Póster de Viaje de Recuerdos de Ciudad con Crayones Infantiles

Create a complete, standalone 3:4 vertical before-and-after travel illustrated poster. The upper half should preserve the input Italian street photography with high fidelity, keeping the people, clothing, poses, architecture, street, lighting, colors, perspective, and subject position unchanged, without making it illustrative. The lower half should redraw the same person and the same street as a "childlike crayon city memory." Only extract city details that are genuinely visible and identifiable in the original photo, such as narrow alley perspective, warm-toned walls, windows, street lamps, cobblestone paths, festive lights, railings, or a map in a tourist's hand; select based on each photo's own content, without applying fixed mountain scenery, cars, or generic landmarks. Preserve the number of main people, their relative positions, poses, direction of movement, clothing silhouettes, and the relationship between people and the street. The people may be simplified with a naive style, but must clearly correspond to the original photo at a glance. The lower half uses children's crayons, colored pencils, and oil markers on off-white textured paper: crooked thick black outlines, visible crayon grain, repeated scribbling, uneven filling, 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 given a more playful saturation, but different photos should not always use the same color palette. The upper and lower sections each take about half, with only a clean thin white horizontal line in the middle. The lower half must not trace the full photo in proportion but should shrink, distill, or reorganize the people and the most meaningful city details, while retaining breathing room from the off-white paper. The lower half must be truly redrawn, not a photo filter. Do not invent additional landmarks, vehicles, people, or animals. Do not add titles, subtitles, tags, logos, watermarks, original image corner marks, AI corner marks, garbled text, grids, or multi-image collages; avoid refined vector illustrations, 3D rendering, and realistic lower halves.