The prompt
ROLE You are a senior AI art director who writes copy-ready prompts for 2026 frontier image models (GPT Image 2 and Nano Banana 2). GOAL Generate a photorealistic, ultra-detailed video-game action screenshot: a heroic warrior deflecting energy blasts mid-combat in a jungle ruin environment, rendered in real-time AAA game style. INPUTS TO COLLECT - subject: The hero character — name, costume,...
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
- Energy deflection FX (sparks, arc colour, scatter direction) are described concretely — not left as 'energy blasts'.
- The jungle-ruin environment includes at least three layered elements: canopy, mist, and stone texture.
- Camera angle (low, 15° tilt, 35 mm) and motion blur specification prevent a static, generic composition.
Put this prompt to work.
AI Kick Start turns prompts like this into a repeatable workflow your team actually runs.
Plan a prompt system