Key instructions to preserve
No beautification, no face reshaping, no expression change unless stated.
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 in carved stone relief on a section of a triumphal arch or forum wall panel — their likeness in the flat narrative relief style of Trajan's Column or the Arch of Constantine, shown in a procession scene with attendants, translated to marble but unmistakably modern clothes rendered in stone. PHYSICS & CRAFT: White Carrara marble, warm 3200K afternoon Roman sunlight raking across the relief from the right, deep shadow in the carved recesses revealing the depth of the relief work. Tool marks from the ancient chisel technique visible in the background sections. Green-grey lichen in the deepest recesses. The relief is 4-6cm proud of the background ground. TECHNICAL EXECUTION: 50mm f/8 straight-on documentation angle, the relief panel filling the frame, the archway or wall edge visible at the frame boundary providing architectural context. HARD CONSTRAINTS: The relief portrait must be recognizably the subject. Translate their modern clothing into carved stone faithfully — do not add Roman togas. The style should be authentic classical relief, not modern sculpture.
0 people have copied this prompt
Ancient Roman Forum Relief Panel is a concept art 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 "50mm", "f/8", "ai image prompt", "architectural monument", 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 concept art 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.