Branding & Graphic Design · Asset variant

Create size and composition variations from one design

Generate size and composition variations from one design. Each run creates only the currently selected image. Generate other images in the series separately.

No full prompt needed—just complete the required text fields.

How it works
Before · 1 reference image
Create size and composition variations from one design — key visual master
After · Generated result
Create size and composition variations from one design — generated result

What this workflow creates

Generate size and composition variations from one design. Each run creates only the currently selected image. Generate other images in the series separately.

Who it’s for
Brand operation and design team
What it does
Stretch with different proportions, typography and backgrounds
Where to use it
Omni-channel campaign

Each run creates only the currently selected image. Generate other images in the series separately.

What you need

Key visual masterRequired · 1 image
Preserve the subject, brand assets, and campaign identity
Target channel list and immutable elementsRequired · 1 item
Select each current canvas and record its safe area and copy version

Provide every required input. Add optional inputs only when useful, and mark conditional inputs as applicable only when they apply to this request.

How to use this workflow

  1. Open the generation form

    Select “Use this workflow” to see the required inputs. You’ll need to sign in before generating.

  2. Add the required inputs

    Prepare: Main visual master + target channel list and immutable elements → Extend different proportions, layouts and backgrounds → Multi-channel asset variants of the current single sheet. Complete every required field, add optional inputs only when useful, and mark each conditional input as applicable or not applicable.

  3. Review text and output settings

    Check “Target channel list and immutable elements” for accuracy, then choose the aspect ratio, resolution, and quality that fit this use case. The generation form shows the available options.

  4. Generate and review

    Select “Generate image,” then review the result and open the full-size image. Check it against the detailed requirements below. Each run creates only the currently selected image. Generate other images in the series separately.

Do I need to write a prompt?

No full prompt needed—just complete the required text fields.

Complete “Target channel list and immutable elements” to describe what this request should contain or create. You do not need to write generation instructions. Use the form fields to provide the images, exact copy, data, or description requested by this workflow.

Detailed result requirements

Required inputs

Main visual master + target channel list and immutable elements → Extend different proportions, layouts and backgrounds → Multi-channel asset variants of the current single sheet

Input quality

Brand assets, event copywriting, product/character materials and target platforms.;Master, brand safe area and target channel list.

Composition

Fit retains the entire image, Fill will crop the edges, and AI expands the image to generate new content; key logos/texts are placed in the safe area.

Output aspect ratio

Set the output canvas from the selected platform placement or production template, not from a reference image. Choose the target aspect ratio before generation; do not default to 1:1. Use a custom ratio only when the actual placement or production template requires it. The aspect ratio for multi-channel asset variants must follow the selected platform, device, finished format, or production template. If no target ratio is provided, request it before generation; never infer it from a reference image. Create one aspect-ratio-specific deliverable per request; generate each additional placement as a separate output. Recompose for the selected ratio while preserving the complete subject, all text, and every required safe area. Never stretch the subject or treat cropping important content as adaptation.

What stays unchanged

No universal public standard is available. Check the requirements of the platform or service you will use.

What can change

No universal public standard is available. Check the requirements of the platform or service you will use.

Background and setting

No universal public standard is available. Check the requirements of the platform or service you will use.

Lighting and color

No universal public standard is available. Check the requirements of the platform or service you will use.

Text requirements

Google responsive advertising images avoid overlaying text/logo/buttons; different advertising slots have different rules.

Platform size guidelines

Google Ads recommends 1200×628, 1200×1200, 900×1600; TikTok’s minimum is 1280×720, 640×640, 720×1280.

Output format

No universal public standard is available. Check the requirements of the platform or service you will use.

What to avoid

Avoid blur, borders, collages, misleading buttons and excessive filters; Campaign variations need to lock in the logo, color palette and core selling points.; It cannot just be mechanically stretched; it is necessary to check the cutting, text wrapping, character and product integrity on a page-by-page basis.

Official and platform requirements

No universal public standard is available. Check the requirements of the platform or service you will use.

FAQ

What can I create with this workflow?

Generate size and composition variations from one design. Each run creates only the currently selected image. Generate other images in the series separately.

Do I need to write a prompt?

Complete “Target channel list and immutable elements” to describe what this request should contain or create. You do not need to write generation instructions. Use the form fields to provide the images, exact copy, data, or description requested by this workflow.

What do I need to upload?

“Key visual master”: 1 image; required. JPG, PNG, and WebP are supported, up to 10 MB per image.

What does one generation produce?

Each run creates only the currently selected image. Generate other images in the series separately.

Common search terms

variation generatorcreative variations

Public evidence and sources

Four directly relevant public sources have been found, and six types of specific constraints have been extracted. The following content only restates information that appears clearly from the source; no filling in of blank fields will be made.

Generate an image

Create size and composition variations from one design

Main visual master + target channel list and immutable elements → Extend different proportions, layouts and backgrounds → Multi-channel asset variants of the current single sheet