Key instructions to preserve
No beautification, no face reshaping, no expression change unless stated.
GuardrailThe subject's face must be completely calm — this is the entire point.
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 walking toward camera in slow-motion action-movie style, a massive explosion blooming orange and black behind them — they don't look back, expression completely calm, clothing catching the explosion wind blast, the scene impossibly cool. PHYSICS & CRAFT: The fireball behind is physically accurate — orange core, black smoke billowing upward and outward, the shockwave creating visible air distortion between the explosion and the subject. The explosion light — 2000K intense orange — creates a dramatic warm backlight on the subject, rim-lighting their hair and shoulders while the camera-facing front of the body is lit by the cooler 5500K ambient daylight ahead. Clothes are slightly buffeted by the blast wind. TECHNICAL EXECUTION: 85mm f/2.8 from ahead of the subject at slightly below eye level, the explosion framed symmetrically behind the subject, the fireball peak at the top of the frame, wide enough that the explosion scale is awe- inspiring. HARD CONSTRAINTS: The subject's face must be completely calm — this is the entire point. Keep their clothing unchanged. The explosion must follow combustion physics — correct orange-black-grey smoke stratification. Do not make the explosion cartoonish.
0 people have copied this prompt
Anti-Hero Mid-Explosion Walk- Away is a dark fantasy prompt for GPT Image 2, composed for a 16:9 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 "85mm", "f/2.8", "backlight", "ai image prompt", so you can identify which instruction changes the result.
Use the wide frame to establish the environment, place supporting details around the subject, and maintain a clear focal point.
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.
