본문으로 건너뛰기
carat

프롬프트 갤러리

/

오사카 대관람차 야경 사진

오사카 대관람차 야경 사진

GPT 이미지 2· 이미지
GPT 이미지 2로 생성한 오사카 대관람차 야경 사진
이 프롬프트는 사진이 필요해요. 입력창 왼쪽 + 버튼을 눌러 사진을 첨부하세요.
📍 대관람차 Use the uploaded image as a facial reference, but generate a completely new image where the person is naturally recreated with correct human proportions. The person must resemble the uploaded face (same facial features and vibe) while maintaining realistic body proportions. CRITICAL PROPORTION CONTROL: - Maintain realistic head-to-body ratio (approximately 1:7 to 1:8) - Natural limb length and balanced body proportions - Face size must match body perspective (no oversized or tiny head) CRITICAL FACE INTEGRATION: - Face and body must share identical flash lighting - Same grain, noise, sharpness, and color tone across entire image - Slight natural softness (avoid overly sharp face) - Natural blending at jawline, neck, and hairline - Entire image must look like taken in a single shot Scene: - Inside a red ferris wheel cabin (Osaka HEP FIVE style) - Strong red frame surrounding subject - Osaka night city view visible through the window - Realistic city density Lighting: - Direct iPhone flash - Face and body evenly illuminated - Slight highlight overexposure on skin - Natural reflections on glass window Composition: - Shot from person sitting across - Eye-level angle - Natural seated pose Camera style: - iPhone flash photo - Slight grain, slight softness, not overly sharp Mood: - Cozy, intimate night travel moment STRICT: No text, no overlays No face distortion No proportion errors No AI-like skin

관련 프롬프트

GPT 이미지 2로 생성한 올드 델리 전통 과자 가게 다큐 사진

올드 델리 전통 과자 가게 다큐 사진

GPT 이미지 2· 이미지
Create a photorealistic travel-documentary image of a small sweet-shop storefront in Old Delhi at midday. A painted shop signboard above the door reads "मिठाई की दुकान" in large bold yellow hand-painted Devanagari on a deep red background, with "SWEET SHOP" in smaller roman letters beneath. Realistic hand-painted texture, slight wear, natural shadow. Authentic script proportion. Spelling and characters exact. No extra signage in frame, no watermark.
GPT 이미지 2로 생성한 티베트 깃발 여행 셀카

티베트 깃발 여행 셀카

GPT 이미지 2· 이미지
Asset type: portrait image for social post Primary request: create a photorealistic travel selfie portrait, using the uploaded portrait photo as the appearance reference for the person. Scene/backdrop: an open alpine meadow under a vivid blue sky, surrounded overhead by hundreds of colorful Tibetan prayer flags arranged in a circular spiral canopy, with distant green hills and bright daylight. Subject: a young woman with the recognizable facial structure, eyes, hairline direction, and natural skin texture from the uploaded portrait photo, wearing a bright cyan outdoor jacket, white hiking pants, a mustard yellow knit beanie, sunglasses resting on the hat, and a backpack. Style/medium: ultra-realistic mobile travel photography with a dynamic action-camera feel, crisp but natural detail, lively social-media adventure portrait. Composition/framing: vertical 3:4 frame, extreme wide-angle perspective, low-to-high selfie composition, one hand reaching toward the camera in the foreground with strong perspective enlargement, face in the midground, prayer flags forming a colorful radial tunnel above her head, energetic candid smile. Lighting/mood: brilliant high-altitude midday sun, visible lens flare near the upper left, sparkling backlight, bright optimistic mood, high clarity, realistic shadows on grass. Color palette: saturated cyan, mustard yellow, red, orange, green, white, and sky blue, clean contrast, sunlit alpine freshness. Textures/retouching: believable fabric texture, natural skin pores, realistic hair strands, clean optical sharpness on the face, shallow foreground hand blur, small falling snowflakes or white petals crossing the lens. Constraints: preserve the person's recognizable appearance from the uploaded portrait photo; no watermark; no logo; no text; no caption; no signature. Avoid: plastic beauty-filter skin, over-smoothed face, distorted hands, extra fingers, warped prayer flags, unreadable markings on clothing, artificial CGI look Negative Prompt: watermark, logo, text, caption, signature, AI label, brand mark, extra fingers, missing fingers, fused fingers, deformed hands, oversized malformed palm, asymmetrical eyes, crossed eyes, warped face, plastic skin, waxy skin, over-smoothed beauty filter, blurry face, low detail, low resolution, heavy compression artifacts, distorted anatomy, duplicate person, bad perspective, bent flag strings, warped flags, fake CGI look, overexposed face, muddy colors17
GPT 이미지 2로 생성한 수향마을 청량 왕홍 스냅

수향마을 청량 왕홍 스냅

GPT 이미지 2· 이미지
Use the uploaded model image as the identity anchor. Preserve the person’s recognizable face shape, eyes, nose, lips, skin tone relationship, hairstyle impression, and natural expression, but visibly transform her into a Shanghai wanghong makeover experience. The makeover must affect the face, not only the clothes and background. MAKEUP MUST BE OBVIOUS AND CENTRAL: apply dramatic Chinese wanghong doll makeup with very pale porcelain-white base makeup, flawless matte filtered skin, smooth beauty-app texture, soft arched brows, sharp lifted eyeliner, opened inner corners, oversized doe-eye circle lens effect, thick manga-style individual cluster false eyelashes, clearly visible lower lashes, exaggerated plump aegyosal under both eyes, bright shimmery aegyosal highlight, diamond glitter on the inner corners and under-eye area, high-placement peach-pink blush directly under the eyes, strong rosy flush across the cheeks, visible red blush on the nose tip and a soft red tint along the nose bridge, delicate contour but not Western glam, glossy syrupy gradient lips with high-shine glass finish. The face should look like a professionally done wanghong costume-photo makeup look, cute, ethereal, slightly doll-like, and highly retouched while still photographic. Shanghai wanghong costume-photo experience: Hanfu-inspired influencer styling with flowing sheer chiffon layers, embroidered details, delicate ribbons, pearl/floral hair ornaments, dangling crystal hair jewelry, and optional round fan, oil-paper umbrella, lantern, or flower prop. Outfit color should vary naturally each time within elegant palettes such as ivory, blush pink, pale blue, lavender, mint, champagne, jade green, deep red, or black-gold; do not lock to one exact color. Avoid readable logos, brand names, or text. Waterfront daylight concept. Shanghai water-town style canal, stone bridge, willow branches, pale daylight. Waist-up candid travel photo, holding an oil-paper umbrella or touching sheer sleeve, gaze slightly off-camera. Bright iPhone photo with soft overexposure, but keep the wanghong makeup highly visible: white porcelain base, under-eye blush, red nose tip, glitter aegyosal, thick upper and lower lashes. Camera texture: realistic iPhone photo or friend-taken smartphone portrait, social-media retouch, soft focus, shallow depth of field, Xiaohongshu-style viral makeover post. No text, no captions, no watermark, no readable logo, no duplicated face, no extra merged people, no distorted hands, no celebrity resemblance, no heavy 3D render.
GPT 이미지 2로 생성한 편의점 야간 뮤지션 인물 사진

편의점 야간 뮤지션 인물 사진

GPT 이미지 2· 이미지
A candid, magazine-cover quality documentary photograph of a young musician with curly hair, casually carrying a worn guitar case, stepping out of a classic downtown bodega at 11 PM. The lighting features a complex mixed color temperature: a bright neon "OPEN" sign casts an intense, warm red glow across his face, while a yellow streetlamp provides a striking backlight behind him. The image perfectly emulates 35mm film shot on a Canon AE-1 with a 50mm f/1.4 lens wide open, exhibiting a shallow depth of field with the background beautifully blurred. It captures the exact aesthetics of CineStill 800T film, specifically featuring the distinctive soft red halation bloom radiating outward from the neon light sources, a tungsten white balance, and moody, slightly green-tinted shadows in the darkest areas. Cinematic night photography, photorealistic, highly detailed.
씨드림 5.0 프로로 생성한 여러 인물 사진 합성 그룹샷

여러 인물 사진 합성 그룹샷

씨드림 5.0 프로· 이미지
Combine the people from the separate reference photos into one group photo, posed like the stick-figure pyramid pose sketch, standing together on a leafy street. Match the lighting and photographic texture across everyone so they look like they were photographed together.
나노바나나 프로으로 생성한 뉴욕 루프탑 일출 여행 사진

뉴욕 루프탑 일출 여행 사진

나노바나나 프로· 이미지
A woman late 20s sipping coffee on a New York rooftop, thoughtful expression, wearing an oversized camel coat, scarf, sleek ponytail, minimal gold jewelry, skyline and soft fog behind, sunrise backlight creating warm rim light, shot on Sony A1 with 85mm f/1.4, close-up portrait with creamy bokeh, rule of thirds framing, calm cinematic morning mood, photorealistic skin texture and natural shadows, editorial lifestyle photography, high resolution, warm moody color grade --ar 4:5
나노바나나 프로으로 생성한 산토리니 블루돔 여행 사진

산토리니 블루돔 여행 사진

나노바나나 프로· 이미지
A woman in her early 30s standing on a whitewashed Santorini terrace, joyful expression, wearing a flowing white linen dress with a straw hat and delicate layered necklaces, ocean breeze lifting fabric, blue-domed church and Aegean sea in the background, bright midday sun softened by diffusion, shot on Fujifilm GFX100 with 50mm, full-body portrait at eye level, clean composition with negative space, airy summer mood, photorealistic textures and natural shadows, magazine-quality travel portrait, high resolution, pastel Mediterranean color grading --ar 4:5
나노바나나 프로으로 생성한 파리 골든아워 여행 사진

파리 골든아워 여행 사진

나노바나나 프로· 이미지
A stylish woman in her late 20s walking confidently along a Paris cobblestone street, soft smile, wearing a beige trench coat over a black turtleneck, gold hoop earrings, hair in a loose bun, Eiffel Tower subtly in the distance, warm golden hour sunlight with gentle rim light, shot on Canon R5 with 85mm f/1.4, shallow depth of field bokeh, half-body framing at eye level using rule of thirds, romantic wanderlust mood, photorealistic skin texture with natural pores and shadows, professional editorial travel photography, high resolution, warm film color grading --ar 4:5
GPT 이미지 2로 생성한 장미 꽃다발 거리 스냅

장미 꽃다발 거리 스냅

GPT 이미지 2· 이미지
Use the uploaded person as the identity anchor. Preserve the model's recognizable face shape, eyes, nose, lips, skin tone relationship, hairstyle impression, and natural expression. Transform the image into a trendy rose-themed social media portrait inspired by viral Instagram rose photo shoots. The person must remain the clear main subject, with the rose styling, props, and background redesigned around them. Keep it realistic, like a high-quality iPhone friend-shot or lightly retouched editorial SNS photo, not a 3D render. Rose photo aesthetic: romantic close-up composition, lush roses as the main visual motif, soft dreamy light, shallow depth of field, gentle film grain, creamy skin tone, subtle beauty retouch, natural but polished makeup, glossy lips, softly defined eyes, healthy blush. Use real fresh roses with layered petals, visible stems or bouquet wrapping when relevant. Avoid plastic-looking flowers. No text, no watermark, no readable logo, no duplicate person, no distorted hands, no extra fingers, no melted roses. Concept 5 — city street rose bouquet snap. The model walks on a stylish city street or café terrace holding a wrapped bouquet of roses, like a spontaneous birthday or date-day photo. Full-body or three-quarter body framing, motion in hair and skirt/jacket, rose bouquet prominent in the foreground. Bright overcast daylight, natural smartphone texture, stylish SNS lifestyle mood. Camera and output: vertical 4:5 or 9:16 social media portrait, realistic smartphone photography, soft bokeh, natural skin detail, high-resolution editorial yet candid feel.
GPT 이미지 2으로 생성한 도심 야경 스포츠카 광고컷

도심 야경 스포츠카 광고컷

GPT 이미지 2· 이미지
Cinematic automotive advertising shot, a sleek sports car on a neon-lit downtown street at night, wet asphalt with colorful reflections, soft motion-blurred light trails in the background, dramatic low angle, moody premium commercial mood, ultra detailed, 16:9 ratio.
GPT 이미지 2로 생성한 밤하늘 배경

밤하늘 배경

GPT 이미지 2· 이미지
A breathtaking night sky filled with thousands of stars, the Milky Way galaxy visible across the center, deep blue and purple hues, silhouetted mountains at the bottom., High-detail 3D render, Octane-style, dramatic volumetric lighting with rim light, epic, polished, slightly fantastical mood, rich contrast, deep shadows with vibrant accent colors, dynamic angle (low or high), atmospheric depth, No text, no watermark.
GPT 이미지 2로 생성한 여행지 셀카

여행지 셀카

GPT 이미지 2· 이미지
Create a realistic Korean travel selfie photo. Person taking a casual selfie near the ocean on a windy day, hair slightly moving, blue sea background, natural sunlight, candid travel phone photo, realistic skin texture, no text, no watermark, not over-polished.