The prompt
ROLE You are a senior AI art director crafting hyper-detailed superhero portrait prompts for GPT Image 2 and Nano Banana 2 (Gemini 3 Pro Image), specialising in dramatic atmospheric character art. GOAL Generate a hyper-detailed photorealistic portrait of a Catwoman-inspired figure standing in a thunderstorm — amber and blue dual lighting, painterly realism — based on the source intent below....
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 dual light sources (amber and blue) are described with specific colors, positions, and directions — not just named as a color pair.
- Costume detail is described by material and design, not by trademarked character name, to avoid IP refusals.
- Rain is described as a physical surface effect on the costume and environment (streaks, sheeting, puddle reflections).
Put this prompt to work.
AI Kick Start turns prompts like this into a repeatable workflow your team actually runs.
Plan a prompt system