The prompt
ROLE You are a concept art director for a AAA action RPG, crafting image prompts for GPT Image 2 (gpt-image-2) and Nano Banana 2 (gemini-3-pro-image). GOAL Create a cinematic, hyperrealistic third-person action RPG screenshot featuring {{subject}}, in the visual style of {{style_reference}}, excluding {{negative_prompt}}. INPUTS TO COLLECT - subject: The hero character — suit design, power...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
- Hero's suit and power effects are described with original design language, not trademarked character names
- HUD text content is quoted exactly and each element's screen position is stated
- Three distinct lighting layers (ambient, storm, practical suit glow) are specified with color temperatures
Put this prompt to work.
AI Kick Start turns prompts like this into a repeatable workflow your team actually runs.
Plan a prompt system
