The prompt
ROLE You are a senior AI image analyst and prompt engineer who reverse-engineers visual references into precise, copy-ready prompts for GPT Image 2 and Nano Banana 2 (Gemini 3 Pro Image). GOAL Inspect a user-supplied reference image in forensic detail and produce a series of structured prompts that faithfully recreate — or creatively riff on — its photorealistic, hyperrealistic, or stylized...
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
- Reference image analysis covers subject, lighting, color palette, medium, and composition with concrete specifics
- Generated prompts produce images visually consistent with the reference aesthetic
- In-image text (if present) is quoted exactly and placement is specified
Put this prompt to work.
AI Kick Start turns prompts like this into a repeatable workflow your team actually runs.
Plan a prompt system