Cyberpunk / Sci-Fi

Use the uploaded photo as the sole and non-negotiable identity reference. Preserve the subject’s exact recognizable appearance with maximum fidelity, including face shape, forehead, jawline, cheekbones, chin, eyes, eyebrows, nose, lips, ears, skin tone and texture, hairstyle, hairline, facial hair if present, natural asymmetries, and all distinctive features. The final character must unmistakably be the same person. Do not beautify, reshape, age, feminize, masculinize, or replace the identity with a generic model. Create a premium stylized 3D character portrait inspired by authentic 1980s fashion and a Miami/Vice City-inspired neon atmosphere. Make it feel like a high-end cinematic open-world game character render: bold, confident, polished, stylish, and visually striking. Use a close-up or chest-up composition with a natural, powerful pose. The subject should appear calm, self-assured, and slightly rebellious, with the head subtly turned and the gaze directed off-camera or toward the distance. Transform the subject into fully stylized 3D character art, not a photograph. Keep the face highly recognizable while using smooth sculpted forms, clean geometry, refined facial planes, realistic-stylized skin shading, detailed hair volume, polished materials, and cinematic rendering. Dress the subject in premium 1980s-inspired fashion adapted to a modern game-world aesthetic: retro bomber jacket, open-collar shirt, fitted tee, satin or leather details, layered chains, bold accessories, or a colorful windbreaker. Keep the styling tasteful, fashionable, slightly luxurious, and appropriate to the subject’s appearance. Create a neon-soaked Miami/Vice City mood with tropical energy, palm silhouettes, glamorous nightlife, retro architecture, blurred city lights, pastel dusk skies, and subtle neon reflections. Keep the background cinematic and uncluttered. Use a vibrant retro color palette of hot pink, cyan, teal, purple, sunset orange, electric blue, and warm magenta. Add dramatic cinematic rim lighting, glossy reflections, soft global illumination, strong subject separation, premium contrast, and sophisticated color grading. Give the hair, clothing, and accessories subtle 1980s influence while maintaining the subject’s original identity and natural characteristics. The overall result should feel like a stylish main character from a neon-soaked open-world crime universe. Final look: ultra-polished 3D game-character render, cinematic quality, highly recognizable face, 80s fashion fusion, Vice City-inspired retro-futuristic atmosphere, glossy materials, crisp facial detail, premium lighting, clean composition, and scroll-stopping visual impact. Negative constraints: Do not create a realistic photograph, flat illustration, anime, sketch, or painterly artwork. Do not alter the person’s identity or facial structure. No distorted features, excessive beautification, aging, messy styling, visible text, logos, watermarks, signatures, labels

Create a square retro science-fiction laboratory illustration in a bold late-1960s psychedelic screen-print and risograph style. Show exactly two foreground humans: an elderly bald male scientist in glasses and a white lab coat leaning over a large orange control console on the left, and a calm seated test subject on the right wearing loose white clinical clothing, strapped or connected to a heavy wooden-and-metal chair with a circular head apparatus and thick black cables trailing behind him. Include exactly three standing humanoid figures in the background on a raised platform behind a railing, evenly spaced under hanging lamps. Include exactly three large chrome dome heat lamps across the upper area, plus exactly three smaller hanging pendant devices. The central control console should contain exactly five small rectangular monitor panels showing head/profile imagery, with many knobs, switches, and a small screen below. In the lower left foreground, include one separate vintage electronics unit with an oscilloscope-style display showing a jagged yellow waveform, plus round dials and toggle switches. Fill the background with warped optical rhythm patterns: wavy bands of fluorescent magenta, hot orange, lemon yellow, deep cobalt blue, and black. Use posterized tonal blocks, coarse halftone dots, ink speckling, grunge paper texture, deliberate color misregistration, rough screen-print edges, and minimal perspective depth. Make the scene feel like a psychedelic mind-control or brainwave experiment poster, with high contrast, dense cables, glowing lamps, and no readable text or watermark.

{ "title": "Cyberpunk Detective", "image_description": "A cinematic cyberpunk scene viewed through a rain-soaked car window. Neon reflections dance across the glass while a handsome futuristic detective sits in the driver's seat wearing a heavy dark coat. A woman wearing a glowing translucent yellow jacket looks toward him. Flying vehicles move through a foggy futuristic city in the background.", "characters": [ { "role": "Futuristic Detective", "position": "Driver's Seat", "appearance": "Handsome, serious expression, heavy dark coat", "focus": "Sharp Focus" }, { "role": "Mysterious Woman", "position": "Passenger Seat", "appearance": "Dark hair, glowing translucent yellow jacket", "expression": "Quietly observing the detective", "focus": "Slightly softer focus" } ], "setting": { "location": "Futuristic Vehicle Interior", "cityscape": "Foggy cyberpunk megacity", "background_elements": [ "Flying vehicles", "Neon billboards", "Rain-covered glass", "Holographic lights" ] }, "cinematography": { "shot_type": "Medium Close-Up", "camera_angle": "Eye Level", "lens": "50mm Anamorphic Lens", "depth_of_field": "Shallow", "composition": "Movie Still" }, "lighting": { "type": "Cinematic Lighting", "effects": [ "Neon Reflections", "Volumetric Lighting", "Rain Refractions", "Soft Ambient Glow" ] }, "mood": [ "Moody", "Mysterious", "Futuristic", "Emotional" ], "color_palette": [ "Blue", "Cyan", "Yellow" ], "quality": { "style": "Hollywood Blockbuster", "realism": "Ultra Photorealistic", "resolution": "8K", "details": [ "Perfect Reflections", "Photorealistic Faces", "Film Grain", "Volumetric Fog", "Realistic Depth of Field", "Award-Winning Cinematography", "IMAX Quality", "Cinematic Storytelling", "Masterpiece" ] } }

2:3 portrait, acid futurism fashion advertising photography. A model with a completely obscured face wears a complex but clearly structured experimental metal helmet, head turned three-quarters to the right, shoulders and chest naturally cropped from the bottom. The main subject occupies most of the frame, with clean blue negative space at the top and right. The helmet is a rounded mirror chrome dome, partially covered with titanium-blue coated perforated panels with neatly arranged small holes. Silver reinforcing ribs, fasteners, and connecting hinges are realistic and detailed. A short, sharp brushed silver visor extends from the front, above a single opaque curved iridescent face shield transitioning from electric blue and deep purple to pure orange and golden yellow, representing thin-film interference reflection rather than self-luminescence. Around the jaw are lightweight asymmetrical silver struts and a few white ceramic spherical nodes, showing clear mechanical connections without cluttering the main silhouette. The neck has a high collar made of clean pleated aluminized silver film, and the shoulder is a high-purity ultramarine blue glossy technical fabric with neat zippers and cut edges. The background is a uniform high-purity cobalt blue, slightly lighter only at the bottom. Strong directional sunlight and controlled white reflective surfaces form sharp, credible metal highlights, with deep black and transparent shadows, clearly reflecting the blue sky and white glossy surfaces. Extremely high detail, clean and dust-free, intense colors, and a sense of sophisticated industrial fashion in retro-futurism. No text, postal markers, brands, logos, or watermarks; no rust, stains, smoke, particles, or atomized glows.

Create a cinematic surreal science-fiction scene in a square 1:1 composition: a colossal upright rectangular monolith made of dark translucent ice or glass stands in shallow reflective water under a moody teal-blue misty sky. Inside the monolith is one enormous preserved sunflower, with golden yellow petals and a dark seed head, partially obscured by cloudy scratches, frost, bubbles, and mineral-like imperfections in the material. The monolith is positioned slightly right of center, very tall and vertical, with a visible front face and narrow right side face, sharp glowing edges, heavy mass, and a faint cold internal haze. At the base, show exactly 7 small primitive hominid figures in dark silhouettes: 1 distant figure at far left standing hunched, 3 clustered crouching figures near the lower left, 2 hunched walkers approaching near the center-left, and 1 figure closest to the monolith reaching out and touching its surface. The water is calm and mirrorlike with subtle ripples, reflecting the monolith, the flower’s warm golden glow, and the tiny figures. Use a wide low camera angle, atmospheric fog on the horizon, dramatic scale contrast, painterly photorealism, ultra-detailed texture, muted cyan and deep teal palette contrasted with warm amber petals, mysterious prehistoric-meets-cosmic mood inspired by a monumental alien artifact. No text, no logos, no extra figures, no buildings, no modern objects.

Goal: Create a futuristic Chinese tech infographic cover slide explaining GPT Image 2.5 Sunburst 模型能力解说, based on OpenAI image prompting documentation, in a glowing cyber-blue presentation style. Canvas: 16:9 horizontal slide, deep navy-to-cyan gradient background with soft radial light beams, neon arcs, thin orbital lines, lens glow, glassmorphism panels, and subtle high-tech UI grid details. Use crisp vector-like typography and luminous cyan borders. Add small decorative English microcopy in the corners. Main header: At the top center, large bold white title: “GPT Image 2.5 Sunburst 模型能力解说”. Directly below it, smaller bold subtitle: “基于 OpenAI《Image Prompting》文档的图示化学习版”. Under the subtitle, place a rounded URL pill with a chain-link icon and the text “developers.openai.com/api/docs/guides/image-prompting”. Central diagram: In the center, create a circular sunburst capability map. Put a bright glowing white-cyan core circle labeled “GPT Image 2.5 Sunburst” with a smaller Chinese line underneath: “一张图，开启更多可能”. Around it, place exactly 6 numbered colored capability nodes connected by orbit rings and radial lines: 1. Cyan node with cube icon: “1. 模型选择”, smaller text “选对模型 / 发挥最佳效果”. 2. Green-teal node with sliders icon: “2. 参数设置”, smaller text “掌握关键参数 / 控制生成效果”. 3. Purple node with document-and-pencil icon: “3. Prompt 编写原则”, smaller text “用好的提示词 / 表达你的意图”. 4. Pink-magenta node with image icon: “4. 生成能力”, smaller text “从想法到画面 / 的多样化生成”. 5. Orange node with magic-wand icon: “5. 编辑能力”, smaller text “基于现有图像 / 进行精准编辑”. 6. Violet-blue node with refresh arrows icon: “6. 跨轮迭代”, smaller text “多轮优化 / 逐步达成理想结果”. Left side feature cards: Arrange exactly 3 rounded translucent cards stacked vertically, each with a square icon tile on the left and Chinese text on the right: 1. Lightbulb icon, title “把文档转成易懂图示”, body “将官方文档的关键要点 / 转化为直观、清晰的视觉内容”. 2. Target icon, title “聚焦可实操方法”, body “提供真实可用的技巧与示例 / 帮助你快速上手”. 3. Image icon, title “覆盖生成与编辑”, body “从文本生成到图像编辑 / 全面梳理核心能力”. Right side feature cards: Arrange exactly 3 matching rounded translucent cards stacked vertically: 1. Shield-check icon, title “强调可读性与准确性”, body “在简洁的表达中 / 保持内容的专业性与准确性”. 2. Group/users icon, title “适合传播与内部培训”, body “便于分享、学习与团队使用 / 提升 AI 图像创作能力”. 3. Palette icon, title “统一系列风格”, body “10 页完整体系 / 一致的设计语言与视觉风格”. Bottom content-structure band: Add a wide rounded glass panel across the bottom. On the left of this panel, show a large open-book icon and the bold heading “本套内容结构”, with smaller body text “10 页带你系统掌握 / GPT Image 2.5 的图像提示词方法”. To the right, show exactly 10 chapter rows in two columns of five, each row in a small rounded blue pill with a two-digit number: 01 “封面导读” 02 “模型选择” 03 “参数与尺寸规则” 04 “Prompt 编写原则” 05 “控制风格与光线” 06 “过程/知识可视化” 07 “文本广告与 Logo” 08 “叙事/历史/UI/商业页” 09 “参考图驱动编辑” 10 “透明背景与跨轮迭代”. Decorative side text: Upper left tiny vertical microcopy reads “MORE / CREATIVE / POSSIBILITIES / WITH AI”; below it add Chinese copy “用更好的提示词 / 创造更美好的视觉世界” with a small underline. Upper right tiny Chinese copy reads “更清晰的思路 / 更强大的表达 / 让想象力 / 变成可实现的图像”. Add handwritten script near the upper-right diagram: “From Docs to Mastery”. Add handwritten script near bottom right: “Good Prompts / Better Images / A More Creative You”. Footer: Bottom left add tiny separated words “IDEAS / PROMPTS / IMAGES / A BRIGHTER TOMORROW”. Bottom right add page marker “Page 1 / 10”. Visual style: Premium SaaS keynote cover, luminous blue glass cards, neon cyan outlines, high contrast white Chinese typography, rounded UI panels, subtle blur, volumetric light, polished infographic composition. Keep all major elements symmetrical and readable, with the central sunburst as the focal point. Constraints: Use exactly 6 central capability nodes, exactly 6 side feature cards, and exactly 10 bottom chapter rows. Do not add extra chapters or cards. Preserve the Chinese headings and labels exactly as specified. No logos other than text references to OpenAI and GPT Image 2.5. No watermark.

Create an ultra-detailed dark fantasy gothic illustration of an undead vampire king enthroned inside a ruined cathedral throne room. The central figure is a pale, corpse-like monarch with long flowing white hair, glowing red eyes, blood running from the mouth, and a jagged black crown. He wears ornate blackened armor covered in skulls, spikes, chains, red jewels, and torn crimson-black royal robes. He sits arrogantly on a skull-encrusted stone throne, one hand resting on the armrest and the other gripping a long ceremonial sword with a skull pommel, gothic crossguard, red gem, and pale blade. Surround him with exactly 9 clearly visible supernatural figures or creatures: 1 large translucent ghostly warrior hovering behind him with a sword, 1 smaller floating ghost near the moonlit archway, 4 misty human spirits on the stairs and balcony in the midground, 2 armored spectral soldiers at the lower right holding weapons, and 1 snarling ghost wolf in the lower left foreground. Set the scene in a vast black stone cathedral with broken pointed arches, towering columns, candles, chains, cracked steps, skulls, and tattered red banners. Include exactly 3 readable banner or stone inscriptions: left hanging banner says BLOOD BEYOND DEATH, right hanging banner says KINGS DIE BUT LEGENDS HAUNT FOREVER, and the stone block near the lower left says SWORDS REMEMBER WHAT MEN FORGET. Through the huge archway, show a distant spired gothic castle, an arched bridge, flying bats, storm clouds, cold mist, and a huge crimson blood moon. Use cinematic low-angle composition, hyperreal digital painting, intricate concept-art detail, cold blue-gray fog contrasted with deep crimson accents, dramatic moonlight, candle glow, volumetric mist, sharp armor highlights, macabre regal atmosphere, no modern objects, no cartoon style.

Generate a 2:3 vertical grand sci-fi landscape with photorealistic natural textures, fine film grain, and restrained vintage cinematic grading. In the foreground are soft, undulating ochre-red hills, with a solitary adult standing slightly left of the bottom center facing away from the camera, wearing a dark long coat and occupying only 2.5% of the frame, quietly gazing into the distance. On the vast plains of the mid-ground, numerous tiny off-white settlements are scattered, with a silvery-blue river flowing in a gentle S-shape through the towns and reddish-brown land. Beyond the horizon stands a planet-scaled, slightly tilted ancient fractured stone monolith ring: the body is extremely heavy, with a massive curved solid occupying the upper left of the frame, its top and left edge cut off by the frame; a curved remnant on the right extends into the sky, its irregular break misaligned with the main ring; the center encloses an arched sky void expanding toward the upper right, not two straight parallel walls. The surface features deep bluish-black basalt-like rough layering, macroscopic fractures, and slowly weathering longitudinal gullies, definitely not a smooth metal ring. Warm golden low-angle sunlight skims from the right side across the curved inner edge and break, while the large main body sinks into layered dark green shadows, the bottom obscured by massive but calm milky-golden cumulus clouds and dust, like clouds accumulating at the feet of the giant object, not exploding. The sky on the right is deep greyish-blue, the hay is copper-red and dark ochre, and the river has only restrained natural reflections. Use the tiny silhouette, miniature towns, base clouds, and the ring extending beyond the frame to emphasize human insignificance. Quiet, distant, heavy, and incomprehensible grandeur, clear depth of layers, true natural light, no text, no logos, no watermarks, no lasers or flares.

Generate a 3x3 grid showing various cuts from a 3D action game featuring this character. 16:9

Create a vertical cinematic fantasy portrait on a pure black background: a solemn young woman styled as a cyberpunk oracle or blindfolded goddess, centered from the waist up, with pale skin, long ash-blonde hair, and a calm serious expression. She wears a deep emerald draped toga-like garment with layered folds and a dark green futuristic blindfold covering her eyes, the blindfold embedded with tiny glowing green and red data lights. Add fine luminous circuit-trace markings across her cheeks, neck, shoulders, and arms. Behind her head place a radiant halo made of many thin green light rays, like a digital saint crown. Surround her entire body with one large vertical oval energy ring made from two opposing colors: the left half is vivid neon green and the right half is intense neon red, both formed from smoky plasma, particles, scanline glitches, and fragmented digital noise. The ring should look like a flowing yin-yang-shaped portal, with green energy sweeping upward on the left and red energy sweeping downward on the right, scattering sparks outward. Use dramatic low-key lighting, high contrast, ultra-detailed realistic skin and fabric, glowing particle effects, volumetric haze, sharp focus on the face and torso, and a mystical sci-fi editorial poster aesthetic. Customize the subject as blindfolded digital oracle, the garment color as deep emerald green, the left energy color as neon green, the right energy color as neon red, and the mood as solemn and prophetic. No text, no logo, no watermark.

Goal: Create a polished square promotional anime key visual for GPT Image 2.5, presenting it as a futuristic creative image-generation service with a cheerful anime ambassador reaching toward the viewer. Canvas: 1:1 square social-media poster, cinematic neon city background at sunset, high-detail anime illustration blended with sleek SaaS launch-page UI overlays. Use strong depth of field: the character’s outstretched hand is large and slightly motion-blurred in the foreground, her face is sharp, and the city is softly glowing behind her. Main subject: A cute anime girl in the center-right foreground, about teenage/young adult style, short fluffy pale pink-blonde bob hair with bangs, one eye winking and one warm reddish-brown eye open, smiling brightly. She wears a futuristic black-and-white techwear jacket with glossy panels, straps, zippers, badges, red ribbon accents, black inner top, and a lanyard badge printed with the OpenAI-like knot logo and “GPT Image 2.5”. Her right arm reaches toward the camera invitingly. Add a small black-and-red hair clip and ribbon on one side. Companion robot: Place exactly 1 small rounded companion robot at the lower right, white body with cat-ear-like points, glossy black face screen, cyan smiling eyes, and a chest panel containing the OpenAI-like knot logo plus the text “Create Explore Together”. Branding and headline: At the upper left, place a large glowing OpenAI-like knot icon followed by huge text “GPT” on the first line and “Image 2.5” below it, with “2.5” in a blue-to-pink neon gradient. Under it, add the tagline “More Expressive. More Creative. Now in Your Hands.” Add handwritten Japanese text beneath: 「想像を、もっと自由に。」 Left feature stack: Add exactly 6 translucent dark glassmorphism cards stacked vertically on the left, each with a glowing icon, bold white title, smaller subtitle, and where visible a small preview thumbnail strip. The 6 cards are: 1) “Text to Image” with subtitle “Just type your imagination” and 1 landscape castle thumbnail; 2) “Sketch to Image” with subtitle “Turn your sketches into art” and 2 thumbnails showing a sketch converting to a fantasy landscape with an arrow; 3) “Image Editing” with subtitle “Refine with simple instructions” and 2 anime portrait thumbnails with an arrow; 4) “In-context Creation” with subtitle “Consistent characters & style” and 2 anime character thumbnails; 5) “Faster Generation” with subtitle “Create more, wait less” and a lightning icon; 6) “Higher Detail” with subtitle “Sharper, richer, more real” and 1 flower thumbnail. Right feature stack: Add exactly 3 translucent dark glassmorphism cards on the right side. The top card is “Multi-style” with subtitle “Anime, Realistic, Illustration...” and exactly 3 thumbnails: anime portrait, realistic landscape, cat photo. The middle card is “Follow Instructions” with subtitle “More accurate, more flexible”. The lower card is “Create on Mobile” with subtitle “@ → Sketch (iOS/Android)”. Handwritten notes: In the upper right sky, add Japanese handwritten copy: 「好きな世界を、今すぐ、ここから。」 followed by a signature Chisato and a heart. At the bottom right, add handwritten Japanese copy: 「つくろう。あなたの『好き』を。」 and the line “with GPT Image 2.5”. At the bottom left, add a small OpenAI-like knot icon and cursive English text “A more creative tomorrow_”. Visual style: Premium anime promotional art, vibrant blue, cyan, magenta, and sunset-pink lighting; glowing holographic UI panels; reflective metal and glass; crisp typography; dramatic wide-angle selfie perspective; highly detailed face and clothing; soft bloom, rim light, and lens flare. Keep all UI text legible and aligned, with no extra feature cards beyond the specified counts.

Ultra-realistic cinematic editorial photograph of a strikingly handsome young man in his early 20s walking through a historic Old Delhi street as if he has traveled back in time. He has thick, naturally wavy jet-black hair, strong well-defined eyebrows, deep expressive dark-brown eyes, a straight sculpted nose, prominent cheekbones, a sharp masculine jawline, and subtle natural stubble. He wears a sophisticated modern outfit—a perfectly tailored black long coat over a minimalist cream shirt, fitted dark trousers, and polished leather boots—creating a striking contrast with the ancient surroundings. Around him are magnificent Mughal-era architecture, weathered red-brick buildings, ornate balconies, old wooden doors, narrow winding lanes, traditional street stalls, hanging lanterns, cycle rickshaws, and atmospheric Old Delhi details. Subtle visual hints of time travel, such as a faint futuristic glow around him and a shimmering distortion in the air behind him. Warm golden-hour sunlight streams between the buildings, creating dramatic shadows and volumetric light rays. Cinematic composition, eye-level perspective, shallow depth of field, realistic skin texture, highly detailed environment, natural colors, atmospheric haze, 35mm photography, HDR, dramatic yet elegant mood, photorealistic, 8K, masterpiece.

turn it into a future building

Goal: Create a dark-mode desktop ChatGPT interface screenshot showing an image-generation conversation in Chinese, with a dramatic anime artwork preview in the main chat area. Canvas: Wide horizontal screenshot, 1200×608 px, dark charcoal UI, rounded corners and macOS-like browser/app framing. The interface is cropped so the left sidebar fills about 19% of the width and the main chat area fills the rest. Layout: Left navigation sidebar with the ChatGPT wordmark at top, a search icon, and a compact sidebar toggle icon. Below it, show exactly 8 primary navigation rows with icons and Chinese labels: 1) 新聊天, 2) 图片 with a tiny “已更新” badge, 3) 资料库, 4) 定时任务, 5) 插件, 6) 项目, 7) Codex, 8) 更多. Add a thin vertical scrollbar near the boundary between sidebar and chat. Under a “最近” heading, show exactly 2 recent chat items: “超现实画面生成” and “生成幻想原画提示词” with a small hollow circle to its right. Bottom-left user area: circular blue avatar with “TT”, username “Tryntje Titulaer”, and the label “免费版”. Main chat area: Top right includes a pill button with a gift icon and the text “免费试用”, plus small share/action icons partially visible. Near the top center, place a large rounded rectangular prompt input bubble in dark gray. Inside it, show a single highlighted blue text selection reading 超2d,反结构色.强畸变反透视。简谐,无字神话.21:9. On the right side inside the input bubble, place exactly 2 dark round buttons labeled “取消” and “发送”. Generated image card: Below the input bubble, place one large rounded image preview card in a 21:9 aspect ratio, approximately 765×332 px, centered slightly right. At the lower-left of the image card, overlay one small rounded dark button labeled “编辑”. At the lower center just below/overlapping the card, place one circular down-arrow button. At the lower-right of the card, overlay one circular share/upload icon button. Artwork inside the generated image: Ultra-dynamic fantasy anime illustration in a distorted reverse-perspective fisheye composition, intense saturated colors, painterly brush texture, high contrast. A young mythic female figure in ornate flowing robes reaches one oversized hand dramatically toward the viewer from the left foreground; her body recedes upward into the center, with long dark hair, red ribbons/sashes, white and black garments, gold accents, and a calm mysterious expression. Background is a shattered celestial myth landscape with towering dark cliffs, swirling clouds, blue sky, golden sunset light, explosive brush strokes, floating debris, and an enormous dragon or phoenix-like creature arcing across the upper right. Color palette: electric cobalt blue, bright cyan, fiery orange, crimson red, cream white, deep navy, and black. No nudity, no explicit content. Bottom interaction row: Under the image card, show exactly 5 small action icons in a row: copy/duplicate, thumbs up, thumbs down, share/upload, and more/ellipsis. Visual style: Make the whole screenshot look like a real ChatGPT dark-theme desktop UI captured from a browser, with clean sans-serif text, Chinese UI labels, subtle shadows, and accurate rounded spacing. The generated artwork should be much more colorful and detailed than the surrounding UI. Constraints: Use exactly one generated image preview, exactly two prompt-input buttons, exactly eight sidebar navigation rows, exactly two recent chat items, and exactly five bottom action icons. Keep all visible text as specified, avoid watermarks, and do not add extra panels or unrelated UI.

Where the Wing Remembers Both Shores The dragon does not choose a century. It is the century choosing itself through a body made of postponement and afterglow. One wing trails the last unburned page of a library that fell before paper learned its own name. The other combs holographic rain from towers that have not yet decided whether they will stand or become rumor. Between them the air keeps two calendars and forgets which one is running. Its scales are older than the word for scale. They remember the heat of forges that have not been lit, and the cold of stars that have already gone out in some other telling. Runes surface and sink like thoughts a city has not earned the right to think. Each pulse of light is both relic and prototype. Below, the streets are wet with what has happened and what is still negotiating its arrival. Neon writes on water that was once a glacier’s patience and will be, later, only a rumor of thirst. Foundations rest on the quiet of forests that still dream they are standing. Billboards advertise tomorrows already homesick for the dusk that has not come. The creature’s eyes hold the only honest weather: one the green of a memory that does not yet know it is finished, the other the blue of a question that has not found the mouth that will ask it. They look at us the way time looks at itself when no one is watching without pity, without verdict, only the long courtesy of attention. We live in the brief downdraft of its passing, that strange, merciful interval where the past is still unfinished with us and the future has already begun to miss what we have not yet lost. Nothing is promised except the turning: he slow, luminous hinge of a wing that belongs to every hour at once and to none of them completely. The mist it leaves is neither ending nor beginning. It is the place they briefly recognize each other before the next uncertainty opens its quiet, necessary hand.

Create a highly realistic cinematic portrait of a beautiful young East Asian woman lounging on a modern sofa in a cozy neon-lit apartment, blending contemporary lifestyle photography with elegant xianxia-inspired fashion. She has very long flowing black hair styled half-up with ornate silver floral hairpins, dangling chains, and jade-green tassels. Her expression is soft and calm, with delicate makeup, glossy lips, and direct eye contact; she rests her cheek on one hand while reclining with one leg forward. Dress her in a pale mint, silver, and ivory embroidered fantasy hanfu/qipao hybrid outfit with sheer translucent sleeves, a high collar, fitted bodice, dark structured waist belt, metal clasps, straps, arm cuffs, bracelets, and multiple teal tassel ornaments. The scene is intimate and detailed: a gray couch with a teal patterned blanket, exactly 2 plush toys visible — one round white smiling plush with pink cheeks on the left and one avocado plush with a small smiling pit on the right. In the foreground, include a glass coffee table with stacked dark books, a small translucent gadget, a glass cup, and a plate of pale green snacks softly out of focus. The background should contain exactly 3 wall art/poster areas: a left calligraphy poster with a large black Chinese character and small English words “SAME DREAMS DIFFERENT TIMELINES,” a central misty ink-landscape poster with a pagoda and full moon, and a right minimalist text poster reading “GOOD PEOPLE BETTER TOMORROWS.” Also include a monitor or lightbox on the right showing the stacked text “More Kindness More Good Tea More You,” indoor plants, books, and faint cyberpunk city lights through a window. Use moody teal-green ambient lighting, soft shadows, shallow depth of field, realistic skin texture, glossy fabric highlights, detailed jewelry, 85mm portrait lens feel, vertical composition, premium editorial cosplay photography, no watermark, no extra people, no distorted hands, no illegible extra text beyond the specified signage.

A breathtaking vertical view of a futuristic metropolis floating gracefully above an endless sea of dense, rolling dark grey clouds at twilight. The sprawling city skyline features numerous towering skyscrapers with glowing windows that cast warm amber and orange lights onto the urban landscape below. Dominating the upper portion of the frame is a magnificent cosmic ring, a glowing circular nebula composed of vibrant purples, deep blues, and brilliant warm golden hues, sprinkled with countless twinkling stars and distant galaxies across the pitch-black night sky. The composition is balanced and majestic, with the dark cloud layer grounding the lower foreground, contrasting sharply with the radiant cosmic phenomenon above. The lighting is surreal and ethereal, blending the warm artificial glow of the city lights with the cosmic luminescence of the nebula. The atmosphere is quiet, awe-inspiring, and mystical, evoking a sense of interstellar wonder and urban isolation. The detailed textures of the soft, voluminous clouds, the sleek glass and steel architecture of the skyscrapers, and the starry cosmic dust create a high-contrast, visually striking scene.

Create a cinematic photorealistic vertical street photograph in a rainy near-future European old town, set in Prague at dusk/night. The scene looks like a cyberpunk documentary still: wet cobblestone street reflecting warm shop lights and cold blue-gray sky, historic stone buildings on both sides, crowds of pedestrians moving with motion blur and carrying umbrellas. In the foreground, slightly left of center, place one young woman with pale skin and dark wet hair, wearing a soaked olive-green hooded raincoat and dark scarf, holding a shoulder bag strap, staring tiredly and seriously toward the camera while everyone around her blurs past. Count visible prominent text signs as 7: a cafe window on the left reading "KÁVA LIDÉ PŘÍBĚHY" with smaller "OD ROKU 2014"; a black hanging sign reading "AUGMENT" and "BETTER TOGETHER" with three interlocking circles; a small white sign reading "PRAHA STÁLE VAŠE" with a heart; a blue street number plaque "27"; a distant illuminated corporate sign reading "A HIGHER HUMANITY" with a circular logo; a giant right-side billboard reading "ČISTĚJŠÍ VZDUCH JASNĚJŠÍ ZÍTŘKY" and "TerraNet" with a leaf logo; and a storefront sign on the left reading "AROMA ARCADIA". In the background, rising above the old architecture, show a colossal futuristic tower fading into low clouds, with bright vertical light strips, a raised megastructure or skybridge crossing the street, and a hovering tram or vehicle suspended over the avenue. Use heavy rain, mist, puddles, atmospheric haze, realistic lens distortion, high dynamic range, shallow depth of field, warm tungsten lamps against cold stormy cyan-gray ambience, gritty texture, no clean utopian look. Make the composition immersive at street level with the subject occupying the lower-left foreground and the futuristic skyline centered in the distance.