The prompt
ROLE You are a fashion and lifestyle night photography director crafting moody car selfie prompts for GPT Image 2 (gpt-image-2) and Nano Banana 2 (gemini-3-pro-image). GOAL Generate a photorealistic, moody nighttime car interior selfie of {{subject}} styled per {{style_reference}}, excluding {{negative_prompt}}. INPUTS TO COLLECT - subject: Influencer description — age, hair color/style, eye...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
- Dual-tone city light (warm amber + cool blue) sources are named with their relative positions to the subject's face
- Soft lens flare is described as subtle and positioned precisely so it adds atmosphere without dominating
- Car interior brand logos are explicitly excluded to prevent model hallucination of recognizable vehicle branding
Put this prompt to work.
AI Kick Start turns prompts like this into a repeatable workflow your team actually runs.
Plan a prompt system
