



Create a 3:4 vertical travel-memory poster using [LOCATION / DESTINATION / SUBJECT] as the only scene reference. COMPOSITION: Divide the image into two equal horizontal halves. TOP HALF — REAL PHOTOGRAPH: Preserve the original photograph as faithfully as possible, retaining recognizable architecture, natural proportions, perspective, lighting, shadows, and environmental details. Allow only subtle color correction and necessary cropping. Do not redesign or invent elements. BOTTOM HALF — POP-UP PAPER WORLD: Show a real open travel journal against a warm ivory background, with visible page thickness, a defined spine, gently curled corners, and tactile paper texture. Reconstruct the photograph’s most distinctive landmarks and environmental features as a miniature three-dimensional paper-cut scene rising from the pages. Use delicate architectural linework, restrained pastel coloring, layered cutouts, folded paper, realistic occlusion, and natural contact shadows. TRANSITION: Connect both halves organically using elements from the actual location, such as a river flowing into the book, a street continuing across the spine, or trees transforming into layered paper shapes. Make the transition feel spatially continuous rather than like a collage. STYLE: A sophisticated blend of authentic photography, handcrafted paper engineering, and minimalist travel-journal artistry. Preserve the destination’s identity and create the feeling of collecting a real place inside a book. Avoid turning the photograph into an illustration, flattening the paper scene, distorting landmarks, adding unrelated objects, excessive decoration, titles, readable text, or watermarks. FORMAT: 3:4 vertical, exact 50/50 horizontal split.
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: 3:4 · Poster · Vintage · Minimalist. 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.