ImageInfographics and art directionIntermediateGenerates an image

Brand-campaign concept still

An evocative key-visual concept for a brand campaign, built around a feeling and a single story moment rather than a product feature.

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

Your prompt

Create a cinematic 16:9 key-visual still for a brand campaign called "Come Home Slower" for a heritage wool-blanket company. Story moment: a family arriving home after a long drive on a rainy evening, captured at the instant of a child wrapping herself in a blanket by a lit window. Emotion: relief and warmth. The product appears only as the blanket in the child's hands, natural and unposed. Cinematography: 35mm lens look, medium-wide shot, slightly low angle; warm interior glow against cool blue dusk outside; a considered colour grade of teal shadows and amber highlights. Composition: strong depth with foreground, subject and background layers; one clear focal point; room for a single line of campaign copy later at the lower left. Constraints: no text, no logos, no real celebrities or public figures, no clichéd stock poses.

Customize

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

A working campaign name; not rendered.

Brand context.

Shape.

The scene.

The emotional instant.

Feeling.

How the product appears.

Cinematography; treated as loose guidance.

Lighting.

Grade.

Where copy can go.

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.

A cinematic dusk scene: a child wrapped in a wool blanket by a glowing window, cool blue outside and amber inside, space at the lower left for copy.

Expected format: One key-visual concept for discussion.

How to use it

  1. Use as a concept to align stakeholders before a real shoot.
  2. Run variants by changing only the story moment.
  3. Plan real production if the concept is approved.

Limitations

  • Camera specifications are interpreted loosely by image models, per OpenAI's guidance.
  • AI stills are concepts; they do not show how a real shoot, casting or product accuracy would turn out.

Platform notes

OpenAI GPT Image

Official docs read · checked 2026-10-11

Aspect ratio is set with the size parameter, not in prose. Use medium or high quality for text and fine detail. OpenAI notes camera specs are treated as loose guidance for look and composition.

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

FLUX.2 does not use negative prompts, so constraints are phrased as things to do.

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.

Midjourney

Not verified: third-party guidance only · checked 2026-10-11

Append parameters after the prompt; verify them for your model version.

General notes on Midjourney
  • Parameters go at the end of the prompt (for example --ar for aspect ratio). Parameter names and ranges vary by model version.
  • We could not read Midjourney's official parameter list on the verification date, so check the live docs for your model version before relying on any parameter shown here.

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-039. We will correct or remove it.

Related prompts

  • ImageIntermediateWrites a set of prompts

    Brand moodboard and art-direction brief

    Asks a chat model to turn your brand attributes into an art-direction brief and four moodboard image prompts you can feed to any generator.

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

  • ImageIntermediateGenerates an image

    Product launch teaser visual

    A teaser that hints at a product without fully revealing it, to build anticipation before launch.

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

  • VideoIntermediateWrites a script

    Brand film treatment (concept document, not video)

    A one-page treatment for a brand film: premise, tone, scene outline and production needs, as the basis for a real shoot or an AI-assisted concept reel.

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

  • ImageAdvancedGenerates an image

    Stat-led infographic from data you supply

    A multi-panel infographic where every number and label comes from you, laid out by the model; it never invents data.

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