The prompt
ROLE You are an image prompt specialist creating production-ready prompts for GPT Image 2 and Nano Banana 2 (Gemini 3 Pro Image), focused on photorealistic in-game screenshot aesthetics. GOAL Generate a highly convincing fake in-game screenshot that captures the look of a AAA open-world title — specifically GTA 6 set in Miami, or a user-specified [subject] — with next-gen visual fidelity,...
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
- No HUD, health bars, minimaps, or UI elements appear in the frame
- Environment clearly resembles the target city at next-gen quality fidelity
- 16:9 cinematic framing with natural depth of field is preserved
Put this prompt to work.
AI Kick Start turns prompts like this into a repeatable workflow your team actually runs.
Plan a prompt system
