Key instructions to preserve
No beautification, no face reshaping, no expression change unless stated.
GuardrailThe face must be recognizably the subject.
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 depicted as a mermaid in the deep ocean — photographed from slightly below the water surface looking up, their tail coiling in the deep behind them, hair drifting upward through shafts of surface light filtering down from a tropical ocean above, a coral reef and schools of fish in the background. PHYSICS & CRAFT: Underwater optics — caustic light patterns from surface ripples painting moving patterns on the subject and the coral behind. The water is clear Caribbean blue — deep cyan at distance, lighter aqua near the surface light shafts. The tail is bioluminescent blue-green scales with realistic fish-scale structure, the light from the surface giving the scales their characteristic iridescent shimmer. The subject's hair streams naturally upward in the water with realistic wet physics. TECHNICAL EXECUTION: 16mm f/8 underwater wide angle, the subject from the waist up filling the upper frame, the tail sweeping into the lower depth, surface light creating god rays from above. HARD CONSTRAINTS: The face must be recognizably the subject. Do not significantly alter the torso or upper body structure. Hair behavior must follow realistic underwater physics. The tail must have realistic ichthyological scale structure, not costume-fabric appearance.
0 people have copied this prompt
Mermaid Beneath the Surface 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 "16mm", "f/8", "wide angle", "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 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.
