#Long Distance

Use reference image 1 for the adult man's exact face and skin tone, and reference image 2 for the adult woman's exact face and skin tone. Preserve both identities and natural appearances. These may be separate photos supplied by a long-distance couple. Use a scene reference only for composition. Combine the two adults into one intimate fashion portrait against a plain warm-grey studio background. Place the man in the right foreground wearing a black ribbed turtleneck. He faces left in a clear side profile and looks beyond the frame. Place the woman slightly behind him on the left in a black square-neck outfit, looking directly toward the camera with a calm expression. His shoulder and profile overlap the right edge of her face slightly, while her visible eye, nose and mouth remain readable. Frame both people tightly from the top of their heads to the upper torso. Build a layered diagonal between the man's foreground profile and the woman's near-frontal gaze. Their bodies stand naturally close without merging, and neither person's neck or shoulder should disappear into the other. Keep the two identities distinct rather than blending their features. This can be a long-distance relationship keepsake made from separate photos, but the final composition is one shared studio scene. Light both subjects with one large diffused source from the left, using subtle fill to retain detail in the darker side of the faces. Match the direction and softness of shadows across both people. Preserve their individual skin tones and natural facial texture. The backdrop stays quiet and softly out of focus, with no visible props or decorative patterns. Use a natural portrait-lens perspective and enough depth of field to keep both the man's profile and the woman's visible eye clear. Show restrained fabric texture in the turtleneck and neckline. No hands are required in the crop. Avoid double exposure, pasted cutout edges, duplicated facial features and matching the scene example's faces instead of the uploaded identities. Full-colour vertical 9:16 photograph. Add a small, subtle semi-transparent "promptybox.com" watermark at bottom right. No other text, logos, duplicated faces, malformed hands or plastic skin.

Use [reference image 1] for the adult man's exact face and skin tone and [reference image 2] for the adult woman's exact face and skin tone. Preserve both identities and natural appearances. The two references may be separate photos taken in different places. Use any third scene reference for composition only, never for either identity. Create a photorealistic long-distance relationship portrait as a vertical diptych: two equal side-by-side panels separated by one fine straight seam. The man appears alone in the left panel and the woman alone in the right panel. They are on a video call from different apartments. Keep the spaces clearly separate; the relationship is conveyed through their expressions and inward-facing composition rather than physical contact. In the left panel, the man wears a charcoal knit sweater and sits beside a window overlooking cool blue evening city lights. He holds one plain phone upright at chest height and looks toward it with a gentle, attentive expression. In the right panel, the woman wears an ivory knit sweater and sits beside a warm amber lamp, with a different apartment window and dusk sky behind her. She holds one plain phone at chest height with a quiet, affectionate smile. Show phones from the back or an oblique angle, without readable screens or interface graphics. Use medium portraits at eye level, with both faces at a similar scale and their torsos turned slightly toward the centre. Preserve each person's exact identity from their own reference. Keep all hands inside their respective panels, with anatomically plausible fingers around the phones. Give each room its own believable light: cooler window light on the left, warmer lamplight on the right, without making either person's skin look unnaturally blue or orange. Render realistic knit texture, subtle facial detail, soft background depth and restrained reflections in the windows. Leave enough surrounding room detail to communicate distance, but keep both people as the clear focus. The mood is hopeful and connected. Avoid crying, heart-shaped overlays, floating chat bubbles, text captions, map graphics, duplicated phones or a hand reaching impossibly across the seam. This is one composed photographic diptych, not a screenshot of a video-call application. Create a full-colour vertical 9:16 image. Add a small, subtle, semi-transparent "promptybox.com" watermark at the bottom right. Avoid extra people, duplicated faces, distorted anatomy, plastic skin, unreadable text and unrelated logos.

Use [reference image 1] for the adult man's exact face and skin tone and [reference image 2] for the adult woman's exact face and skin tone. Preserve both identities and natural appearances. The two references may be separate photos taken in different places. Use any third scene reference for composition only, never for either identity. Combine the two adults into one photorealistic studio portrait, standing gently back to back. This is a long-distance relationship keepsake made from separate reference photos, so preserve both people instead of averaging their faces into new identities. The man stands slightly behind on the left in a tailored black collared shirt, looking calmly toward the camera. The woman stands in front on the right in a black V-neck blouse, with a delicate gold butterfly pendant. She raises her chin slightly and looks upward toward the right. Their shoulders touch naturally while their bodies remain separate. Use a clean off-white studio background and a vertical 9:16 crop from approximately the waist or mid-torso upward. Keep both faces fully visible and leave comfortable space above both heads. The man's face is slightly higher in the composition, creating a gentle diagonal toward the woman's face. Avoid a symmetrical passport-photo layout. No hands are needed in the frame, and no arms should appear to pass through the other person. Light the pair with one large soft studio source from the upper left, supported by gentle fill. Match the colour temperature, shadow direction and contrast across both people so they appear to share a real studio. Retain natural skin tones in a full-colour image; the black outfits and pale background provide the contrast. Keep fabric folds visible and give the small pendant realistic metal highlights without making it the focal point. Use a natural portrait-lens perspective and sufficient depth of field for both faces to be clear. Preserve fine facial texture and believable shoulder proportions. Do not copy clothing or backgrounds from the identity photos, blend the two faces, apply double exposure or turn the portrait into a cutout collage. The result should feel like a quiet fashion photograph of the same two people together. Create a full-colour vertical 9:16 image. Add a small, subtle, semi-transparent "promptybox.com" watermark at the bottom right. Avoid extra people, duplicated faces, distorted anatomy, plastic skin, unreadable text and unrelated logos.

Use the uploaded [reference image] as the subjects' exact faces, likeness and skin tone. Create a realistic image styled to look like an unedited, real photograph rather than a polished AI render. Subjects: a couple (faces from the [reference image]) sitting close together on a couch, one resting their head on the other's shoulder, both looking down at a phone screen between them, genuine soft smiles. Wardrobe: plain everyday loungewear, no styling. Setting: an ordinary living room, warm lamp light, a blanket draped over the couch arm. Lighting: soft uneven lamp light, natural and slightly warm. Camera: shot to look like it came from a real phone camera, slightly soft focus, natural imperfect framing. Mood: quiet, intimate, genuinely real. Rendering: intentionally imperfect — natural film-like grain, soft focus, natural unretouched skin texture, true-to-life warm lamp lighting, correct anatomy, no extra fingers. Add a small, subtle, semi-transparent "promptybox.com" watermark in the bottom-right corner. Aspect ratio 9:16. Optimised for Gemini and ChatGPT / DALL·E (also works in Midjourney). Parameters: --ar 9:16 --style raw --v 6 --stylize 150 --quality 2 --seed [insert seed] --iw [insert image weight 1-3 for the reference faces] --no distortion, extra limbs, warped hands, text artifacts, overly smooth skin, glossy AI look

Use the uploaded [reference image] as the subjects' exact faces, likeness and skin tone. Create a hyper-realistic, photorealistic image. Subjects: a couple (faces from the [reference image]) leaning together against a classic red British telephone booth, one resting their head gently on the other's shoulder, holding a to-go coffee cup. Wardrobe: he wears a cream knit sweater and grey cargo trousers; she wears a white fuzzy fur-textured coat, white trousers, and white sunglasses, with a white handbag. Setting: a London street beside the iconic red telephone booth, a red double-decker bus softly blurred passing in the background. Lighting: soft overcast daylight, cool and even. Camera: waist-up shot, shallow depth of field, the bus and street softly out of focus. Mood: relaxed, stylish, effortlessly cool travel-couple energy. Rendering: ultra-detailed and razor-sharp, natural skin texture with visible pores and fine detail, realistic fabric weave (knit, fur texture), true-to-life lighting and shadows, professional cinematic color grade, no distortion, no extra fingers, correct anatomy. Add a small, subtle, semi-transparent "promptybox.com" watermark in the bottom-right corner. Aspect ratio 4:5. Optimised for Gemini and ChatGPT / DALL·E (also works in Midjourney). Parameters: --ar 4:5 --style raw --v 6 --stylize 250 --quality 2 --seed [insert seed] --iw [insert image weight 1-3 for the reference faces] --no distortion, extra limbs, warped hands, text artifacts, visible logos or brand names

Use the uploaded [reference image] as the subjects' exact faces, likeness and skin tone. Create a hyper-realistic, photorealistic image. Subjects: a couple (faces from the [reference image]) close together, one standing behind with a direct, intense stare into the camera, lips slightly parted, an alert and moody expression; the other in front making a playful exaggerated growl expression with mouth open and one hand raised in a clawing gesture. Wardrobe: both wear matching grey furry hooded onesies with pointed wolf ears sewn into the hood, hoods up. Setting: a dim indoor room with a warm lamp glow and dark curtains softly visible in the background. Lighting: warm low ambient lamp light, soft shadow, cozy indoor feel. Camera: close waist-up shot, both faces and the raised clawing hand in frame. Mood: playful, silly, affectionate. Rendering: ultra-detailed and razor-sharp, natural skin texture with visible pores and fine detail, individually rendered fur texture on the onesie hoods, realistic fabric weave, true-to-life lighting and shadows, professional cinematic color grade, no distortion, no extra fingers, correct anatomy. Add a small, subtle, semi-transparent "promptybox.com" watermark in the bottom-right corner. Aspect ratio 4:5. Optimised for Gemini and ChatGPT / DALL·E (also works in Midjourney). Parameters: --ar 4:5 --style raw --v 6 --stylize 250 --quality 2 --seed [insert seed] --iw [insert image weight 1-3 for the reference faces] --no distortion, extra limbs, warped hands, text artifacts, blank expression, neutral expression

Use the uploaded [reference image] as the subjects' exact faces, likeness and skin tone. Create a hyper-realistic, photorealistic three-panel vertical grid image, all three panels the same size and framing. Subjects: the same couple (faces from the [reference image]) lying on their backs on green grass in all three panels, shot from directly overhead, heads tilted together near the center of each frame. Panel 1: both partners smiling naturally and warmly at the camera. Panel 2: he winks playfully while she smirks with one eyebrow slightly raised. Panel 3: both purse their lips in a playful kissy-face expression. Wardrobe: both wear simple solid dark-colored crew-neck t-shirts, identical across all three panels. Setting: closely mown green grass filling the frame in every panel, a thin white dividing line separating each panel. Lighting: soft even overcast daylight, consistent and matching across all three panels, no harsh shadows. Camera: directly overhead top-down shot, identical framing and distance in every panel. Mood: playful, lighthearted, candid. Rendering: ultra-detailed and razor-sharp, natural skin texture with visible pores and fine detail, individual hair strands, true-to-life lighting and shadows, professional cinematic color grade, no distortion, no extra fingers, correct anatomy. Add a small, subtle, semi-transparent "promptybox.com" watermark in the bottom-right corner. Aspect ratio 3:4. Optimised for Gemini and ChatGPT / DALL·E (also works in Midjourney). Parameters: --ar 3:4 --style raw --v 6 --stylize 250 --quality 2 --seed [insert seed] --iw [insert image weight 1-3 for the reference faces] --no distortion, extra limbs, warped hands, text artifacts, inconsistent framing between panels, mismatched lighting between panels

Use the uploaded [reference image] as the subjects' exact faces, likeness and skin tone. Create a hyper-realistic, photorealistic image. Subjects: a close low-angle selfie of a couple (faces from the [reference image]) — one partner leaning in close, pointing up toward the Eiffel Tower behind them; the other partner smiling directly at the camera. Wardrobe: he wears a dark button-up shirt and tortoiseshell sunglasses pushed up; she wears a light beige jacket and dark oversized sunglasses. Setting: the Eiffel Tower rising behind them against a bright blue sky with soft scattered clouds, a softly blurred crowd of tourists below. Lighting: bright natural daylight, slight wide-angle lens distortion typical of a close selfie shot. Camera: close selfie framing held at arm's length, both faces large in frame, tower sharp in the background. Mood: joyful, spontaneous, travel-selfie energy. Rendering: ultra-detailed and razor-sharp, natural skin texture with visible pores and fine detail, realistic fabric weave, true-to-life lighting and shadows, professional cinematic color grade, no distortion, no extra fingers, correct anatomy. Add a small, subtle, semi-transparent "promptybox.com" watermark in the bottom-right corner. Aspect ratio 4:5. Optimised for Gemini and ChatGPT / DALL·E (also works in Midjourney). Parameters: --ar 4:5 --style raw --v 6 --stylize 200 --quality 2 --seed [insert seed] --iw [insert image weight 1-3 for the reference faces] --no distortion, extra limbs, warped hands, text artifacts, visible logos or brand names

Use the uploaded [reference image] as the subjects' exact faces, likeness and skin tone. Create a hyper-realistic, photorealistic image. Subjects: a bride and groom (faces from the [reference image]) standing close together, both raising their hands toward the camera to show off matching wedding bands. Wardrobe: she wears a white gown with a pearl-beaded tiara and sheer veil, holding a bouquet of white lilies and orchids; he wears a black tuxedo with a white bow tie and a small white flower boutonniere, one eye closed in a playful wink. Setting: a softly lit indoor space with a dark wood-paneled wall behind them. Lighting: soft warm indoor light with a gentle highlight catching the rings. Camera: close mid-shot with both faces and both raised hands in frame, shallow depth of field. Mood: joyful, candid, "just married" celebration. Rendering: ultra-detailed and razor-sharp, natural skin texture with visible pores and fine detail, individual hair strands, realistic fabric weave, true-to-life lighting and shadows, professional cinematic color grade, no distortion, no extra fingers, correct anatomy. Add a small, subtle, semi-transparent "promptybox.com" watermark in the bottom-right corner. Aspect ratio 3:4. Optimised for Gemini and ChatGPT / DALL·E (also works in Midjourney). Parameters: --ar 3:4 --style raw --v 6 --stylize 250 --quality 2 --seed [insert seed] --iw [insert image weight 1-3 for the reference faces] --no distortion, extra limbs, warped hands, text artifacts, cleavage, revealing necklines

Use [reference image 1] as the exact face, likeness and skin tone of the first person, and [reference image 2] as the exact face, likeness and skin tone of the second person. These are two separate photos, taken apart — combine them naturally into ONE single photorealistic image, matching the scene below exactly. This is a "long-distance couple" prompt for people who can't currently be in the same place. Subjects: her face from [reference image 1], his face from [reference image 2], sitting up together in bed, a wooden breakfast tray between them with coffee cups, toast and fruit, both smiling at each other. Wardrobe: she wears a plain white oversized shirt, he wears a plain grey t-shirt, hair soft and undone, relaxed morning look. Setting: a bright bedroom with white linen bedding, sheer curtains softly diffusing morning light in the background. Lighting: warm soft morning sunlight streaming in from one side, gentle natural shadow, airy and bright overall tone. Camera: full-frame, 50mm lens, waist-up framing, shallow depth of field with the curtains softly blurred. Mood: warm, relaxed, lazy-Sunday-morning intimacy. Rendering: ultra-detailed and razor-sharp, natural skin texture with visible pores and fine detail, individual hair strands, realistic fabric weave, consistent single light source and color grade across both frames so the pairing looks intentional, correct anatomy, no distortion, no extra fingers. Add a small, subtle, semi-transparent "promptybox.com" watermark in the bottom-right corner. Aspect ratio 3:4. Optimised for Gemini and ChatGPT / DALL·E (also works in Midjourney). Parameters: --ar 3:4 --style raw --v 6 --stylize 300 --quality 2 --seed [insert seed] --iw [insert image weight 1-3 per reference face] --no distortion, extra limbs, warped hands, mismatched lighting, text artifacts

Use [reference image 1] as the exact face, likeness and skin tone of the first person, and [reference image 2] as the exact face, likeness and skin tone of the second person. These are two separate photos, taken apart — combine them naturally into ONE single photorealistic image, matching the scene below exactly. This is a "long-distance couple" prompt for people who can't currently be in the same place. Subjects: her face from [reference image 1], his face from [reference image 2], seated close together on a window seat, her head resting on his shoulder, both looking out at the rain, two warm mugs of coffee held between them. Wardrobe: she wears a soft oversized cream knit sweater, he wears a plain grey henley, both cozy and casual. Setting: indoors beside a large rain-streaked window, soft grey daylight outside, a blanket draped over their laps. Lighting: soft, cool window light on their faces, warm interior lamp glow filling the shadows, gentle contrast between the cool outside and warm inside. Camera: full-frame, 50mm lens, three-quarter framing, shallow depth of field with the rain-streaked glass softly blurred. Mood: cozy, quiet, intimate rainy-day comfort. Rendering: ultra-detailed and razor-sharp, natural skin texture with visible pores and fine detail, individual hair strands, realistic fabric weave, consistent single light source and color grade across both frames so the pairing looks intentional, correct anatomy, no distortion, no extra fingers. Add a small, subtle, semi-transparent "promptybox.com" watermark in the bottom-right corner. Aspect ratio 4:5. Optimised for Gemini and ChatGPT / DALL·E (also works in Midjourney). Parameters: --ar 4:5 --style raw --v 6 --stylize 300 --quality 2 --seed [insert seed] --iw [insert image weight 1-3 per reference face] --no distortion, extra limbs, warped hands, mismatched lighting, text artifacts

Use [reference image 1] as the exact face, likeness and skin tone of the first person, and [reference image 2] as the exact face, likeness and skin tone of the second person. These are two separate photos, taken apart — combine them naturally into ONE single photorealistic image, matching the scene below exactly. This is a "long-distance couple" prompt for people who can't currently be in the same place. Subjects: her face from [reference image 1], his face from [reference image 2] — each shown as a separate phone lock-screen wallpaper, both phones placed together in one scene. Details: both phone lock screens show the same time and date, a lock icon, and status bar; her hand reaches out from her screen toward his, fingers gently touching his chin — as if she's reaching through the screen to him. Wardrobe: she wears a fitted rose-pink tank top with wavy hair down; he wears a dusty-rose zip hoodie with his arms crossed, a wristwatch visible. Setting: both phones standing upright side by side on a warm wooden tabletop, a softly blurred evening city skyline glowing through a window behind them, warm ambient room lighting. Lighting: warm golden interior light on the tabletop and phone frames, the soft glow of each phone screen lighting their faces gently from the front. Camera: full-frame, 50mm lens, eye-level with the two phones, both screens sharp and legible. Mood: tender, playful, long-distance-relationship "reaching across the distance" concept — designed for couples who can't be photographed in person. Rendering: ultra-detailed and razor-sharp, natural skin texture with visible pores and fine detail, individual hair strands, realistic fabric weave, consistent single light source and color grade across both frames so the pairing looks intentional, correct anatomy, no distortion, no extra fingers. Add a small, subtle, semi-transparent "promptybox.com" watermark in the bottom-right corner. Aspect ratio 3:4. Optimised for Gemini and ChatGPT / DALL·E (also works in Midjourney). Parameters: --ar 3:4 --style raw --v 6 --stylize 300 --quality 2 --seed [insert seed] --iw [insert image weight 1-3 per reference face] --no distortion, extra limbs, warped hands, mismatched lighting, text artifacts

Use [reference image 1] as the exact face, likeness and skin tone of the first person, and [reference image 2] as the exact face, likeness and skin tone of the second person. These are two separate photos, taken apart — combine them naturally into ONE single photorealistic image where they appear physically together in the same scene, as if photographed side by side in person. This is a "long-distance couple" reunion-style prompt for people who can't currently be in the same place. Subjects: her face from [reference image 1], his face from [reference image 2], appearing together in one seamless scene. Wardrobe: she wears a soft pink ribbed knit top and a delicate thin necklace, hair in loose soft waves; he wears a relaxed white button-up shirt and a simple silver watch. Pose: lying on their backs in a wildflower meadow, her head resting near his shoulder with hair gently overlapping, hands loosely clasped between them, both smiling softly up at the camera. Setting: a meadow of green grass dotted with small pink and white wildflowers and clover. Composition: overhead top-down shot, both subjects centered, flowers scattered around the frame edges. Lighting: warm soft late-afternoon sunlight, gentle golden tone, soft flattering shadows. Camera: overhead shot, 35mm lens, crisp detail throughout. Mood: romantic, warm, nostalgic long-distance-reunion aesthetic. Rendering: ultra-detailed and razor-sharp, natural skin texture with visible pores and fine detail, individual hair strands, realistic fabric weave, consistent single light source and color grade across both people so the merge looks seamless and unedited, correct anatomy, no distortion, no extra fingers. Add a small, subtle, semi-transparent "promptybox.com" watermark in the bottom-right corner. Aspect ratio 9:16. Optimised for Gemini and ChatGPT / DALL·E (also works in Midjourney). Parameters: --ar 9:16 --style raw --v 6 --stylize 300 --quality 2 --seed [insert seed] --iw [insert image weight 1-3 per reference face] --no distortion, extra limbs, warped hands, mismatched lighting, text artifacts

Use [reference image 1] as the exact face, likeness and skin tone of the first person, and [reference image 2] as the exact face, likeness and skin tone of the second person. These are two separate photos, taken apart — combine them naturally into ONE single photorealistic image where they appear physically together in the same scene, as if photographed side by side in person. This is a "long-distance couple" reunion-style prompt for people who can't currently be in the same place. Subjects: her face from [reference image 1], his face from [reference image 2], appearing together in one seamless scene. Wardrobe: she wears a fitted red tank top; he wears a plain black crew-neck t-shirt. Pose: both lying on their backs in the grass, heads tilted together near the top of the frame, hands linked with fingers interlaced between them, both looking straight up at the camera with calm, content expressions. Setting: a bed of lush green grass scattered with tiny white wildflowers, soft dappled shade at the frame edges. Composition: shot directly from above (top-down bird's-eye view), both subjects centered, grass filling the frame around them. Lighting: soft natural daylight filtering through leaves, gentle dappled light and shadow across the grass, even matching skin tones on both faces. Camera: overhead shot, 35mm lens, everything in sharp focus. Mood: tender, warm — the reunited-at-last feeling this prompt trend is built for. Rendering: ultra-detailed and razor-sharp, natural skin texture with visible pores and fine detail, individual hair strands, realistic fabric weave, consistent single light source and color grade across both people so the merge looks seamless and unedited, correct anatomy, no distortion, no extra fingers. Add a small, subtle, semi-transparent "promptybox.com" watermark in the bottom-right corner. Aspect ratio 9:16. Optimised for Gemini and ChatGPT / DALL·E (also works in Midjourney). Parameters: --ar 9:16 --style raw --v 6 --stylize 300 --quality 2 --seed [insert seed] --iw [insert image weight 1-3 per reference face] --no distortion, extra limbs, warped hands, mismatched lighting, text artifacts