◆ Photoshop · generate

Aspect-Ratio Conversion Constraint

We need a 3:1 banner for an outdoor buy but the best image we have is a 16:9 crop. I don't want the horizon to bend or…

1height
1tasks
1roles do it

The same job, four prompts

do it · improve it · decide · become
CDecide — “help me choose”We need a 3:1 banner for an outdoor buy but the best image we have is a 16:9 crop. I don't want…+
We need a 3:1 banner for an outdoor buy but the best image we have is a 16:9 crop. I don't want the horizon to bend or obvious cloning across a large print. Tell me whether it's safer to extend the frame with generated content or to redesign the composition, and if extension is feasible, explain which parts of the scene must be reconstructed first so the generated fill will read authentic at scale.
when the reply comes backPush once: ask it to sharpen the weakest part, and to say what it assumed.

How to do it

the tool · the steps · what to avoid
The tool
Generative Fill

Generative Fill uses AI to add, expand, or remove content from your images based on text prompts.

  1. 1

    Open your image by selecting File > Open.

  2. 2

    Select the area you want to transform using a selection tool.

    Best practiceFor expanding the canvas, use the Crop Tool to extend the image boundaries first.

  3. 3

    Click the Generative Fill button in the Contextual Task Bar.

    NoteYou can also access it from Edit > Generative Fill, or Select > All then Edit > Generative Fill.

  4. 4

    Type a prompt describing the object or scene you want to generate in the text-entry field.

    NoteYou can leave the prompt field empty to have Photoshop generate content based on the surrounding image.

  5. 5

    Click Generate.

  6. 6

    Review the generated variations in the Properties panel.

  7. 7

    Select your preferred variation from the options.

  8. 8

    Save your image by selecting File > Save As or File > Save a Copy.

Generative Fill creates new content on a separate generative layer, allowing non-destructive edits.

Generative Fill functionality is integrated within Photoshop and is not directly exposed as a standalone API for external automation.

Glossary

words on this page
Contextual Task BarA floating bar that provides relevant tools and actions based on the current selection or task.ExampleWhen you select an object, the Contextual Task Bar appears with options to duplicate or delete it.
Generative FillAn AI-powered feature that creates new image content based on text prompts or existing selections.ExampleUsing Generative Fill, you type 'add a sandy beach' to extend the ocean scene in your image.
AdjustmentsNon-destructive edits applied to an image to change its color, tone, or other visual characteristics.ExampleYou can use Adjustments to brighten a dark photo or change its color balance.
Save a CopyTo save the current document as a new file, leaving the original document open and unchanged.ExampleYou can 'Save a Copy' of your edited photo to share, while keeping the original file untouched.
TransformTo change the size, shape, or orientation of an image layer or selection.ExampleYou can transform an image layer to rotate it clockwise or make it much smaller.

The real tasks

1 of them
Marketing wants a 3:1 banner from a 16:9 asset for an outdoor buy and I don't want anything to look stretched or cloned.

Who does this

1 roles
Art Director

Questions people actually ask

with the jobs and tasks they touch

When using AI to add props, set size guidelines based on the final print dimensions. Avoid making added elements too small or too large compared to real objects. For a large-format print, like an A-frame, double-check proportions by overlaying reference objects in Photoshop.

Avoid generating props that need precise scale, like storefront signs or furniture, if accuracy is critical. AI may not always respect real-world proportions, risking visual inconsistency in big prints, especially for roles like Visual Merchandiser who need authentic displays.

Use masking and layer adjustments to control where AI adds pixels. Also, set specific size constraints in your generate settings. For example, when generating props for a window display, limit height and width to match real-world measurements.

They often forget to check scale after generation, assuming AI got it right. Always compare generated elements to real-world references and adjust manually if needed, especially important for roles like Visual Merchandiser preparing window displays.

A Visual Merchandiser does this before finalizing window displays, ensuring props look authentic at large sizes and match store branding.

AI can quickly fill large areas with contextually appropriate pixels, but you should manually verify scale and realism. For example, AI might generate a lamp that's too small or large for a retail window, so check proportions carefully.

Both involve adding or changing elements in an image. When generating props, make sure they blend naturally with backgrounds you might also replace, like skies or overcast scenes, to keep the visual consistent.