Key instructions to preserve
No beautification, no face reshaping, no expression change unless stated.
GuardrailDo not add religious symbols unless requested.
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 the central figure in a Gothic cathedral stained glass window — their face rendered in translucent colored glass in the medieval style, backlit by exterior daylight, surrounded by traditional lead caming and geometric border patterns. No halo or religious iconography unless naturally fitting — this is an artistic composition, not a religious statement. PHYSICS & CRAFT: Translucent cathedral glass — deep sapphire, ruby, and amber panes with realistic light transmission variation. Face section uses a lighter flesh-tone glass with lead line articulation following the subject's actual facial structure. Visible lead caming network throughout. Dust motes floating in the projected colored light beams onto the stone floor below. TECHNICAL EXECUTION: Interior photography looking up at the window, wide diffuse exterior daylight backlighting, 24mm f/5.6, stone tracery framing the window, colored light projection on the floor visible in foreground. HARD CONSTRAINTS: Do not add religious symbols unless requested. The face in the glass must be recognizably the uploaded person. Maintain the stained glass color palette strictly.
0 people have copied this prompt
Stained Glass Window Saint is a concept art prompt for GPT Image 2, composed for a 3:4 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 "24mm", "f/5.6", "backlighting", "ai image prompt", so you can identify which instruction changes the result.
Use the portrait frame for editorial-style compositions with enough surrounding context to establish the scene.
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.
