocopter concept a Lindbergh Prize for Innovation in April, Yolanka Wulff, executive director of The Charles A. and Anne Morrow Lindbergh Foundation, admitted the idea of the multi-blade chopper at first seems «nutty.» Looking beyond the novel appearance, however, she says, e-volo’s concept excels in safety, energy efficiency and simplicity, which were the bases of the prize.

All three attributes arrive thanks largely to evolo’s removal of classic helicopter elements. First, the energy-robbing high-mass main rotor, transmission, tail boom and tail rotor are gone. The enormous blades over a normal chopper’s cabin create lift, but their mass creates a high degree of stress and wear on the craft. And the small tail rotor, perched vertically out on a boom behind the cabin, keeps the helicopter’s body from spinning in the opposite direction as the main blades, but it also eats up about 30 percent of a helicopter’s power.

The volocopter’s multiple rotor blades individually would not create the torque that a single large rotor produces, and they offer redundancy for safety. Hypothetically, the volocopter could fly with a few as 12 functioning rotors, as long as those rotors were not all clustered together on one side, says Senkel, the aircraft’s co-inventor and e-volo’s lead construction engineer.

Without the iconic two-prop configuration, the craft would be lighter, making it more fuel efficient and reducing the physical complexity of delivering power to the top and rear blades from a single engine. Nor would the volocopter need an energy-hungry transmission. In fact, «there will be no mechanical connection between the gas engine and the blades,» Senkel says. That means fewer points of energy loss and more redundancy for safety.

E-volo’s design eliminates the dependence on a single source of power to the blades. As a serial-hybrid vehicle, the volocopter would have a gas-fueled engine, in this case an engine capable of generating 50- to 75 kilowatts, typical of ultralight aircraft. Rather than mechanically drive the rotors, the engine would generate power for electric motors as well as charge onboard lithium batteries. Should it fail, the batteries are expected to provide enough backup power so the craft could make a controlled landing.

Whereas helicopters navigate by changing the pitch of the main and tail rotor blades, the volocopter’s maneuverability will depend on changing the speed of individual rotors. Although more complex, it is more precise in principle to control a craft using three to six redundant microcontrollers (in case one or more fails) interpreting instructions from a pilot using a game console–like joystick—instead of rudder pedals, a control stick and a throttle.

Wulff’s first impression about the volocopter’s design is not uncommon. E-volo’s computer-animated promotional videos of a gleaming white, carbon-fiber and fiberglass craft beneath a thatch of blades recall the many-winged would-be flying machines of the late 19th century. This point is not lost on Senkel.

«I understand these skeptical opinions,» he says. «The design concept looks like a blender. But we really are making a safe flying machine.»

That would be progress in itself. Multicopter 1 looked like something from an especially iffy episode of MacGyver, complete with landing gear that involved a silver yoga ball. Senkel rode seated amid all those rotors powered only by lithium batteries. Multicopter 1 generated an average of 20 kilowatts for hovering and was aloft for just a few minutes.

There’s a reason why the experimental craft flew briefly and only once.Senkel describes that first craft as «glued and screwed together.» Seated on the same platform as the spinning blades, he says, «I was aware of the fact that I will be dead, maybe. Besides, we showed that the concept works. What do we win if we fly it twice?» he asks rhetorically.

Other than putting the pilot safely below the blades, the revised volocopter design would operate largely the same as the initial prototype. The design calls for three to six redundant accelerometers and gyroscopes to measure the volocopter’s position and orientation, creating a feedback loop that gives the craft stability and makes it easier to fly, Senkel says.

The volocopter’s revised prototype under construction could debut as soon as next spring. The first production models, available in perhaps three years, are expected to fly for at least an hour at speeds exceeding 100 kilometers per hour and a minimum altitude of about 2,000 meters, still far shy of standard helicopter’s normal operating altitude of about 3,000 meters. «This could change our lives, but I don’t expect anything like that for 10 years,» Senkel adds.

Given that most of the technology needed to build the volocopter is already available, «this idea is fairly easy to realize,» says Carl Kühn, managing director of e-volo partner Smoto GmbH, a company that integrates electric drive systems and related components.

Like Senkel, Kühn has modest short-term expectations despite his repeated emphasis on the standard nature of the technology involved. «I guess that e-volo will have [a prototype] aircraft in three years that can do the job—that it will lift one or two persons from one point to another,» he says.

The biggest immediate limitations appear to be regulatory. For instance, European aviation regulators consider any electrical system greater than 60 volts to be high voltage and regulate such systems more aggressively, Kühn says. As a result, the volocopter will operate below that threshold. The craft will also need to weigh no more than 450 kilograms to remain in the ultralight category, which is likewise subject to fewer government aviation regulations, according to Senkel.

The Lindbergh Foundation’s Wulff says the organization’s judges felt e-volo had «a greater than 50 percent chance of succeeding, or they wouldn’t have given them the innovation award.» Asked if she would line up to fly one someday, she says, «I sure would. It looks very compelling to me.»