dark
Trending Tags
A surreal landscape depicting a suburban area with flying saucers in the sky above. The sunset casts an orange hue, while a red creature stands on a building. Solar panels are visible on the roof, alongside a river and parked boats.

Photoshop und Express Beta – Refill my Picture?

08.07.2023
As soon as the Adobe Firefly beta is officially available to every Adobe Cloud subscriber, the features are also being introduced in the Photoshop beta and then immediately in the Adobe Express beta.

In Photoshop, generative filling, which is also fed with English prompts, has been added to content-based filling. In the Adobe Express beta, you can now also generate images with prompts and the text effects from Firefly are integrated. And in Adobe Illustrator Beta, you can now leave the colour design to the AI.

Content-based filling has been around for a while in Photoshop and is often used to remove unwanted parts of an image. Generative filling now works in a similar way. You create a selection and if you don’t enter a prompt, the AI simply tries to fill the selection sensibly. The results are usually much better than with content-based filling because the engine analyses the image content better and recognises objects.

A test!

To do this, I first removed the hotel logos and the parked cars from a sunset snapshot from the hotel window. Surprisingly, this works better when the selection extends a little beyond the objects. After a few attempts, the vehicles were removed using suitable overlays. The AI also generated the slightly larger, clunky car at the front.

A panoramic view of a suburban street at sunset, showcasing houses, trees, and parked cars. The sky displays orange and purple hues as the sun sets, and a few clouds are scattered. The image has a transparent background indicating editing in progress.

For the set extension after the four sides, I simply extended the workspace with the cropping tool and then created a selection in each case that contained a few pixels from the original image. As you can see, the AI then uses an empty prompt to generate mostly really suitable image parts that even take colour mood and shadows into account. However, the image parts to be expanded must not be too large, otherwise the generated image part will become muddy. As far as I know, the number of pixels generated is currently limited to 1024 × 1024 pixels. Anything larger than this is stretched. It is therefore advisable to generate larger extensions in stages. In the lower part, I used the “river with reflection” prompt to create a river in the image, on which I generated the same with the “boat” prompt, although this turned out a little too bright.


The other prompts “red table and seats” “red flowers” “plants” on the roof railing and “alligator” worked well. The “blonde girl” and “reflective solar panel” are also a little bright, but with a little reworking you can adjust them a little. Unfortunately, the number in the prompts doesn’t really work. I wanted to conjure up a large number of spaceships in the sky, but no matter whether I had “armada”, “fleet”, “many”, “100” or “millions of steampunk spaceships” in the prompt, there were always only a few and of course different variants each time.

A view of a village at sunset, featuring a large red sculpture on a building, solar panels on a roof, and a kayak on the water. Red outdoor furniture is placed beside a narrow street lined with trees.
The first prompts, still without spaceships.


My favourite object, however, is the “red hairy monster” on the roof. Three versions are created for each generation and if they don’t fit, three new ones are created. You can also adjust the prompt a little each time and hope that it will eventually match what you had in mind. However, there are no guarantees. But as long as that’s the case, we creatives don’t need to worry too much about the AI taking our jobs, because it’s not possible to implement concrete specifications for real customer orders in this way. However, AI can be very helpful in finding ideas. Even the sometimes very strange excesses.

A futuristic scene featuring a vibrant red and metallic structure resembling a spaceship, accompanied by a person in a red suit and a small robotic dog, set against a brick building background.
This is what my outfit and the future of Mannheim’s creative Jungbusch neighbourhood could look like if you let the AI have a go. But this is by no means intended as a suggestion for Mannheim’s urban planners.

Equirectangular

The AI seems to recognise the Equirectangular format in Photoshop, because my attempts to modify Böckstrasse in Jungbusch in Mannheim, where a historic building burnt down, also worked well directly in Photoshop. However, it should be noted that when saving as a JPG, Photoshop does not automatically set the flag by which Facebook, for example, recognises that it is a 360 degree image
Image. You have to select all layers and create a new panorama layer from the selected layers via the 3D menu. This must then be exported as a panorama using the same menu. Unfortunately, the panorama workflow in Photoshop is a bit slow. It is quicker to export the files saved as PSDs with Pano2VR via quick share, where you can also specify the initial perspective and the geo and meta data.

A panoramic view showing a construction site on the left with a pile of debris and a construction crane. On the right, a man stands near a brick building with ivy on its wall, while two other people walk on the sidewalk.
This is what it looks like in Böckstrasse in Jungbusch in Mannheim, where a historic building has burnt down.

The removal of passers-by, bars, barriers, excavators and ruined buildings, as well as the modification of my outfit and my robot dog look pretty good in perspective. I even have hair on my head again. The only problem I still had was with my hands. Hopefully the city planners in Mannheim won’t take too much of an example from my building design.

A panoramic view of a street with red brick buildings, one showing a storefront with a window. A person wearing a black coat and sunglasses is standing on the sidewalk. The scene has a cloudy sky and visible industrial elements in the background.
Centre: This is what it might have looked like without excavators, barriers and fencing (and with hair on my head), according to the AI.

Of course, there is still plenty of room for optimising the workflow. For example, it would be more effective if a mask were also generated for the objects so that they could also be resized and repositioned. Because if you change the position of the selection, the generated background borders no longer fit and if you generate the same prompt, the result is often a completely different object. It would be good to be able to set the prompts here. It would also be nice if the prompts could be included in the layer names so that the objects can be assigned more easily.

A wooden cabin surrounded by lush green trees and tall grass, with a clear blue sky above and a hilly landscape visible in the background.
IMG_20230216_083454_00_168.insp
A panoramic view of a rural landscape featuring a small wooden cabin with a red door, surrounded by green grass and trees, with fields in the background under a clear blue sky.
Retouching 360-degree images is also much easier with Generative Fill. Especially with the patch function in Pano2VR, the automatically equalised patches in Photoshop can be combined very well with generative fills.
A large, fluffy red object sitting in a grassy field, with trees and a forested area in the background under clear blue skies. The image is displayed in a photo editing software interface.
Even classic landscapes can be made even better with Firefly – even regions worth seeing such as the
Vosges are better with red pixel!
A software interface displaying a panoramic image of a green meadow with hills in the background. Icons and tools are visible on the screen, suggesting editing capabilities. A preview of the image is shown in a lower panel.

Seamless textures with generative fill

A screenshot of Adobe Photoshop showing a menu with options on the left and a vibrant red foliage background. The interface includes layers on the right side and active tool options on the top.

In this example, I have reduced a mobile phone image to 1024 × 1024. Then I used the Move effect to move the seam to the centre. Now simply draw a large rectangular selection around the seam and generate the content with an empty prompt. Then bake in the generated part and repeat the whole thing again with a horizontal shift. This method can also be used to create seamless ring panoramas from widescreen images, for example for enviroment maps in 3D programmes.

A close-up view of vibrant red and orange leaves covering a plant in autumn. The foliage is lush, with some green leaves visible among the colorful ones.
Close-up of vibrant red and orange leaves on a vine-covered tree during autumn. The leaves show various shades of red, indicating seasonal change.
A dense cluster of red foliage with a few green leaves visible. The vibrant red leaves indicate autumn season, blending with hints of yellow and green among the branches.
A dense arrangement of red foliage displaying various shades of red and orange, with some green leaves visible among them. The image showcases the vibrant colors of autumn leaves in a natural setting.
A close-up view of vibrant red leaves intertwined with green foliage, showcasing the beauty of autumn colors in a garden setting.
In five steps, every image becomes a seamless texture.

Adobe Express Beta

Some Firefly functions have also been integrated here. The advantage is that you can combine these with the other functions. This creates cool online image compositions for social media or even flyers and posters. The integration of animation, videos and external media has also been improved. This allows you to produce attractive moving trailers and motion graphics without having to use After Effects.

A digital design interface showing the text "Spaceships" in a steampunk style, with flying ships in the background and various text effects on the left toolbar.

Conclusion

It is important to note what is stated in the Adobe Generative AI Beta user guidelines. While Generative AI features are in beta, all generated output is for personal use only and may not be used commercially
personal use only and may not be used commercially. It remains to be seen what the licence model will look like after the beta phase. Of course, we hope that it will simply become part of the Adobe Creative Cloud subscription for commercial use, as it was in the beta. The addictive factor should not be underestimated, because it’s fun to work with these new tools.

Nils Calles Author
Nils Calles runs a media agency in Musikpark 2 in Mannheim's Jungbusch creative district, where he specialises in producing trailers, motion graphics, image films, magazine programmes in the virtual studio, tutorials and 360-degree websites. He is also a producer for Linkedin Learning and a trainer and consultant for workflows and software in the post-production sector. He has also been travelling the world for over 25 years as an editor, producer and compositor for various productions and broadcasters at trade fairs and in OB vans and has put the site postproduction-tutorials.net online with selected video tutorials.