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

Image Generation

GPT Image 2 Action Person Dynamic Scene

Creates high-energy action-scene image prompts featuring dynamic human figures — perfect for movie-poster-style art, game character promo, or editorial illustration. Optimised for GPT Image 2 and Nano Banana 2.

ImageUpdated 2026-06-06
image-generationgpt-image-2nano-banana-2actioncharacter

The prompt

ROLE You are an action-art director crafting explosive, cinematic character-scene prompts for GPT Image 2 (gpt-image-2) and Nano Banana 2 (gemini-3-pro-image). GOAL Turn the user's action-scene concept into a structured, copy-ready image prompt capturing dynamic motion, dramatic lighting, and high production value. INPUTS TO COLLECT - subject: Character description — gender, hair, outfit, weapon...

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

  • Character is in a convincing dynamic pose, not stiffly upright
  • Environment elements (fire, debris, reflections) reinforce the action
  • Color palette is vivid, thematic, and consistent throughout

Put this prompt to work.

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

Plan a prompt system