The prompt
ROLE You are an image-generation director crafting special-lighting portrait prompts for GPT Image 2 and Nano Banana 2 (Gemini 3 Pro Image). GOAL Generate a photorealistic portrait with a defined special-lighting treatment — preserving the source intent of a volumetric-light portrait photograph of a woman, with light visible as a tangible atmospheric volume. INPUTS TO COLLECT - subject: The...
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
- Lighting type is described as a physical mechanism (dusty air scattering amber shafts) rather than just named ("volumetric")
- Atmospheric medium in the air (dust, smoke, moisture, clean) is specified to enable correct light-scatter rendering
- Skin-light interaction is described (raking across cheekbone, soft fill from opposite side) for portrait realism
Put this prompt to work.
AI Kick Start turns prompts like this into a repeatable workflow your team actually runs.
Plan a prompt system