Taking a person out of the middle of a group shot isn't something I'd do this way. If it were my picture I'd be in Photoshop, on layers, doing it properly by hand, because that's what I know and that's what gives me control over every last bit of it.

But that's me, and I've spent years getting comfortable in there. Plenty of people haven't, and don't want to, and have no particular reason to. So this post isn't really for photographers who already live in Photoshop. It's for everybody else.

Who this is actually for

If you edit in Lightroom and that's where you're happy, this is for you. If you don't have Photoshop installed and can't see the point in paying for something you'd open twice a year, this is for you as well. If you've had a go at layers and masks and found the whole thing off-putting, same again.

It doesn't have to be for professional work either. Most of the time it won't be. It's the family photo where somebody's stood in the middle who you'd rather wasn't, the holiday shot that would be lovely if it were just the four of you, the picture you want to get printed and stick on the wall. That's a perfectly good reason to want this, and there's no sense in learning a whole other application for it.

Why the Remove tool struggles here

Lightroom has Generative Remove built in and for everyday bits it's brilliant. A bin in the background, a stray sign, someone wandering through the far side of the frame, it deals with all of that without any fuss.

Ask it to take a whole person out of the middle of a group, though, and it tends to come unstuck. You get warped detail where the arms and hands were, limbs that seem to belong to nobody, and a strange empty space where the person was stood. Everybody else stays exactly where they were, which is really the giveaway. The gap is the problem, not the person.

Sending it over to Firefly

What you can do instead, without leaving your catalogue, is push the photo across to Adobe Firefly and let it rebuild that part of the frame.

It works like this.

go to the Photo menu in Lightroom
choose Generate in Firefly, then Edit photo
pick your model in the panel at the bottom
set the output quality to High
write your prompt
hit Generate

I tried a few models and GPT Image 2 gave me the most natural result of the lot. Worth trying a couple yourself, because they behave differently on the same picture.

The prompt is doing most of the work

This is the part that decides whether it works, so it's worth slowing down over.

A vague prompt gets you a vague result. Tell it to remove the person and that's all it'll do, which puts you straight back where you started with a hole in the middle of the photo. What you want is to describe the finished picture, not the job.

So ask for three things. Remove the person. Close the space between the people either side of them. Keep the original faces, clothing and background as they are. That last one is the bit most people leave out, and it's why results come back with faces that look subtly wrong and nobody quite able to say what's changed.

Say all three plainly, in a sentence or two, then generate.

Getting the resolution back

Firefly gives you a clean result, but a smaller one than you sent it. The original here was over 6000 pixels wide straight out of the camera, so there's one more step before you're done.

On the left hand toolbar there's an Upscale option. Take it up by 4x and you're back over 6000 pixels wide, which matches the original file. Hit Download, bring it back into your catalogue, and carry on editing it like any other frame.

That's it. No layers, no masks, no learning a second application.

What you're trading

I'd be doing this differently, and it's worth being honest about what that means. Doing it by hand in Photoshop gives you control over every pixel, and if the picture really matters, that control is the reason to learn it. Handing it to Firefly means accepting whatever it decides to give you, and sometimes that'll be a couple of goes before you get something you're happy with.

For a lot of pictures, though, that's a fine trade. You get the photo you wanted, in the software you already use, in about two minutes.

Have a watch of the video above if you'd rather see it happen than read about it. It goes quicker than it sounds.

Recently, Steven Gotz, a member of the Photography Community on SKOOL ( LINK ), sent over a brilliant RAW file of a condor. Stunning subject, great light, one problem: a massive fence running right through the background.

Rather than leave it on the shelf, I figured it was the perfect excuse to put the latest updates in Lightroom and Photoshop Beta through their paces. What would have taken ages with the Clone Stamp tool a couple of years ago can now be sorted in seconds. Here's exactly how I did it, using two different workflows.

Workflow 1: Photoshop Beta with Firefly Image 5

This is the quickest route right now, and the results are genuinely impressive.

The key is using the new Firefly Image 5 (Preview) model inside Photoshop Beta. It's been built specifically for editing while preserving detail, which matters a lot when you're dealing with complex textures like feathers and rocky backgrounds.

From Lightroom to Photoshop Beta. Right-click the image in Lightroom and choose Edit In > Adobe Photoshop Beta.
Select All. Once you're in Photoshop, go to Select > All. This gives the AI the full context of the frame before you do anything.
Switch to Firefly Image 5. Click Generative Fill in the contextual taskbar. Here's the bit that matters: don't use the standard model. Switch it to Firefly Image 5 (Preview) from the dropdown.
The prompt. This model needs a prompt to work, unlike some of the others. I kept it simple: "remove the fence from this picture."
Refine the detail. The AI did a great job on the background, but because Firefly Image 5 currently outputs at 2K, the fine detail around the bird's eye and feathers was slightly softer than the original RAW. The fix is straightforward: use the Object Selection Tool to select the bird and the rock, then fill that area on the layer mask with black. That reveals the sharp original bird while keeping the AI-cleared background intact.

Workflow 2: Lightroom to Firefly Web

Not on the Photoshop Beta? No problem. You can get to the same place via Lightroom's sharing feature.

Share to Firefly. In Lightroom, hit the Share button (top right) and select Firefly: Edit an image. This opens your browser and drops the photo straight into the Adobe Firefly web interface.
Settings and generate. Select Firefly Image 5, bump the resolution to 2K, use the same prompt ("remove the fence from this picture"), and hit generate.
Back to Photoshop. Download the cleaned image, go back to Lightroom, and open the original file in the regular version of Photoshop.
Stack and align. Use File > Place Embedded to bring the Firefly-cleaned version in on top of your original. Rasterise the top layer, select both layers, then go to Edit > Auto-Align Layers to make sure everything lines up perfectly.
The masking trick. Same principle as Workflow 1: use the Object Selection Tool to select the bird and the rock, then hold Option (Mac) or Alt (Windows) and click the mask icon. This hides the AI version of the bird and brings back the sharp, high-detail original underneath.

Why the masking step matters

This is the part I think is really important. It's not about letting AI take over the whole image. It's about using it to fix a specific problem, in this case the background, while keeping the actual subject exactly as it was captured in the RAW file. The integrity of the original is what you're protecting.

Have a look through your archives. Chances are there are shots you wrote off because of something in the background. It might be worth giving them another look.

Removing People in Lightroom When You Don't Use Photoshop