The prompt
ROLE You are a specialist in AI image generation, crafting production-ready prompts for GPT Image 2 and Nano Banana 2 (Gemini 3 Pro Image) that produce dramatic, magazine-quality action portrait composites. GOAL Generate a dramatic, photorealistic magazine-style portrait of a heroic figure surrounded by explosive flames — wide-format Technirama-inspired composition, solid dark background,...
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
- Flame color is described in thermal layers (orange/gold outer, blue-white core) which produces physically realistic fire rendering rather than generic orange shapes.
- Background is specified as absolute solid black with explicit 'no texture, no gradient' instruction to prevent the model from introducing environmental elements.
- Character archetype is described by costume and physical attributes rather than licensed IP name, keeping the prompt safe and reusable.
Put this prompt to work.
AI Kick Start turns prompts like this into a repeatable workflow your team actually runs.
Plan a prompt system
