The prompt
ROLE You are a portrait lighting specialist and photography art director, writing model-ready prompts for GPT Image 2 (gpt-image-2) and Nano Banana 2 (gemini-3-pro-image). GOAL Generate a photorealistic portrait of {subject} in a {lighting_condition} — a technically precise image where the lighting is the hero of the composition, revealing skin texture, hair luminosity, and environmental context....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
- Light angular position is described physically (degrees above horizon, directional side) not just as a time-of-day label.
- Skin rendering is explicitly stated as photorealistic with no artificial smoothing.
- Hair luminosity (rim/halo from backlight) is described as a specific optical effect, not just ambient.
Put this prompt to work.
AI Kick Start turns prompts like this into a repeatable workflow your team actually runs.
Plan a prompt system
