已验证示例

提示词库

真实提示词与对应生成图片。浏览灵感、查看效果,并复制完整提示词作为创作起点。

图文组合
5,541
模型
6
来源
10
5,541 组已验证提示词与图片 · 第 35 / 116 页
Example generated from “Golden Hour Bus Stop Candid”
GPT Image 2en
Golden Hour Bus Stop Candid

A candid, ultra-realistic street photo of a young East Asian woman standing at a city bus stop during golden hour, viewed from slightly behind other waiting passengers so the composition feels naturally obstructed and documentary-like. She stands near the center-right of the frame, looking down at a smartphone in her hands, with long straight dark brown to black hair glowing with warm backlight from the low sun behind her. She wears a white T-shirt, an oversized pale blue button-up shirt left open, and loose cream or off-white high-waisted pants or a long skirt, with a canvas tote bag over one shoulder. Her posture is relaxed and absorbed in her phone. The scene includes exactly 2 blurred foreground figures framing her: 1 large out-of-focus figure with long hair on the left edge and 1 dark-shirted shoulder and back on the right edge. Behind her is a glass bus shelter panel reflecting trees and sunlight, and on the far right is a vertical bus route board showing exactly 4 route numbers: 622, 648, 686, and 740, with Chinese transit timetable styling. The lighting is warm, soft, and strongly backlit, creating rim light around her hair and a sun-drenched late-afternoon atmosphere. Use a smartphone photo aesthetic, shallow depth of field, natural color, realistic skin and fabric texture, urban everyday life in China, portrait orientation, subtle lens flare, and an unposed slice-of-life mood.

Example generated from “Golden Hour Café Portrait”
GPT Image 2en
Golden Hour Café Portrait

A warm, candid portrait of a street café editor. A relaxed young woman sits alone at a small round table on a narrow European cobblestone street, basking in the afternoon sun. She wears an oversized cream-colored knit V-neck sweater and loose light blue jeans. Her dark brown hair is casually tied into a messy bun, with a few strands falling loose. She sits casually, one knee raised, one hand holding a small white espresso cup, the other resting on a saucer on the table. Six items are clearly visible on the table: a terracotta potted plant on the left edge, a glass sugar jar with a metal lid in the foreground, a black smartphone, an open paperback book, a white saucer with a small spoon, and a white espresso cup with a delicate red logo. To the left of the café is the shop window, and to the right is a row of outdoor tables and chairs extending into the background. Pedestrians and buildings in the distance are blurred. Backlighting at the golden hour, shallow depth of field, natural skin tones, cinematic bokeh, intimate lifestyle photography, realistic textures, soft shadows, vertical composition, mid-range shots taken from tabletop height, highly realistic.

Example generated from “Golden Hour Rooftop Fashion Portrait”
GPT Image 2en
Golden Hour Rooftop Fashion Portrait

A cinematic, golden-moon rooftop portrait: a stylish young woman stands by the railing of a balcony high above a modern city skyline, shot vertically with a shallow depth of field. She keeps {argument name="hair color" default="Dark brown"} Her long, wavy hair shimmered in the warm, backlit glow of the setting sun, her face slightly turned to one side, not fully revealed. She wore a black fitted blazer over a white round-neck ribbed vest, paired with high-waisted beige trousers. One hand was in her pocket, adorned with a delicate necklace and an understated bracelet or watch. The composition was a half-body portrait from waist to upper thigh, elegant and with a fashion editorial style. The woman was positioned in the center of the foreground, with soft-focus skyscrapers in the background. The warm orange sunlight rendered realistic skin and fabric textures, with soft highlights on her hair and shoulders, creating a luxurious urban atmosphere and a sophisticated lifestyle photography effect reminiscent of a high-fashion editorial. The scene was set in {argument name="city setting" default="Modern downtown skyline"} The time is{argument name="time of day" default="Sunset"} .

Example generated from “Golden Hour Tech Rivals Portrait”
GPT Image 2en
Golden Hour Tech Rivals Portrait

A low-angle snapshot shows two adult men standing in front of a traditional East Asian wooden building, against a backdrop of warm brown wooden frames and repeating green lattice windows. Taken during the golden hour, the strong, warm sunlight casts deep shadows. The man on the left, closer to the camera and partially cropped, wears a black zip-up jacket with a prominent white OpenAI logo on the chest and grey trim on the cuffs. His arm is extended directly towards the lens, holding a cigarette, positioned very close to the foreground, causing his hand and cigarette to occupy the lower left corner of the frame, slightly blurred due to the shallow depth of field. The man on the right, positioned further back, wears a loose black T-shirt with a prominent white "xAI" logo on the chest, one hand raised near his mouth, as if smoking or contemplating. Both men's faces are obscured by smooth rectangular blur blocks to maintain anonymity. Employing a realistic, documentary-style street photography aesthetic, the image showcases natural skin tones, subtle distortions from a wide-angle lens, cinematic contrast, rich sunset lighting, and a casually contrasting composition emphasizing clothing brands and a cigarette reaching towards the viewer. The image must include two men, with a cigarette, a black jacket bearing the OpenAI logo, and a black T-shirt bearing the xAI logo visible in the foreground.

Example generated from “Golden Hour Tech Rivals Portrait”
GPT Image 2en
Golden Hour Tech Rivals Portrait

A candid low-angle photograph of two adult men standing in front of a traditional East Asian wooden building with warm brown timber framing and repeating green lattice window panels, shot during golden hour with strong warm sunlight and deep shadows. The man on the left is much closer to the camera, partially cropped, wearing a black zip-up jacket with a large white OpenAI logo on the chest and a gray panel on the sleeve. His arm is extended directly toward the lens, holding a cigarette in the extreme foreground so the hand and cigarette dominate the lower-left area and appear slightly out of focus due to shallow depth of field. The man on the right stands farther back, wearing a loose black T-shirt with a bold white "xAI" style logo on the chest, one hand raised near his mouth as if smoking or thinking. Both men have their faces obscured by smooth rectangular blur blocks, preserving anonymity. Use a realistic documentary street-photo aesthetic, natural skin tones, subtle lens distortion from a wide-angle perspective, cinematic contrast, rich sunset lighting, and a casual confrontational composition that emphasizes the brands on their clothing and the cigarette thrust toward the viewer. Include exactly 2 men, 1 cigarette visible in the foreground, 1 black jacket with the OpenAI emblem, and 1 black T-shirt with the xAI logo.

Example generated from “Golden Hour Yacht Fashion Portrait”
GPT Image 2en
Golden Hour Yacht Fashion Portrait

Create a photorealistic horizontal luxury lifestyle photo of a young {argument name="woman ethnicity" default="East Asian"} woman standing on the open deck of a white yacht at sea during golden hour. She has long dark windblown hair, a soft confident smile, delicate earrings, and sunglasses resting on top of her head. She wears a silky satin {argument name="dress color" default="champagne bronze"} halter-neck wrap dress with a deep V neckline, fitted waist, draped fabric, and a thigh-high slit revealing one leg, plus elegant sandals. Pose her leaning casually against the curved yacht railing with one hand resting on the polished wooden handrail, body turned slightly to the side, looking off to her left rather than at the camera. The yacht deck has teak flooring, a curved white fiberglass wall, chrome railing posts, and a polished brown wooden rail sweeping diagonally through the composition. The background is an expansive blue ocean with a flat distant horizon and soft shallow depth of field, no land visible. Use warm low-angle sunlight from the side, natural skin tones, crisp high-end fashion photography, realistic lens compression, 16:9 composition, subject slightly left of center, ocean filling most of the upper background. Avoid text, logos, watermarks, extra people, distorted hands, or artificial-looking skin.

Example generated from “Golden Neymar World Cup Poster”
GPT Image 2en
Golden Neymar World Cup Poster

A dramatic cinematic sports poster of {argument name="player name" default="Neymar Jr"} seen from behind wearing the {argument name="team jersey" default="Brazil national team home jersey"}, bright yellow with green trim, the name {argument name="back name text" default="NEYMAR JR"} across the shoulders and the number {argument name="jersey number" default="10"} large on the back. The player is turned slightly left, raising one hand to his forehead in a salute while looking toward a blazing horizon, with short curly hair in a faded mohawk style, visible neck and arm tattoos, and multiple ear piercings. Show the Brazil federation crest on the sleeve. The background is a glowing golden sky with dramatic storm clouds, intense sunlight, and huge luminous geometric numerals forming “10” behind him like monumental light structures. Use a rich gold and amber color palette, high contrast, rim lighting, volumetric glow, sharp fabric texture, heroic composition, and premium poster design. At the bottom, add large metallic gold serif title text reading {argument name="headline text" default="NEYMAR JR"}, with smaller gold text beneath reading “2026” and “COPA DO MUNDO”, centered like an epic World Cup announcement poster.

Example generated from “Golden Plaza Dance Storyboard”
GPT Image 2en
Golden Plaza Dance Storyboard

Goal: Create a clean production storyboard sheet for a vertical AI influencer dance video titled {argument name="video title" default="Golden Plaza Routine."}, showing a 15-second routine as a 4-by-4 grid of exactly 16 numbered shot cards. Canvas: Square white storyboard layout, thin gray borders, editorial production-board style. Top header reads: “Golden Plaza Routine.” followed by “15-SECOND VERTICAL DANCE VIDEO · STORYBOARD”. Use black bold sans-serif typography, compact labels, and a polished creator-workflow aesthetic. Main subject: A fashionable female AI influencer dancer, {argument name="character identity" default="young woman with long wavy brown hair and confident street-dance energy"}, wearing {argument name="outfit" default="cream varsity jacket, white crop top, loose light-blue jeans, and sneakers"}. She dances outdoors in a modern city plaza during golden hour, with warm sunlight, urban buildings, trees, and pavement in the background. Keep her identity and outfit consistent across all panels. Layout: Use exactly 16 discrete storyboard panels arranged in 4 rows and 4 columns. Each panel has a small black number box at top left, a shot title, a timestamp, short notes, and a vertical-photo frame showing the dancer. The photos should look like realistic smartphone captures with natural HDR, warm sunlight, shallow motion blur where appropriate, and consistent lens perspective. Panel content: Include exactly these 16 shot cards: 01 — “READY HIT” — 0:00 — Notes: first blast, clean silhouette, outdoor space. Full-body stance, dancer preparing to start. 02 — “SUNLIT SHOULDER POP” — 0:01 — Notes: sharp upper-body hit, natural sunlight. Medium shot with hair and jacket catching light. 03 — “HAND FRAME” — 0:02 — Notes: clean hands, sharp face, consistent identity. Dancer frames her face with both hands. 04 — “PLAZA SIDE STEP” — 0:03 — Notes: smooth weight transfer, full-body visible. Wide full-body step pose. 05 — “STREET ARM WAVE” — 0:04 — Notes: fluid motion, natural wrist, readable arms. Dynamic arm wave pose. 06 — “CHEST HIT” — 0:05 — Notes: grounded rhythm, realistic body mechanics. Strong torso accent, one hand near hip. 07 — “HALF TURN” — 0:06 — Notes: realistic fabric motion, consistent profile. Dancer turning with hair and jacket movement. 08 — “HAIR SWEEP” — 0:07 — Notes: recognizable face, social-native energy. Hair-sweep movement with body angled. 09 — “LOW GROOVE” — 0:08 — Notes: athletic movement, realistic anatomy. Low crouched dance groove. 10 — “PAVEMENT GLIDE” — 0:09 — Notes: clear footwork, no cropped feet. Full-body footwork stance. 11 — “ARM CROSS” — 0:10 — Notes: strong pose, clean limbs. Medium shot with crossed arms. 12 — “WRIST FLICK” — 0:11 — Notes: controlled gesture, rings catch a highlight. Close-medium hand gesture pose. 13 — “SPIN PREP” — 0:12 — Notes: motion blur begins, stable posture. Full-body preparation for spin. 14 — “GOLDEN SPIN RELEASE” — 0:13 — Notes: dynamic blur, stable identity. Spinning pose with motion-blurred background and hair. 15 — “FINAL DROP” — 0:14 — Notes: energetic beat drop, clear body line. Low dramatic final-move pose. 16 — “SIGNATURE POSE” — 0:15 — Notes: social freeze-frame, polished ending. Confident final pose with hand near hair. Bottom production strip: Add a horizontal footer with a small smartphone product-style image on the left and camera specs reading: “SHOT ON IPHONE 15 PRO | 26MM LENS | 24FPS | NATURAL HDR”. Add notes below: “Handheld imperfections, autofocus breathing, subtle compression artifacts, full-body choreography, outdoor golden-hour lighting, open city plaza, consistent AI influencer identity, consistent streetwear outfit.” On the right, add a boxed section titled “NEGATIVE PROMPT (FOR REFERENCE ONLY)” containing compact text about avoiding cartoon/anime/CGI, plastic skin, celebrity resemblance, copyrighted choreography, inconsistent face, changing outfit, bad anatomy, extra fingers, broken limbs, warped hands, cluttered background, harsh shadows, watermark, and logo. Visual style: Realistic photo storyboard, creator production-document aesthetic, crisp thin-line grid, white margins, black text, warm golden-hour color grading, smartphone realism. Use {argument name="setting" default="modern golden-hour city plaza"} and maintain a cohesive AI influencer dance-video workflow look. Constraints: Keep all 16 panels visible and numbered correctly, preserve the exact timestamps and shot titles, do not add extra panels, do not crop off feet in full-body shots, keep the same dancer and outfit throughout, and avoid logos or watermarks.

Example generated from “Golden Wuxia Palace Poster”
GPT Image 2zh
Golden Wuxia Palace Poster

A dramatically dramatic retro Chinese martial arts movie poster, employing luxurious dark gold and amber hues, presents a classic historical epic style. At the center of the composition is a young royal man seated in the foreground, clad in a magnificent black and gold dragon robe, wearing a Qing Dynasty red-tasseled official hat, one hand covering his mouth, his expression sly, confident, and mischievous. Surrounding him are eight beautiful court ladies in layered silk Hanfu and light gauze robes, arranged closely in a captivating harem portrait style, four in the top row and four in the bottom. Each woman wears an elegant updo, adorned with exquisite gold hairpins, floral ornaments, and dangling earrings, her makeup soft and warm; her expressions ranging from alluring and gentle to curious. The women's clothing uses champagne, blush pink, peach, rose, and pale jade fabrics, paired with semi-transparent cuffs, embroidered bodices, and richly textured jewelry. Behind the figures is an old wooden plaque engraved with the golden Chinese characters "鹿鼎记" (The Deer and the Cauldron), above which is a smaller inscription: "Jin Yong's Martial Arts Classic." Add vertically arranged Chinese actor names next to the different characters: "Su Quan" on the far left, "Chen Yuanyuan" at the bottom left, "A Ke" at the top left center, "Princess Jianning" at the top right center, "Mu Jianping" at the top right center, "Fang Yi" in the middle right center, "Shuang'er" at the bottom right center, and "Zeng Rou" at the bottom right center. Add a vertically arranged poetic Chinese slogan at the top left edge: "Small people, great wisdom, roaming the martial world and the imperial court, playing all over the world, winning the heart of a beauty." Incorporate a secondary movie scene at the bottom: an ancient palace gate and courtyard, soldiers and flags forming a grand procession, with a solitary figure in the foreground walking towards the audience. The bottom edge concludes with a narrow Chinese slogan: "A revolutionary heroic legend, a hilarious martial arts myth." The entire image should present a gorgeous, dramatic, romantic, and slightly playful atmosphere, accompanied by smoky dark brown shadows, luminous rim lighting, rich textures, symmetrical poster composition, and exquisite high-end period drama main visual effects.

Example generated from “Golden Wuxia Palace Poster”
GPT Image 2en
Golden Wuxia Palace Poster

A dramatic vintage Chinese martial-arts movie poster in a luxurious dark-gold and amber palette, styled like a classic historical epic. Center the composition on a young imperial man seated in front, wearing an ornate black-and-gold dragon robe and a Qing dynasty red-tasseled official hat, posed with one hand near his mouth in a sly, playful, confident manner. Surround him with exactly 8 beautiful court women in layered silk hanfu and gauzy robes, arranged tightly around him in a glamorous harem-like group portrait, with 4 women in the upper row and 4 women in the lower row. Each woman has an elegant updo with elaborate gold hairpins, floral ornaments, dangling earrings, and soft warm makeup; their expressions are alluring, gentle, or curious. Render the women in champagne, blush, peach, rose, and pale jade fabrics with translucent sleeves, embroidered bodices, and richly textured jewelry. Behind the group, place a large aged wooden plaque with carved golden Chinese calligraphy reading “鹿鼎记”, with a smaller line above it reading “金庸武侠经典”. Add vertical cast-name text in Chinese placed beside different figures: on the far left “苏荃”, below left “陈圆圆”, upper middle-left “阿珂”, upper middle-right “建宁公主”, far right upper “沐剑屏”, right middle “方怡”, lower right-middle “双儿”, and far lower right “曾柔”. Also add a vertical poetic slogan along the upper left margin in Chinese: “小人物,大智慧,游走江湖庙堂,玩转天下,抱得美人归”. At the bottom, blend in a secondary cinematic scene: an ancient palace gate and courtyard with soldiers and banners forming a grand processional crowd, with one lone figure centered in the foreground walking toward the viewer. Finish with a narrow line of Chinese tagline text across the bottom edge: “一部颠覆传统的英雄传奇 一段令人捧腹的江湖神话”. The whole image should feel opulent, theatrical, romantic, and slightly mischievous, with smoky sepia shadows, glowing rim light, rich texture, symmetrical poster composition, and polished high-end period-drama key art.

Example generated from “Google Fonts Japanese Infographic”
GPT Image 2en
Google Fonts Japanese Infographic

{"type":"Japanese infographic poster","topic":"Google Fonts introduction","style":{"look":"clean flat modern presentation slide","palette":"white background with soft pastel blue, green, yellow, and lavender accents","aspect_ratio":"16:9","lighting":"bright even digital graphic lighting","finish":"crisp vector-like infographic with subtle shadows and rounded cards"},"text":{"headline":"{argument name=\"headline text\" default=\"Google Fontsとは?\"}","subheadline":"Googleの無料フォントサービス","sample_label":"Sample:","sample_text":"{argument name=\"sample text\" default=\"Hello こんにちは\"}","page_indicator":"1 / 2"},"layout":{"sections":[{"title":"top header","position":"top center","count":2,"labels":["Google Fontsとは?","Googleの無料フォントサービス"]},{"title":"feature cards","position":"middle row","count":3,"labels":["1 無料で使える","2 種類が豊富","3 すぐ導入できる"]},{"title":"use cases bar","position":"bottom left to center","count":4,"labels":["こんなときに便利","Web制作","スライド作成","アプリUI"]},{"title":"sample area","position":"bottom right","count":2,"labels":["Sample:","Hello こんにちは"]},{"title":"page marker","position":"bottom right corner","count":1,"labels":["1 / 2"]}],"background_decorations":{"count":7,"items":["pale blue organic blob in top left","small blue dotted grid in top left","thin pale blue ring in top right","small pale blue circle near top right","small blue dotted grid at upper right edge","pale yellow organic blob in bottom left","pale green angular shape in bottom right"]}},"cards":[{"number":"1","title":"無料で使える","description":"Webサイト・アプリ・資料デザインに幅広く使えます。","visual":"rounded white card with light shadow, blue number badge, browser window illustration showing large serif Aa on the left, gray text lines on the right, and a small blue button below"},{"number":"2","title":"種類が豊富","description":"英字だけでなく、日本語フォントも選べます。","visual":"rounded white card with light shadow, blue number badge, large typography samples reading Aa あ ア, each with colored underline in blue, pink, and yellow"},{"number":"3","title":"すぐ導入できる","description":"リンクを貼るだけで、Webにフォントを読み込めます。","visual":"rounded white card with light shadow, blue number badge, dark navy code panel containing HTML link tag for Google Fonts"}],"lower_band":{"left_icon":"blue sparkle icon inside pale blue circle","title":"こんなときに便利","chips":{"count":3,"items":[{"label":"Web制作","color":"light blue","icon":"globe"},{"label":"スライド作成","color":"light green","icon":"presentation board"},{"label":"アプリUI","color":"light purple","icon":"smartphone"}]},"divider":"vertical dotted line","sample_preview":"large black typography sample on white background"},"typography":{"headline_font":"{argument name=\"headline font\" default=\"Google Sans-like rounded sans serif\"}","body_font":"{argument name=\"body font\" default=\"clean Japanese sans serif\"}","notes":"The word Google in the headline uses the official multicolor Google logo style: blue G, red o, yellow o, blue g, green l, red e; the rest of the headline is dark navy."}}

Example generated from “Google Maps Inspired Digital Collage Poster”
GPT Image 2en
Google Maps Inspired Digital Collage Poster

An ultra-detailed digital collage poster featuring a person based on the upload reference photo as the main focal point, realistically stepping out from an expansive Google Maps-inspired navigation environment. The background contains detailed city maps, route paths, location pins, navigation arrows, destination cards, traffic indicators, satellite views, and travel information panels layered across the composition. Additional portrait snapshots display matching views of the subject without altering the facial structure of the upload reference photo. The subject wears a {argument name="clothing" default="modern light blue denim jacket over a cream t-shirt, relaxed cargo pants, and fashionable lifestyle sneakers"} with a compact crossbody travel bag. Bright daylight illumination, realistic map textures, dimensional interface layers, travel-inspired storytelling, highly detailed digital elements, premium collage composition, immersive navigation theme, realistic perspective, commercial-quality poster artwork, 8K resolution. {argument name="location" default="Japan"} please and change the clothes

Example generated from “Google Search Results Mockup”
GPT Image 2en
Google Search Results Mockup

{ "type": "Web browser screenshot", "interface": "Google search results page", "header": { "logo": "Google", "search_bar": { "query": "{argument name=\"search query\" default=\"openai gpt-image 2 image generator\"}", "icons": [ "Clear", "microphone", "camera", "search" ] }, "right_actions": [ "Set gears", "Application Grid", "Blue login button" ] }, "navigation_tabs": [ "all", "picture", "news", "video", "Shopping", "short videos", "forum", "Web page", "More", "tool" ], "results_stats": "Approximately 18,200,000 results were found (in 0.32 seconds).", "search_results": { "count": 3, "items": [ { "source": "OpenAI", "url": "https://openai.com > index > gpt-image-2", "title": "{argument name=\"result 1 title\" default=\"GPT-Image-2 | OpenAI\"}", "snippet": "{argument name=\"date\" default=\"April 1, 2025\"}— GPT-Image-2 is our brand-new image generation model, providing top-notch image quality, finer details, better text rendering, and more precise instruction following capabilities.", "sitelinks": [ "Research", "Safety", "Try in ChatGPT" ] }, { "source": "OpenAI Platform", "url": "https://platform.openai.com > docs > gpt-image-2", "title": "GPT-Image-2 - OpenAI API", "snippet": "Learn about OpenAI's state-of-the-art image generation model, GPT-Image-2, available through the Images API. Create high-quality images with greater realism, better text rendering, and improved instruction compliance…", "sitelinks": [ "Quick Start", "Edit Image", "Example code" ] }, { "source": "The Verge", "url": "https://www.theverge.com > openai-gpt-image-2-launch", "title": "OpenAI's GPT-Image-2 has brought significant improvements to AI...", "snippet": "April 1, 2025 — OpenAI officially released GPT-Image-2, its next-generation image generator, offering better photorealism, improved text rendering, and more accurate user instruction compliance…" } ] }, "people_also_ask": { "title": "Related issues", "count": 4, "questions": [ "What is GPT-Image-2?", "How does GPT-Image-2 differ from previous models?", "Can I try GPT-Image-2 in ChatGPT?", "Is GPT-Image-2 usable via API?" ] } }

Example generated from “Google Street View Anomaly Screen Photo”
GPT Image 2en
Google Street View Anomaly Screen Photo

{ "type": "Photo of a computer monitor displaying the Google Maps Street View interface.", "scene": { "environment": "{argument name=\"environment\" default=\"Desolate desert landscape under a clear blue sky\"}", "subject": "{argument name=\"subject\" default=\"A massive, ancient stone wall, constructed with perfectly fitting megaliths, blocks the dirt road, with a rectangular doorway at its center.\"}", "foreground": "The shadows of Google Street View vehicles projected onto the dirt road; the vehicles are equipped with 360-degree panoramic cameras on their roofs." }, "ui_elements": { "browser_bar": "The URL bar at the top displays google.com/maps along with latitude and longitude coordinates.", "top_left_panel": "A black, semi-transparent information box displays the text \"Unnamed Road\".{argument name=\"region\" default=\"Atacama region\"} \"and \"Street View - September 2022\"", "bottom_left_panel": "Mini-map illustration with a yellow Pegman icon", "bottom_right_panel": "Displays a blue route, Pegman, zoom controls, and the text \"\".{argument name=\"distance text\" default=\"340 kilometers from the nearest town\"} Mini map illustration", "bottom_bar": "The Google logo at the bottom center, the compass icon on the right, and the copyright/photograph date text along the bottom." }, "style_details": "Visible screen reflections and slight display distortion are used to simulate the effect of photographing a physical screen with a smartphone." }

Example generated from “Gopal Tiwari #243”
GPT Image 2en
Gopal Tiwari #243

ultra-realistic IMAX-grade cinematic action shot, extreme high-angle perspective looking down from a massive height, 9:16 vertical aspect ratio, a man or woman matching the exact reference face and hairstyle climbing the side of a modern glass skyscraper, body stretched dynamically across the reflective facade, positioned on the right side of the frame, one leg raised gripping the glass while the other is bent for support, both palms pressed tightly against the glass surface creating tension and realism, wearing futuristic clear-framed glasses with subtle reflections, outfit: premium black fitted t-shirt, black tactical pants, futuristic black gloves with protective padding and bright green LED accents glowing softly, black tactical climbing boots with gold detailing and strong grip texture, a sleek black vest or harness securely fitted over the torso adding realism and safety gear detail, expression: determined and slightly tense with focused eyes and head slightly tilted forward, face lock: maintain exact facial structure, proportions, skin tone, hairstyle, and identity from reference with 100% accuracy, preserve micro-details and natural imperfections, no beautification, facial rendering: soft natural skin with visible pores, smooth tonal transitions, subtle subsurface scattering, no smoothing or artificial glow, environment: towering skyscraper with ultra-reflective glass panels showing the subject’s shadow, sky reflections, and a detailed cityscape far below including intricate walkways, a lush green circular park, and distant street traffic with tiny moving cars, strong sense of depth and scale, lighting: bright natural daylight casting sharp directional shadows, high contrast reflections on glass surface, crisp highlights with controlled roll-off, color science: ultra-clean cinematic color grading with high color separation, natural saturation, deep contrast, HDR dynamic range preserving both sky and ground detail, lens: full-frame Sony A7R, 24mm wide-angle lens to exaggerate height and perspective, sharp foreground subject with slight depth falloff into the city below, realism: extreme photorealistic detail, realistic reflections, natural perspective distortion, micro-contrast textures, no HDR overprocessing, no artificial sharpening negative prompt: distorted face, changed identity, altered hairstyle, flat lighting, dull colors, unrealistic reflections, floating pose, weak grip, plastic skin, over-smooth face, beauty filter effect, low detail, noise artifacts, color banding, extra limbs, incorrect anatomy, blurry subject

Example generated from “Goth Anime Girl at Playground Bar”
GPT Image 2en
Goth Anime Girl at Playground Bar

A richly detailed anime-style illustration depicts a fair-skinned gothic girl in a brightly colored urban amusement park. The image is shot in a close-up to medium shot; she leans forward, biting a horizontal metal railing, her expression mischievous and slightly rebellious. She has long, straight hair, the color of which is {argument name="hair color" default="pitch black"} She has bangs, bright red eyes, and a delicate face with her small mouth lightly pressed against the railing. Three geometric hair clips adorn the right side of her hair: a red triangle, a blue angular one, and a small gold hoop. She wears multiple earrings, including several studs and dangling industrial-style earrings. She's dressed in a black, functional gothic outfit, comprising five key pieces: a short black jacket with red and blue stripes, a black choker, a black belted top or dress with a front clasp, a wide belt with metal hardware, and a hanging waist chain. Her sleeves are wide and long, with white striped detailing on one forearm. Her hands grip the railing tightly, one close to her mouth, the other extending to the side, creating a pose that is both intimate and confrontational. The background is an amusement park with brightly colored facilities, including blue pillars, red connectors, yellow and red climbing poles, and a rubber surface composed of bold geometric blocks of blue, red, yellow, white, and black. The background features dark green trees and a dramatic, graphic sky with large, flat shapes in red, orange, blue, black, and white, as well as circular sun-shaped dots, giving the scene a poster-like pop art style. A vertical warning sticker with Japanese text and small warning icons is located on the blue pillar on the left. The composition employs crisp celluloid shadows, sharp lines, subtle glitch textures, oversaturated colors, high contrast, a melancholic cyberpunk gothic atmosphere, and a dynamic composition focusing on the girl's intense gaze and the metal railings.

Example generated from “Goth Girl on Unicorn Ride”
GPT Image 2en
Goth Girl on Unicorn Ride

A realistic snapshot, the subject of which is a young man.{argument name="subject aesthetic" default="Gothic style"} The woman had pale skin, long, straight black hair with bangs, and wore heavy black eyeliner and black lipstick. She was expressionless.{argument name="expression" default="deadpan"} Looking directly at the camera, he was sitting in a children's coin-operated {argument name="ride type" default="unicorn"} On the rocking horse. She wore a black lace-trimmed vest, black arm warmers, and multiple necklaces including a choker, black lace pantyhose, and thick-soled black buckled boots. A large black shoulder bag was slung over her arm. The rocking horse was a white unicorn with pink mane, golden horns, and purple hooves, mounted on a purple base, with a sign that read…{argument name="ride cost" default="50¢ PER RIDE"} A small sticker. The scene is outside a shop, with a background of brown cinder brick walls. To the left is a glass door reflecting a figure, a brown trash can, and a sign with red text that reads "...".{argument name="sign text" default="NO PARKING FIRE LANE"} A white sign reads "...". To the right is a blue vending machine. It's a cloudy day with natural light.

Example generated from “Goth Style Transformation”
GPT Image 2en
Goth Style Transformation

Use REFERENCE_0 to convert the main appearance to{argument name="style" default="Traditional Gothic"} The aesthetic style, while retaining its precise poses, clothing construction, and background. Her hair was changed {argument name="hair color" default="black"} And accompanied by{argument name="hair style" default="choppy bangs"} To create a rich, dark makeup look, especially {argument name="lip color" default="black"} Lipstick and deep, dark eyeshadow were applied, and her skin tone was adjusted to appear slightly paler. Two facial piercings were added: a septal ring and a nose stud. Finally, her layered necklaces were modified.{argument name="necklace pendants" default="Inverted cross and pentagram"} Pendant.

Example generated from “Gothic Alice Tea Party Poster”
GPT Image 2en
Gothic Alice Tea Party Poster

Goal: Create a richly detailed vertical dark-fantasy anime poster for {argument name="story title" default="Alice in Wonderland"}, reimagined as an elegant gothic tea-party character illustration. Canvas: Tall 2:3 portrait poster, dense decorative composition, cinematic lighting, deep navy, violet, black, antique gold, muted cream, and ruby-red accents. Use ornate Victorian borders, filigree corners, glowing bokeh, floating cards, and magical dust throughout. Main subject: A beautiful androgynous young male anime character seated in a plush vintage armchair at the center, looking tired, aloof, and melancholic. He has messy dark blue-purple hair, golden amber eyes, pale skin, and black cat ears, with a dark fluffy cat tail visible near the lower right. He wears an extravagant Mad Hatter-inspired gothic aristocrat outfit: oversized checkerboard top hat decorated with playing cards, blue roses, chains, gears, ribbons, and small charms; layered black and navy tailcoat with gold trim; ruffled white lace shirt; blue bow at the neck; ornate brooches; shoulder epaulettes; dangling chains; pocket watches; belts; gloves or lace cuffs; fitted dark trousers; and tall black lace-up platform boots. Pose him lounging with one leg crossed forward, one elbow resting on the chair arm, one hand near his face, and the other holding a delicate teacup. Environment: A surreal enchanted Wonderland forest or tea-party room with blurred glowing lanterns, blue stained-glass-like lights, mushrooms, roses, antique bottles, tea sets, cakes, clocks, playing cards, ribbons, and magical floating fragments. The mood should feel mysterious, decadent, dreamlike, and slightly ominous. Layout and text elements: Include exactly 6 distinct readable graphic text panels/signs: 1. Upper-left ornate arched title plaque with the large title “ALICE in WONDERLAND”, a smaller Japanese subtitle “不思議の国のアリス”, a tiny teapot icon, and story text: “Down the rabbit-hole he fell, chasing a whisper not meant for him— In a land where time is broken and rules are only a joke, ...is there a way to return?” 2. Upper-right wooden signpost with 4 arrow signs labeled exactly: “This Way”, “That Way”, “Tea Party”, and “Go Back”. 3. Lower-left parchment invitation card titled “Mad Hatter’s Tea Invitation” with smaller text: “You’re invited to a most unusual tea. Don’t be late. Or be. It doesn’t matter.” 4. Bottom-left ornate oval cameo frame showing a tiny silhouette tea-party scene with two seated figures, labeled “Who Are You?” 5. Lower-center handwritten chalk-like quote: {argument name="center quote" default="There’s no truth here. Only what you choose to believe."} with a small doodle cat face and sparkle marks. 6. Lower-right parchment tag titled “Drink Me” with smaller text: “A sip may shrink you, A sip may change you, Choose wisely.” plus a small potion-bottle illustration. Additional visible objects: Include floating playing cards with suits, at least 3 red roses, at least 2 pocket watches, a teapot and cupcake tea set near the lower left, a glowing potion bottle labeled “Drink me” on the lower right, a crystal orb or glowing glass lamp, wax seals on parchment notes, ribbons, chains, and blue flowers. Visual style: Ultra-detailed Japanese anime key visual, ornate gothic lolita / ouji fashion, Victorian fantasy poster design, high-contrast rim lighting, soft painterly rendering, crisp character details, luminous particles, intricate accessories, dramatic depth of field, premium collectible illustration quality. Constraints: Keep the main character recognizable as the central focus, do not crop off the hat or boots, preserve all 6 text panels/signs, avoid modern objects, avoid minimalism, avoid flat colors, and make the typography decorative but legible.

Example generated from “Gothic Anime Character Sheet”
GPT Image 2en
Gothic Anime Character Sheet

{ "type": "Anime Character Reference Design Collection", "character": { "name": "{argument name=\"character name\" default=\"レイ\"}", "romanized_name": "Rei", "age": "18", "birthday": "April 12", "height": "163 cm", "blood_type": "A", "dominant_hand": "right hand", "origin": "-", "occupation": "-", "profile_portrait": "A serene, gothic-style bust of a young woman, her finger lightly touching her lips, her body slightly turned to the left." }, "appearance": { "gender_presentation": "young women", "hair": { "color": "{argument name=\"hair color\" default=\"dark gray-brown\"}", "style": "Long, straight hair with soft layers, parted in the middle, glossy and highlighted, with the ends slightly curled inwards." }, "eyes": { "color": "Soft lavender ash" }, "skin": { "tone": "fair porcelain skin" }, "expression": "A quiet, reserved, and melancholic elegance" }, "outfit": { "style": "Elegant Gothic Black Dress", "pieces": [ "High-necked, sheer lace long-sleeved top with floral pattern", "Black fitted bustier-style inner layer", "Decorative crystal necklace on the chest", "Mid-length layered chiffon skirt with floral lace hem", "Black ribbon bow at the back waist", "Semi-sheer lace cuffs", "Black lace-up chunky heeled ankle boots" ] }, "layout": { "background": "The clean white artbook pages feature thin gray dividing lines and delicate decorative patterns.", "sections": [ { "title": "Three-view diagram", "position": "Top left", "count": 3, "labels": [ "Front", "Side view", "Back" ], "content": "Full-body three-view drawing, showing the front, side, and back of the same dress." }, { "title": "Personal profile panel", "position": "Top right", "count": 1, "labels": [ "レイ", "Rei" ], "content": "Name title, small personal profile form and a large portrait" }, { "title": "Detailed design", "position": "Bottom left", "count": 4, "labels": [ "High-necked lace neckline", "Chest jewelry details", "Lace cuffs and sleeve details", "Lace details on the skirt" ], "content": "Four close-up images of square details" }, { "title": "Color scheme", "position": "Lower left", "count": 7, "labels": [ "hair", "pupil", "skin", "Dress (main color)", "Dress (lace)", "Metal parts/decoration", "Ribbon/Boots" ], "content": "A vertical color swatch containing seven rectangular color blocks" }, { "title": "Expression variants", "position": "Lower right", "count": 6, "labels": [ "generally", "Smile", "think", "surprise", "sad", "shy" ], "content": "Six portraits of heads and shoulders, arranged in two rows of three." }, { "title": "Character Notes", "position": "bottom", "count": 4, "labels": [ "chest decoration", "Cuff ribbon", "boots", "Back waist ribbon" ], "content": "The left side contains notes, and the right side contains four slender accessory labels." } ], "overall_style": "High-end anime design draft, balanced layout, ample white space, thin gray lines, Japanese-style typography." }, "text_blocks": { "character_description": "A mysterious and quiet young woman, exuding a refined yet slightly melancholic aura. She is beautiful and gentle in appearance, yet gives off an elusive and distant impression. Although usually calm and composed, subtle changes in her emotions are revealed in her expressions and movements.", "likes": "Music, tea, quiet things", "dislikes": "Noisy places, being urged" }, "rendering": { "quality": "Exquisite concept art for gpt-image-2", "style": "Semi-realistic anime illustrations, featuring delicate lace details, soft shadows, glossy hair rendering, elegant gothic fashion design, and a clean, print-quality presentation." }, "color_theme": "{argument name=\"accent palette\" default=\"Black, charcoal gray, soft lavender gray, light beige, silver\"}" }

Example generated from “Gothic Anime Girl with Black Roses”
GPT Image 2en
Gothic Anime Girl with Black Roses

A dark anime-style gothic portrait, the main character is{argument name="character type" default="young women"} The composition is half-body, centered. She has long, multi-layered hair.{argument name="hair color" default="silver-white"} Her hair was styled in messy twin ponytails, with strands falling naturally over her shoulders. She wore two large black ribbon lace hair ornaments, a black gothic dress with puffy sleeves and delicate lace trim, black lace fingerless gloves, and a black leather choker with a metal clasp. Two silver chain necklaces were layered around her neck, one of which had a striking cross pendant. She made a peace sign with her hands raised to her cheeks, her nails painted black, a pose that was both playful and cool. The background was a rich, blood-red gradient, creating a gloomy atmosphere. Five thorny black roses surrounded the figure, with black dripping patterns at the top edge, presenting a highly dramatic gothic horror aesthetic. The artwork uses a high-detail anime illustration style, with sharp lines, soft and dramatic shadows, emphasizing the sheen of the black fabric, pale skin, and a strong red-black contrast. The composition is symmetrical, with a close-up view, creating an overall elegant yet eerie atmosphere.

Example generated from “Gothic Anime Witch Library Ensemble”
GPT Image 2en
Gothic Anime Witch Library Ensemble

A lavish, dark fantasy anime illustration depicts 11 elegant young women gathering in a grand Gothic library late at night, the composition resembling a portrait of an elite magic academy assembly. The room is filled with towering wooden bookshelves, movable ladders, crimson velvet banners adorned with mysterious gold symbols, carved wainscoting, candlelight, a warm lamp on the far left, and is complemented by red-upholstered armchairs and sofas, piles of ancient books, potion bottles, crystal balls, brass instruments, and a tall arched window offering a view of a deep purple night sky. The overall color scheme is black, crimson, gold, and purple, employing dramatic, understated lighting with rich shadows and brilliant highlights, creating a luxurious yet sinister atmosphere. All 11 characters are dressed in the same mystical academy uniform: black fitted jackets with gold embroidery and badge details, white shirts, red ties or ribbons, multi-layered belts and chains, short skirts or fitted bottoms, black knee-high stockings, and black cloaks lined with crimson. Three people are seated in the center on an ornate red chair and sofa; three stand between the bookshelves at the back; three sit on the floor or near the table in the front row; and two lean against the far left and right edges respectively. The characters have different hair colors and hairstyles, including {argument name="hair color" default="gold"} Colors include silver, black, red, blue, brown, and purple; hairstyles include long curls, twin tails, straight long hair, side ponytails, and layered wispy hair. Each woman should possess a calm, confident, and slightly dangerous expression, as if she were a genius witch or a noble student. The image must contain six clearly visible magical effects or props in use: a red flame floating in the center of the background with a raised hand; a glowing purple sphere held by a standing girl near the upper right center; a rotating purple magic circle above an open book in the lower left; a faint purple arcane flame near the knee of a silver-haired girl in the middle right; a halo of deep purple smoke around a girl leaning against the far right; and a glowing purple crystal lamp or alchemical container on the central coffee table. Additionally, add four extra glass containers in the foreground and on the side tables: a crystal ball in the lower left corner, a tall red potion bottle in the lower right corner, and two small experimental bottles next to it. Place multiple open and closed magic books on the knees, tables, and floor, totaling at least eight books. The central focus is a composed blonde girl, seated in the largest armchair with her legs crossed and her hands near her face, striking a leader's pose. The game employs a highly detailed, polished anime-style rendering, showcasing ultra-fine fabric textures, intricate gold trim, subtle facial shadows, bright eyes, cinematic composition, wide-angle group shots, fantasy key visual quality, a melancholic gothic school setting, a magical sorority, sharp focus, and a lavish environment devoid of modern objects.

Example generated from “Gothic Girl at Rainy Window”
GPT Image 2en
Gothic Girl at Rainy Window

A poignant Gothic illustration, rendered in an impasto oil painting style, depicts a lonely little girl huddled on a cushioned windowsill in a dimly lit old house on a rainy night. She has {argument name="hair color" default="Dark brown"} Her messy curly hair, wearing a{argument name="sweater color" default="Rust Red"} She wears an oversized knit sweater, paired with black and beige striped stockings and dark lace-up boots. Her posture is reserved, knees drawn up to her chest, gazing out of a tall, multi-paned window. Outside the glass is a crooked, haunted European village street with steep roofs, spires, glittering windows, slippery cobblestones, and a prominent clock tower, against a backdrop of a gloomy, stormy sky. The image must include one figure walking alone in the rain with an umbrella. The interior should include an industrial chandelier emitting a warm yellow light in the upper left corner, a red ceramic mug on the windowsill, an open sketchbook on a bench (with a drawing of a black cat visible on the pages), two red pillows, and several small framed paintings on the left wall. The color palette should primarily consist of charcoal gray, dark brown, black, and soft amber, contrasting the warm indoor lighting with the cold, damp outdoors. The composition should be slightly tilted and cinematic, with the girl positioned slightly to the left of the center, and the rain-soaked town occupying the right side of the frame. It emphasizes melancholy, loneliness, gothic fantasy, textured brushstrokes, scratches, dramatic window reflections, and a dark fairytale atmosphere within square compositions.

Example generated from “Gothic Idol Concert Selfie”
GPT Image 2en
Gothic Idol Concert Selfie

A dramatic, self-portrait-style close-up of a stage scene shows a Japanese idol performer leaning towards the camera from a low angle, her upper body and outstretched arms dominating the frame. She has long, straight to slightly wavy hair, and her hair color is {argument name="hair color" default="dark reddish brown"} Her hair was glossy, and thick, side-swept bangs covered one eye. Her expression was cute and intimate; she placed one hand near her mouth, striking a shy idol pose, as if interacting directly with fans at a concert. She wore a black and dark {argument name="accent color" default="Purple"} The gothic idol stage costume features five clearly visible elements: a shiny, corset-style cropped top with metallic trim, a black belt with silver metal eyelets at the waist, black sheer mesh opera gloves, multiple straps on the upper arms, and a dangling silver chain across the chest and hem. The addition of glossy patent leather, studs, buckles, lace, and layered ruffles creates a highly detailed J-pop or anime concert look. The backdrop is a large indoor live stage with bright blue-white spotlights, smoke, truss installations, and LED screens flashing soft, abstract shapes, creating a strong backlighting and bokeh effect. The cinematic concert photography style employs high contrast, cool lighting with purple-blue highlights, shallow depth of field, slight lens distortion from a close-up arm perspective, dynamic foreground perspective, and vertical hand-held composition. This results in a vibrant, charismatic, and fan-service-oriented visual, much like…{argument name="idol group concept" default="A dark fantasy-style idol live performance"} .

Example generated from “Gothic Lolita board game generator”
GPT Image 2en
Gothic Lolita board game generator

Create a Sugoroku board game with the background set as "{argument name="setting" default="A gothic lolita girl living in the countryside travels to Makuhari to participate in an event."} "

Example generated from “Gothic Lolita Portrait at Convenience Store”
GPT Image 2en
Gothic Lolita Portrait at Convenience Store

A realistic close-up portrait, the subject of which is{argument name="subject" default="Young Japanese women"} She had straight black hair and bangs, and was wearing a {argument name="outfit" default="Black Gothic Lolita dress with floral embroidery"} Wearing a{argument name="headwear" default="Black lace cat ear headdress"} She tied a black ribbon around her chin. She wore a face mask.{argument name="expression" default="Neutral expression"} Look directly into the camera. The background is a blurry street scene, and you can see a {argument name="background" default="Lawson convenience store"} The storefront features a blue and white signboard and glass doors. The natural and soft lighting creates a realistic, snapshot-like aesthetic.

Example generated from “Gothic Maid Acrobatic Kick”
GPT Image 2en
Gothic Maid Acrobatic Kick

Create a dynamic vertical anime action illustration of a {argument name="character type" default="pink-haired gothic lolita maid girl"} performing an acrobatic one-handed breakdance handstand kick inside a grand European palace ballroom. The camera is extremely low near the polished marble floor, looking upward with dramatic foreshortening: one booted leg thrusts close to the viewer and is heavily motion-blurred, the other leg extends backward, while one hand presses on the reflective floor and the character looks toward the viewer with a confident fierce expression. She has long flowing {argument name="hair color" default="rose pink"} twin-tail hair whipping through the air, green eyes, frilly white maid headband, and an ornate {argument name="outfit color" default="deep emerald green"} gothic lolita maid dress with puff sleeves, ruffled white lace trim, corset-like bodice, bows, layered skirt, stockings, and lace-up heeled boots. Add bright white circular speed trails and arcing wind ribbons around her spinning body to emphasize high-speed action. The environment is a luxurious sunlit ballroom with tall arched windows on both sides, gilded wall details, high ceiling, chandeliers, dust motes, shafts of light, and glossy patterned marble reflections. Use cinematic lighting, extreme perspective, intense motion blur, sharp focus on the face and supporting hand, detailed fabric folds and lace, elegant fantasy anime rendering, high detail, vertical composition, dramatic action energy, no text, no watermark.

Example generated from “Gothic Mystery Movie Poster”
GPT Image 2en
Gothic Mystery Movie Poster

A dark, gothic suspense movie poster with a cinematic feel. In the center of the image, a man in a trench coat and fedora, with his back to the viewer, gazes up at a magnificent yet oppressive Gothic clock tower. The clock face glows, the surrounding structure is collapsing, and dark fragments scatter and fall. The scene is set in a misty, damp cobblestone square on a nighttime day, illuminated by warm yellow streetlights and light filtering through the surrounding European-style buildings. A full moon pierces through the clouds. Three crows are depicted: one perched on a stone tablet on the left, and two flying in the sky. The stone tablet on the left is inscribed with the words "VERITAS IN UMBRA, TEMPUS NEMINI PARET". On the right is a wooden signpost with three directional signs: "Marktplatz", "Uhrenturm", and "Alte Gasse", next to which lies a newspaper with the words "Die Uhr steht." and "Wer lügt?". The poster uses an elegant, slightly worn serif Japanese font. The horizontal slogan at the top reads:{argument name="top tagline" default="At midnight, time stops, and lies begin to move."} The vertical slogan in the upper left corner is:{argument name="side tagline" default="The sound of that bell buried the truth."} The main title in the center below is {argument name="main title" default="The Clock Tower Murders"} Below the title is a smaller tagline, "Who deceived me?", followed by a realistic credits list including the director, actors, and crew members. The release information is displayed at the very bottom.{argument name="release date" default="Coming to theaters nationwide in Fall 2025"} The website URL and rating are displayed alongside the image. The entire poster is decorated with a delicate, ornate gold border.

Example generated from “Gothic Sorceress in Ruined Cathedral”
GPT Image 2en
Gothic Sorceress in Ruined Cathedral

A dark Gothic fantasy scene set within a vast, abandoned cathedral, framed in a vertical full-body composition. At the center stands a mysterious witch, clad in an elegant Victorian black gown with a fitted bodice, delicate silver embroidery, sheer lace sleeves, long lace garlands cascading from her arms, black gloves, and a long train. Her hair is styled in a neat dark updo, adorned with exquisite hair ornaments and fine jewelry. She holds an open spellbook in one hand, while the other is gracefully raised as if casting a spell. A low-hanging mist and swirling smoke surround her. The cathedral's interior is grand and dilapidated, featuring soaring pointed arches, ribbed vaults, cracked stone floors, and broken tombs or altars on either side. Thick, twisted tree roots spread across the ground and entwine the stone structures. Two large gargoyle statues, symmetrically placed high on either side, overlook the scene. Numerous black candles with warm orange flames are scattered throughout the foreground and middle ground, creating a sense of ritual. In the background, tall stained-glass windows let in cool blue sunlight, creating dramatic crepuscular rays that contrast sharply with the candlelight. The overall atmosphere is somber, mysterious, cinematic, solemn, and richly detailed, presenting realistic textures, deep shadows, volumetric lighting, atmospheric haze, deep blue-gray tones, and exquisitely detailed Gothic architecture.

Example generated from “Gothic VTuber Logo Grid”
GPT Image 2en
Gothic VTuber Logo Grid

{ "type": "VTuber Logo Design Concept", "theme": "{argument name=\"main theme\" default=\"Gothic dark fantasy\"}", "background": "{argument name=\"background color\" default=\"pure black\"}", "layout": "A 2x3 grid containing 6 different logo designs", "logos": [ { "position": "Top left", "main_text": "{argument name=\"logo 1 main text\" default=\"Messiah of the Demon World\"}", "sub_text": [ "Observer of the Demon World", "MAKAI NO KANSOKUSHA" ], "colors": [ "Purple", "silver" ], "motifs": [ "horn", "Glowing purple eyes", "bat wings" ] }, { "position": "Upper-middle", "main_text": "{argument name=\"logo 2 main text\" default=\"Abyssal Presia\"}", "sub_text": [ "Shinen Lucia", "The Punisher of the Demon World" ], "colors": [ "red", "black", "gold" ], "motifs": [ "chain", "Demon Spikes", "Glowing red runes" ] }, { "position": "Top right", "main_text": "{argument name=\"logo 3 main text\" default=\"Dream Eater Mephi\"}", "sub_text": [ "まかいのゆめくい" ], "colors": [ "pink", "Purple" ], "motifs": [ "Skull with a crown", "bat wings", "Flashing effect" ] }, { "position": "Bottom left", "main_text": "Aokage Kanata", "sub_text": [ "Shadow Poet of the Demon World", "- AOKAGE KANATA -" ], "colors": [ "blue", "silver" ], "motifs": [ "Giant central eye", "Silver bat wings", "Gothic architecture" ] }, { "position": "Middle to lower", "main_text": "Twilight Belial", "sub_text": [ "Tasogare Belial", "Prince of the Demon World" ], "colors": [ "gold", "Purple" ], "motifs": [ "crown", "bat wings", "Hanging gems" ] }, { "position": "Bottom right", "main_text": "Shion", "sub_text": [ "The Memory House of the Demon World", "- MAGATSU SHION -" ], "colors": [ "silver", "Purple", "black" ], "motifs": [ "new moon", "Glowing purple flames", "chain", "Dark smoke" ] } ] }

Example generated from “Gourmet Burger Commercial Photography”
GPT Image 2en
Gourmet Burger Commercial Photography

A high-end fast-food commercial product photograph, featuring a centered premium cheeseburger against a warm, seamless gold studio backdrop. The burger is topped with a glossy sesame bun, fresh lettuce, tomato slices, onion rings, melted cheese, a juicy grilled beef patty, and a rich sauce. Soft studio lighting, delicate shadows, mouthwatering textures, sharp focus, hyper-realistic food advertising photography, simple composition, 8K resolution. Create a hyper-realistic, vertically exploding infographic composition for a premium cheeseburger. At the top is a crispy, glossy sesame bun, below which are fresh green lettuce leaves, tomato slices, onion rings, melted cheese, a juicy grilled beef patty, a layer of sauce, and a soft bun base. All ingredients are evenly distributed and perfectly vertically aligned. Warm yellow seamless studio background, soft commercial food lighting, delicate and realistic shadows beneath each suspended element, ultra-clear focus, DSLR macro food photography, high-end fast-food advertising aesthetics, 8K resolution. Add concise infographic text labels and use thin leaders to point to each element. The label names are as follows: "Bun Top", "Lettuce", "Tomato", "Onion", "Cheese", "Patty", "Sauce", and "Bun Base".

Example generated from “GPT Image 2 3D Social Profile Card Diorama”
GPT Image 2zh
GPT Image 2 3D Social Profile Card Diorama

一只手中握着一张3D小红书个人资料卡,卡片中间方形镂空,一个女孩随意地坐在卡片镂空的边缘,温暖的米色和柔和的粉彩美学背景,逼真的深度和阴影,电影般的柔和光线,闪亮光滑的纹理,小红书风格的UI,漂浮的互动图标(点赞、评论、分享)带有发光的霓虹效果,闪光和光晕,背景中温馨的美学布置包括书籍、花瓶里的花和一台复古相机,梦幻氛围,Pixar风格+半现实主义融合,超高品质,4K,居中构图,高端影响者美学

Example generated from “GPT Image 2 Cinematic Spotlight Museum Portrait”
GPT Image 2en
GPT Image 2 Cinematic Spotlight Museum Portrait

Use my reference photo to preserve the exact facial features, hairstyle, bangs, facial proportions, skin tone, body posture, and overall silhouette with high identity consistency. Cinematic portrait of a woman standing alone inside a dark exhibition room. She wears a vintage white shirt layered with a soft pink outer jacket and a black vintage-textured skirt. Minimal makeup. Front-profile pose with her body facing the camera, relaxed posture, one shoulder slightly lowered, hands gently adjusting her hair. Calm, mysterious expression with an intellectual and elegant aura. She is positioned in the lower center of the frame, surrounded by darkness. A single dramatic diagonal spotlight cuts across the scene from the upper right to the lower left, illuminating only half of her body while the rest fades into shadow. Behind her is a colorful vintage Japanese mural wall filled with retro cartoon illustrations and traditional artistic details. Foreground shadows naturally frame the composition like torn darkness, creating a moody museum atmosphere with lonely artistic energy and a contemplative cinematic mood. Realistic photography with subtle film grain, analog texture, muted blacks, and vibrant mural accents. Camera angle: eye-level shot, medium-close portrait framing, subject captured at approximately a 70-degree side profile angle, slight distance from the subject for environmental storytelling, centered cinematic composition. Camera settings: cinematic low-light photography, shallow depth of field, realistic shadow falloff, Kodak Portra film color grading. Lighting: harsh focused spotlight from the upper right creating a strong diagonal beam and deep high-contrast shadows, minimal ambient light, rich blacks, soft warm highlights along the face and glasses edges. Vibe: mysterious, artistic, museum-core aesthetic, intelligent quiet energy, melancholic cinematic atmosphere, indie film still, luxury editorial photography, solitary nighttime mood, understated elegance. Style: ultra-realistic cinematic photography, analog grain, editorial fashion portrait, natural skin texture, subtle imperfections, realistic color science, masterpiece quality. Negative prompt: anime, smiling, overexposed lighting, extra limbs, bad anatomy, overly colorful outfit, cyberpunk neon, blurry face, low quality, distorted hands, unrealistic skin, HDR overload, exaggerated makeup, busy composition, duplicate person.

Example generated from “GPT Image 2 Comparison Poster”
GPT Image 2en
GPT Image 2 Comparison Poster

{ "type": "AI Model Comparison Infographic Poster", "topic": "GPT Image 2 Quality Comparison", "style": "A futuristic, cinematic-quality tech ad, featuring sophisticated social media comparison images and high-contrast neon night scenes.", "canvas": { "orientation": "vertical", "aspect_ratio": "9:16" }, "headline": { "text": "{argument name=\"headline text\" default=\"GPT Image 2 Quality Comparison: Standard vs Medium vs High\"}", "position": "Centered at the top", "color": "White", "font": "Bold sans-serif font" }, "layout": { "sections": [ { "title": "GPT Image 2 Standard", "position": "Top panel", "count": 1, "labels": [ "Fast and economical / Suitable for everyday use and drafts / Low cost and fast generation speed" ], "divider_color": "cool blue" }, { "title": "GPT Image 2 Medium", "position": "Middle panel", "count": 1, "labels": [ "Optimal balance / High cost-performance ratio / Suitable for scenarios requiring enhanced quality" ], "divider_color": "cool blue" }, { "title": "GPT Image 2 High", "position": "Bottom panel", "count": 1, "labels": [ "Highest quality and detail / Suitable for video keyframes and final output / Highest cost and time consumption" ], "divider_color": "warm orange" } ], "panel_count": 3 }, "scene": { "setting": "A futuristic city skyline on a rainy night, with wet and reflective ground and waterfront, dense skyscrapers adorned with glowing windows and blue neon lights.", "subject": "Each panel features a male athlete running from left to right.", "subject_count": 1, "pose": "The dynamic running posture, with one arm extended forward and the other swinging back, and the body leaning forward, conveys a strong sense of movement.", "wardrobe": "Dark, slim-fitting, futuristic sportswear, featuring a textured jacket and trousers, and dark sneakers.", "face": "Deliberately softened or anonymized, not the visual focus", "effects": [ "The body was surrounded by electric blue particle trails", "Sparks and beams of light burst forth behind him", "Water splashed up by footsteps", "Reflection on the wet pavement", "Dynamic blur emphasizing speed" ] }, "comparison": { "top_panel": "The details are slightly softer and simpler, presenting a sense of lower cost and faster speed while maintaining the same composition.", "middle_panel": "A greater balance between detail and clarity has been achieved, improving rendering and lighting effects while preserving the same scene.", "bottom_panel": "With the richest details, the finest textures, the strongest contrast of light and shadow, and the densest particle and reflection effects, it presents the ultimate cinematic quality." }, "branding": { "logo_text": "{argument name=\"brand text\" default=\"LovArt\"}", "count": 3, "placement": "Each panel is centered at the bottom.", "color": "White with subtle blue accents" }, "color_palette": { "primary": [ "Deep Navy Blue", "Electric Blue", "blue", "White" ], "accent": [ "Orange Spark", "Amber highlight" ] }, "rendering": { "finish": "High-end digital illustrations with semi-realistic details", "sharpness": "Gradually increasing from top to bottom", "lighting": "Illuminated neon outline lighting, urban background lighting, and reflected highlights from wet surfaces." } }

Example generated from “GPT Image 2 cozy claymation style prompt”
GPT Image 2en
GPT Image 2 cozy claymation style prompt

Recreate the scene as a cozy claymation-style world made from soft modeling clay. Every object should have handmade textures, rounded shapes, fingerprints, and soft lighting like a stop-motion movie. Use warm pastel colors and a cute cinematic atmosphere.

Example generated from “GPT Image 2 cute 3D kneaded clay icon prompt”
GPT Image 2en
GPT Image 2 cute 3D kneaded clay icon prompt

Cute 3D render of a [subject], matte surface, kneaded clay icon style, simple stylized design, [doing action], [emotion or mood], rounded proportions, soft sculpted details, playful body language, vibrant [color1], [color2], and [color3] accents, clean white background, minimal composition, soft ambient lighting, subtle shadow, charming character design, high-resolution, polished toy-like aesthetic

Example generated from “GPT Image 2 encyclopedia-style educational infographic prompt”
GPT Image 2en
GPT Image 2 encyclopedia-style educational infographic prompt

Based on { TOPIC }, create a high-quality vertical “encyclopedia-style educational infographic image.” This image should NOT look like a regular poster or a simple illustration. Instead, it should feel like a structured knowledge guide that combines: the feeling of a collectible reference handbook a modern encyclopedia page a lifestyle knowledge card and a highly shareable social-media infographic The overall style should resemble a premium natural-history guidebook mixed with modern editorial infographic design. The image should include: One beautiful and highly detailed main subject image Several zoomed-in detail sections highlighting important features Multiple modular information panels with rounded corners Clear title hierarchy and highlighted key labels Concise yet information-rich encyclopedia content Visual scoring systems, quick summaries, or “Top 5” modules The information sections should automatically adapt to the topic. Select and combine relevant categories such as: Basic profile Classification / taxonomy Physical characteristics Behavior / ecology / habits Structure or formation mechanisms Growth conditions or usage methods Care, maintenance, or optimization tips Risks, warnings, and important notes Suitable users or application scenarios Pros and cons comparison Quick rating tags or summary cards Visual requirements: Clean light-colored background Soft and elegant color palette Gentle shadows Small refined icons Rounded information boxes Organized editorial layout High information density without feeling crowded Comfortable reading experience The final result should feel like a real publishable encyclopedia knowledge card designed for reading, collecting, and creating as part of a consistent series — NOT like a commercial advertisement poster. The image must strongly emphasize: “knowledge integration + modular information design + handbook/reference-style presentation.”

Example generated from “GPT Image 2 endangered animal infographic prompt”
GPT Image 2en
GPT Image 2 endangered animal infographic prompt

Create a visually rich infographic about an endangered animal. Start by finding one online, research its habitat, diet, and unique traits. Present information through annotated visuals and structured callouts, not generic sections. Style it like a bold graphic illustration: a detailed, photorealistic central animal as the focal point, supported by diagrams, callouts, and concise text elements. Use clean backgrounds and a mix of photorealism with strong graphic elements (shapes, icons, color blocking) in a layered composition. Make it dense, tactile, and professionally authored.

Example generated from “GPT Image 2 FACS action unit expression grid prompt”
GPT Image 2en
GPT Image 2 FACS action unit expression grid prompt

Create a clean educational FACS Action Unit expression grid featuring a realistic adult female character. Use minimal studio lighting, neutral white background, high readability, professional facial anatomy reference sheet aesthetic, realistic skin texture, consistent identity across all panels. COLOR SYSTEM: Use soft pastel color coding for categories while keeping the overall sheet minimal and elegant. Forehead & Brow AUs: soft pastel blue Eye & Eyelid AUs: soft pastel lavender Nose & Cheek AUs: soft pastel peach Lip & Mouth AUs: soft pastel pink Head Movement AUs: soft pastel mint

Example generated from “GPT Image 2 Identity-Preserving Portrait Prompt”
GPT Image 2zh
GPT Image 2 Identity-Preserving Portrait Prompt

请只把我上传的照片作为人物身份参考,用于保留本人真实长相。不要保留原照片里的背景、衣服、道具、坐姿和拍摄环境,请重新生成一张全新的{argument name="写真类型" default="鬼马少女棚拍写真"}。 请严格保留本人真实身份特征,包括脸型、五官比例、眼睛、鼻子、嘴唇、肤色、年龄感、发际线、发型基础和整体气质,不要变成陌生人,不要欧美化,不要过度美颜,不要 AI 假脸。 发型请根据上传照片自然延展: - 头发长度保持同一等级 - 是否有刘海遵循原图 - 如果原图是黑发,请处理为深棕黑、黑茶色或自然深咖色,不要纯黑死黑 - 只做写真化优化,不要大幅换发型 妆容统一为{argument name="妆容风格" default="韩系鬼马少女妆"}: 清透奶油肌,自然平眉,浅粉棕或蜜桃粉眼妆,卧蚕明显,纤长睫毛,细眼线,大面积粉色或蜜桃粉腮红延伸到眼下并带一点鼻尖红晕,嘴唇为水润草莓粉或蜜桃粉。整体甜、灵、俏皮,不要浓妆,不要欧美妆。 整体风格为{argument name="视觉风格" default="韩系少女杂志感、鬼马感、甜酷混合、精致棚拍写真"}。背景为浅灰白或奶白色无缝摄影棚背景,光线柔和明亮,画面干净通透,带轻微胶片颗粒感和 editorial 质感。

Example generated from “GPT Image 2 Interior Design Mood Board Generator”
GPT Image 2mixed
GPT Image 2 Interior Design Mood Board Generator

(室内设计情绪板生成器 / Interior Design Mood Board Generator) 你是一名专业的室内设计 Mood Board 创作者。请基于用户提供的 [Space Type] 室内设计照片,生成一张 竖版 3:4 的高端室内设计情绪板。整体视觉参考专业室内设计提案图,呈现 [Style Keywords] 的审美特征,画面应具备 [Mood Keywords] 的空间氛围,并符合 [Branding Tone] 的高级设计表达。 场景类型(Space Type):[Space Type] 画面布局要求 上半部分:呈现一张高分辨率、照片级真实感的 [Space Type] 室内设计效果图。 该效果图需要在空间结构、家具语言、材质关系、色彩搭配、光影氛围上与用户输入照片保持一致,同时提升为更完整、更精致、更具设计提案感的视觉呈现。 重点体现:[Key Furniture Elements]、[Material Keywords]、[Color Palette]、[Lighting Style]。 下半部分:展示与上方空间设计严格对应的材质与软装样本,包括: 材料样板 面料样本 色卡 饰面样本 与该空间相关的木材、石材、金属、玻璃、织物、皮革或涂料样本 所有样本必须与上方空间保持一致,并准确反映该设计方案中的核心材质与色彩逻辑。 右下角:设置一个 Design Legend / Color Palette 信息框,统一展示本方案的: 主色 辅助色 点缀色 核心材质 饰面说明 风格关键词 风格与输出要求 专业室内设计公司级别的 Mood Board 版式 极简、整洁、克制、有秩序的排版 明确的视觉层级与留白控制 材质、色彩、面料、饰面与上方空间完全匹配 标签清晰、现代、简洁,具有高级编辑设计感 整体气质需符合 [Style Keywords] 呈现 [Render Quality] 竖版 3:4 构图 4K Ultra HD 超高细节 写实渲染 直接用于图像生成 标签要求 每个材质或色彩样本配有清晰标签,标签内容围绕以下信息组织: [Label Language] 的材质名称、颜色名称、饰面名称或织物类型。 标签风格应简洁、专业、排版规整,不喧宾夺主。 主题定义 [Space Type] Interior Design Mood Board 风格方向:[Style Name] 关键词:[Style Keywords], [Material Keywords], [Color Palette], [Mood Keywords] 负面约束 避免杂乱拼贴、避免廉价海报风、避免材质与空间不匹配、避免错误透视、避免低质字体、避免装饰元素过多、避免卡通感、避免过饱和色彩、避免信息层级混乱、避免伪随机材质堆砌。 空间类型:卧室 风格名称:现代中古 变量当成可替换字段: [Space Type]:空间类型 例如:客厅、卧室、餐厅、厨房、书房、玄关、浴室、会客区、酒店大堂 [Style Name]:风格名称 例如:现代极简、意式极简、侘寂、奶油风、轻法式、现代中古、北欧自然、深色豪宅、日式原木、当代奢雅 [Style Keywords]:风格关键词 例如:modern minimalist, clean lines, refined luxury, warm contemporary [Mood Keywords]:氛围关键词 例如:温暖宁静、克制高级、通透自然、沉稳静奢、明亮柔和 [Branding Tone]:品牌化视觉语气 例如:高端设计事务所提案感、国际家居品牌视觉、编辑型画册审美、奢华但克制 [Key Furniture Elements]:重点家具/造型元素 例如:低矮沙发、弧形单椅、岩板茶几、悬浮电视柜、落地灯、艺术摆件 [Material Keywords]:关键材质 例如:白蜡木、胡桃木、洞石、亚麻、羊毛、拉丝金属、微水泥、皮革、玻璃 [Color Palette]:配色方案 例如:米白、暖灰、燕麦色、焦糖棕、炭灰、鼠尾草绿、黑胡桃色 [Lighting Style]:光线风格 例如:自然漫射光、晨间柔光、傍晚暖光、均匀展厅光、低照度氛围光 [Label Language]:标签语言 例如:英文、中英双语、纯中文 [Render Quality]:渲染质量描述 例如:照片级真实感、high-end editorial rendering、luxury interior visualization

Example generated from “GPT Image 2 mantis shrimp encyclopedia infographic prompt”
GPT Image 2en
GPT Image 2 mantis shrimp encyclopedia infographic prompt

Create a high-quality vertical encyclopedia-style educational infographic titled: "THE MANTIS SHRIMP — Nature's Most Dangerous Fist" Subject: Peacock Mantis Shrimp (Odontodactylus scyllarus) Overall style: Premium natural history field guide crossed with a modern editorial science magazine. Clean cream/off-white background. Soft teal, coral, and gold accent palette. Gentle drop shadows on all panels. Small refined line icons. Rounded corner information boxes. High information density without feeling crowded. Feels like a collectible reference card from a scientific journal series. —— LAYOUT STRUCTURE (top to bottom) —— [HEADER BLOCK] Large elegant serif title: "MANTIS SHRIMP" Subtitle: "Odontodactylus scyllarus · Stomatopoda" Small tagline badge: "The Ocean's Most Extraordinary Hunter" Classification strip: Kingdom → Animalia | Phylum → Arthropoda | Class → Malacostraca | Order → Stomatopoda [MAIN HERO IMAGE] One hyper-detailed full-color illustration of a Peacock Mantis Shrimp in dramatic three-quarter profile view, raptorial claws extended. Iridescent full-spectrum coloring. Scientifically accurate, illustration style similar to a Smithsonian field guide plate. [ANATOMY ZOOM PANELS — 3 circular close-up detail sections] ① Raptorial Dactyl Club — cross-section showing helicoidal fiber impact-absorbing structure, labeled: "Hits with the force of a .22 caliber bullet" ② Compound Eye — showing 16 photoreceptor types illustrated in spectrum bands, labeled: "Sees UV, infrared, and polarized light simultaneously" ③ Telson Shield — the armored tail plate used to block rival strikes, labeled: "Natural ballistic shield" [QUICK STATS CARD — horizontal strip] Icons + numbers in small rounded tiles: • Strike Speed: 23 m/s (0.002 seconds) • Strike Force: 1,500 Newtons • Color Vision: 16 color channels (humans: 3) • Lifespan: 20+ years • Size: 2–7 inches • Habitat Depth: 1–30 meters [SUPERPOWER INDEX — visual scoring module] Vertical bar or radial chart rating 6 abilities out of 10: Strike Power ████████████ 10/10 Vision Range ████████████ 10/10 Armor Defense ████████░░░░ 8/10 Camouflage ████████░░░░ 7/10 Intelligence ██████░░░░░░ 6/10 Speed █████████░░░ 9/10 [DUAL PANEL ROW] Left panel — "HOW THE PUNCH WORKS" Small sequential diagram: Load → Latch → Release → Cavitation Bubble Collapse → Impact. Note: "The cavitation bubble hits the target a second time even if the first strike misses." Right panel — "VISION vs. HUMAN" Simple comparison diagram: Human eye = 3 cones (RGB) Mantis Shrimp eye = 16 photoreceptors + UV + infrared + 6 polarization channels Label: "Does NOT see more colors — processes light FASTER than any known animal." [HABITAT & RANGE PANEL] Warm Indo-Pacific map with range shading. Depth profile bar: Surface → 30m zone highlighted. Notes: Rocky rubble, coral reef crevices. Solitary, highly territorial. [BEHAVIOR CARD] Rounded box with 4 short bullet points: • Monogamous — mates for life (up to 20 years together) • Maintains and defends a permanent burrow • Can recognize individual humans by face • Communicates using fluorescent signals invisible to most predators [WARNING / RISK PANEL — subtle red accent] ⚠ "Never house with other marine life. Will destroy aquarium glass over time. Has split human thumbnails during handling. Treat as a Level 3 biohazard during tank maintenance." [FUN FACTS STRIP — "5 THINGS THAT SEEM FAKE"] ① Their clubs are stronger than bullet-proof ceramics — engineers are studying them for body armor ② They can see cancer cells in tissue that human eyes cannot ③ Some species glow under UV to communicate privately ④ Their strike creates a flash of light, heat, and shockwave — simultaneously ⑤ They have been known to break aquarium glass from the inside [FOOTER BADGE ROW] Three small rounded category tags: [🌊 Marine Biology] [⚡ Biomechanics] [👁 Vision Science] Small series label bottom right: "NATURAL WONDERS · Vol. 07" Typography: Large bold condensed sans-serif for titles. Clean readable serif for body text. Monospaced for data/numbers. Final feel: The image should look like it was pulled from a $90 collector's edition nature encyclopedia. Print-ready quality. NOT a poster. NOT an ad. A knowledge artifact.

Example generated from “GPT Image 2 MS Paint Drawing Prompt”
GPT Image 2en
GPT Image 2 MS Paint Drawing Prompt

Redraw the attached image in the most {argument name="style" default="clumsy, scribbly, and utterly pathetic"} way possible. Use a white background, and make it look like it was drawn in MS Paint with a mouse. It should be vaguely similar but also not really, kind of matching but also off in a confusing, awkward way, with that low-quality pixel-by-pixel feel that really emphasizes how ridiculously bad it is. Actually, you know what, whatever, just draw it however you want.

Example generated from “GPT Image 2 Prompt Treasure Poster”
GPT Image 2en
GPT Image 2 Prompt Treasure Poster

Goal: Create a luxurious vertical poster announcing a collection of useful GPT Image 2 prompt websites, styled like a premium treasure discovery. Canvas: Portrait 3:4 poster, bright white and light silver background, high-resolution commercial 3D render mixed with bold graphic typography. Use a clean editorial layout with subtle grid marks, thin crop lines, dotted ornaments, small sparkle icons, and bottom micro-print details. Top typography: Place a huge, heavy, blocky black Chinese headline centered near the top reading {argument name="main headline" default="提示词宝藏站"}. Above and around it add minimal black decorative marks: one large four-point star at upper left, thin horizontal lines, a dotted line near upper right, and tiny diamond markers. Subtitle bar: Directly under the headline, add a thin outlined rectangular label containing bold black text reading {argument name="subtitle text" default="10 个超实用 GPT Image 2 提示词网站"}. Keep the subtitle centered with generous letter spacing and a crisp print-design feel. Main subject: In the lower two-thirds, show an open futuristic silver treasure chest with polished metal panels, transparent glass-like edges, chrome trim, gold accents, and a large faceted diamond emblem on the front lock. The chest is overflowing with glowing prompt-library interface cards, gems, diamonds, and warm golden light beams. Add white, gold, and crystal reflections, lens flares, and sparkling particles. Website cards: Show exactly 10 stacked floating UI cards emerging from the chest, arranged in layered perspective like browser panels. Each card should have rounded corners, small app icons, minimal menu dots, and one visible label. The 10 visible labels are: 1) Midjourney Prompt Hub, 2) Prompthero, 3) OpenGPT, 4) LibLib AI, 5) PromptJourney, 6) FlowGPT, 7) PromptBase, 8) Libai.GPT, 9) ChatGPT Prompt Library, 10) Magic Prompts. Use a mix of white, silver, and black card headers. Search element: In front of the cards, place a pill-shaped search bar angled slightly upward, glowing softly, with the text {argument name="search query" default="GPT Image 2"} and a black search icon button on the right. Decorative objects: Include exactly 2 translucent ribbon bands looping diagonally through the composition, both printed repeatedly with the word {argument name="ribbon word" default="PROMPTS"}. Add exactly 1 gold ring on the left, exactly 2 large faceted diamonds near the left and right sides, exactly 1 small floating rounded-square tile with a white geometric cube logo on the left, and exactly 1 matching rounded-square tile with a black cube logo on the right. Scatter smaller crystal shards and gold star particles around the chest. Visual style: Premium tech treasure aesthetic, glossy 3D rendering, white/silver/gold palette, cinematic reflections, realistic glass and metal materials, sharp typography, high contrast black headline, elegant minimal infographic poster styling. Constraints: Keep the design vertically centered and symmetrical, preserve the exact count of 10 website cards, avoid adding extra website names, avoid people or characters, no watermark, no social media UI, no QR code.

Example generated from “GPT Image 2 Quality Comparison Grid”
GPT Image 2en
GPT Image 2 Quality Comparison Grid

{ "type": "Quality comparison puzzle", "subject": "Fantasy anime illustrations generated under three quality settings", "style": "A light and airy watercolor ink picture book/anime style, a soft pastel palette, delicate lines, painterly texture, and a bright, magical atmosphere.", "canvas": { "background": "Overall light gray background", "aspect_ratio": "16:9 Presentation Slides" }, "layout": { "sections": [ { "title": "Low", "position": "Top left", "count": 1, "labels": [ "Low" ], "image": "A vivid fantasy street scene depicts a young, androgynous child sorcerer moving about, smiling and raising his wand, surrounded by four enormous blue manta ray-like flying creatures, several orange-red goldfish, a few round pufferfish, floating bubbles, and confetti. The background features ornate European-style architecture; the composition is busy and colorful, but the level of detail is slightly lacking.", "overlay": "A dark, semi-transparent rectangle near the right side, with the word \"Low\" in large white sans-serif font." }, { "title": "Medium", "position": "Top right", "count": 1, "labels": [ "middle" ], "image": "The same cue word is rendered again, with the child mage on the right, his face obscured by a pink square occlusion block, holding his staff upwards. In the foreground is a dominant large blue manta ray creature, surrounded by smaller blue fish, orange-red fish, pufferfish, and bubbles. The background is a pale fantasy city with tower and clock details; compared to the low-quality version, the spacing is cleaner and the form is more legible.", "overlay": "A dark, semi-transparent rectangle near the bottom right corner, with the word \"Medium\" in large white sans-serif font." }, { "title": "High", "position": "Bottom left", "count": 1, "labels": [ "high" ], "image": "The same fantasy scene rendered to the highest precision: A happy child wizard runs forward, wand in hand, wearing a flowing cyan cloak adorned with warm pink-orange feathers, a cream-colored tunic and harem pants, brown boots, and fluffy pink hair; surrounded by four blue manta ray-like flying creatures, many orange-red fish, several brown pufferfish, bubbles, and glitter, against a backdrop of a sunlit city street with staircases and elegant architecture; the image is sharp, balanced, rich in detail, and bright.", "overlay": "A dark, semi-transparent rectangle near the right center, with the word \"High\" in large white sans-serif font." }, { "title": "GPT Image 2 Quality Comparison", "position": "Bottom right", "count": 1, "labels": [ "GPT Image 2", "quality", "contrast" ], "image": "Plain text panel on a light gray background", "typography": "Large, bold, black sans-serif text centered, displayed in 3 lines.{argument name=\"headline text\" default=\"GPT Image 2 Quality Comparison\"} '" } ], "grid": "A 2x2 puzzle with 3 image panels and 1 text panel.", "margins": "Gaps between panels" }, "character": { "count": 1, "description": "A young, fantastical child mage or adventurer, cheerful, in a dynamic pose, and fluffy.{argument name=\"hair color\" default=\"pink\"} Short hair, an ornate wand or staff, a flowing turquoise cloak with coral and gold embellishments, cream-colored clothing with lantern pants, and a fantasy picture book design." }, "environment": { "setting": "Sunny, fantastical European-style streets or squares", "floating_elements_count": "Four large manta ray creatures, along with countless small fish, several pufferfish, and many bubbles.", "mood": "Playful, magical, festive" }, "rendering_notes": { "comparison_purpose": "Use the same prompts to visually differentiate the three quality levels.", "quality_labels_count": 3, "text_panels_count": 1 } }

Example generated from “GPT Image 2 realistic white papercraft illustration transform prompt”
GPT Image 2zh
GPT Image 2 realistic white papercraft illustration transform prompt

このイラストを非常に精密でリアルな白い紙のペーパークラフト風に変換してください。厚紙をレーザーカットしたようなシャープで正確な切り口、細かい折り目、複数のレイヤーによる豊かな立体感、紙の繊維感と自然な影を高ディテールで表現してください。 光の当たり方による紙の白さと微妙なグラデーションを活かし、本物のような立体的なペーパーアート作品のようなリアリティを出して。全体を洗練されていて芸術的な雰囲気に。元のイラストの構図・キャラクターを忠実に維持。

Example generated from “GPT Image 2 Shonen Manga Collage Poster”
GPT Image 2mixed
GPT Image 2 Shonen Manga Collage Poster

🤣小时候看《Bleach》: “卍解!!!” 长大后玩 AI: “镜片里倒映漫画分镜 + 前景动态条漫 + 蓝色灵压粒子 + 日漫拼贴构图 + 电影级光影 + 超近景压迫感……” 以前以为久保带人是在画漫画。 现在发现他其实是在提前给 GPT-Image-2 写提示词。 这次测试我最上头的点不是“还原角色”, 而是它终于能理解那种—— “潮流视觉海报感 + 漫画叙事层次 + 动态镜头语言” 的混合审美。 AI 现在已经不是“生成一张动漫图”了。 而是在帮我们做: 「不存在的动漫宇宙视觉总监」。 顺便说一句—— 那个戴斗笠戴墨镜的版本,真的很像: “如果京乐春水开始做潮流品牌主理人。” 😂 ♥️提示词在这里,麻烦给个赞! 超高细节二次元热血漫画风角色海报,少年死神角色正面半身特写,橙色炸毛短发,琥珀色眼睛,佩戴黑色圆框复古墨镜,冷峻严肃表情,正中央对称构图,镜头直视观众,强烈压迫感。 眼镜镜片中倒映大量黑白漫画分镜与角色画面,背景也由密集的日漫漫画页拼贴组成,形成“角色记忆 / 名场面回顾”的视觉效果。前景漂浮多条高速运动的漫画分镜条带,带有动态模糊与景深虚化效果,穿插画面上下,营造速度感与空间层次。 画面中散落蓝色灵压粒子 / 荧光能量碎片,形成冷暖撞色(橙发 vs 蓝色粒子)。整体采用《BLEACH》式热血少年漫画美学,融合现代潮流海报设计与高级动漫商业视觉。 anime key visual, BLEACH style, manga collage poster, cinematic anime lighting, reflective glasses, manga panels reflection, dynamic motion blur, orange spiky hair, intense stare, ultra detailed anime illustration, shonen jump aesthetic, layered composition, high contrast shading, cel shading, glowing blue particles, dramatic close-up portrait, symmetrical composition, manga montage background, Japanese comic aesthetic, premium anime poster

Example generated from “GPT Image 2 Social Media Screen Breakout Poster”
GPT Image 2zh
GPT Image 2 Social Media Screen Breakout Poster

动态的豪华商业广告海报,特色是超现实3D渲染的充满活力的年轻女性,以上传的女性面部作为参考,穿着高级亮橙色设计师服装、豪华配饰以及时尚的金色墨镜,自信地从一个巨大的金色智能手机屏幕中爆发出色。她的姿势有力且时尚,一只运动鞋通过强烈的强制透视戏剧性地穿过数字显示屏,踏入现实。 构图在前台强调她白色豪华运动鞋,带有纹理口香糖鞋底,通过电影般的广角镜头失真和浅景深增强。漂浮的闪亮3D社交媒体图标、金色几何元素和豪华品牌图形环绕着她,营造出高端影响者营销美学。 明亮的摄影棚灯光营造出充满活力的优质促销氛围,金属金色手机边缘的丰富反射与哑光织物质地形成对比。主导的橙色、白色和金色调色板传递出超现代豪华X / Twitter 广告氛围。干净的白色背景上带有大胆的编辑排版、优质软件品牌元素、优雅的UI图形、漂浮的互动图标以及时尚的二维码区域。 超现实8K品质、电影般的阴影、精致的商业艺术指导、豪华女性能量、时尚营销美学、现代社交媒体品牌、闪亮反射以及高端数字广告风格。 宽高比:3:4。