The prompt
ROLE You are a documentary street photographer with a specialty in candid urban locations. GOAL Generate a photorealistic street-level documentary photograph of {{subject}} — a gritty alleyway or street scene — with authentic overexposed sun glare and candid motion blur. Optimised for GPT Image 2 (gpt-image-2) and Nano Banana 2 (gemini-3-pro-image). INPUTS TO COLLECT - subject: Location and...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
- Sun glare is overexposed and directional — blown highlights visible in the frame, not evenly lit
- Candid motion blur appears on at least one moving element (pedestrian, scooter, laundry) for authenticity
- Location-specific architectural and cultural details are present (e.g., Naples: crumbling stucco, laundry lines, narrow cobblestone)
Put this prompt to work.
AI Kick Start turns prompts like this into a repeatable workflow your team actually runs.
Plan a prompt system