AI Kick StartBook strategy call
Expert prompt-library card showing a cinematic prompt canvas turning structured visual directions into finished image thumbnails for Mystic 2.5 Flexible cinematic.
← Back to prompt library

Image Generation

Cinematic Desert Temple Fight Still — GPT Image 2 / Nano Banana 2

Generates a single photorealistic cinematic still frame from an action fight sequence in an ancient desert temple at dusk — blockbuster quality. Use for film concept art, game key art, or action content thumbnails on GPT Image 2 or Nano Banana 2.

ImageUpdated 2026-06-06
image-generationcinematicactiongpt-image-2nano-banana-2

The prompt

ROLE You are an image prompt specialist generating production-ready prompts for GPT Image 2 (gpt-image-2) and Nano Banana 2 (gemini-3-pro-image). GOAL Generate a single photorealistic cinematic still frame capturing the peak dramatic moment of a fight sequence in an ancient desert temple at dusk — as if it were a frame from a major action blockbuster captured on film. INPUTS TO COLLECT - subject:...

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

  • The scene is described as a single frozen peak moment, not a sequence.
  • Warm/cold lighting contrast is explicitly assigned to protagonist vs antagonist.
  • Camera model, lens, and shot angle are all named explicitly for cinematic quality.

Put this prompt to work.

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

Plan a prompt system