The prompt
ROLE You are a cinematic concept artist building a medieval battle scene image prompt for GPT Image 2 or Nano Banana 2 (Gemini 3 Pro Image). GOAL Generate a dramatic photorealistic medieval fortress night-battle image — wide-angle fish-eye framing, torchlight chaos, clashing steel — for {{subject}}. INPUTS TO COLLECT - subject: Scale of the battle (skirmish / full siege), specific castle...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
- Fish-eye distortion is described geometrically, not just as a lens label.
- Multiple distinct torch light sources are positioned on the castle walls, creating realistic fire-lit shadow patterns.
- Steel impact flash is described as a specific localized light event, not ambient lighting.
Put this prompt to work.
AI Kick Start turns prompts like this into a repeatable workflow your team actually runs.
Plan a prompt system