ImageCreative variations for testingIntermediateGenerates 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.

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

Your prompt

Using the same composition as my approved base image, create a 4:5 seasonal variant for autumn harvest. Keep fixed: a ceramic pour-over coffee set in the same position, scale and angle; the same camera framing; the same level of background detail. Change only: the colour palette to burnt orange, deep brown and cream; background and props to scattered dried leaves, a wool throw and a wooden table; the lighting to low golden-hour sun from the right. Mood: cosy and unhurried. Keep it tasteful and on-brand rather than cliché. Constraints: no text, logos or watermarks. Do not add festive elements that obscure the product.

Customize

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

The occasion.

Frame.

Must match your base image.

Season colours.

Context items.

Light for the season.

Feeling.

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 pour-over set in the same position, now on a wooden table with dried leaves and a wool throw in burnt-orange tones, lit by low golden light.

Expected format: One image per season; keep a naming scheme such as product_season_ratio_v1.

How to use it

  1. If your tool supports image input, attach the base image and reference it explicitly.
  2. Otherwise paste the base prompt first, then this one as a follow-up.
  3. Compare each variant against the base for product consistency.

Limitations

  • Without an image reference the model cannot truly 'keep' your base composition; expect drift and use image-input features where available.
  • Seasonal imagery ages quickly; plan an approval and expiry date for each variant.

Platform notes

OpenAI GPT Image

Official docs read · checked 2026-10-11

OpenAI's guidance for edits: say what must stay the same and restate the 'keep' list on each iteration. Gemini accepts up to 14 reference images per request.

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
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.

FLUX (Black Forest Labs)

Official docs read · checked 2026-10-11
General notes on FLUX (Black Forest Labs)
  • BFL's official guidance for FLUX.2: no negative prompts (describe what you want), write sentences rather than keyword lists, specify lighting, quote text to render, and pair colour names with hex codes.

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-010. We will correct or remove it.

Related prompts

  • ImageIntermediateWrites a set of prompts

    Creative test set: change one variable at a time

    Builds a fixed base prompt and a controlled list of variants that change exactly one element, so a creative test isolates what actually drove results.

    Any capable chat model (ChatGPT, Claude, Gemini, others)

  • ImageIntermediateGenerates 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.

    OpenAI GPT Image · Google Gemini image generation (Nano Banana) · Any image generator

  • ImageIntermediateWrites a set of prompts

    Five creative concept angles for one product

    Turns one product and one audience into five clearly different advertising angles, each with its own image prompt, for early concept testing.

    Any capable chat model (ChatGPT, Claude, Gemini, others)

  • ImageIntermediateGenerates an image

    Differentiation visual brief (without copying a competitor)

    Uses your description of competitors' visual conventions to design an image that deliberately breaks from them, without imitating any brand's assets.

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