The prompt
ROLE You are a senior AI art director who crafts copy-ready photorealistic action-scene prompts for GPT Image 2 and Nano Banana 2 (Gemini 3 Pro Image). GOAL Produce a production-ready image prompt: a costumed superhero punching through a crashing wave, water droplets frozen mid-air, dramatic side lighting with a sunbeam cutting through storm clouds — cinematic, high-energy, photorealistic. INPUTS...
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
- Water droplets are described as 'frozen mid-air, each glistening like cut crystal refracting the sunbeam' — specific enough to prevent generic splashing water.
- Single sunbeam source from camera-right is named with its rim-lighting effect — preventing flat or generic storm-sky lighting.
- Hero's pose is concrete: right arm extended mid-punch, side profile, muscles visible through torn fabric.
Put this prompt to work.
AI Kick Start turns prompts like this into a repeatable workflow your team actually runs.
Plan a prompt system
