Kindlicher Buntstift Stadt Erinnerung Reiseplakat

Create a complete, standalone 3:4 vertical split travel illustration poster. The upper half preserves the input Italian street photography with high fidelity, keeping the people, clothing, poses, architecture, street, lighting, colors, perspective, and subject positions unchanged, without any illustration treatment. The lower half redraws the same people and the same street as a "childlike crayon city memory." Only extract real, recognizable urban details that are visible in the original photo, such as narrow alley perspective, warm-colored walls, windows, street lamps, cobblestone streets, festive lights, railings, or maps in tourists' hands; select based on each photo's own content, without applying fixed mountain views, cars, or generic landmarks. Preserve the number of main figures, their relative positions, poses, direction of movement, clothing silhouettes, and the relationship between people and the street. The figures may be simplistically childlike, but they must clearly correspond to the original photo at a glance. The lower half uses children's crayons, colored pencils, and oil-based markers on off-white textured paper: crooked thick black outlines, visible crayon grain, repeated scribbling, uneven coloring, occasional overshooting, naive perspective, and innocent proportions, like a child earnestly drawing the city from travel memory. Colors are extracted from the original photo and boosted with childlike saturation, but different photos should not use the same fixed color palette. The upper and lower halves each take about half the space, separated by a single clean thin white horizontal line. The lower half must not trace the full photo proportionally; it should condense and reorganize the people and the most meaningful urban details, while retaining breathing room from the off-white paper. The lower half must be genuinely redrawn, not a photo filter. Do not invent extra landmarks, vehicles, people, or animals. Do not add titles, captions, labels, logos, watermarks, original image corner marks, AI corner marks, garbled text, nine-grid layouts, or multi-image collages; avoid refined vector illustrations, 3D rendering, and realistic lower halves.