ImageProduct photographyIntermediateGenerates an image

Swap the background, keep the product unchanged

An editing prompt for tools that accept an input image: change only the scene around the product and lock everything else in place.

For: Performance marketers, Creative strategists, E-commerce marketers · Works with: OpenAI GPT Image, Google Gemini image generation (Nano Banana), Any image generator

Your prompt

Edit the attached product photo. Change only the background and the lighting on the background. Do not change the product. New background: a rustic wooden kitchen counter with a blurred window behind. Light on the new scene: soft morning window light from the left, with a natural contact shadow matching the product's position. Keep exactly the same: the product's shape, proportions, colour, texture, label text, logo, orientation, crop and position in the frame. Do not change: product details, any text on the product, camera angle, or image aspect ratio (1:1). If something cannot be changed without altering the product, leave it as it is.

Customize

The fields start with example values so you can see how the prompt works. Everything stays in your browser.

The scene you want.

Light on the new background.

Restated so the crop does not change.

Example of what to expect

Illustrative only. It describes the kind of result this prompt aims for; real output varies by tool, model and run.

The same product in identical position and detail, now sitting on a wooden kitchen counter with soft window light and a matching contact shadow.

Expected format: One edited image. Overlay it on the original to confirm the product is unchanged.

How to use it

  1. Attach your product photo in the tool's image-input or edit mode.
  2. Make one change at a time and restate the keep-list on each follow-up.
  3. Compare the product pixel-for-pixel against the original.

Limitations

  • Even with explicit instructions, models can subtly alter product details, labels and text. Verify before publishing.
  • This requires a tool with image input; plain text-to-image tools cannot keep your exact product.

Platform notes

OpenAI GPT Image

Official docs read · checked 2026-10-11

OpenAI advises 'change only X' plus 'keep everything else the same', restating the preserve list every iteration. input_fidelity applies to older models only and is disabled for gpt-image-2.

General notes on OpenAI GPT Image
  • OpenAI's guide covers gpt-image-2 (recommended), gpt-image-1.5, gpt-image-1 and gpt-image-1-mini.
  • Aspect ratio is set through the size parameter, not in prose. Quality is low, medium or high; medium or high is advised for small or dense text.
  • Put literal text in quotation marks, and when editing say what must stay unchanged.

Google Gemini image generation (Nano Banana)

Official docs read · checked 2026-10-11

Gemini's docs show edits as image plus instruction and multi-turn constraints such as not changing other elements.

General notes on Google Gemini image generation (Nano Banana)
  • Google's docs list several Nano Banana models (2.1, 2 Lite, 2, Pro) and recommend 2.1 for new projects as of the verification date.
  • Supported aspect ratios include 1:1, 4:5, 9:16, 16:9 and 21:9; sizes 1K, 2K and 4K. Up to 14 reference images per request.
  • All generated images carry a SynthID watermark.

Any image generator

Official docs read · checked 2026-10-11
General notes on Any image generator
  • Written as natural-language descriptions that the verified image models accept. Syntax for aspect ratio, quality and negative prompts differs by tool, so set those in your tool's own controls.

Source, license and attribution

Origin
Original by MarketerTools
Publisher
MarketerTools
License
Original work by MarketerTools, free to copy and use. Informed by the linked documentation; no third-party text is reproduced.
Platform assumptions checked
2026-10-11

Documentation and references behind this prompt

These informed the structure and the platform notes. A reference is not a license, and no third-party prompt text is copied here.

Spotted an attribution error, or are you a source owner with a request? Use the chat button at the bottom right and quote prompt ID img-020. We will correct or remove it.

Related prompts

  • ImageBeginnerGenerates an image

    Marketplace-ready white-background product shot

    A clean, evenly lit packshot on a pure white background for marketplaces and product-detail pages, with accurate shape and a soft ground shadow.

    OpenAI GPT Image · Google Gemini image generation (Nano Banana) · FLUX (Black Forest Labs) +1

  • ImageAdvancedGenerates an image

    Transparent-background product asset

    An isolated product designed for transparent PNG or WebP output so it can be dropped onto any ad or banner background.

    OpenAI GPT Image · Any image generator

  • ImageIntermediateGenerates an image

    Seasonal campaign image variants

    One approved base visual re-skinned for a season or holiday by changing only palette, props and light, keeping product and composition fixed.

    OpenAI GPT Image · Google Gemini image generation (Nano Banana) · FLUX (Black Forest Labs) +1

  • ImageIntermediateGenerates an image

    Lifestyle product-in-context scene

    Places a product in a believable real-world setting that signals who it is for, with the product still the visual priority.

    OpenAI GPT Image · Google Gemini image generation (Nano Banana) · FLUX (Black Forest Labs) +2