carat

Galeri prompt

/

인스타그램 피드 템플릿

Masuk
Daftar

인스타그램 피드 템플릿

GPT Image 2· Gambar
GPT 이미지 2로 생성한 인스타그램 피드 템플릿
a graphic design Instagram feed template mockup with a 3-column grid of square photo placeholder frames, top profile section with circular avatar placeholder and username text area, pastel mint and cream color scheme, modern minimal UI layout design, vertical scroll format, clean vector graphic illustration style, flat shapes and outlines. premium graphic design layout, strong hierarchy, modular grid, tasteful typography placeholders. front-facing centered composition with generous padding. soft pastel palette with warm highlights. Make the subject immediately recognizable at thumbnail size. Use clean composition, purposeful details, and no watermark. Keep the layout organized, readable, and purposeful; avoid clutter and illegible typography.
Instagram Feed TemplatePoster, Branding & Graphic DesignInstagram PhotoSNS Marketing ImageLicense Plate FrameInstagram CarouselFlea Market Design가격표 Farmers Market Price Tag스토리 템플릿 Instagram Story TemplateGPT Image 2
fal:223227

Prompt terkait

GPT 이미지 2로 생성한 명패 디자인

명패 디자인

GPT Image 2· Gambar
A sleek modern office desk name plate with brushed metal surface and engraved typography on a wooden base, minimalist corporate aesthetic, soft directional light highlighting the metal texture., Photorealistic product photography, soft diffused studio lighting, gentle highlights and shadows, clean, premium, editorial mood, natural saturated colors with subtle warmth, centered or slight Dutch angle, shallow depth of field, blurred gradient background, No text, no watermark.
GPT 이미지 2로 생성한 접시 일러스트

접시 일러스트

GPT Image 2· Gambar
photograph, Glimmerglass micro-diffusion on skin only. Crystal clear on product. Lifted blacks to soft gray. Overexposed highlights high-key. Skin L0-L1 glass reflection poreless. Flat front lighting no shadows. White or pale pastel background. Ultra-clean digital. No grain. Hasselblad X2D, clean vector sticker illustration of a white ceramic plate, round dinner plate with a decorative rim, dining icon style, white and blue palette, centered composition, thick crisp outline, flat colors, light background. No text, no watermark, no 3D render, no warm yellow tones, no film grain, no harsh shadows.
fal:213615
GPT 이미지 2로 생성한 쇼츠 배경

쇼츠 배경

GPT Image 2· Gambar
Square preview of a vertical short-form video background template, energetic layered gradient in electric violet, cyan and coral, subtle radial speed lines and soft glowing geometric accents, clean central safe area for future subject placement, balanced modern creator aesthetic, no platform branding. No text, no logo, no watermark.
fal:237174
GPT 이미지 2로 생성한 깨끗한 의원 홍보 비주얼

깨끗한 의원 홍보 비주얼

GPT Image 2· Gambar
밝고 청결한 현대식 의원 내부, 따뜻한 자연광이 들어오는 대기실, 파스텔 블루와 화이트 톤, 미니멀한 인테리어와 초록 식물 포인트, 깔끔한 안내 데스크, 신뢰감 있고 전문적인 분위기, 부드러운 그림자, 의료 브랜드 홍보용 광고 비주얼, 고해상도 사진
AI-generated 1. json prompt version ```json { "subject": { "description": "A croppe… made with Midjourney

Eyes in Editing Interface Close-up

Midjourney· Gambar
1. json prompt version ```json { "subject": { "description": "A cropped, low-resolution digital image of a person's eyes inside a rectangular selection box, resembling an image-editing canvas or screenshot. Only the eye area and eyebrows are visible; the rest of the face and body are cut off.", "mirror_rules": "Not a mirror selfie. Preserve the screen-capture / interface-editing feel rather than treating it as a conventional portrait.", "age": "adult or young adult, exact age unclear due to extreme crop and pixelation", "expression": { "eyes": { "look": "wide, direct, slightly tense gaze", "energy": "alert, uncanny, quietly confrontational", "direction": "looking straight toward the viewer" }, "mouth": { "position": "not visible", "energy": "not applicable" }, "overall": "fragmented and decontextualized, with the eyes carrying all emotional weight" }, "face": { "preserve_original": "Preserve the exact cropped eye-band framing, visible eyebrows, dark pupils, low-resolution halftone texture, and slight pink-gray screen tint.", "makeup": "No clear makeup is visible. The face should read as a raw, pixelated screen image rather than a polished beauty portrait." } }, "hair": { "color": "not visible", "style": "not visible", "effect": "not applicable" }, "body": { "frame": "not visible", "waist": "not visible", "chest": "not visible", "legs": "not visible", "skin": { "visible_areas": "Only a narrow strip of facial skin around the eyes, eyelids, under-eye area, bridge of the nose, and brow region is visible. No shoulders, chest, waist, hips, legs, back, or arms are visible.", "tone": "pale pink-gray skin tone distorted by screen pixels and scanline-like color separation", "texture": "The skin appears roughened by digital pixel structure, like it would feel visually grainy or screen-printed rather than physically smooth; any natural skin texture is obscured by the low-resolution display pattern.", "lighting_effect": "The skin is not lit by natural photographic light; it appears illuminated through a flat digital screen or screenshot, with no realistic shadow depth, only pixel-level contrast and faint magenta-gray banding." } }, "pose": { "position": "Only the eyes are framed horizontally inside a selected rectangular crop.", "base": "No body pose visible.", "overall": "The composition feels like a fragment being actively selected, edited, or dragged inside a design interface." }, "clothing": { "top": { "type": "not visible", "color": "not visible", "details": "not visible", "effect": "not applicable" }, "bottom": { "type": "not visible", "color": "not visible", "details": "not visible" } }, "accessories": { "device": "Implied computer interface or editing software canvas", "prop": "Multiple oversized black-and-white mouse cursor arrows surrounding and pointing toward the selected eye image" }, "photography": { "camera_style": "Not a traditional photograph; a screenshot-like digital collage or UI-capture aesthetic with a pasted low-resolution eye image.", "angle": "Straight-on, flat frontal view with no perspective depth.", "shot_type": "Extreme close-up crop of eyes embedded in a graphic interface composition.", "aspect_ratio": "Overall image is near 4:5 vertical canvas; the selected eye strip is a long horizontal rectangle.", "texture": "Visible pixel grid, moire-like vertical RGB scanlines, compressed low-res texture, hard-edged UI elements, clean white canvas background.", "lighting": "Flat screen illumination, no cinematic lighting, no natural directionality; contrast comes from the digital image and interface overlay.", "depth_of_field": "No optical depth of field; all elements appear flattened like a graphic screenshot." }, "background": { "setting": "Minimal white digital workspace or blank canvas", "wall_color": "white", "elements": [ "bright cyan-blue rectangular selection outline", "round blue resize handles on corners and midpoints", "small dark floating size tooltip near the top-right edge", "several repeated mouse cursor arrows arranged around the eye crop", "large empty white space above and below the selected image" ], "atmosphere": "Sparse, internet-art, meme-adjacent, slightly uncanny and obsessive", "lighting": "Pure digital white background with no physical environmental light" }, "the_vibe": { "energy": "hyper-focused, intrusive, glitchy", "mood": "uncanny, anxious, surveillance-like, absurdly intimate", "aesthetic": "early internet collage, screenshot art, low-res UI manipulation, digital found-image surrealism", "authenticity": "Should feel like an imperfect screenshot taken during editing, not a clean vector recreation or polished poster.", "intimacy": "The extreme eye crop creates uncomfortable closeness while the interface elements keep it emotionally detached.", "story": "It feels as if someone had been selecting a stranger's gaze on a blank canvas, and the repeated cursors are still converging on it.", "caption_energy": "something that was clicked too many times, a gaze trapped inside an editing box" }, "constraints": { "must_keep": [ "white blank background", "horizontal rectangular crop containing only both eyes and eyebrows", "cyan-blue selection box with circular resize handles", "visible pixelated / scanline texture across the eye image", "multiple large black-and-white cursor arrows pointing toward or around the eyes", "small size-tooltip near the upper right of the selection box", "flat screenshot-like composition", "uncanny direct gaze" ], "avoid": [ "do not turn it into a full-face portrait", "do not add visible body, clothing, hair, or environment", "do not make the image high-fashion or cinematic", "do not remove the UI selection handles", "do not smooth out the pixel grid", "do not replace the cursors with realistic hands or objects", "do not add dramatic shadows or realistic depth" ] }, "negative_prompt": [ "full body", "full face", "beauty portrait", "cinematic lighting", "realistic background", "smooth skin", "high resolution glamour", "fashion editorial", "hands", "extra facial features", "removed cursor arrows", "removed selection box", "3D depth", "polished vector art" ] } ``` 2. Natural language prompt Create a flat, screenshot-like digital collage on a mostly blank white canvas. In the center, place a long horizontal rectangular crop showing only a person's eyes, eyebrows, eyelids, under-eye area, and a narrow strip of pale pink-gray facial skin. The gaze should look straight at the viewer, wide and slightly tense, with an uncanny, alert emotional residue. Do not show the full face, mouth, hair, body, clothing, shoulders, chest, waist, hips, legs, arms, or any physical environment. The eye crop should look low-resolution and screen-captured, with visible pixel grid, vertical RGB scanline texture, faint moire, compression artifacts, and a slightly gray-magenta digital tint. The skin should not look polished or naturally lit; it should feel visually grainy, like a rough screen-printed or monitor-textured surface rather than smooth real skin. Lighting should be flat screen illumination with no realistic shadows, no cinematic directionality, and no depth-of-field blur. Surround the eye strip with a bright cyan-blue editing selection rectangle, including circular resize handles on the corners and midpoints. Add a small dark size-tooltip near the upper-right edge of the selected rectangle, as if the image is actively being resized in editing software. Place several oversized black-and-white mouse cursor arrows around the eye crop, some pointing toward the eyes and some overlapping the area below, creating a repetitive obsessive clicking energy. The composition should remain front-facing, flat, and graphic, with a near 4:5 vertical canvas and a large amount of empty white space above and below the selected eye strip. Preserve the imperfect screenshot feeling: slightly awkward placement, low-res texture, hard UI edges, and a casual internet-art quality. The image should feel as if someone had been selecting a stranger's gaze on a blank canvas, and the cursors are still converging on it. Avoid turning it into a full portrait, beauty shot, fashion editorial, cinematic scene, polished vector poster, or realistic environment. Keep the selection box, cursor arrows, pixelation, flat white background, and direct uncanny gaze as the core visual identity.
d1f13b0062b253274393e0ac28bf3555
AI-generated { "subject": { "description": "A young adult woman sitting in a dim in… made with Midjourney

Vintage Flash Indoor Portrait

Midjourney· Gambar
{ "subject": { "description": "A young adult woman sitting in a dim indoor corner, facing the camera from a slightly low and close angle. The image feels like a vintage flash snapshot with a private-room atmosphere, quiet melancholy, and a slightly underground poster-wall aesthetic.", "mirror_rules": "Not a mirror selfie; keep it as a direct close-range seated snapshot. The camera should sit slightly below face level, with a little tilt, imperfect framing, and possible edge obstruction.", "age": "young adult woman, early 20s", "expression": { "eyes": { "look": "looking directly into the camera, calm and slightly vacant", "energy": "low-energy, restrained, faintly tired, emotionally withheld", "direction": "gaze slightly lowered from under the bangs toward the photographer" }, "mouth": { "position": "lips naturally closed with a soft lip line", "energy": "cool, quiet, no visible smile" }, "overall": "a still, distant expression, as if captured by flash right after she sat down quietly" }, "face": { "preserve_original": "Preserve the small rounded face shape, soft jawline, large eyes, thick bangs covering part of the forehead, and the realistic flash highlight across the face.", "makeup": "A cool vintage makeup style inspired by East Asian fashion aesthetics: soft matte base, muted pink-brown eyeshadow, thin eyeliner, natural under-eye highlight, low-saturation blush, and soft rose-brown lips. Keep it slightly imperfect, with subtle smudging, darkness, and snapshot realism." } }, "hair": { "color": "deep black or near black-brown", "style": "shoulder-length bob with thick straight bangs, softly inward-curled ends, side hair close to the cheeks", "effect": "soft but heavy silhouette in the dark, with faint cool-white flash reflections on a few strands; overall subdued by the night interior" }, "body": { "frame": "slim, small-framed body; the seated pose makes the silhouette feel compact and inward", "waist": "mostly hidden under the loose cardigan, only subtly suggested by the inward posture", "chest": "the V-neck cardigan reveals the collarbones, a small central upper-chest area, and a hint of the inner white layer; the focus should stay on the neckline shape rather than exaggeration", "legs": "both legs bent in the foreground; one knee is raised close to the camera, the other leg folds sideways below; thighs and knees are clearly visible and softly flash-lit", "skin": { "visible_areas": "Visible skin includes the face, neck, collarbones, a small upper-chest area, subtle hand or wrist shadow areas, thighs, knees, and the upper edge of the lower legs. Shoulders, back, waist, hips, and buttock-adjacent areas are mostly covered and should not be additionally exposed.", "tone": "light beige to warm ivory skin tone, appearing slightly cooler and paler under direct flash, with faint green-blue color shift in the shadows", "texture": "realistic human skin texture: visually fine and smooth, as if it would feel soft, cool, and lightly velvety to the touch. The legs have a mild flash sheen but should never look plastic or over-smoothed.", "lighting_effect": "direct on-camera flash hits the face, collarbones, and knee, creating local bright spots and fast-falling shadows. Highlights are slightly hard, shadows fall into dark greenish-black film grain, and edges are mildly soft." } }, "pose": { "position": "sitting on the floor or a low step, body tucked into the lower center of the frame", "base": "one leg raised near the lens, the other folded sideways; arms naturally gathered in front or hidden by long loose sleeves", "overall": "inward, quiet, slightly guarded posture, like a close candid photo taken in a narrow room or corridor corner" }, "clothing": { "top": { "type": "loose V-neck knitted cardigan with a pale camisole or tank top edge visible underneath", "color": "light gray cardigan with an off-white inner layer", "details": "soft fuzzy knit texture, long sleeves, relaxed neckline, slightly thick body, front buttons or a lightly closed placket", "effect": "the fabric looks thick, warm, soft, and slightly fuzzy to the touch; the oversized fit makes the figure appear smaller and more intimate" }, "bottom": { "type": "short bottom mostly hidden by the cardigan, paired with black knee-high or long socks", "color": "mostly black lower styling with dark socks", "details": "black socks cover the lower legs, ending below the knees; the exposed leg skin contrasts strongly with the dark socks" } }, "accessories": { "jewelry": "layered delicate necklaces, two thin chains with small pendants resting near the collarbones; possible tiny earrings but not visually dominant", "device": "no visible handheld device", "prop": "vintage posters, stickers, or magazine pages on the wall creating dense visual texture" }, "photography": { "camera_style": "low-light close-range flash portrait, like a compact digital camera, disposable film camera, or phone flash snapshot; keep grain, slight blur, color cast, dirt, and imperfect exposure", "angle": "slightly below eye level, mild upward angle; the subject tilts her face downward toward the camera; the frame feels slightly tilted and compressed", "shot_type": "close seated portrait from upper body to thighs, with knees and legs entering the foreground and the poster wall compressed behind the head", "aspect_ratio": "vertical 2:3 or 3:4", "texture": "high-ISO grain, old-photo haze, flash dust specks, shadow noise, slight motion blur, soft edges, dark vignette", "lighting": "main light is direct front on-camera flash, illuminating the face, neckline, cardigan, and knee; background exposure is uneven, posters catch partial glare, while the right side and lower frame fall into deep shadow; no polished fill light or rim light", "depth_of_field": "shallow to medium depth of field; the face is relatively clear, while legs and background are slightly soft, like an inexpensive camera autofocus result in darkness" }, "background": { "setting": "dim indoor room, corridor corner, or basement-like private space", "wall_color": "dark wall covered in posters, overall blue-green, gray-black, and dark brown tones", "elements": [ "dense vintage film or music posters", "blurred text and image collage", "dark vertical edge or doorframe on the right", "dark obstruction or shadow block on the left", "wooden or dark floor visible at the bottom" ], "atmosphere": "narrow, humid, nocturnal, private, slightly underground, like the moment after a quiet conversation had already happened", "lighting": "very weak ambient light, mostly dependent on camera flash; uneven background brightness, slight poster reflection, greenish-black noise in the shadows" }, "the_vibe": { "energy": "hushed, still, darkened, faintly rebellious yet tired", "mood": "vintage, lonely, intimate, cool, with a night-after feeling", "aesthetic": "East Asian / Japanese-inspired retro girl portrait, Y2K dark-room feeling, flash film snapshot, underground poster wall, non-commercial casual photography", "authenticity": "preserve imperfections: color cast, noise, flash overexposure, crushed blacks, off-center framing, messy posters, slight missed focus", "intimacy": "the photographer feels very close, like a familiar person taking a quiet late-night room snapshot", "story": "She had just sat in a corner covered with old posters; the room was dark, the flash suddenly fired, and it left behind a silent, cool moment.", "caption_energy": "like a short social caption: 'the things left unsaid that night.'" }, "constraints": { "must_keep": [ "young adult woman seated in a dark indoor corner", "black shoulder-length bob with thick bangs", "quiet cool expression looking directly at the camera", "loose light-gray V-neck knit cardigan", "collarbones and small upper-chest area visible", "bent seated legs with one knee close to the camera", "black long socks", "dense vintage poster wall background", "direct front-flash film snapshot look", "shadow noise, color cast, slight blur, and candid realism" ], "avoid": [ "overly commercial studio portrait", "plastic skin smoothing", "exaggerated sensual pose", "adding extra exposed skin not present in the reference", "bright clean modern bedroom", "perfectly symmetrical composition", "ultra-sharp noise-free image", "visible brand text, watermark, or username", "AI-looking facial features or hands" ] }, "negative_prompt": [ "overexposed studio light", "plastic skin", "perfect symmetry", "clean luxury room", "sharp commercial portrait", "extra fingers", "distorted hands", "bad anatomy", "heavy retouching", "glamour pose", "logo", "watermark", "readable text", "oversaturated colors" ] }
b900c8b6415bb719a8271c4e1d222c95
AI-generated Сториборд из 9 кадров сеткой 3x3 в стиле скриншотов из современной вид… made with GPT Image 2

Miami Car Wash Storyboard

GPT Image 2· Gambar
Сториборд из 9 кадров сеткой 3x3 в стиле скриншотов из современной видеоигры с открытым миром, эстетика неонового приморского города 80-х в духе Майами. Сквозная героиня всех кадров: Камила - латиноамериканка с длинными вьющимися тёмными волосами, в розовом слитном купальнике с надписью Ocean Drive и белых кроссовках. Машина одна и та же: чёрный советский запарожец, в начале весь в засохшей грязи, к финалу отполирован до блеска. Локация: открытая ручная автомойка Ocean Drive Car Wash в солнечном приморском городе - пальмы, выцветший мурал Car Wash на бетонной стене, мокрый асфальт с лужами. На каждом кадре игровой интерфейс: крупный номер кадра в углу, плашка задания миссии, круглая мини-карта внизу слева; все надписи интерфейса на английском.Кадр 1: ночь, героиня сидит на чёрном спортбайке у входа, неоновая вывеска Ocean Drive CAR WASH и вертикальный неон WASH WAX SHINE REPEAT, отражения неона в мокром асфальте, плашка NEW SIDE MISSION - CAR WASH.Кадр 2: день, героиня со спины идёт к грязной машине с синим ведром, зелёным шлангом и жёлтой губкой, задание Grab your gear.Кадр 3: поливает машину из шланга, веер брызг искрится на солнце, задание Pre-rinse the vehicle.Кадр 4: намыливает капот большой жёлтой губкой, густая пена по кузову, задание Soap it up.Кадр 5: на корточках оттирает губкой литой диск колеса, рядом синее ведро с логотипом мойки, задание Scrub the details. Focus on the wheels.Кадр 6: смывает пену струёй из шланга, хлопья пены сползают с крыши, задание Rinse it off.Кадр 7: полирует крыло жёлтой микрофиброй, чёрный лак блестит, задание Dry and shine.Кадр 8: экран MISSION PASSED - Car Wash, ниже REWARD $1,250 и REP +750, довольный клиент в тёмных очках и гавайской рубашке протягивает деньги, субтитр Thanks, Camila. She's spotless.Кадр 9: финал - сияющий чёрный запарожец со спины на закате, небоскрёбы и пальмы приморского города, розово-оранжевое небо, отражения в мокром покрытии, подпись Ocean Drive.Фотореализм уровня некстген-игры, тёплый солнечный свет, влажные отражения, высокая детализация кожи и материалов.
531fd5e104c1b79ef4fae3de6f90c8ae
AI-generated Urban Fashion Editorial Poster made with GPT Image 2

Urban Fashion Editorial Poster

GPT Image 2· Gambar
1. json prompt version ```json { "subject": { "description": "A cropped, low-resolution digital image of a person's eyes inside a rectangular selection box, resembling an image-editing canvas or screenshot. Only the eye area and eyebrows are visible; the rest of the face and body are cut off.", "mirror_rules": "Not a mirror selfie. Preserve the screen-capture / interface-editing feel rather than treating it as a conventional portrait.", "age": "adult or young adult, exact age unclear due to extreme crop and pixelation", "expression": { "eyes": { "look": "wide, direct, slightly tense gaze", "energy": "alert, uncanny, quietly confrontational", "direction": "looking straight toward the viewer" }, "mouth": { "position": "not visible", "energy": "not applicable" }, "overall": "fragmented and decontextualized, with the eyes carrying all emotional weight" }, "face": { "preserve_original": "Preserve the exact cropped eye-band framing, visible eyebrows, dark pupils, low-resolution halftone texture, and slight pink-gray screen tint.", "makeup": "No clear makeup is visible. The face should read as a raw, pixelated screen image rather than a polished beauty portrait." } }, "hair": { "color": "not visible", "style": "not visible", "effect": "not applicable" }, "body": { "frame": "not visible", "waist": "not visible", "chest": "not visible", "legs": "not visible", "skin": { "visible_areas": "Only a narrow strip of facial skin around the eyes, eyelids, under-eye area, bridge of the nose, and brow region is visible. No shoulders, chest, waist, hips, legs, back, or arms are visible.", "tone": "pale pink-gray skin tone distorted by screen pixels and scanline-like color separation", "texture": "The skin appears roughened by digital pixel structure, like it would feel visually grainy or screen-printed rather than physically smooth; any natural skin texture is obscured by the low-resolution display pattern.", "lighting_effect": "The skin is not lit by natural photographic light; it appears illuminated through a flat digital screen or screenshot, with no realistic shadow depth, only pixel-level contrast and faint magenta-gray banding." } }, "pose": { "position": "Only the eyes are framed horizontally inside a selected rectangular crop.", "base": "No body pose visible.", "overall": "The composition feels like a fragment being actively selected, edited, or dragged inside a design interface." }, "clothing": { "top": { "type": "not visible", "color": "not visible", "details": "not visible", "effect": "not applicable" }, "bottom": { "type": "not visible", "color": "not visible", "details": "not visible" } }, "accessories": { "device": "Implied computer interface or editing software canvas", "prop": "Multiple oversized black-and-white mouse cursor arrows surrounding and pointing toward the selected eye image" }, "photography": { "camera_style": "Not a traditional photograph; a screenshot-like digital collage or UI-capture aesthetic with a pasted low-resolution eye image.", "angle": "Straight-on, flat frontal view with no perspective depth.", "shot_type": "Extreme close-up crop of eyes embedded in a graphic interface composition.", "aspect_ratio": "Overall image is near 4:5 vertical canvas; the selected eye strip is a long horizontal rectangle.", "texture": "Visible pixel grid, moire-like vertical RGB scanlines, compressed low-res texture, hard-edged UI elements, clean white canvas background.", "lighting": "Flat screen illumination, no cinematic lighting, no natural directionality; contrast comes from the digital image and interface overlay.", "depth_of_field": "No optical depth of field; all elements appear flattened like a graphic screenshot." }, "background": { "setting": "Minimal white digital workspace or blank canvas", "wall_color": "white", "elements": [ "bright cyan-blue rectangular selection outline", "round blue resize handles on corners and midpoints", "small dark floating size tooltip near the top-right edge", "several repeated mouse cursor arrows arranged around the eye crop", "large empty white space above and below the selected image" ], "atmosphere": "Sparse, internet-art, meme-adjacent, slightly uncanny and obsessive", "lighting": "Pure digital white background with no physical environmental light" }, "the_vibe": { "energy": "hyper-focused, intrusive, glitchy", "mood": "uncanny, anxious, surveillance-like, absurdly intimate", "aesthetic": "early internet collage, screenshot art, low-res UI manipulation, digital found-image surrealism", "authenticity": "Should feel like an imperfect screenshot taken during editing, not a clean vector recreation or polished poster.", "intimacy": "The extreme eye crop creates uncomfortable closeness while the interface elements keep it emotionally detached.", "story": "It feels as if someone had been selecting a stranger's gaze on a blank canvas, and the repeated cursors are still converging on it.", "caption_energy": "something that was clicked too many times, a gaze trapped inside an editing box" }, "constraints": { "must_keep": [ "white blank background", "horizontal rectangular crop containing only both eyes and eyebrows", "cyan-blue selection box with circular resize handles", "visible pixelated / scanline texture across the eye image", "multiple large black-and-white cursor arrows pointing toward or around the eyes", "small size-tooltip near the upper right of the selection box", "flat screenshot-like composition", "uncanny direct gaze" ], "avoid": [ "do not turn it into a full-face portrait", "do not add visible body, clothing, hair, or environment", "do not make the image high-fashion or cinematic", "do not remove the UI selection handles", "do not smooth out the pixel grid", "do not replace the cursors with realistic hands or objects", "do not add dramatic shadows or realistic depth" ] }, "negative_prompt": [ "full body", "full face", "beauty portrait", "cinematic lighting", "realistic background", "smooth skin", "high resolution glamour", "fashion editorial", "hands", "extra facial features", "removed cursor arrows", "removed selection box", "3D depth", "polished vector art" ] } ``` 2. Natural language prompt Create a flat, screenshot-like digital collage on a mostly blank white canvas. In the center, place a long horizontal rectangular crop showing only a person's eyes, eyebrows, eyelids, under-eye area, and a narrow strip of pale pink-gray facial skin. The gaze should look straight at the viewer, wide and slightly tense, with an uncanny, alert emotional residue. Do not show the full face, mouth, hair, body, clothing, shoulders, chest, waist, hips, legs, arms, or any physical environment. The eye crop should look low-resolution and screen-captured, with visible pixel grid, vertical RGB scanline texture, faint moire, compression artifacts, and a slightly gray-magenta digital tint. The skin should not look polished or naturally lit; it should feel visually grainy, like a rough screen-printed or monitor-textured surface rather than smooth real skin. Lighting should be flat screen illumination with no realistic shadows, no cinematic directionality, and no depth-of-field blur. Surround the eye strip with a bright cyan-blue editing selection rectangle, including circular resize handles on the corners and midpoints. Add a small dark size-tooltip near the upper-right edge of the selected rectangle, as if the image is actively being resized in editing software. Place several oversized black-and-white mouse cursor arrows around the eye crop, some pointing toward the eyes and some overlapping the area below, creating a repetitive obsessive clicking energy. The composition should remain front-facing, flat, and graphic, with a near 4:5 vertical canvas and a large amount of empty white space above and below the selected eye strip. Preserve the imperfect screenshot feeling: slightly awkward placement, low-res texture, hard UI edges, and a casual internet-art quality. The image should feel as if someone had been selecting a stranger's gaze on a blank canvas, and the cursors are still converging on it. Avoid turning it into a full portrait, beauty shot, fashion editorial, cinematic scene, polished vector poster, or realistic environment. Keep the selection box, cursor arrows, pixelation, flat white background, and direct uncanny gaze as the core visual identity.
d1f13b0062b253274393e0ac28bf3555
AI-generated Graveyard Plague Doctor Poster made with Midjourney

Graveyard Plague Doctor Poster

Midjourney· Gambar
A plague doctor with a textured mask, holding a lantern and a staff with a cross, standing in a graveyard, dynamic pose, surrounded by skulls and remains, Raven, hazy architectural background, dramatic high contrast lighting, realistic 4K --chaos 11 --ar 2:3 --exp 35 --raw --sref 931379730 3600739026 2856554496 2403970710 --profile gw85t4j rxbd514 --hd --preview
b5dc213527df2ee94adde656a8c477f2
AI-generated Geoje gyaru vlog screenshot collage made with GPT Image 2

Geoje Gyaru Vlog Screenshot

GPT Image 2· Gambar
Use image 1 only for the adult woman's identity and facial structure. Use images 2 and 3 only as styling references, not identity. Create a vertical 4:5 Korean pop-culture Instagram carousel card with two stacked realistic smartphone vlog screenshots. The same woman appears in both screenshots, transformed into a clearly recognizable modern Japanese/Korean gyaru style. Mandatory gyaru styling: voluminous glossy warm-blonde hair with soft big waves and face-framing pieces; dramatic doll-eye gyaru makeup with extended black winged eyeliner, thick upper and lower false lashes, visible lower-lash definition, glittery aegyo-sal highlight, bright filtered complexion, pink blush, glossy overlined pink lips. Add maximalist Y2K/kawaii accessories: layered silver and pearl necklaces, heart charms, phone strap charms, multiple rings, rhinestone bracelets, tiny plush keychain, decorative hair clips. Outfit must be hyper-feminine and kitsch: pale pink cat-ear cap or fuzzy animal-ear hood, fitted turquoise or baby-blue top, lace camisole layer, ruffled mini skirt or layered lace trim, pink/teal color accents. Top screenshot: inside a small Korean tour bus, close selfie angle, she does a gyaru peace sign near her cheek with a playful pout. Bottom screenshot: sunny Geoje seaside harbor with boats and low mountains, she crouches in a cute exaggerated pose, showing the layered outfit and accessories. Add a rounded white Korean caption sticker near the lower left that clearly reads exactly: ‘거제도 갸루 브이로그♡’. Fan-edit collage layout, realistic smartphone video-still texture, high-key daylight, slightly overexposed social-media filter, cute chaotic Y2K vibe. Avoid natural minimal makeup, avoid plain casual traveler styling, avoid celebrity likeness, no brand logos.
fal:93464
GPT 이미지 2로 생성한 유튜브 썸네일 템플릿

유튜브 썸네일 템플릿

GPT Image 2· Gambar
a bold YouTube thumbnail template design with large headline text zone on the left side, rectangular photo placeholder frame on the right, red arrow accent pointing at the photo frame, red circle highlight, high contrast yellow and dark charcoal background, geometric layout grid, 16:9 horizontal format, clean vector graphic style. lifestyle photo composition, natural light, authentic setting, realistic texture detail. three-quarter view with clear silhouette and subtle depth. bright friendly palette suitable for Korean mobile UI. Make the subject immediately recognizable at thumbnail size. Use clean composition, purposeful details, and no watermark. Keep materials and lighting realistic unless the keyword explicitly asks for illustration.
fal:223167
GPT 이미지 2로 생성한 인스타 하이라이트 커버 예시 3

인스타 하이라이트 커버 예시 3

GPT Image 2· Gambar
Cute Instagram highlight cover icon set with pastel pink, lavender, mint backgrounds, simple lifestyle symbols, clean vector style, balanced spacing, no readable text.

Galeri Prompt Carat

Buat prompt AI yang lagi tren dalam sekejap

Prompt

  • Logo
  • Desain presentasi
  • Thumbnail
  • Poster
  • Sampul novel web
  • Pasfoto
  • Karikatur
  • Halaman detail produk
  • Banner

Model

  • GPT Image 2
  • Seedance 2.0
  • Nano Banana Pro
  • Nano Banana 2

Carat

  • Mulai
  • Tentang
  • Blog
  • Karier
  • Kontak
  • Kemitraan
  • Ketentuan
  • Privasi

© 2026 Paradot.Inc All rights reserved.