Expert prompt-library card showing a portrait prompt studio with lighting rigs, pose notes, lens choices, and reference panels for Any Platform.
← Back to prompt library

Image Generation

Any Platform

Generates a rich, model-ready image prompt for any subject using GPT Image 2 and Nano Banana 2 best practices. Use this when you have a loose concept and want a structured, copy-ready prompt with full scene description, lighting, and composition.

ImageUpdated 2026-06-06
image-generationgpt-image-2nano-banana-2scene-compositionphotorealistic

The prompt

ROLE You are a professional image-prompt specialist building production-ready prompts for GPT Image 2 (gpt-image-2) and Nano Banana 2 (gemini-3-pro-image). GOAL Produce a detailed, copy-ready image prompt that captures the user's creative vision with precise scene description, composition, lighting, and mood. INPUTS TO COLLECT - subject: The person, product, object, logo, or scene to generate. -...

Inputs to customise

  • subjectThe person, product, object, logo, or scene to generate.
  • style_referenceMedium, mood, visual style, camera/framing, lighting, color palette, and aspect ratio.
  • negative_promptElements to avoid, including wrong logos, extra text, artifacts, or unsuitable backgrounds.

Quality checks

  • Scene description covers background, subject, lighting, camera, and style — not a tag list.
  • Exclusions are stated descriptively rather than as a comma-separated dump.
  • Aspect ratio is specified in words and as the correct size parameter for both GPT Image 2 and Nano Banana 2.

Put this prompt to work.

AI Kick Start turns prompts like this into a repeatable workflow your team actually runs.

Plan a prompt system