Key instructions to preserve
No beautification, no face reshaping, no expression change unless stated.
GuardrailThe wok flame must follow real combustion physics — orange to white to transparent at the tip, not a CGI fireball.
IDENTITY LOCK: Use the uploaded photo as the sole identity reference. Preserve the subject's facial structure, skin tone, eye shape, hairstyle, and every distinguishing feature exactly — the person must remain instantly recognizable. No beautification, no face reshaping, no expression change unless stated. SCENE: Subject running a street food cart at a vibrant Asian night market — wok flames erupting as they toss an enormous wok full of stir-fry, the flame illuminating their face from below, market stall lights strung above, the market crowd blurred behind in warm evening light. PHYSICS & CRAFT: The wok flame is the primary light source — 1800K intense orange-white from below, creating dramatic uplight on the subject's face, the kind of live-fire cooking light that no photographer can plan. The market string lights behind are 2800K warm tungsten creating a second layer of warm ambient. Steam and wok smoke rise through the string lights. TECHNICAL EXECUTION: 35mm f/2.0 from across the cart at counter height, the wok flame peak freezing mid-burst, the subject's face lit from below and in front by the flame, market crowd beautifully bokeh'd behind. HARD CONSTRAINTS: The wok flame must follow real combustion physics — orange to white to transparent at the tip, not a CGI fireball. The subject's face, lit from below by real fire, must remain recognizable. Keep their own clothing plus a basic cooking apron.
0 people have copied this prompt
Street Food Cart at Night Market is a photorealistic prompt for GPT Image 2, composed for a 4:5 image. No beautification, no face reshaping, no expression change unless stated.
No beautification, no face reshaping, no expression change unless stated.
Keep the prompt structure, then replace the main subject, action, or environment in "No beautification, no face reshaping, no expression change unless stated.".
Adjust one visual signal at a time, such as "35mm", "f/2.0", "bokeh", "ai image prompt", so you can identify which instruction changes the result.
Keep the focal subject prominent in the portrait frame while preserving enough background detail for feed and poster layouts.
Use one clear reference image and retain the identity-lock instructions when changing clothing, lighting, background, or camera direction.
Use direct natural-language edits after the first generation. State what must remain unchanged before describing the single element you want to revise.
Judge the result by believable materials, natural anatomy, coherent light direction, and a camera perspective that matches the scene.
Three simple steps to generate your AI image.
Click the "Copy Full Prompt" button above to copy the entire prompt text to your clipboard instantly.
Open your preferred image generator and paste the prompt into the text input. You're ready to create.
Hit generate and watch the magic happen. Tweak the prompt parameters to make it your own.
