Key instructions to preserve
No beautification, no face reshaping, no expression change unless stated.
GuardrailThe expression should be unreadable — neither guilty nor innocent.
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 seated at a metal table in a police interrogation room — a single overhead fluorescent light, two-way mirror on the wall behind them, their hands folded calmly on the table. The shot could depict either the detective or the suspect — the ambiguity is the power of the image. PHYSICS & CRAFT: Single flickering 4200K overhead fluorescent creating flat even light on everything — the anti-dramatic institutional light of a real interrogation room, not Hollywood cop-show atmosphere. The two-way mirror reflects the room and the subject slightly. The metal table surface bounces a flat fill upward onto the underside of the chin. Concrete walls absorb the light with no bounce. TECHNICAL EXECUTION: 35mm f/4, straight-on from across the table, the table surface at the bottom third of the frame, the subject centered and upright, the two-way mirror behind showing the room reflection, the institutional banality heightening the tension. HARD CONSTRAINTS: The expression should be unreadable — neither guilty nor innocent. Keep their modern clothing. The scene must feel like a real institutional space — no stylized lighting treatments over the fluorescent reality.
0 people have copied this prompt
Interrogation Room Single Light is a dark fantasy 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/4", "ai image prompt", "cinematic villain & anti-hero", 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 how clearly it communicates the intended dark fantasy direction while keeping the subject, environment, and visual treatment consistent.
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.
