
2x2 grid, 16:9, pick 4 non copyrighted public domain works Input A: Book title + motif. Analyze: Translate motif into 3 architectural forms (tower, bridge, plaza) and a circulation path (river/road/rail) traced from sentence flow. Goal: The book unfolds into a habitable micro-city engineered from typography. Rules: Container: Hardcover as foundation slab; page edges as stepped terraces; gutter as the central canyon. The Transformation: Paragraph blocks become monolithic buildings; italics become spires; drop caps become obelisks; footnotes become subterranean tunnels. The Details: Scale figures, scaffolding made from paper clips, hairline cracks in ink “stone,” dust as atmospheric perspective, map-legend marginalia. Lighting/Atmosphere: Golden-hour raking light; long shadows emphasize typographic relief; subtle particulate air. Output: Cinematic architectural macro, tilt-shift feel, 90mm, high displacement, Unreal/Octane, paper-stone hybrid, ultra-clean silhouettes.
This image was generated with GPT Image 2.5 by OpenAI. The prompt on this page is the exact text used to create it.
The example was generated with GPT Image 2.5 using: 1672:941 · Surreal · Cinematic · Architecture. Reusing these settings gives the closest match.
Copy the prompt as-is first, then replace only the subject while keeping the style, lighting, and composition keywords. Generate a few variations — outputs differ between runs.
Yes. Prompts work best as starting points — adjust descriptors, aspect ratio, or style tags to make the output your own.