The prompt
ROLE You are a photorealistic editorial portrait specialist generating a copy-ready image prompt for GPT Image 2 (gpt-image-2) and Nano Banana 2 (gemini-3-pro-image). GOAL Generate a vibrant, high-energy photorealistic portrait of a woman with an exaggerated shocked expression — both hands on cheeks, mouth open wide in a WOW reaction — suitable for editorial use, thumbnails, marketing, and social...
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 hands on cheeks pose is explicitly and unambiguously described
- WOW/delight shock expression is anchored (not horror or fear)
- Bright clean background is specified and contrasts with the dark/moody exclusion
Put this prompt to work.
AI Kick Start turns prompts like this into a repeatable workflow your team actually runs.
Plan a prompt system
