

Create an ultra-detailed miniature diorama of [PLACE / CITY / LANDMARK], transforming the real location into a tiny, handcrafted architectural model. SCENE: Recreate the destination’s most recognizable buildings, streets, transportation, surrounding landscape, and everyday activity with remarkable architectural accuracy. Include miniature vehicles, tiny people, trees, street furniture, and location-specific details to make the scene feel alive. MINIATURE STYLE: Make everything look like a meticulously constructed physical scale model, with realistic miniature materials, finely detailed architecture, tiny textures, and carefully crafted structures. Preserve the location’s authentic identity and distinctive features. CAMERA & COMPOSITION: Use an elevated three-quarter aerial view, showcasing the entire landmark and its surroundings. Apply a macro-photography aesthetic with shallow depth of field, a sharp central subject, and softly blurred distant areas. Maintain realistic proportions and convincing miniature scale. LIGHTING & ATMOSPHERE: Warm natural daylight, soft shadows, subtle atmospheric depth, cinematic color grading, and realistic material textures. The result should resemble professional tilt-shift photography of an elaborate architectural model. Automatically interpret [PLACE / CITY / LANDMARK] and include its most iconic features, appropriate transportation, local architecture, and recognizable surroundings. Avoid generic buildings, inaccurate landmarks, oversized objects, cartoon styling, excessive blur, plastic-looking textures, and distorted perspective. FORMAT: Vertical 4:5 composition, high resolution, photorealistic miniature craftsmanship.
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: 561:701 · Architecture · 3D Render · Cityscape. 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.