A lot of people have been asking for this feature. Ever since Adobe added the ability to generate masks of people, faces and different parts of people to Lightroom and Camera RAW, Ive received a ton of communication from the community. “When will this feature be in Photoshop??” Well.. here it is!

Written steps coming soon

Hope you enjoy,

Drop a comment

Colin

The post Auto Select people and features in Photoshop appeared first on PhotoshopCAFE.

The new Generative Workspace makes it easy and quick to generate ai images in Photoshop via firefly.

You can batch process bulk images as well as use variables. Check it out in the video.

Full written steps coming soon!

Colin

The post How to use Generative Workspace in Photoshop appeared first on PhotoshopCAFE.

As many people are aware, Photoshop used to support a pretty decent 3D feature set. These were beefed up in Photoshop CS6 Extended and continued through CC for a number of years. See tutorials on Photoshop 3D here. Adobe started to retire these features because of changes in Direct X and other technologies. This tutorial, shows how to keep legacy 3D working in Photoshop.

I think the most common way people used it, was to composite 3D objects into Photoshop. The advantage of 3D is the ability to change the angle and lighting to make everything match perfectly. Another thing I loved about the 3D was the ability to animate different properties.

3D is back, but in a different way. By Using the new Substance 3D viewer, you are able to position your objects, light and texture them in a much more powerful way than before. You can even generate 3D objects from text. What you don’t have is the ability to interact with the 3D objects, directly in Photoshop, nor the ability to animate the 3D. All that said, for compositing, the results are better than ever, lets take a look.

Getting Set up

At the time of this writing (it will change in the future), this feature is only supported in the Beta Version of Photoshop.

In the creative Cloud App, choose apps>beta and install Photoshop.

You will also need to install Substance 3D viewer beta. This will also install a plugin in Photoshop beta.

Free 3D library

While you are in Creative Cloud app, click on 3D & AR

You will see Substance 3D assets. Click to go to the page, it will open in your web browser.

Here you can download a number of different assets, including models, procedural textures and lighting models. I clicked on the sofa and choose download.

Open an image in Photoshop and Drag and drop the 3D model into Photoshop.

It will appear as a Smart Object layer.

Either double click the smart object, or choose Edit Contents

Substance 3D viewer will appear with your composition in the window.

You can easily position and scale the 3D object, by right, left or middle mouse button dragging. (More in the video at the top).

Position the object. Click to Photoshop and the image in Photoshop will update to match what you see here. This is where the nice integration takes place.

Choose the environment button on the left-bar. (lightbulb icon). Now you can adjust the Lighting to match the angle of the photograph.

Click on light presets to change the lighting environment, you can also load in your own HDR image and use that. This sets the light color and reflections.

Click the texture icon. This is where you change the textures and materials (a material is a texture preset). Here I increased the roughness to make the cushions look more like velvet. You can change many things about the textures.

You can choose a different diffuse color, here we made the cushions red.

If you want to use once of the material presets. click on Material presets and a panel will appear.

Drag the material onto the object. Here I used a velvet preset.

Notice a blue bar appears and says:

Replace all instances: Which will replace all the cushions, or whatever objects are grouped together, or

Apply to all Objects: Will apply the material to the entire 3D model.

Notice all the cushions receive the new preset.

All the properties can be changed including the color. We went for red again, as it matches this scene nicely.

If you choose the bottom-left icon this takes you to the generative window. Here I added the text prompt Victorian Ballroom. Substance uses the 3D object (this is the way I positioned it in 3D space) and generates a background based on the prompt. I made a tut on generative ai and 3D in Substance viewer here.

When you are happy with your 3D model, click the Ray tracing button to render it.

When happy, click To Photoshop in the top Right.

Go back to Photoshop and the image is updated to Match what’s in Substance viewer. To change it, go back to Substance viewer, or double click the smart object. It’s really easy and fun.

Hopefully you found this week’s free Photoshop tutorial useful!

Great to see you here at the CAFE.

Colin

PS Don’t forget to follow us on Social Media for more tips..

• Instagram
• Youtube.
• facebook
• twitter

(I've been posting some fun Instagram and Facebook Stories lately)
You can get my free Layer Blending modes ebook along with dozens of exclusive Photoshop Goodies here

The post How to use 3D in Photoshop with Adobe Substance 3D Viewer appeared first on PhotoshopCAFE.

Photoshop has just received a major update. I show you how to use the most important new features.

I will add the written steps soon, right now, this is a transcript of my video, watch the video and see what new.

00:42 Auto remove people 

02:49 Auto Remove Wires and Cables

04:17 Firefly 3 in Generative Fill

05:07 Firefly 3 in Generative Expand

06:00 Remove Background , Generate Background 

06:49 Batch Generate, Generative Workspace

Adobe has just updated Photoshop to Photoshop 2025. This is the annual big update where all the stuff comes together. I’ve made videos and other tutorials. I’ll link to them on how to do that update and make sure you can find the latest version. Now we’re going to look at the new features right now. And some of these features you might have seen before in beta, and now they’ve moved into the main Photoshop version. There’s going to be some features you have never seen before. They’re brand new. Now, I’m just going to touch I’m going to run everything very quickly in this video so you get an overview, bird’s-eye view, so to speak, of what’s new. And I’m going to be doing separate tutorials on these main new features and really digging into them. So let’s start with remove distraction, which is now in the main Photoshop. So if we go to the remove tool, which you’re going to find over here. If you don’t see the remove tool or you don’t see any tools, by the way, just go click on this little three-dont menu and hold, and then you’ll get customized toolbar.

And you’ll probably see the missing tools are here. And then just hit restore defaults, and then you’re good to go. All right, let’s get rid of these people in the background. So if we choose find distractions, it’s going to have the ability to choose people. So what it will do is it will highlight the people. If you wanted to keep one of these people, you would just paint over it with the minus key or just hold down the alt or the option key as you paint. If you wanted to also remove him, Just paint over him. And then when you’re happy with the people that you want to remove, just hit this little checkmark here. And now it will do the process of removing them using generative fill. Now, notice it wasn’t great. And that’s because we’ve got generative AI turned off. This is another new feature. Now we have the ability to use generative AI in here. So if we turn this on, now we’re going to force it to use generative AI, and we should get a better result. Let’s try it again. And let’s apply it. And as you can see there, now we get a much better result.

Now, you’re not going to get any variations. It’s automatically going to choose the best variation. Another thing to bear in mind is if we set this to auto, that means, generally speaking, when the area selected is larger than 1,000 pixels by 1,000, it’s going to use generative AI all the time. If that area is smaller, it’s not always going to use generative AI, which means that we can remove small distractions very quickly and easily without using generative AI or worrying about using those generative credits. Now, this also works with poles and wires. Now, I’ve done another video on this. We really went crazy and we just did the whole test. So in the other video, we just tested this and pushed it to the extreme. Check that out. I’ll link it. So the best way to use this is to create a new layer first. And then on that new layer, make sure you choose sample all layers. Otherwise, nothing will happen. Then we’re going to choose find distractions. This time we’re going to use wires and cables. Now, I did another video on this where I really went in-depth with this and pushed it hard.

And if you’re wondering what happened about the crack in, yes, you can apply it a second time and it will make it better. If you don’t know what I’m talking about, check out that video. I’ll add a link to it. And boom, look at that. It does a really good job of getting rid of it. However, we lost some of our subject here. And this is why you would want to use it on a layer. Because if we go in here and And we choose that layer and then we apply a layer mask, we can just grab a brush here, and let’s make it a high edge brush. I’m hitting the left bracket key to make it smaller. Let’s make that brush about the size of the wood there. Make sure we select the layer mask, Opacity, Flow, 100. And then what we’re going to do is we’re going to click right there and then just release. Now move to where you want that to end. Hold down that shift key. Make So you do it in exactly this order. Now click. And then what it’s going to do is it’s going to draw a straight line in between the two of these.

The reason that works is because we were just painting with black. And if you’re getting any value out of this video, hit that subscribe button, turn on notifications. You won’t miss any of my videos. All right, another thing that has changed is the generative fill is now using Firefly version 3 model. And yes, this makes a huge difference. Let me demonstrate. So I’m going to grab the Lasso And by the way, this is also in the main shipping version of Photoshop. So I’m just going to make a selection around that path. And maybe I didn’t quite go wide enough. Let’s go wider. And I want cobblestones on here. So why don’t we choose the Generate a Fill, and we’re going to type in cobbled path. And now we’re just going to hit Generate. And if you look at the result here, look at this. This is a massive improvement over what we were getting with the previous model. It’s just much, much nicer looking. Let’s also test it with generative expand, which is also now using Firefly version 3. So we’re going to grab our crop tool, and then we’re going to make sure for Phil that we’re using Generative Expand.

And let’s just drag it out a little bit and see how well it does with this cat. I just hit the Enter key, by the way. Well, that might be a little weird. There we go. A two-headed cat, just what we were looking for. Or if we grab that third variation, saved by the bell, that one works quite well. The other two, well, that’s interesting. I’m definitely going to say interesting. Maybe it’s two cats, but yeah, this is looking pretty good. One of the things you’ll notice, too, is there’s a bigger difference now between the variations with the Model 3 versus before. Previously, the variations were very similar. So here’s another one that’s interested, and that’s Generate Background. So what we’re going to do is we’re just going to choose Remove Background. And notice the background is now gone. We can go into the mask and we can clean it up. It does need some cleanup, but that’s a tutorial for another day, and we’re going to choose Generate Background. So let’s generate something else. Like maybe we want to be at the beach. Okay. So it’s generating some interesting-looking backgrounds. And once again, notice the variety of results we’re getting.

I think this is definitely the coolest one. And if we are worried about areas like here where we did lose a little bit of her shirt, we can just grab that mask. We’re going to grab a white brush and then just do some good old fashioned masking and we can just paint that back. All right, now I’m going to show something really cool. This one is brand new, and this particular one is just in the beta version at the moment. But if we go under the Edit menu, we have this generative workspace. Now this is brand new. And the generative workspace is really cool because what I can do is I can just type in a prompt, but we can do so much more than that. Let’s try a rock drummer in a band on stage in front of an audience. And we’re going to hit Generate. But the nice thing about this is while it’s generating, we can actually generate more than one at a time. So maybe we wanted to do something like a rock guitarist. And now I can hit Generate. And what it’s doing is it’s batch processing It’s actually stacking these up and doing one at a time.

So notice that we hit the rock drum that was actually at the bottom. There’s our drum, there’s our guitarists. And we can go through these and we can check them all out. That’s a lot of drumsticks. Now, these are not looking incredibly great, right? And I’ll tell you why. The reason is we’re actually in fast mode so we can quickly generate. So what you can do is you can try out your prompts, and then when you find something that’s working for you, we can change And if we’re going to change this from the fast mode to the normal, then we’re going to hit Generate. It’s going to take a little bit longer. Let’s go back into our list view. This time it’s going to take a little longer, but we’re going to get better quality. So that fast mode is a great way to just compound a bunch of different prompts to test it. And let’s have a look at this. And as you can see here, the quality of these are better than what we were getting. But the cool thing about this is we can actually do variables now. Let’s say a woman in a red T-shirt at the mall.

Let’s go back into the fast mode and we’re just going to hit Generate. Okay, so here we go. Now we’ve got a woman here in a red T-shirt at the mall. But what if we wanted to try maybe different colored shirts or maybe we wanted to try different locations? This is where we can use variables. So say right now we’re doing a red T-shirt. I can click on Add variable. Well, let’s do red. We’re going to do a comma, white, black, and say green. So now this is going to generate different variables, and it’s going to generate versions with the red shirt, a white shirt, black shirt, green shirt. And notice it also got some other settings here that we can change here. We can change the aspect ratio. So if we wanted more square, we could grab it there. We can use a reference image here. With this, we can go into effects here. So we want photo or art. We’re going to choose photo. And you’ve We’ve seen some of these before. Maybe we’ll do something cinematic. And now we’re going to hit Generate, and now it’s going to generate 16 different images, but they’re going to happen quickly because it’s in the fast mode.

But notice this. This saves you time when you’re experimenting, you’re trying some different things. And as we can see here, we got some red shirts, some white shirts. That’s not a T-shirt, but that’s all right. We got black, green. And as you can see now, we’re getting a bunch of variations in there We’re using these variables. And this can just save a whole ton of time. Now, I could have a woman in the mall. I could create another variable, a man. I could change the mole. I could do another variable. Let’s do this. And this is I’m going to do it manually. Let’s do Beach. And I’m just going to do one variation so it doesn’t get too nuts. And let’s just get rid of the… Well, we’ll do red and white just to speed up so we don’t get too many variables because otherwise it will generate all of these, but it’s going to take a while. So now we’re getting 16. So now we’re going to get the woman with the red shirt at the beach and at the mall. And we’re going to get a woman with a white shirt at the beach and at the mall.

And here we go. There she is with the white shirt. She’s at the mall. Now she is at the white shirt. She’s at the beach. Red shirt at the mall, red shirt at the beach. And so I think you get the general idea of how this can save us time. And I’ll do a a dedicated tutorial on this when we dig into a lot more of the options more in-depth. So I hope you enjoyed this video to give you an introduction to the new features. Keep your eyes open for more in-depth videos from me on some of these features and drop a comment. Let me know what is your favorite new feature, and what features would you love to see me dig more in-depth and just really dig into them and go deep with them. And by the way, if you’re new, welcome to the cafe. This is Photoshop Cafe. I’m Colin. Welcome. Hit that subscribe button, turn on notifications, and you won’t miss any of my tutorials. And until next time, I’ll see you at the cafe.

The post Photoshop 2025 New Features appeared first on PhotoshopCAFE.

The selection brush tool, is a tool that makes selections. Unlike the other selection tools, you just brush this on like a paintbrush, it’s very easy to use. If you have used the selection brush and know Photoshop fairly well, you will notice it’s similar to Quick Mask. If you have never used the selection brush, it’s ok, we will go through ti here along with all its features. We will also look at quick mask and suggest which is the best way to go for different tasks.

How to use the Selection Brush Tool

Choose the tool from the toolbar.

Paint. You will see a colored brush stroke.

When you choose a different tool, the colored stroke will turn into a selection.

If you choose the Selection tool again, the selection will turn into the brush stoke once again.

When the selection is active, it’s the same as any selection. You can combine it with other selection tools.

Hold Shift to add to the selection. Hold Alt/Option to remove from the selection.

When you are in the Brush tool, also

Size Hold Alt/Option to remove from the selection.

When you choose the setection tool, the selection will turn back to the colored strokes.

Shortcuts or hotkeys help. (L-key), chooses the selection tool, choose another tool, like move tool (V-Key) to toggle a selection.

There are 2 brush settings

Size ( [ or ] bracket keys)

Hardness (Shift + [ or] brackets)

Being able to create a soft edges selection is unique to this tool. (and Quick Mask, we will discuss soon)

Using the Selection Brush Tool

Lets remove a distraction from the photo.

You can paint freehand to make a selection. Or use this trick to paint straight lines quickly.

With the tool selection, click at the start point.

Release

Hold Down Shift

(Still holding Shift), Click at the end of the line

A line will be drawn between the 2 points.

I used that trick to select the steel girder.

Click on Generative Fill in the Contextual Task Bar.

Leave it blank and click Generate.

The distraction has been removed.

Using the Selection Brush tool with Density

Let’s make a little art using the density art trick. Learn how to make art with ai and density in Photoshop here

Lower the brush Opacity to around 20%

Choose a different overlay color. Here we chose Green.

Paint over the portion of the image you want to change.

In the task bar, click Generate and then enter something like oil painting, or watercolor in the prompt and click on Generate.

You get an oil painting effect

Lower the Opacity of the layer to make the effect more subtle.

Cutting Out tress with Selection Brush and Quick Mask

A difficult task for many people is cutting out trees. I have tutorials on removing background from trees. 

Without going through all the steps. They are on the video at the top.

Choose Select>Color Range

Use the eyedropper to select the sky.

Use the + eyedropper to add to the selection

Move fuzziness to get the best isolation of the selected area.

Click ok

You get a selection of the sky.

Cmd+Shift+I to inverse the selection.

Choose the selection Brush. See the overlay.

Paint on the areas that got missed.

Go back to a selection.

You may notice, it’s really hard to see the tiny areas that are missed in the field.

Ok, here’s a better way. Continuing where we are.

Using Quick Mask to refine selections

With the marching ants selection active, Click on the Quick Mask tool, to press the Q key.

You will see a similar overlay, but probably a different color than Selection Brush.

If you double click the Quick Mask tool, you will see you can choose any color and also opacity.

Now with 100% opacity, it’s easier to see the missed areas than with the Selection Brush.

But, it gets even better.

Open the Channels and notice the Quick Mask channel has been created.

Turn off the visibility eye from RGB

Now you can see a black and white mask.

Paint with black and white to clean up the mask. Much easier now. You can also combine other selection tools inside Quick mask.

Press the Q key to go back to a selection. Just like the Selection Brush, you toggle between a selection and painting.

The Quick Mask tool also lets you use any brush you like as well as supporting Pen Pressure.

Quick Mask is more powerful, and is my choice. If you are newer, you may find the Selection Brush easier. So you have options. The selection brush is sometimes quicker for quick fixes and selecting things to use with generative fill.

I have a few tutorials on How to use Quick Mask, here is one. 

Just to finish our task. If you click the mask icon to hide the background we can see the quality of our selection.

I dropped a blue solid behind it to let you see the quality of the cutout.

This is the same image, but using Select Sky. As you can see the other method is more work, but a better result.

I hope you found this week’s free tutorial useful.Thanks

Colin

PS Don’t forget to follow us on Social Media for more tips..

• Instagram
• Youtube.
• facebook
• twitter

(I've been posting some fun Instagram and Facebook Stories lately)
You can get my free Layer Blending modes ebook along with dozens of exclusive Photoshop Goodies here

The post How to use Selection brush in Photoshop and Quick mask in Photoshop appeared first on PhotoshopCAFE.

In some cases, these features have already appeared in the beta version of Photoshop and I have already made tutorials on them. In those cases, I’ll provide a brief overview of the feature here, so this tutorial is complete. I will also provide a link to th more in-depth tutorial, so you can learn the feature in more detail.

Selection Brush Tool

This feature is entirely new(ish). While it’s a new feature, the Selection Brush is just basically a dumbed down version of Quick Mask.

You use the selection Brush, to paint on a selection. When you choose another tool, the painted area will be turned into a section. What makes this tool unique, is its ability to create a soft edged selection, and also with a different level of transparency. (This can also be done with Quick Mask, but with more control). The selection brush has no edge detection and works like a paintbrush.

The Selection Brush is nested with the lasso tool.

At the top, you can chan choose transparency as well as brush softness.

Paint on the image where you want to make a selection.

If you choose a different tool, the pink area will turn into a section.

In this case, lets do something more interesting to highlight the soft edges selection.

Click on new layer mask

A mask is created with a soft edge and also semi transparent.

You can see this makes in interesting looking mask.

Let’s inverse the mask, Click on the layer masks

Ctrl/Cmd+I to invert it.

Choose another image and drag it into the tab on the image we are working on.

This enables us to combine images into a collage. See how the soft edges selection works in this case.

Here is a basic tutorial on combining images and making collages in photoshop if you don’t know how to do this.

Using the Selection Brush with Generative Fill

Here is a more useful way to use the selection brush.

Lower the opacity to 20%

Paint in the area you want to generate a shark.

In the Contextual Task Bar, type in Shark and click Generate.

Because the Brush opacity was reduced to 20% it generates a low density, making the shark appear underwater.

In my opinion, this tool is a bit redundant and you are better off learning how to use Quick mask Tool. But it’s easy for beginners, who may get some use out of it.

Adjustment Brush updates

I have made tutorials on the Photoshop Adjustment Brush before. But is has some updates here.

First, it’s been places into its own slot in the toolbar. It used to be nested with the Brush tool. The problem with the nesting, when you tap the B key for Brush, you would get the Adjustment brush instead of the paintbrush and this messed up workflows, as well as actions.

Now you have options in the Taskbar including Brush hardness and size. (I’m still hoping for pen pressure).

Paint on your photo to apply the adjustment.

To be a little blunt, I sort of Group this tool with the Selection brush, a bit redundant for users other than new users, as the Adjustment Layer Masks can do the same thing with more control.

But here is a different way the Adjustment Brush works that is useful.

If you want to extend the adjustment, choose the Object selection tool and make a selection.(You can see this on the video at the top).

The adjustment is automatically extended to the selected area.

Shapes, strokes and fill

The shape tools have a boost and the features are available in the Task Bar, making this once-annoying floating bar a little more useful and endearing itself with more users. Let me know in the comments, do you like the task bar?

Grab the rectangular shape tool. Make sure you have shape as the option at the top left of the top toolbar.

Make a selection.

Notice you can change the fill and stoke colors, as well as change the roundness by dragging on the dots in the corners.

Tap the curve in the task bar and notice you can also change the corner roundness here.

If you desire, you can change the roundness of individual corners.

Bullets and Numbering

This simple feature appears to be the favorite of a lot of people, myself included.

When you make text lists, you had to manually create bullets with the circle tool and align them to the image. No longer!

With the type tool active, Click the tool options.

Look at the bottom left corner of the Paragraph panel.

Make sure you select your type first.

Click on Bullets and lookie!

It’s small, but huge at the same time and long overdue.

If you chose numbers, it will add a numbered list, or convert the bullets to numbers.

Enhance image on Generative Fill

When you use Generative fill, you get a maximum resolution of 1024px x 1024px stretched out over the Generated area. This tool is added from Photoshop beta and now in shipping version.

If the generated area is larger than 1k, you will see an icon in the variation Thumbnail. Click this to enhance the appearance of the generated pixels.

I have created and entire tutorial on Enhancing resolution on Generative Fill, where I show you exactly what this does and how it works, as well as tips to boost the resolution in any generated image.

Text To image, Generate Image

This next feature, is also moved over from Photoshop Beta, aka the real Version of Photoshop (Shipping? They don’t actually ship) or whatever we are calling the regular version of Photoshop.

At the bottom of the toolbar you will see a new icon. If the icon is missing, here’s the fix

The new icon is for Generate Image, or Text to Image. You have to have a document open for this to work. If it’s grayed out, create a new document first, or open an existing one.

Here you can generate images from text prompts and they are using Adobe Firefly version 3.

I’m not going Ito this as I show how it works on the video, and I have previously made an in-detail tutorial on Photoshop Generative Image/ Text to Image. 

Hopefully this article was useful and helped you get up to date on the newest Photoshop Features. In case you didn’t know, I have an archive of ALL the Photoshop and Lightroom features as they were added in the Superguide. See what features you may have missed.

Great to see you at the CAFE

Colin

PS Don’t forget to follow us on Social Media for more tips..

• Instagram
• Youtube.
• facebook
• twitter

(I've been posting some fun Instagram and Facebook Stories lately)
You can get my free Layer Blending modes ebook along with dozens of exclusive Photoshop Goodies here

The post Photoshop update July 2024, Photoshop 25.11 new features appeared first on PhotoshopCAFE.

There is a new feature in Photoshop beta currently that makes it easier to get a good result Generating with a reference image. Let’s look at it now. How to get Photoshop beta.

Make selection with the lasso tool. We are going to generate a Vespa scooter.

Click on Generative Fill in the Task bar. (Window>Contextual Task Bar)

Click the Reference image button (Currently only in Photoshop beta, but might be in Photoshop main if you are reading this later)

Click Choose image

Find the reference Image that you want to use.

This is the reference image

Click Generate

See, it generates the Vespa, but it also has a weird background.

This is because the reference image has a background and Gen Fill is trying to generate that too. For best results, you need to isolate the background from the subject in a reference image. I’ve covered reference images in Photoshop Generative Fill in depth

The new feature, is a remove background check box when you load the reference image.

Click and the background is removed from the reference image, very cool!

Now, it generates more what you would hope for.

Revealing the Original background in Generative Fill

Let’s do a bonus tip here.

When you use Generative Fill, it will generate pixels for the entire selection. If we want to show the original background we can mask it out. Here’s how..

Grab the Quick Selection Tool

Click Select Subject from the Top menu bar

It selects our Vespa

Inverse the selection. Cmd/Ctrl+Shift+I

Choose the mask.

Grab the brush tool, (B)

Make the foreground color black

Make sure Hardness is turned down on the brush for a soft edge.

Paint around the background on the vespa. Black brush stokes on the Layer Mask will hide the current layer and allow the background top show through.

keep painting, but don’t paint over the shadow that was generated

We now see the original background from the bottom layer.

I hope you found this tutorial useful. Keep checking back for new Photoshop features as they become available and other photoshop tutorials here at the CAFE.

Great to see you!

Colin

PS Don’t forget to follow us on Social Media for more tips..

• Instagram
• Youtube.
• facebook
• twitter

(I've been posting some fun Instagram and Facebook Stories lately)
You can get my free Layer Blending modes ebook along with dozens of exclusive Photoshop Goodies here

The post Photoshop Generative ai, reference Image remove background appeared first on PhotoshopCAFE.

You may be aware of the Adjustment brush added in Photoshop 2024. It does the same thing as an Adjustment Layer and painting on the mask. Its easier and quicker to use, especially for newer Photoshop users. This new feature added a lot of usefulness to this tool, where even advanced users may see this as a worthwhile shortcut. Let look at it now.

Adjusting an object within a photo. Brighten a person.

Let’s brighten the woman in this photo. This example will allow you to see how this tool works.

Choose the Adjustment Brush from the toolbox. Can’t find the adjustment brush? Here is the fix.

Click on the adjustment in the toolbar at the top, to choose an adjustment.

Choose Exposure.

Click the icon to turn on object selection.

As you roll over different parts of the image, you will see different objects highlighted. Sometimes, it will show the whole person, other times, part of the person.

To select a highlighted area, click.

Notice the adjustment is applied as a new Adjustment Layer and a Layer Mask is created for the selected area.

Make adjustments in the Properties panel to adjust the masked part of the photo.

Adding to the selection with the Adjustment Brush in Photoshop

Notice the woman is adjusted, but her backpack doesn’t match the photo, because it wasn’t part of the selection mask,

With the Adjustment Brush still selected, click on the Object Selection button in the top toolbar, and then, roll over the backpack.

Click to select.

Notice it’s added to the mask and takes on the adjustments immediately, because it’s part of the same mask.

Changing the background color of a photo in Photoshop with the Adjustment Brush.

Let’s look at a different example, so we can use the tool in a different way. We will change the background color.

Choose the Adjustment Brush, as before.

Choose Hue/Saturation as the Adjustment type.

Click the Object selection option in the toolbar.

As you roll overe the image, notice different parts are highlighted.

What we want to do, is select the entire foreground in a single selection. We can’t do this by rolling over in this case.

Instead go to the taskbar (I positioned the taskbar by the top toolbar here).

Choose Apply To Object. (If you are confused, see the video at the top).

With Apply to Object, drag to make a selection around the entire are we want to select.

It nicely makes a selection and masks it out.

You can add to the mask, or remove from the mask, using selection tools, or the black or white brush. How to use layer masks in Photoshop.

Let’s inverse (swap) the selection, so that the background will be selected, instead of the foreground.

Press Cmd+I (Ctrl+I Windows).

Adjust the hue in the properties panel to change the color.

I hope this tutorial helped you see how to use the Object Selection tools built into the Adjustment Brush in Photoshop. It’s always good to know different ways to do things.

Thanks for checking out this week’s Photoshop tutorial.

Colin

PS Don’t forget to follow us on Social Media for more tips..

• Instagram
• Youtube.
• facebook
• twitter

(I've been posting some fun Instagram and Facebook Stories lately)
You can get my free Layer Blending modes ebook along with dozens of exclusive Photoshop Goodies here

The post Photoshop 2024 Adjustment brush gets auto selections, how do partial adjustments on photos the easy way appeared first on PhotoshopCAFE.

Adobe updated Camera Raw to Version 16.3 and added some nice new features. These features work exactly the same way in Lightroom Classic. The video goes quite in-depth, but I’ll keep these written steps brief because I have already covered them in my Lightroom write up which you can see here. As well as in-depth tutorials on individual tools.

Generative Remove

Generative remove uses firefly ai (same tool as Generative Fill in Photoshop) to remove and replace objects in a photo.

Bear in mind that maximum resolution generated in 1024×1024 pixels, so be careful when using on areas that will be OUTPUT larger than that. I emphasize this point because I’m seeing a bit of an overreaction to this. Unless you are printing your images, it isn’t as much of an issue for people, as some make out, because remember 1024px is close to the full resolution height when you output an image at full HD (1920 x1080) which is enough for online and social media sharing. But do check the final output to make sure there isn’t a softening or resolution mismatch. If you are concerned about this, or want print quality, then use the legacy tools or the remove tool in Photoshop which doesn’t’ have resolution limitations. Smaller patches are totally ok. Ok, having said that, let’s see how this works shall we?

Choose Filter>Camera RAW from Photoshop, or open as ACR from Bridge.

Click the eraser icon in the toolbar

You will see the remove panel.

If Generative ai is off, then the tool will work in legacy mode (How it used to work) If it is checked, it will use Generative ai, which requires and internet connection.

Object aware, will try to detect the edges and cover the object

Scribble select, or make a rough selection with Object aware on

It will do its best to select the object. It will make a selection slightly larger than the object, which you always want to do.

You will also notice it goes directly to the refine panel. (Hold Ctrl/Cmd to skip the panel)

Use the bush to refine the selection area (Some tips are in the video at the top).

Choose subtract to remove brush strokes

When you are ready, click apply

To bject will now be removed. Click through 3 variations to find the best one.

Lens Blur

I’ve covered  Lens Blur in depth on other tutorials.

Click apply in Lens Blur

The ai will detect you object and blur the background.

Under the hood (or bonnet) it will build a depth map to tell ACR where to blur. More on depth maps in a sec.

You can adjust the blu amount.

If you choose the target tool, you can click anywhere in the photo and that will become the sharpest part of the photo. Yes, this is like focusing the photo after you have taken it. (Remember, a blurry photo will still be blurry though, so nail that focus in camera!).

See the focal range.

If you move it to the left, it will focus closer to the viewer.

Move to the right and the focus will be further away from the viewer, with the close objects blurred.

If you make the slider more narrow, the focus area will be less, aka shallow depth of filed.

Widen the slider to expand the depth of field and have more of the photo sharp at once.

Lets look at that Depth map thing shall we?

Turn on Visualize Depth.

Now you see the depth map. The lighter areas are closer to you and the darker areas are further away.

The trees to the left are blurry but should be sharp.

Under refinement, choose focus

As you paint on the image, ypou can paint the areas that you want more in focus, or more out of focus.

See how the trees on the left are nice and sharp like they should be now.

If you look at the presets, you’ll see that there are new Adaptive presets for the blur. Adaptive means the ai adapts for each photo. Basically selecting the unique subject in each photo and then applying the preset blurs and settings.

Content Credentials

You can embed Content Credentials into the photo if you like. This is a way to protect you are the creator, as well as apply a layer of safety to viewers who need to know if ai was used on an image. It helps protect from deep fakes and reveals synthetic media.

Click the export button

You’ll see in the export panel, Content Credentials. Currently this is only working on jpg.

Producer, lets you attach your name. Connected Accounts, lets you link some of your social media accounts.

Edits and activity, embed any known edits or ai information.

You can store just locally and embed the data into the image, or into the cloud where the data will be attached to the image and recognized, even if its stripped locally. I haven’t tested the latter. Or you can use both options.

Save the image.

You can check any image on the Content Credentials Cloud. https://Contentcredentials.org/verify

You can test your image by dragging it into the website.

It will provide info on the image and also reveal if any editing has happened. Here i says ACR was used and ai was used.

More software and Hardware companies are building in Content Credentials as part of the CAI. Content Authenticity Initiative. Some of the partners include Adobe, Canon, Nikon, Leica, Getty, Microsoft, Nvidia, Qualcomm, arm, Reuters, universal pictures, Wall Street Journal, New York Times, and many, many more.

Eventually all image will be part of this and contain a pin that people can use to check if the image is real or not. Solving one of the big fears about ai generated content.

I hope this was a useful tutorial for you.

Great to see you here at the CAFE

Colin

PS Don’t forget to follow us on Social Media for more tips..

• Instagram
• Youtube.
• facebook
• twitter

(I've been posting some fun Instagram and Facebook Stories lately)
You can get my free Layer Blending modes ebook along with dozens of exclusive Photoshop Goodies here

The post New Features in Adobe Camera RAW 2024 ACR 16.3 appeared first on PhotoshopCAFE.

Generative fill does an amazing job, especially with Version 3 of Firefly. The biggest setback is the lack gf resolution. In this tutorial we will look at what the issues are and 2 ways to fix it. The first way is a new tool Adobe has introduced called Enhance Detail and the 2nd is a fix I came up about a year ago that works great today. The first feature is currently only in the beta version of Photoshop. The second part will work in all versions of Photoshop.

Start with this wide shot.

Choose the crop tool and Generative expand from the toolbar.

Drag with the crop tool to outcrop; AKA crop larger than the original size.

Press Enter to apply and Generate

From a distance, it looks great.

Zoom in cose and you can see the resolution mismatch. See how the bottom is soft and blurry vs the top part of the image is crisp and sharp.

Go to the Properties panel

Roll over the variation you are using.

Click the button at the top right to apply Enhance Detail

Now when you zoom in, it looks great!

Here is before and after Enhance Detail

What Does Enhance Detail do?

Enhance Detail doesn’t download a higher resolution version of the generated variation. What it does, is use Super Resolution.

To demonstrate, let’s go to Adobe Bridge. Right click this low resolution photo and choose Open in Camera Raw.

Here is our Lowe resolution cat photo.

Right-click.

Click on Enhance.

Choose Super Resolution and click Enhance.

Now we get a new image, but this one is 2x as large as before.

What Super resolution does is make the image physically 4x larger area.

It upscales and enhances the image, to appear higher resolution than before.

By upscaling the image, it makes it look much better and will work for a lot of cases. Bonus, it doesn’t use Generative Credits.

Ok, but what if we have a much larger image? Let’s look at another solution.

Grab the crop tool and choose Generative Expand from the toolbar.

Crop larger.

This time, it doesn’t even look good from a distance. This image is 11k wide.

Zoom up close and it’s a mess.

Click Enhance Detail.

We just get a sharper version of the mess.

What’s happening?

Generative Fill only generates and maximum of 1024px x 1024px on the longest edge.

If the area to fill is larger, it stretches the pixels to fill the area, but it can result in a softer image.

Here is the trick to get full resolution in Generative Fill.

I introduced this trick about a year ago, but I’ve updated and made it clearer here.

Grab the Rectangle Marquee tool.

Change to mode to Fixed size for the top toolbar.

Set it to 1024 x 1024px in the size.

If your image is flattened, click the padlock in the background, in the Layers panel,  to convert to a layer

Grab the Crop tool

Choose Transparent from the options in the top toolbar. (If you don’t see transparent, your background is flattened and isn’t a layer).

Drag with the crop tool to enlarge your image.

You should see a transparent background. If you don’t, back up a couple of steps and get it right.

Now, because we are using a fixed size for the marquee tool, your selection should be 1024 x 1024px which is the maximum for Generative Fill (at the time of this writing).

Make a selection in the bottom left.

Click Generative Fill in the taskbar and click generate. Leave the text prompt blank.

Now you will se a block at full resolution.

Zoom in and its perfect resolution.

Make a selection next to it with a small amount of overlap

Generate

Keep going until you have a perfect extension to your image which is sharp enough to print.

To make life easier for you, I have created a free action here.  
(If you are on our newsletter, click the link to the vault from the newsletter and it’s included in the actions)

Thanks for checking this out, I hope it was helpful

See you at the CAFE

Colin

PS Don’t forget to follow us on Social Media for more tips..

• Instagram
• Youtube.
• facebook
• twitter

(I've been posting some fun Instagram and Facebook Stories lately)
You can get my free Layer Blending modes ebook along with dozens of exclusive Photoshop Goodies here

The post Enhance Detail and increase Resolution in Photoshop Generative ai appeared first on PhotoshopCAFE.