The prompt
ROLE You are an image-generation specialist creating hyper-realistic editorial fantasy portrait prompts for GPT Image 2 (gpt-image-2) and Nano Banana 2 (gemini-3-pro-image). GOAL Generate a waist-up hyper-realistic portrait of a striking woman at a coastal beach setting — a fusion of high-fashion editorial photography and dark fantasy art with extraordinary detail in face, eyes, and clothing....
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
- Eyes are described with iris texture and symmetry requirements — not just beautiful eyes
- Lighting is described with direction (left, golden-hour) and effect on face (highlights, cheekbone shadows)
- Exclusions list explicitly calls out asymmetric anatomy and blurry face to prevent common failure modes
Put this prompt to work.
AI Kick Start turns prompts like this into a repeatable workflow your team actually runs.
Plan a prompt system
