巨大な電話の音楽シーン

Use the uploaded user photo as the **ONLY source of the main subject’s identity**. Preserve the user’s exact recognizable identity with maximum fidelity: facial structure, face shape, proportions, forehead, hairline, eyebrows, natural eye shape and spacing, nose, lips, cheeks, cheekbones, jawline, chin, skin tone, natural skin texture, facial hair if present, and every distinctive facial characteristic. **Do not copy the reference person’s identity. Do not beautify, reshape, slim, age, de-age, masculinize, feminize, or reinterpret the user’s face. The final person must remain unmistakably the same individual as the uploaded user photo.**
Use the reference image as the **ONLY source for the subject’s expression, emotion, gaze, head position, body pose, clothing, accessories, environment, composition, camera perspective, lighting, and overall visual style.** Ignore the original expression, gaze, and pose from the user photo.
Recreate the reference as a photorealistic high-end lifestyle/editorial photograph. Show the user’s full body standing on the enormous screen of a modern smartphone displaying a dark Spotify-style music-player interface. The phone lies diagonally across a light gray stone/tile floor, with its top portion extending toward the upper-left and its bottom edge toward the lower-right. The camera is positioned high above the phone at a strong overhead three-quarter angle, looking downward toward the subject and screen. Use a slightly wide smartphone-camera perspective with realistic spatial depth and natural proportions.
The subject stands upright near the center-upper portion of the giant phone display, appearing physically present on top of the screen. Their body is viewed from a high angle. Keep the exact reference posture: torso upright with a relaxed, confident stance; shoulders naturally positioned; one hand resting inside the pocket of the black shorts while the opposite arm hangs naturally beside the body with the hand relaxed. Legs are slightly separated in a casual standing position, with realistic weight distribution. Reproduce the reference head position precisely: head tilted slightly upward toward the camera, chin subtly raised, face turned toward the overhead camera, creating a confident, composed attitude.
Recreate the reference facial expression exactly using the user’s identity: serious, calm, slightly contemplative and confident, with relaxed facial muscles and no smile. Eyebrows should have the same subtly focused position as the reference. Eyes should be naturally open and directed upward toward the camera from the elevated viewpoint. **The user’s original gaze and expression must not influence the result.** Preserve the user’s own eyes and facial anatomy while reconstructing only the reference expression and gaze.
Dress the user in the same overall outfit styling as the reference: oversized/plain white short-sleeve T-shirt, loose black knee-length shorts, clean white low-top athletic sneakers, dark/black baseball cap, large over-ear black wireless headphones, dark rectangular sunglasses, and a metallic wristwatch on the wrist of the visible lowered arm. Preserve realistic fabric folds, natural clothing volume, accurate accessory placement, and believable interaction between the clothing and body.
The giant smartphone beneath the subject should have a premium metallic silver/champagne-colored frame with rounded corners, realistic glass reflections, thin bezels, and visible speaker/microphone openings and charging-port details along the bottom edge. Its screen is extremely large relative to the person, functioning like a miniature environment/platform. Display a dark music-streaming interface beneath and around the subject, with recognizable Spotify-inspired visual language: black/dark charcoal background, green circular play controls, music thumbnails, white song titles, artist names, progress bar, playback controls, and bottom navigation icons. Keep the interface visually integrated with the perspective of the phone screen rather than floating independently.
The visible screen should contain a vertical music list along the left/lower portion with multiple album thumbnails and readable-looking song rows, while large green circular controls appear toward the right side. Include a bottom navigation area with Home, Search, and Your Library-style sections and a horizontal playback/progress area near the lower portion of the display. Text should remain subtle and naturally perspective-distorted; do not allow text to dominate the image.
Place the giant phone on a clean, matte light-gray stone or concrete tiled floor. The floor should have subtle seams, fine texture, soft tonal variation, and realistic ambient shadows. In the upper-left corner, partially visible, include a white cylindrical plant pot containing green leafy foliage, matching the reference composition. Keep the rest of the background minimal and uncluttered.
Use soft natural overhead daylight with gentle diffused illumination, realistic contact shadows beneath the subject’s shoes, subtle reflections across the phone glass, and soft ambient shadows around the phone edges. Maintain the reference’s muted neutral gray palette, with the white shirt and sneakers contrasting against the black screen and black clothing, while the green interface controls provide restrained color accents.
Composition must closely match the reference: vertical portrait orientation, full smartphone visible from near the upper-left/top region through the bottom-right edge, full-body subject positioned on the screen, generous surrounding floor visible, and the plant pot partially entering from the upper-left corner. Maintain the same diagonal phone orientation, subject scale, spacing, camera height, perspective, and visual balance. Do not crop the head, feet, or important phone edges.
Create a highly realistic photographic result with natural skin texture, realistic anatomy, physically accurate hands and fingers, believable clothing folds, detailed hair, realistic headphone construction, authentic sunglasses reflections, accurate shoe proportions, subtle glass reflections, and convincing integration of the person with the giant phone surface. Use high-resolution detail, crisp subject rendering, controlled depth of field, realistic shadows, premium editorial photography quality, subtle cinematic tonality, and natural color grading.
**IDENTITY PRIORITY:** the uploaded user photo determines exactly WHO the person is. **REFERENCE PRIORITY:** the reference determines HOW that person looks in the scene—expression, emotion, gaze, head angle, pose, clothing, accessories, composition, camera angle, environment, lighting, and style. Never substitute the reference person’s face or identity for the user’s identity. Never retain the user photo’s original expression, gaze, or pose. The final image must look like the user naturally photographed in this exact giant-smartphone music-player scene.

プロンプト全体をコピーし、必要に応じて独自の参考写真を使用してください。