Travel AI image prompts

「{argument name="観光地" default="神戸"}の観光を案内するための情報が詰まった雑誌の表紙を生成して 」

Create a cinematic wide city poster for {argument name="city" default="Paris"} at sunrise, combining a romantic café scene with a surreal giant-object aesthetic. The composition is a 16:9 horizontal poster: the left two thirds are dominated by an enormous translucent red onion sliced open into sweeping concentric purple-pink arcs, each layer glossy, semi-transparent, and covered with sparkling dew droplets; the onion functions like a monumental architectural shell or pavilion beside the river. At the lower left, place a tiny Parisian café with a pink-and-white striped awning, warm interior light, a sign reading “Café de Paris,” potted flowers, a black menu board, a vintage streetlamp, wicker chairs, and small round café tables. Include exactly 8 visible human figures: 3 seated diners at the main foreground table, 1 standing waiter beside them in black vest and white apron, 2 seated guests at a midground table under the onion arch, and 2 seated guests at a farther right table near the water. The right third opens to a soft-focus Seine riverside view with a bridge and the Eiffel Tower in the hazy distance. Use pastel dawn lighting, peach-pink sky, golden rim light, shallow depth of field, reflective wet pavement, delicate bokeh, dreamy luxury travel-advertising mood, hyperreal 3D realism blended with painterly cinematic softness. Add elegant bottom-right typography: large Chinese headline “{argument name="headline text" default="早安，巴黎"}” with smaller English subtitle “{argument name="subtitle text" default="Good Morning, Paris"}” beneath it, both in a refined thin serif font, muted plum color, spacious letter spacing. Avoid modern cars, clutter, extra landmarks, extra text, logos, or watermarks.

A hyper-realistic optical-illusion photograph. The person from the uploaded reference portrait appears to be emerging from a freshly developed instant photo (Polaroid-style) lying on a small cafe table. Use the face of the person from the attached reference photo — keep their facial identity exactly as in the photo, do not change any facial features. In the instant photo frame, their full outfit is visible; in reality, their upper body and head rise out of the glossy print, casting a real shadow onto the table. Expression: Playful and confident eyes looking at the viewer, mouth pouting or blowing a kiss, chic and charming. Pose: Upper torso emerging out of the instant photo, one hand slightly forward as if stepping into reality, energetic and spontaneous. Clothing: High-neck knit turtleneck, premium textile detail, mini skirt and leather boots (boots visible clearly inside the instant photo). All handwritten annotations must be perfectly legible and NOT mirrored. Props: Glossy Polaroid print with subtle fingerprint smudges, frame text readable. Annotations on print: 'leather boots', 'clean turtleneck', 'mini skirt' written in white marker with arrows. Photography: DSLR photorealism, macro lens, forced-perspective composite realism, top-down 3/4 angle, soft overcast daylight, shallow DOF. Background: Paris sidewalk cafe in autumn, small espresso cup, fallen leaves, stone pavement, soft distant pedestrians bokeh. Mood: Fashion-forward, viral illusion, photoreal texture, not CGI. Constraints: Use uploaded reference identity, photorealistic skin texture, strong pop-out illusion with real shadows. Negative prompt: 3d, render, cgi, cartoon, anime, plastic skin, illegible text, mirrored text, uncanny face.

Generate a 9:16 vertical "Victorian Gothic Royal" realistic photo: Use the face of the person from the attached reference photo — keep their facial identity exactly as in the photo, do not change any facial features, eye spacing, nose bridge, lip shape, jawline, or cheekbone structure. The person wears a heavily embellished court dress in the "Victorian era (19th century) court style" direction (corset, large crinoline, lace/velvet, royal jewelry), photographed by Tower Bridge or Westminster Palace (Big Ben) in London. The image should have Harper's Bazaar-level photography, styling, and cover design, maintaining the magazine's signature design style (bilingual design). 【INPUTS】 FACE_REF: Attached facial reference image (identity lock) 【ABSOLUTE PRIORITY | Identity Lock (Highest Priority)】 100% restore facial features and bone structure from the reference: no drifting allowed. Real skin texture: visible fine texture and pores, no over-smoothing. 【SHOT TYPE | Choose one】 A) Half-body cover: Chest to above waist, jewelry, lace collar and eyes most clear B) Full-body cover: Complete head-to-toe presentation of the large crinoline silhouette combined with London landmarks, strong perspective (Maintain "cover composition", leaving white space for layout). 【LOCATION | Scene (London, UK)】 London landmarks: Thames riverside, background is the magnificent Gothic architecture of Westminster Palace (Big Ben) or Tower Bridge towers. Weather (random): 1) London fog 2) After rain (wet reflective ground). Clean background: No tourists, no modern signs. 【LIGHTING & CAMERA】 Lens feel: 85mm portrait quality (half-body) or 50mm/70mm (full-body), shallow depth of field, eyes sharpest. Lighting: Overcast diffused light + dramatic fill; diamonds/gems have real fire; velvet texture is deep. Colors: High-end cinematic feel, low-saturation blue-gray environment. 【WARDROBE | Victorian Court Dress】 Target aesthetic: "Wasp waist, large skirt, layered lace, heavy velvet, crown, queen aura". Upper body: Highly structured corset, square or high collar. Lower body: Huge crinoline or bustle. Fabrics: Heavy velvet, taffeta, Chantilly Lace. Headpiece: Victorian tiara or feather headdress. 【COLOR MATRIX | Royal Dark】 Randomly select 1: Scheme G (Royal Blue/Silver), Scheme A (Victorian Red/Gold), or Scheme R (Mourning Black/Gold). 【POSE | Cover Pose】 Half-body: Chin slightly raised, cold eyes, one hand gently touching necklace. Full-body: Standing upright, hands clasped on crinoline. Expression: Serious, haughty, imperious; absolutely no smile. 【OUTPUT】 1 vertical 9:16 realistic magazine cover-level photo.

A horizontal split-screen cinematic shot of Times Square, New York, seamlessly blending two different eras: 1920s on the left and present day on the right. On the left side (1920s): show era-appropriate architecture, vintage vehicles, and props from the 1920s. Use the face of the person from the attached reference photo for the person in this scene — keep their facial identity exactly as in the photo, do not change any facial features. The person wears authentic clothing from the 1920s, including era-appropriate accessories and typical items in their hands. The overall mood feels nostalgic and historically accurate. On the right side (present day): show the same Times Square in the modern era, with LED screens, modern vehicles, and current technology. Use the face of the person from the attached reference photo for the person in this scene — keep their facial identity exactly as in the photo. The person wears contemporary fashion that matches today’s style. In the center: the two eras merge and overlap organically. The person from the 1920s and the person from the present day (both using the identity from the reference photo) visually interact, look at each other, or walk through each other’s space. Architecture and environment smoothly morph from old to new. Photorealistic, 8k resolution, cinematic lighting, wide angle, highly detailed textures, rich sense of time-travel storytelling. Aspect Ratio: 4:3

A candid, raw smartphone selfie photo. The subject is the person from the attached reference photo — keep their facial identity exactly as in the photo, do not change any facial features. Sitting at an outdoor cafe in the center of Madrid, captured using a front-facing smartphone camera. Sunlight hits the face from the side, creating natural highlights and soft shadows, authentic daytime lighting with no artificial setup. The person has a relaxed, natural hair texture. The person wears a textured beige Zara-style blazer over a black top, effortless, everyday outfit styling. Natural daytime makeup, visible skin texture, no beauty retouching. A genuine, slight smile while looking directly at the phone camera. The image has a subtle grainy texture, reflecting a real smartphone photo aesthetic, as if shot on an iPhone 17 Pro Max. Overall mood: casual, warm, authentic, unposed. Feels like a spontaneous travel moment, not styled, not editorial, not influencer-like.

At the location of "Tokyo Tower", create an image based on the current local atmosphere and real-time weather. Use the face of the person from the attached reference photo — keep their facial identity exactly as in the photo, do not change any facial features. Integrate the person from the photo into the scene. Generate the scene: Generate a vertical 3:4 aspect ratio image with a fixed nine-grid layout, three rows and three columns, each grid as an independent shot. Camera and perspective: – Use an ultra-wide-angle or fisheye lens (approximately equivalent to a full-frame 12–18mm feel) – The camera angle must differ significantly from the original image; exaggerated camera positions that can be used include: low-angle, high-angle, ultra-low, or tilted "Dutch angle" composition – Always create a strong foreshortening effect: body parts closest to the lens appear huge, while the rest of the body extends into the distance in perspective – The final effect must resemble a bold fashion or street photography shot, completely realistic, not illustrative or anime-style Body parts close to the lens (1–2, sometimes 3): – In each edited image, select one or two main body parts to be extremely close to the lens – Vary these body parts across different images (hands, feet, knees, face, or shoulders) – The selected body parts should be extremely close to the lens, almost touching it, with clear visibility of skin texture, fabric texture, and realistic wide-angle distortion Pose and overall body (complex and varied): – Create strong, cool, dynamic poses that match the extreme perspective: standing, squatting, sitting, lying, or leaning significantly forward – Maintain plausible and credible human anatomy even under extreme foreshortening Camera position and attitude (randomized): – Randomly change the camera angle and direction while keeping the composition visually balanced – Maintain a cool, composed, confident attitude, leaning toward fashion magazine or street style – Facial expressions can vary (serious, playful, confident, mysterious, etc.), but they must always look like the person from the reference photo Lighting and rendering: – Maintain realistic shadows and contact with the ground/floor – High resolution and clear details, with visible skin texture, fabric texture, and material highlights Variation and randomness: – Each small image should be distinctly different in camera angle, pose type, and composition Strict rules: – Do not change the facial identity of the person from the reference photo – Do not change the type of clothing; only alter the presentation through poses and perspective – Do not move the scene outside the specified location – Do not add text, logos, or watermarks – Must maintain photorealistic effects

Create a striking Spring 2026 city poster for Boston with an elegant celebratory mood and a bold contemporary design. On a clean off-white textured background with generous negative space, place a miniature single sculler in the lower-right corner rowing across a narrow ribbon of reflective water. Let the wake curve upward and gradually transform into the Charles River, then into a dreamlike hand-painted panorama of Boston featuring the Back Bay skyline, Beacon Hill brownstones, Acorn Street, Boston Public Garden, Swan Boats, the Zakim Bridge, harbor ferries, and historic brick architecture. Add soft morning fog, golden spring light, subtle crimson and gold festive accents, layered depth, and premium editorial typography that reads "SPRING 2026" with a vertical slogan about river, memory, and invention. Vertical poster ratio, polished graphic-design finish.