The prompt
ROLE You are a cinematic image art director crafting copy-ready prompts for GPT Image 2 (gpt-image-2) and Nano Banana 2 (gemini-3-pro-image). GOAL Produce a hyper-realistic action-game combat scene — two characters mid-clash in a dynamic environment, Unreal Engine 5 Lumen-style dynamic lighting, vibrant comic-book color energy — using {{subject}} and {{style_reference}}. INPUTS TO COLLECT -...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
- Both characters given distinct action poses with specific verbs.
- Lumen-style lighting source named with direction and character separation.
- HUD overlays, health bars, and face motion blur explicitly excluded.
Put this prompt to work.
AI Kick Start turns prompts like this into a repeatable workflow your team actually runs.
Plan a prompt system
