Manus GPT Image 2.0 Comparison Slide

Minimal AI Lock-In Comparison Slide

A minimalist editorial presentation slide in 16:9 format with a warm light-gray paper background, lots of negative space, refined Swiss-style grid layout, and high-end PPT/keynote design aesthetics. The slide is a comparison page about lock-in, using elegant Chinese typography mixed with tiny English navigation text. At the top left, place two small uppercase English breadcrumb lines: “COMPARISON · LOCK-IN” and below it “CLOSED VS OPEN”, in a thin sans-serif with wide tracking. At the top right, place the page indicator “04 / 08”. Center-left across the upper half, add a very large bold black Chinese headline: “真正的锁定，不是模型，是记忆。” On the left half below the headline, create a three-row comparison list separated by thin horizontal gray rules. Row 1 has the bold Chinese label “轻度风险” on the left, with the explanatory sentence “状态存在服务端，换模型后无法恢复线程。” to its right, and a tiny uppercase English keyword aligned far right: “STATE”. Row 2 has the bold label “中度风险”, with the sentence “闭源 harness 的记忆形态不可见,难以迁移。” and the far-right keyword “SHAPE”. Row 3 has the bold label “最高风险”, with the sentence “整个 harness 和长期记忆都在 API 后面。” and the far-right keyword “LOCK-IN”. On the right side of the slide, place a small inset comparison diagram card with a white background and subtle border, containing 2 side-by-side system architecture panels. The left panel represents a closed system in dark gray and muted red accents; the right panel represents an open system in deep blue accents. Each panel should have 5 small top icon tabs, a central highlighted harness block, several stacked rounded rectangular modules below, and a bottom row of 4 small capability icons with short Chinese labels. Keep the inset detailed but small, so it reads as a supporting visual rather than the main focus. At the bottom left, add tiny light-gray Chinese footer text: “布局测试 · 顶部标题 + 下方两段式内容”. At the bottom right, place a small page number “04”. Centered near the bottom edge, add a carousel indicator with exactly 7 small dots, where the 4th dot is a short dark rounded pill indicating the active slide and the other 6 dots are pale gray circles. Also add tiny faint navigation hints at the lower right edge reading “← → 翻页 ESC 关闭”. Use crisp vector text rendering, understated contrast, elegant spacing, and a calm premium infographic style suitable for a business presentation about AI platform comparison and API memory lock-in.

Skin Comparison Portrait — Nano Banana Pro

Split comparison portrait, vertical split center, close-up face, eye-level. Subject: same young woman shown in two skin conditions, facing forward. Left side: neutral tired expression. Right side: soft confident smile. Appearance: dark brown hair, straight middle-parted. Left skin: severe acne, pimples, redness, uneven texture, dull and oily. Right skin: clear smooth glowing skin, even tone, healthy radiant look. Outfit: cream knitted sweater. Environment: car interior, soft daylight, brown seat, blurred outdoor greenery. Lighting: natural light, left side slightly dull and flat, right side brighter and glowing. Left title: 'Foods that ruin skin'. Right title: 'Foods that save skin'. Left foods: instant noodles, fried snacks, sugary sweets, white bread, pizza / fast food, cold drinks, ice cream, packaged chips, chocolate. Right foods: sprouts, methi seeds, lemon water, green tea, amla, almonds, tomato, cucumber, leafy greens. Style: social media comparison graphic, educational, clean contrast, natural tones with strong visual difference. High resolution, sharp facial texture difference clearly visible.

Transparent Background Comparison Grid

Goal: Create a clean comparison grid demonstrating background handling for cutout portrait images generated by {argument name="image model" default="GPT Image 2"}. Canvas: Square 1:1 canvas, approximately 1200 x 1200 px, with a very light gray page background and narrow gutters between panels. Layout: Use exactly 6 rectangular panels arranged in a 2-row by 3-column grid. Each panel contains one full-body studio cutout subject centered vertically and horizontally with ample margin. The three columns compare background types: left column shows a gray-and-white checkerboard transparency pattern, middle column shows a plain white background, right column shows a solid black background. No captions, no logos, no text. Subjects: Use exactly 2 human models. Top row: a {argument name="female model description" default="young woman with long voluminous curly brown hair, neutral expression, barefoot, wearing a loose cream chunky-knit cardigan over a light camisole and wide beige lounge pants"}. She stands front-facing in a relaxed fashion pose, one arm folded across her body and the other hanging down, soft studio lighting, realistic photographic detail. Bottom row: a {argument name="male model description" default="middle-aged man with short dark hair and salt-and-pepper beard, serious expression, walking toward camera, wearing a long dark charcoal overcoat, gray knit sweater, navy trousers, and polished dark brown dress shoes"}. He appears mid-stride with one hand in his trouser pocket and the coat slightly flaring outward. Panel details: Count of repeated elements is exactly 6 panels: 1) woman on checkerboard transparent-style background, 2) woman on white background, 3) woman on black background, 4) man on checkerboard transparent-style background, 5) man on white background, 6) man on black background. Keep the same subject pose, scale, lighting, and crop consistent across each row so only the background changes. Visual style: Hyperrealistic studio product-demo photography, crisp full-body cutouts, clean edges around hair and clothing, neutral soft shadows only if subtle, high contrast on black backgrounds, bright clean white backgrounds, and a standard transparency checkerboard pattern made of evenly sized alternating light gray and white squares. Constraints: Do not include any visible text, labels, watermark, interface chrome, decorative icons, or extra objects. Maintain realistic proportions, full bodies visible from head to feet, centered composition, and consistent spacing between all grid cells.

Japanese Industrial Proposal Cover Slide

Goal: Create a clean 16:9 Japanese corporate proposal cover slide for a construction/civil engineering or industrial automation company, introducing recruitment and PR branding preparation for {argument name="company name" default="ZAXIS"}. Canvas: Wide presentation slide, 1200×675 or 16:9 ratio, bright white background with soft lavender gradients. Use a modern consulting-deck aesthetic: generous whitespace, bold typography, rounded cards, and subtle tech/corporate accents. Layout: Top left has a small rounded purple square badge with white “01”, followed by the company name in black. Below it, place a large bold black Japanese headline “採用・PR” and directly underneath a large bold lavender headline “ブランディング基盤整備”. Add a thin horizontal lavender rule with a small circular dot at the left under the headline. In the left-middle area, place a rounded square outline icon card showing a simple people/community icon in lavender. To the right of that icon, add two lines of black Japanese body copy: “求人募集を始める前に、” and “信頼される公式情報の受け皿を整える”. Near the lower left, place a vivid lime-green rounded pill button containing a small white circle with a black flag icon and the text “第一段階のご提案”. Right side visual: Place one large rounded-rectangle photo card occupying the right half of the slide, with a subtle drop shadow and thin white border. The photo should show a bright futuristic factory floor with orange and white industrial robotic arms assembling mechanical parts, blue-tinted machinery, and a translucent holographic CAD blueprint/interface floating above the work area. The image should feel like advanced manufacturing, automation, precision engineering, and smart factory technology. Background details: Add a large semi-transparent lavender circular gradient shape in the upper-right corner behind the photo, and a soft lavender wave/blob sweeping upward from the lower center toward the right. Add a small dotted halftone pattern in pale lavender at the bottom-left corner. Keep the overall look polished, airy, and presentation-ready. Visual style: Minimal Japanese B2B proposal design, crisp sans-serif typography, high contrast black and purple text, accent color neon lime, rounded corners, subtle shadows, premium consulting slide layout. Text parameters: Use {argument name="main headline" default="採用・PR"}, {argument name="sub headline" default="ブランディング基盤整備"}, {argument name="body copy" default="求人募集を始める前に、\n信頼される公式情報の受け皿を整える"}, and {argument name="button text" default="第一段階のご提案"} exactly as visible Japanese text unless customized. Constraints: Include exactly one section badge, one company name, two headline lines, one divider line with one dot, one people icon card, one two-line body text block, one lime-green CTA pill with one flag icon, one main factory photo card, one upper-right lavender circle, one lower lavender wave/blob, and one dotted bottom-left pattern. Do not add extra logos, watermarks, charts, or additional paragraphs.

3D Footstool Mesh Comparison

Create a realistic architectural visualization comparing two 3D-generated ottoman stools in an interior showroom scene. Canvas: wide landscape 16:9 render, camera at low eye level looking slightly downward. Scene: two small Barcelona-style footstools placed side by side on a dark charcoal tiled floor, in front of a tall glossy stone wall with dramatic brown, cream, rust, and gold onyx/marble veining; a narrow strip of green-tinted glass or window appears at the far right edge, with pale exterior floor tiles visible beyond. Subjects: exactly 2 footstools: left stool is the HD version, slightly smaller and lower, with a white tufted square cushion divided into a 4-by-4 grid, rounded soft edges, light gray leather straps underneath, and reflective polished metal X-shaped legs; right stool is the Smart Mesh version, slightly larger and cleaner, with a thicker smooth white cushion, parallel white underside straps, and gray polished X-shaped metal legs. Add thin black 3D viewport guide lines or wireframe axis lines crossing through and around both stools, including vertical and horizontal alignment lines, as if shown in a 3D modeling comparison viewport. Materials: white leather cushions with subtle seams and soft highlights, chrome legs with reflections, dark matte floor tiles with faint grout lines, glossy veined stone wall. Lighting: soft indoor studio lighting, moderate shadows, realistic but slightly CGI-rendered look. Composition: left stool around one-third of the frame, right stool around two-thirds, both facing forward at a slight angle, enough floor visible in front, marble wall filling the background. No people, no labels, no UI panels, no watermark.

Li Qingzhao Literary Slide

Goal: Create an elegant Chinese literary presentation cover slide about {argument name="topic" default="李清照对当代女性的启示"}, blending Song dynasty poetic atmosphere with modern editorial design. Canvas: 16:9 horizontal slide, clean off-white background with a pale sage-green vertical panel occupying the right third. Use lots of negative space, refined margins, soft paper texture, faint ink-wash stains, and subtle gray botanical shadows across the middle. Layout: Left two-thirds is the text area; right third is a still-life photograph area. Place the large headline in the upper-left, arranged as two lines of dark forest-green Chinese serif type: line 1 “李清照对当代”, line 2 “女性的启示”. Under the headline add a thin muted red horizontal accent line. Below it place the subtitle in smaller black Chinese serif text: {argument name="subtitle text" default="从文学人生，看见女性如何表达自我、选择人生、抵抗困境。"} Middle-left feature row: include exactly 3 small icon cards in a horizontal row, separated by two thin vertical divider lines. Card 1 has a muted rose circular icon with a white leaf symbol and the label “以文学\n确立自我”. Card 2 has a warm beige circular icon with a white balance-scale symbol and the label “在时代与命运之间\n保持判断”. Card 3 has a desaturated teal circular icon with a white user silhouette and the label “不被单一\n身份定义”. Bottom-left keyword row: include exactly 3 keywords separated by vertical bars, with a small dark green leading mark: “表达自我 | 保持独立 | 承受变化”. Right still-life details: show an open antique Chinese letter or manuscript paper lying diagonally on a desk, with visible vertical handwritten Chinese calligraphy in gray ink. A black-and-brown calligraphy brush rests diagonally over the paper, pointing toward the lower-right. Add exactly 2 blooming plum blossom branches: one branch crosses the upper-right corner with several pale white-pink blossoms and buds, and one smaller branch extends from the center-left toward the right, casting soft shadows. The right panel background should be pale sage green; the paper is warm ivory with slightly curled edges and soft folds. Visual style: tasteful, literary, museum-catalog minimalism; calm Song dynasty aesthetics; natural daylight from upper left; soft shadows; muted palette of ivory, forest green, sage, rose, beige, and ink gray; high-resolution editorial composition, realistic still-life photo blended with clean graphic typography. Constraints: Keep all visible text in Chinese exactly as specified, with no extra captions or watermark. Maintain the 3 icon cards and 3 bottom keywords exactly. Avoid clutter, bright colors, cartoon styling, or modern tech UI effects.

Created with GPT Image on ChatGpt Prompt: A cin

A cinematic close-up portrait of a gorgeous young East Asian woman with a gentle warm smile, wearing a traditional black velvet qipao with subtle red floral patterns, high mandarin collar. She has a large pink flower accessory tucked behind her ear in her styled updo hair. Dramatic side lighting, intense golden rim light illuminating one side of her face and shoulder, soft chiaroscuro shadows on the other side. Dewy natural skin texture, glossy lips. Dark moody background with soft ambient warm glow and subtle bokeh. Shot on 85mm lens, f/1.8, cinematic color grading, photorealistic, 8k resolution, highly detailed photography --ar 2:3 --style raw --v 6.0. Do not change the face. There is a small, subtle, hand-written signature "Clover 🍀" in the bottom right corner.

GPT-Image-2 Transparency Prompting Guide

これは1枚の完成された絵ではなく、単体で使う素材です isolated object fully transparent alpha no backdrop no rectangle no plinth no cast shadow

gpt2-youtube-thumbnail-restaurant-pov-change-comparison

A side-by-side comparison graphic on a black background demonstrating a camera-angle change in the same restaurant scene. At the top, large white sans-serif text reads: "Show me the POV from someone standing behind the bar looking out over this crowded restaurant. Change NOTHING in the scene other than the pov". Below, place 2 stacked rectangular photos centered vertically: the top image labeled "Source" in large white text on the left, and the bottom image labeled "Output" in large white text on the left. The top photo shows a warmly lit, upscale, crowded restaurant interior seen from the dining room side, facing a tall back bar filled with many illuminated liquor bottles on wall-to-wall shelves, with bartenders and guests in front, amber lighting, globe pendant lights, wood ceiling, beige columns, and tightly packed seated diners in the foreground. The bottom photo shows the exact same restaurant, same crowd density, same warm lighting, same decor, same bar shelving, same globe pendant lights, and same overall composition elements, but now from the point of view of someone standing behind the bar and looking outward across the crowded restaurant; the foreground includes the bar counter with glassware, metal bar tools, bottles, and a point-of-sale screen visible at the lower left, while guests and staff fill the middle ground and the dining room extends into the background. Preserve the sense that only the camera position changed between the 2 images, with no other scene alterations.

Split Fantasy Portrait Comparison

Create a side-by-side comparison image showing two versions of the same dreamy fantasy portrait. Canvas is a horizontal 16:9 split-screen composition with a perfectly vertical divide down the center, no gap, left panel and right panel each occupying exactly half the image. In both panels, depict the same ethereal young woman in a luminous fairytale garden, shown as a close-up bust portrait with pale porcelain skin, soft gray-blue eyes, delicate lips, and loosely pinned wavy brown hair. She wears an ornate pastel floral crown with pink roses, tiny crystal flowers, pearls, translucent butterfly ornaments, and soft feathers, plus dangling crystal earrings and a sheer embroidered gown with iridescent floral appliqué. Her hand is raised gently near her chin, giving a calm, romantic, slightly wistful expression while looking toward the viewer. The scene is filled with pastel blossoms, sparkling bokeh, floating dust motes, translucent butterflies, crystal petals, and soft backlit haze. Use an ultra-detailed high-fashion fantasy photography style, shallow depth of field, pearly highlights, glittering refractions, delicate skin texture, and pastel lavender, blush pink, silver, and pale blue tones. Make the left panel slightly more textured, crisp, and detailed in skin and fabric microtexture; make the right panel slightly smoother and more airbrushed, with softer pastel lighting and gentler facial texture. Add exactly 2 label boxes: one white rounded rectangle at the top left of the left panel reading {argument name="left label" default="OpenAI 官方"}, and one white rounded rectangle at the top left of the right panel reading {argument name="right label" default="Azure West US 3"}. Use clean black sans-serif text inside the labels. Keep both portraits similar enough to clearly compare rendering differences, but not identical; avoid watermarks, logos, extra captions, borders, or additional text.

Japanese Manus Chat Pixel Art Screenshot

Goal: Create a realistic screenshot of a minimalist AI chat interface showing a Japanese conversation where a user asks for a 16-bit pixel-art conversion and the assistant responds with a generated image. Canvas: Portrait screenshot, 768 x 896 px, white background, clean web-app UI with lots of empty space. No browser chrome, no visible sidebars. Use soft gray dividers, rounded cards, and small interface icons. Layout: Top-right user area contains exactly 2 discrete elements: 1 small square anime avatar, and 1 rounded white chat bubble. The avatar is an anime horse-girl face with brown hair, white forelock, purple eyes, horse ears, and a purple ribbon. The user bubble text is {argument name="user request" default="16bitのピクセルアートにしてください"}. Assistant message block 1: Place the Manus logo and the bold name “manus” on the left. Below it, show exactly 1 small rounded notice pill containing a sparkle icon and Japanese text {argument name="notice text" default="今回は Manus が負担します—クレジットは消費されません"}. Then show the assistant reply line: {argument name="first assistant reply" default="承知しました。元の表情と配色を保ちながら、16bit風のピクセルアートに仕上げます。"}. Under that, show exactly 2 checked task rows with gray circular check icons: 1) “編集要件を整理する” and 2) “16bit風ピクセルアートを生成する”. Beneath the tasks, show exactly 2 small action icons: a copy icon and a curved-arrow/regenerate-style icon. Assistant message block 2: Lower on the page, repeat the Manus logo and bold name “manus”. Under it, show a single Japanese sentence: {argument name="second assistant reply" default="16bitゲーム機時代をイメージした、くっきりしたドット絵調に変換しました。"}. Below this sentence, align a large generated image preview to the left. Generated image preview: The preview is a square-ish pixel-art portrait cropped by the screenshot bottom edge. It shows a cheerful anime horse-girl character in crisp 16-bit game style: brown bob-length hair with a large white forelock, tall horse ears, a purple bow on the left ear, purple sparkling eyes, small blush marks, open smiling mouth, and white hair ties near both sides. Use chunky pixel edges, visible dithering, limited retro palette, and dark outline pixels. Background inside the pixel-art image is a warm indoor room with beige wall, window light, and horizontal furniture/trim, all rendered in pixel art. The visible generated preview should occupy the lower-left portion and be cut off at the bottom of the screenshot. Additional UI details: Add a small floating circular down-arrow button at the bottom-right corner. Keep the overall look like a Japanese Manus chat page, with generous margins, black body text, subtle gray UI accents, and no true transparency checkerboard. Count of visible repeated UI/content elements: 1 user avatar, 1 user message bubble, 2 Manus headers, 1 notice pill, 2 checked task rows, 2 small action icons, 1 generated image preview, and 1 floating down-arrow button. Constraints: Preserve the Japanese text exactly where given in the default parameter values. Do not add extra messages, extra avatars, extra buttons, watermarks, browser tabs, or side navigation.

Photo to Cozy Crayon Drawing Comparison

Goal: Create a vertical 3:4 comparison image showing a warm original-photo scene on top and its cozy crayon-drawing interpretation on the bottom. Canvas: Vertical image, approximately 900 x 1200 px, split into exactly 2 horizontal panels of equal width. The top panel is a soft, sunlit realistic photo; the bottom panel is an off-white paper illustration with wax-crayon texture. Top panel: Show {argument name="character description" default="a young woman with long dark hair"} sitting sideways on a narrow old balcony railing outside a weathered apartment doorway. She is relaxed and slightly introspective, looking down at an acoustic guitar while playing it. She wears {argument name="outfit" default="a loose patterned short-sleeve shirt, dark shorts, white socks, and chunky white sneakers"}. The guitar is a glossy honey-brown acoustic cutaway guitar with a dark tortoiseshell pickguard. Include iron balcony bars, leafy green vines, a cream stucco wall, an open aged door, and a dim interior room in the background. Use golden late-afternoon sunlight with dappled leaf shadows across her legs, guitar, wall, and floor; dreamy lens softness, cozy summer atmosphere, shallow depth of field. Bottom panel: Recreate the same subject as a loose hand-drawn crayon sketch on textured cream paper. The woman, pose, guitar, balcony railing, and shoes should be simplified but recognizable, drawn with sketchy overlapping crayon strokes in warm yellow, teal blue, coral red, green, and charcoal gray. Keep the style childlike yet stylish, soft and cozy, with visible wax grain and imperfect outlines. Add exactly 7 decorative crayon elements around the main figure: 1 simple yellow sun in the upper left, 2 small yellow flowers on green stems on the left, 1 blue musical note near the center-right, 1 short gray handwritten phrase reading {argument name="quote text" default="Better Days Ahead"}, and 2 small yellow flowers on green stems in the lower right. Add a few loose green and blue ground scribbles below the seated figure. Text and branding: The only readable phrase inside the drawing is {argument name="quote text" default="Better Days Ahead"}, set in a small gray typewriter-like handwritten style to the right of the illustrated guitar player. Add a subtle white watermark reading {argument name="watermark text" default="Promptsref.com"} in the bottom-right corner. Constraints: Use exactly 2 panels, with the top photorealistic and the bottom crayon-drawn. Do not add extra people, extra guitars, or additional readable text. Preserve the warm sunny mood and the cozy hand-crafted crayon aesthetic.

Five-Page Manga Quality Comparison

Goal: Create a wide monochrome comparison sheet showing five nearly identical Japanese manga pages placed side by side, like an image-generation quality comparison. Each page should depict the same cute fox-eared girl food-shopping scene, with tiny labels centered above each page for different quality settings. Canvas: Extremely wide horizontal canvas, about 5:1 aspect ratio, white background, crisp black-and-white manga printing. Place exactly 5 complete manga pages in a row with narrow white gaps between them. Each page is vertical and identical in overall composition, using clean screentones, thin panel borders, speed lines, and detailed manga backgrounds. Layout per page: Each of the 5 pages contains exactly 8 panels arranged in 4 tiers: 1 wide top panel, 2 panels in the second tier, 3 panels in the third tier, and 2 panels in the bottom tier. Keep the repeated pages almost the same, with only subtle quality/detail differences between them. Page labels: Add 5 tiny English labels above the pages, one per page: “quality low”, “quality medium”, “quality high”, “quality ultra”, and “quality max”. Story and panel details for every page: 1. Top wide panel: A cheerful anime fox girl with large fox ears, long light hair, and a casual hoodie smiles brightly in a cozy room with a window, curtains, plants, and a round lamp behind her. She raises one hand in excitement. Include a vertical oval speech bubble containing {argument name="top speech bubble" default="今日はお弁当を買いに行こう"}. 2. Second-tier left panel: Close-up of prepared boxed lunches or bento trays in a display case, drawn with detailed food textures and packaging. 3. Second-tier right panel: Exterior of a modern convenience store or deli storefront with glass windows, a signboard, sidewalk, and small background figures. Add two vertical speech bubbles with small Japanese manga text. 4. Third-tier left panel: Rear view of two or three customers standing in line inside the shop; the fox girl is visible among them holding a basket. 5. Third-tier middle narrow panel: A small dialogue/reaction panel with a simple speech bubble, suggesting hesitation or ordering. 6. Third-tier right panel: The fox girl at a counter or table looking at a bento box, smiling and holding chopsticks or a tray, with another speech bubble. 7. Bottom-tier large left panel: Dramatic close-up of the fox girl shocked and overwhelmed by delicious food or the amount she bought; wide eyes, open mouth, blush, speed lines radiating behind her, and a basket or bento boxes in the foreground. Include a bold speech bubble with {argument name="reaction speech bubble" default="やべぇ ついつい買ってるじゃん"}. 8. Bottom-tier small right panel: A simplified stunned reaction portrait of the fox girl facing forward, blank expression, large ears, and a tiny vertical bubble with ellipsis. Character details: The main character is {argument name="character description" default="a young anime fox girl with fluffy upright fox ears, long pale hair with bangs, bright eyes, and a playful expression"}. Her outfit is {argument name="outfit" default="a loose casual hoodie with a simple collar"}. Use a cute modern manga style, expressive face acting, clean linework, and soft grayscale screentone shading. Visual style: Black-and-white manga page art, high detail, sharp ink lines, halftone shading, traditional Japanese comic paneling, realistic convenience-store backgrounds, readable panel borders, no color except grayscale. The five pages should feel like a side-by-side technical comparison, not separate unrelated illustrations. Constraints: Use exactly 5 repeated pages and exactly 8 panels per page, for a total of 40 visible comic panels. Do not add extra characters beyond small background shoppers and staff. Keep all nonessential dialogue as tiny Japanese-style manga lettering, and avoid watermarks or logos.

Multi-Cultural Morning Greeting Infographic Slide

主题：{argument name="主题" default="10 个少数民族，方言如何说：早安"} 一共 10 张，每个都是一个名字主题 不同的排版 每个图片要有 3-5 个知识点、不同的信息呈现方式 专业收藏级的排版 and 字体 比例 3:4 不要有序列号逻辑

Friendly ChatGPT Robot Introduction

Goal: Create a cheerful square promotional 3D illustration introducing {argument name="assistant name" default="ChatGPT"} as a friendly AI robot created by {argument name="company name" default="OpenAI"}, mixing a polished product-render look with hand-drawn whiteboard-style annotations. Canvas: 1:1 square image, warm indoor office/classroom setting, shallow depth of field, cozy natural light, wooden desk foreground, dark blue presentation board in the background. Main subject: Center-right, show exactly 1 cute glossy white robot mascot with a rounded rectangular black face screen, glowing cyan happy crescent eyes, rounded white headphones/ear pods, segmented black-and-white arms, and one raised waving hand with 5 fingers. The robot holds exactly 1 white placard in front of its body. Add a teal OpenAI-knot style emblem on the robot chest. Placard text and design: The placard should have a teal knot logo at top, large bold black "OpenAI" in the middle, and handwritten text above and below: "I was created by", "An AI research and deployment company", and in teal "Better AI. A brighter future." Add small teal doodle rays around the bottom slogan. Left side handwritten intro panel: Use casual hand-lettering as if written on glass or a board. Large top text says "Hi there!" then "I'm" and a big mint-green underlined "ChatGPT". Under it, include exactly 3 explanatory bullet callouts with icons: 1 speech bubble icon with "A large language model (AI assistant)", 1 lightbulb icon with "I can answer questions, explain things, help you create, solve problems, and much more!", and 1 heart icon with "I'm here to be helpful, honest, and friendly." Include small decorative doodle rays around the headline. Background board: On the right rear dark blue board, display a large white OpenAI knot logo above the word "OpenAI". Beneath it, handwritten stacked text reads exactly 4 lines: "Research", "Safety", "Useful AI", "for everyone" with an underline and small radiating doodles. Above the robot head, add handwritten text "That's me!" with an arrow pointing down to the robot. Desk objects: Include exactly 4 stacked books on the left, spine labels from top to bottom: "BETTER QUESTIONS", "CLEARER ANSWERS", "A MORE HELPFUL TOMORROW", and a fourth dark book marked with a small heart. Include exactly 1 open laptop in the lower-left foreground with small writing on the back: "Curiosity builds a better world" plus a heart. Include exactly 1 white coffee mug on the right with text: "Same team. A brighter future." and a smiley face. Along the front edge of the desk, add a small handwritten footer: "OpenAI × ChatGPT = More possibilities for everyone" with doodle rays and a heart. Visual style: High-quality gpt-image-2 style, cute 3D character rendering, soft reflections on plastic, realistic desk materials, bokeh background, bright teal accents, friendly educational startup branding, hand-drawn white marker typography and simple doodle icons. Keep text legible and correctly spelled. Constraints: No extra characters, no extra logos beyond the OpenAI-style knot marks described, no watermark, no photorealistic human hands, keep the robot centered and welcoming, preserve the exact count of 1 robot, 1 placard, 4 books, 1 laptop, 1 mug, and 3 left-side bullet callouts.

Three-Panel Chinese Aesthetic Model Comparison

Goal: Create a vertical three-panel comparison collage showing the same Chinese traditional aesthetic portrait generated in three different styles. Canvas: Portrait format, approximately 4:5 aspect ratio, 960×1200 feel. Divide the image into exactly 3 equal horizontal panels separated by thin white horizontal lines. Overall subject: In all three panels, show the same young East Asian woman in a warm, cinematic ancient Chinese interior, wearing a soft ivory hanfu robe. She is adjusting a peach-pink flower hair ornament near her ear with both hands. Her black hair is loosely pinned up with wispy strands around her face. The atmosphere is golden-hour, backlit, romantic, and traditional, with wooden lattice windows behind her, soft haze, shallow depth of field, warm sunlight, and floating flower petals or dust motes. Panel count and labels: Use exactly 3 panels with large white sans-serif text labels in the lower-left area of each panel: 1) “Midjourney V8.2” on the top panel, 2) “GPT-Image 2” on the middle panel, 3) “Seedream 5.0 Pro” on the bottom panel. Top panel: Label “Midjourney V8.2”. Make this the most dramatic and cinematic version: stronger contrast, moody shadows, glowing rim light, more dynamic pose, windblown hair, petals crossing the foreground, refined facial features, realistic skin texture, premium film still quality. The woman faces slightly toward camera with a serious, elegant expression while placing the flower by her ear. Middle panel: Label “GPT-Image 2”. Make this cleaner and softer, with a slightly polished beauty-retouch look. The woman is turned three-quarters to the right, looking sideways while carefully adjusting the flower. Keep warm window light, cream hanfu fabric with subtle embroidered floral details, and a more smooth, influencer-like face. Bottom panel: Label “Seedream 5.0 Pro”. Make this brighter and slightly more plastic/smooth than the top, with a gentle smile and softer realism. The woman holds the peach flower close to her ear, looking down-left or sideways, with intense backlight from the lattice window and a glowing edge around her hair and hands. Text styling: Large white text, simple sans-serif, no outline, subtle shadow if needed for readability. Place each label consistently near the bottom-left of its panel. Do not add any other text, logos, watermarks, or UI elements. Customizable details: The subject is {argument name="subject description" default="a young East Asian woman in ivory hanfu"}; the setting is {argument name="setting" default="a warm ancient Chinese room with wooden lattice windows"}; the hair accessory is {argument name="hair flower" default="a peach-pink flower"}; the top label is {argument name="top model label" default="Midjourney V8.2"}; the middle label is {argument name="middle model label" default="GPT-Image 2"}.

gpt2-momotaro-explainer-slide-in-hybrid-style

Create an explanatory slide ({argument name="format" default="ponchi-e diagram"}) for {argument name="theme" default="Momotaro"} that fuses the gentle atmosphere of "Irasutoya" with the overwhelming information density of "Kasumigaseki slides".

GeoPT Physics Simulation Overview Slide

Goal: Create a clean 16:9 academic overview slide explaining {argument name="paper concept" default="GeoPT: Scaling Physics Simulation via Lifted Geometric Pre-Training"}, styled like a polished conference-deck infographic. Canvas: Widescreen white slide, navy-blue typography and accents, minimal shadows, high-resolution scientific illustration style. Use a thin blue footer line with small circular endpoints. Header: Large bold dark-navy title at the top: {argument name="headline text" default="GeoPT: Scaling Physics Simulation via Lifted Geometric Pre-Training"}. Directly underneath, smaller blue subtitle: {argument name="subtitle text" default="An intuitive overview of Wu et al. (2026)"}. Big idea banner: Under the subtitle, place a rounded rectangle callout with a blue outline and very pale blue fill. On the left is a blue circular lightbulb icon. Text reads: “Big idea:” in bold blue, followed by “use abundant 3D geometry and synthetic motion to pre-train neural simulators before using scarce real simulation data.” Main layout: A three-column pipeline with exactly 4 rows, connected left-to-right by thick blue arrows. Column headings are: “3D Geometry”, “Physics Simulation (examples)”, and “Fields (pressure / velocity / stress)”. The left side also has 4 row labels: 1) Car, 2) Aircraft, 3) Ship hull, 4) Crash / Deformation. Row details: Row 1 shows a gray 3D car model, then a car in airflow simulation with blue streamlines and colorful vortices plus a small “t →” time marker, then a car colored with a rainbow heatmap field and a vertical color legend labeled “Pressure” with High at top and Low at bottom. Row 2 shows a gray aircraft model, then an airplane with airflow streamlines and colored wakes plus “t →”, then a rainbow heatmap aircraft with a legend labeled “Velocity” High/Low. Row 3 shows a gray ship hull model, then a ship hull moving through ocean waves with simulated water flow plus “t →”, then a rainbow heatmap ship hull with a legend labeled “Pressure” High/Low. Row 4 shows a damaged gray car body for crash/deformation, then a crash simulation with debris, deformation, and internal colored stress/field visualization plus “t →”, then a rainbow heatmap deformed car body with a legend labeled “Stress” High/Low. Bottom explanation strip: Include exactly 3 circular icon-and-caption blocks connected by dotted blue arrows. Block 1 icon is a wireframe cube and title “Abundant geometry”, caption “Easily available 3D shapes from CAD repositories”. Block 2 icon is wind/flow lines and title “Synthetic dynamics”, caption “Scalable simulations produce diverse motion and fields”. Block 3 icon is a neural network graph and title “Better physics simulators”, caption “Pre-trained models that generalize better with limited real data”. Footer: Centered small gray citation text: {argument name="source citation" default="Source paper: Haixu Wu et al., arXiv:2602.20399 (2026)"}. Visual style: Crisp vector-slide composition mixed with realistic 3D renders, blue academic palette, white background, precise alignment, no clutter, no watermark, no extra rows or icons beyond the specified counts.

Three Character Asset Comparison Board

Goal: Create a dark-background comparison board showing character asset sheets for three office-dressed people, comparing two image-generation systems side by side. Canvas: 16:9 landscape presentation image, approximately 2048×1152, with a deep navy-black background, clean white typography, and six large white image panels arranged in a 3-row by 2-column grid. Header text: At the top left, place the large Chinese title {argument name="headline text" default="3组 女生人物资产 · 同提示词对比"}. Under it, add a smaller subtitle line: {argument name="comparison subtitle" default="左：历史 GPT Image 2 右：ChatGPT Images 2.5 网页"}. Layout: Use exactly 6 rectangular white panels with thin spacing: left column represents the older model, right column represents the newer model. There are exactly 3 character rows: Clara, Julian, and Evelyn. Each row has a small Chinese row label above the left panel: “纯文字角色资产 - Clara”, “纯文字角色资产 - Julian”, and “纯文字角色资产 - Evelyn”. Each of the 6 panels contains exactly 4 character depictions on a white studio background: 1 large cropped head-and-shoulders portrait on the left, plus 3 smaller full-body turnaround views on the right: front view, side profile view, and back view. Total visible character depictions: exactly 24. Row 1 subject details: Clara, a young fair-skinned woman with long wavy dark brown hair, soft natural makeup, neutral serious expression, wearing a cream ribbed turtleneck, brown cropped blazer, high-waisted wide-leg cream trousers, a black belt, and low heels. In each Clara panel show 4 views: close portrait, full-body front, full-body side, full-body back. Row 2 subject details: Julian, a young slim fair-skinned man with light brown/blond swept hair, rectangular glasses, calm serious expression, wearing an off-white linen suit, white open-collar shirt, narrow trousers, brown belt, and tan loafers. In each Julian panel show 4 views: close portrait, full-body front, full-body side, full-body back. Row 3 subject details: Evelyn, a middle-aged woman with medium tan skin, dark hair pulled back into a low bun, composed neutral expression, wearing a black business suit, dark gray blouse, small gold necklace, small earrings, black trousers, and black flats. In each Evelyn panel show 4 views: close portrait, full-body front, full-body side, full-body back. Visual style: Realistic photography-like character asset sheets, clean studio lighting, white seamless backgrounds inside each panel, consistent professional wardrobe styling, neutral expressions, no decorative graphics except the dark board and labels. The left and right columns should be visibly similar but not identical, as if comparing outputs from two systems. Footer text: At the bottom left, add two small Chinese notes: {argument name="footer note one" default="历史成品 2048×1152 / 网页新图 1672×941 · 仅排版缩放，无修图、无超分。"} and {argument name="footer note two" default="提示词正文相同，两页端仅补充16:9比例。"}. Constraints: Keep the exact 3-row by 2-column comparison layout, exactly 3 named characters, exactly 6 panels, exactly 4 depictions per panel, with no watermark, no extra logos, and no additional characters.

GPT Image 2 Reference Tutorial Banner

Goal: Create a clean Japanese promotional thumbnail/banner for a GPT Image 2 tutorial about using reference images to keep the same person consistent. Canvas: 16:9 horizontal banner, 1200×675 style, soft pale blue and white background with large organic blob shapes. Use a polished educational course-thumbnail aesthetic, airy spacing, high readability, no harsh shadows. Layout: Split composition with a realistic portrait on the left occupying about 40% of the canvas, and a text-heavy information panel on the right occupying about 60%. The right side has a large white rounded organic shape as the main text area. Add small decorative dotted grids in the top-right and bottom-left corners, a light diagonal hatch pattern near the lower-right edge, and coral accent marks beside the headline. Subject details: On the left, show one smiling Japanese woman in her late 20s to early 30s, photographed from the waist/chest up, facing the camera. She has shoulder-length softly layered black hair, natural makeup, warm friendly expression, and wears a peach sheer button-up shirt over a white ribbed camisole with a delicate gold necklace. Background behind her is bright, soft-focus, and slightly green-white like daylight through a window. Text content: Include exactly 4 text blocks on the right: 1) a dark navy rounded pill at the top reading 「GPT Image 2 実践編 ③」; 2) a large navy Japanese headline reading 「基準画像を\n作った、その次は？」 with a coral underline under the final phrase; 3) a thin outlined rectangle subtitle reading 「人物固定の具体的な使い方」 with 「具体的な」 highlighted in coral; 4) a bottom checklist row with a pale blue circular check icon followed by 「毎回どの基準画像を使う？」. Keep all Japanese text crisp, centered within its area, and use elegant Mincho-style serif for the main headline with modern sans-serif for smaller labels. Color palette: Deep navy text, pale powder blue background, white panels, peach/coral accents matching the woman's shirt, and light blue-gray icon details. Constraints: Use exactly one person, exactly four text blocks, exactly one check icon, and exactly three main decorative accent types: dotted grids, coral rays/underline, and diagonal hatching. Avoid extra logos, watermarks, English translations, or additional text.

Weather Vending Machine Comparison

Create a split-screen comparison image showing two premium cinematic advertising photographs side by side, separated by a thin vertical white divider. The scene is a vast red desert at dusk with dramatic storm clouds, orange sunset glow on the horizon, distant mesas and rock spires, and wet reflective patches on the desert floor. In both panels, place a colossal dark metallic vending machine standing alone, labeled at the top with glowing warm-white text: “CHOOSE YOUR WEATHER”. The machine sells weather instead of snacks, with exactly five large glass display shelves containing: 1) a miniature thunderstorm with dark clouds and lightning, 2) a swirling blizzard over snowy mountains, 3) a glowing sunset sky, 4) a tornado over dusty plains, and 5) green-purple aurora lights over a night landscape. Include a woman in a long cobalt-blue coat and black boots standing beside the vending machine, seen from behind or side-back, reaching toward the selection buttons. The vending machine has a side payment/control panel with small glowing code buttons, a digital price display reading “SKY: $2.00”, and a collection slot. Add black rectangular title tags at the top of each panel: left tag reads {argument name="left model label" default="MONA-LISA-1"}, right tag reads {argument name="right model label" default="GPT IMAGE 2"}. Make the left panel slightly closer and more imposing, with readable small shelf labels such as A01 THUNDERSTORM, B07 BLIZZARD, C03 SUNSET, D09 TORNADO, and E05 AURORA; make the right panel a cleaner vertical machine design with the same five weather windows. Use ultra-realistic photography, cinematic lighting, high contrast, glossy glass reflections, moody atmosphere, premium sci-fi advertising style, sharp detail, 16:9 landscape composition, no extra text beyond the vending machine signage, shelf labels, price display, and model tags.

Hairstyle Analysis Comparison Portrait

Create a {argument name="task" default="hairstyle analysis graphic"} using this portrait. Show side-by-side {argument name="subject" default="hairstyle"} comparisons to highlight which {argument name="plural_subject" default="hairstyles"} suit the subject best

Cinematic GPT-Image 2.5 Poster

Create a cinematic photorealistic widescreen promotional image for {argument name="headline text" default="GPT-IMAGE-2.5"}. Show one young woman adventurer in the foreground, waist-up, soaked by rain, with wet dark brown wavy hair, a muddy gray-brown open overshirt over a dark tank top, glowing skin highlights, and a joyful amazed smile as she looks upward toward the left. Place her slightly left of center, backlit by dramatic golden sunlight breaking through storm clouds. The environment is an epic fantasy-natural valley after a rainstorm: a vast lake and forested islands below, distant cliffs, mist, rain streaks, one large bright rainbow arcing across the upper right sky, and one prominent waterfall dropping from the right-side cliffs into the lake. Use high-end movie poster lighting, ultra-detailed textures, volumetric sun rays, lens flare, wet reflections, warm gold highlights against cool blue-gray storm clouds, shallow depth of field on the woman, and a 16:9 composition. Add the headline text in huge elegant uppercase sans-serif letters across the bottom third, cream-white with subtle gold glow, slight shadow, and a horizontal light flare crossing through the text. Keep the text exactly readable as {argument name="headline text" default="GPT-IMAGE-2.5"}, with no extra logos, captions, watermarks, or interface elements.

Three-Panel AI Billboard Comparison

Goal: Create a clean comparison graphic showing three AI-generated urban billboard photos side by side, as if comparing image model outputs. Canvas: Wide 16:9 presentation slide with a warm off-white background and generous margins. Place three tall vertical photo panels evenly spaced across the canvas, each framed by a pale beige mat/border. Under each panel, add a centered caption. Layout: Exactly 3 vertical street-photo panels in one row. Panel 1 on the left, Panel 2 in the center, Panel 3 on the right. Each panel shows a realistic New York City street scene with parked cars in the foreground, tall buildings, sidewalks, traffic signs, and a large square billboard mounted high on a building. Use slightly different street angles and lighting in each panel, like three separate model outputs of the same concept. Panel details: Left panel: a rear view of a black SUV parked on a city street, looking toward storefronts and buildings; a large white billboard above the street reads like a social-media quote card with a small circular animal avatar, the heading “What do you think?”, a short quote, and small ChatGPT branding. Center panel: a black SUV parked on a narrow Manhattan street with the Empire State Building visible in the distance; a large dark billboard with white text, a circular animal avatar, and ChatGPT branding. Right panel: a black sedan parked along a busier avenue with storefront signs such as “I ♥ NY GIFTS”; a large black billboard with a bright cyan border, white quote text, a circular animal avatar, and ChatGPT branding. Caption text: Use exactly 3 captions beneath the panels. Left caption: “ChatGPT Images 2.0” on the first line and “MEDIUM” in bold quotation marks on the second line. Center caption: “mona-lisa-1” in bold quotation marks. Right caption: “ChatGPT Images 2.0” on the first line and “HIGH” in bold quotation marks on the second line. Customizable text slots: The comparison labels should read {argument name="left model label" default="ChatGPT Images 2.0"}, {argument name="center model label" default="mona-lisa-1"}, and {argument name="right model label" default="ChatGPT Images 2.0"}. The left quality tag should be {argument name="left quality tag" default="MEDIUM"} and the right quality tag should be {argument name="right quality tag" default="HIGH"}. Visual style: Photorealistic smartphone street photography inside each panel, but arranged as a polished social-media comparison slide. Keep the overall slide minimal, with no decorative graphics beyond the three framed images and their captions. The billboard text inside the photos may be small and partially imperfect, but it should clearly resemble AI quote-card advertising with ChatGPT logos.

Ultra-Realistic Cinematic Spotlight Portrait

Use the reference image as the identity of the person, preserving the exact facial features, face shape, hairstyle, beard, skin tone, proportions, and overall identity while recreating the same artistic composition, illustration style, and visual energy. Ultra-realistic cinematic portrait of a {argument name="subject" default="stylish man"} in a {argument name="outfit" default="black suit"}, captured from behind with his head turned over his shoulder, giving a sharp, intense look toward the camera. {argument name="hair style" default="Short textured hair with subtle highlights"}, well-groomed beard. Dramatic spotlight from above creating a warm golden halo effect on his hair and face, fading into a dark background. Strong chiaroscuro lighting with deep shadows and soft highlights. Aspect ratio 4:3. Add the watermark

Kawaii Cactus Sticker

Create a cute printable sticker illustration on a transparent background: a kawaii green cactus in a terracotta flower pot, centered and filling most of a square canvas. The cactus has one large oval ribbed central body and exactly 2 curved side arms, one on the left and one on the right, both raised upward. Give it a happy face with exactly 2 glossy black oval eyes, 2 pink circular blush cheeks, and 1 open smiling mouth with a dark interior and pink tongue. Add a red-pink flower on top-left of the cactus with exactly 6 rounded petals and a cluster of small yellow dots in the center. Cover the cactus with many small star-shaped cream spines with orange bases, distributed across the main body and both arms. Place the cactus in an orange terracotta pot with a thick rim, darker orange shading, small speckles, and glossy highlights; show brown soil and several rounded pebbles at the top. Use a polished digital cartoon style with thick dark green outlines, soft gradients, shiny highlights, saturated colors, and a clean die-cut sticker look with a thick white border around the entire cactus and pot. Background should be transparent, optionally previewed by a light gray checkerboard only to indicate transparency. No text, no watermark, no extra objects.

Minimalist Flat Vector Travel Poster

Premium minimalist flat-vector travel poster for {argument name="city name" default="[CITY_NAME]"}, 3:4 vertical format. Design an original, sophisticated travel poster that captures the authentic visual personality of [CITY_NAME]. The composition must feel purpose-built for this city rather than following a reusable template. CITY IDENTITY First interpret the unique visual character of [CITY_NAME] and build the scene around these five elements: 1. A recognizable landmark, architectural feature, or skyline element. 2. A distinctive local way of moving through the city. 3. One subtle everyday lifestyle moment. 4. A native plant, landscape, or environmental characteristic. 5. A composition and viewpoint that naturally belongs to the city. The overall scene structure must change from city to city. Do not repeatedly use the same object positions or visual formula. Possible compositions include: harbor viewpoint, narrow historic lane, riverside garden, coastal path, elevated city overlook, lively market passage, tram avenue, ferry terminal, botanical setting, heritage square, beach promenade, cultural plaza, or skyline terrace. Choose whichever composition best represents [CITY_NAME]. TYPOGRAPHY Place “[CITY_NAME]” in the upper-left area with generous clean negative space. Add one short, sophisticated English tagline inspired by the atmosphere of the city. Typography should feel understated, editorial, spacious, and premium. Never allow text to dominate the artwork. VISUAL HIERARCHY Use one iconic landmark or architectural feature as the main focal point. Support it with only 2–4 carefully selected local elements. Every added detail should strengthen the sense of place. Avoid landmark collections or postcard-style collages. Keep the scene visually quiet and intentional. PEOPLE Include only 3–6 small-scale figures. Give each person a believable activity connected to local life, such as: walking through a historic lane, cycling, waiting for public transport, sketching architecture, boarding a ferry, reading outdoors, taking a quiet photograph, carrying beach equipment, browsing a market, or jogging beside the water. Avoid crowds and avoid making any single person the main character. Figures should integrate naturally into the environment. LOCAL CHARACTER Use city-specific elements only when they genuinely fit [CITY_NAME]: - local transportation - architecture - street furniture - vegetation - small signs or wayfinding - local food references - recreational activities - pavement markings - cultural details Transport and signage should remain subtle. Instead of always using a large signboard, incorporate details naturally through a small transit marker, station clock, ferry information panel, bike symbol, painted road marking, beach flag, or understated metro icon. ART DIRECTION Japanese stationery-inspired aesthetic, luxury sticker illustration, premium commercial vector artwork, modern editorial travel branding, clean delica

Train Mirror Selfie Fashion Portrait

Create a tall vertical photorealistic fashion portrait of a {argument name="subject" default="young adult woman"} sitting on a purple speckled bench seat inside a commuter train, taking a mirror selfie with a smartphone. She is framed full-body from a slightly high front angle, seated near the left wall of the train with a window on the right and beige metal interior panels behind her. Her face is partially hidden by a black smartphone with a quilted case and multiple rear cameras, covering the lower half of her face while her large eyes look directly toward the mirror/camera. She has {argument name="hair color and style" default="long wavy black hair with soft bangs"}; one hand holds the phone and the other lightly touches a lock of hair beside her face. She wears a Japanese school-uniform-inspired outfit with exactly 6 main visible clothing/accessory items: a beige cardigan, a white collared shirt, a navy plaid bow tie, a navy plaid pleated skirt, black thigh-high socks, and black loafers. A large black rectangular school bag rests across her lap, with one small round pink charm hanging from a silver keychain. The train seat is deep purple with a mottled texture, the floor is beige, the window shows a softly blurred outdoor scene, and the lighting is natural daylight, candid, realistic, slightly soft, with authentic phone-selfie composition and no text or watermark.

Seaside Sunset Portrait

Ultra-realistic iPhone photograph taken by the {argument name="setting" default="seaside during sunset"}. A {argument name="subject" default="handsome Korean young man"} is sitting naturally on a large coastal rock, captured from slightly to the side in a waist-up composition. His soft dark hair reaches his ears and gently blows in the ocean breeze, with a few strands falling across his face. He has smooth light warm-toned skin, delicate Korean facial features, straight brows, soft lips, and a calm, peaceful expression with a subtle smile. He is wearing a {argument name="clothing" default="relaxed white linen button-up shirt"} with a few top buttons undone, loose light gray-blue wide-leg trousers, and gray Nike Dunk sneakers. His physique is lean and athletic with broad shoulders and a slim waist. Around his neck is a delicate silver necklace with the letter "N" surrounded by small diamonds. The background features a calm gray-blue sea and a glowing golden sunset reflecting softly on the water. He is looking slightly toward the camera instead of directly at it, creating a candid atmosphere. His face is perfectly visible and sharply focused. Natural skin texture, realistic details, soft cinematic lighting, gentle wind movement, authentic iPhone photography aesthetic, ultra-photorealistic, high detail, serene mood, shallow depth of field, editorial lifestyle photography.

Luxury Emerald Green Product Photography

A luxury commercial product photography shot featuring a sleek {argument name="bottle color" default="matte emerald green"} glass bottle with a tall cylindrical neck, rounded shoulders, and a premium brushed gold cap. The fictional brand name {argument name="brand name" default="VERDARA"} is elegantly printed in embossed gold typography with a minimalist botanical emblem. The bottle is centered against a rich emerald green textured paper backdrop. The paper is dramatically torn open across the middle, revealing an overflowing bed of fresh green grapes, sliced kiwi, mint leaves, and sparkling lime wedges hidden beneath. A curled section of torn paper on the lower left adds depth and realism. Several fruits are scattered naturally across the foreground. Elegant editorial typography appears in the upper left: “{argument name="slogan" default="Sip Into Pure Freshness"}” “Sip” in modern handwritten brush script, “Into Pure Freshness” in sophisticated high-fashion serif typography. The bottle label features premium botanical illustrations of kiwi, grapes, mint, and lime with subtle metallic foil accents. Hyper-realistic glass reflections, natural condensation droplets, premium studio lighting, soft shadows, vibrant colors, razor-sharp focus, luxury beverage advertisement, photorealistic, ultra-detailed, award-winning commercial product photography, minimalist composition, 8K.

Cinematic Beach Walk with Flash

Ultra-realistic smartphone photograph of a {argument name="subject" default="woman"} walking along a {argument name="setting" default="secluded beach"} at dusk, captured in a vertical frame with an on-camera flash that creates the look of an authentic, spur-of-the-moment snapshot. The scene takes place beside the shoreline as the last traces of a deep crimson sunset fade into an almost black night sky. Behind her, dark ocean waves roll onto the sand, leaving bright white foam illuminated by the flash. The setting has a moody coastal atmosphere with cool sea breeze, subtle motion, and the feeling of an unplanned evening moment. A strong gust of wind sweeps her exceptionally long hair dramatically across her face, with loose strands obscuring part of her features. She instinctively lifts one hand to move the hair aside while continuing to walk, creating a candid sense of movement rather than a posed fashion shoot. Her facial details remain softly blurred by motion and wind, adding realism and mystery. She wears a {argument name="outfit" default="flowing black maxi dress"} with delicate spaghetti straps that moves naturally with the breeze, accentuating a graceful hourglass silhouette. High-detail textures, realistic flash reflections, natural skin tones, subtle motion blur, cinematic coastal lighting, authentic smartphone photography, premium lifestyle editorial aesthetic.

Japanese AI Training Banner

Create a sleek Japanese corporate training banner in a wide horizontal web-ad format with a dark navy-to-deep-blue gradient background, subtle glowing network nodes and connecting lines across the upper and middle area, and a high-tech AI/business atmosphere. Place a confident businessman on the right side from waist-up, wearing a dark navy suit, white dress shirt, and blue striped tie, arms crossed, facing forward; crop him partially at the top and right edge. On the left, create a strong typographic hierarchy with a small cyan headline at the top reading {argument name="headline text" default="AIを活用した開発スキルを、最短で習得"}, then an oversized bold white main title reading {argument name="main title" default="ClaudeCode研修"}. Along the lower-left area, place exactly 3 rounded rectangular feature boxes outlined in bright cyan with dark interiors and cyan icons: box 1 shows a terminal/code icon and the text "Claude Codeの基本と応用", box 2 shows a rocket icon and the text "開発スピードを飛躍的に向上", box 3 shows a two-person/team icon and the text "現場ですぐに活かせるスキル". On the far right, overlay a large cyan angled polygon callout panel with bold dark text in 2 lines reading {argument name="callout text" default="明日からの開発が\n変わる体験を。"}. Use crisp modern sans-serif Japanese typography, strong contrast, polished marketing design, clean spacing, luminous cyan accents, and a premium AI seminar advertisement look.

Futuristic Void Fang Mech

Mine pulses red beneath a {argument name="shell color" default="black shell"}. {argument name="model id" default="JFC-01"}｜{argument name="name" default="VOID FANG"}

Game of Thrones Isometric Map Diorama

Goal: Create an ultra-detailed photorealistic isometric miniature scale-model diorama map of the world from {argument name="TV show" default="Game of Thrones"}, floating on a pure warm off-white studio background with a soft drop shadow beneath. Canvas: Vertical poster composition, 4:5 aspect ratio, centered diorama occupying the lower two-thirds and large title typography in the upper third. Use clean studio lighting, realistic shadows, shallow but readable depth, and a premium collectible tabletop model look. Title text: At the top, set small spaced uppercase text reading {argument name="world label" default="WESTEROS & ESSOS"}. Below it, place a huge tall condensed serif/fantasy title reading {argument name="main title" default="GAME OF THRONES"}, dark charcoal with slightly weathered texture; make the O in THRONES resemble the Iron Throne vertical blade motif. Beneath the main title, add small spaced text reading {argument name="subtitle" default="HBO | 2011"}. Map layout: Build two separate raised landmass miniatures divided by blue sea. On the left is Westeros, tall and narrow, with a snowy northern region at the top, a wall-like icy boundary, rugged green central lands, winding pale roads, mountain ridges, forests, lakes, castle miniatures, and a warmer southern desert region at the bottom. On the right is Essos, wider and more horizontal, with jagged central mountains, dry yellow-orange plains to the east, green-brown western terrain, rivers, roads, fortified cities, pyramids, towers, and ruins. Both continents have thick carved cliff edges like cutaway terrain, rocky brown sides, and tiny coastal islands. Discrete elements to include: Use exactly 10 heraldic banner markers placed across the map: 6 on Westeros and 4 on Essos. Westeros banners: one black northern banner in the snowy top region, one yellow-and-blue banner in the upper central region, one red lion banner in the central region, one dark red banner near the central-west castle, one blue banner in the lower central region, and one red lion banner at the southern castle. Essos banners: one dark blue banner in the mountain region, one red banner in the far upper-right city, one green banner at the right-side city, and one blue-gold banner in the lower central city. Add exactly 24 tiny sailing ships and boats scattered in the surrounding seas and between the continents, all miniature scale and varied in size. Visual style: Hyper-real miniature realism, isometric three-quarter top-down view, highly detailed terrain texture, tiny castles and settlements, crisp roads and rivers, muted fantasy-map colors, blue water, snow white north, ochre desert, mossy greens, rocky grays, and subtle atmospheric shadows. The diorama should feel like a handcrafted museum-quality prop or board-game map, not a flat illustration. Constraints: No people, no modern objects, no watermark, no UI, no border frame. Keep all text legible and centered. The background must remain plain off-white with ample negative space around the title and floating map.

Isometric France Diorama Poster

Create a polished isometric country diorama poster for {argument name="country name" default="France"} in a premium travel-atlas style. Use a vertical 4:5 canvas on a warm off-white background, with the country shown as a thick floating 3D terrain cutout in its real recognizable outline, including the separate island of Corsica as a smaller detached cutout at lower right. The landmass should have steep rocky vertical edges, soft studio shadows, and an isometric camera angle looking down from above. At the top, add clean centered typography: small spaced uppercase region label "EUROPE", then a huge bold condensed uppercase title "{argument name="country title" default="FRANCE"}" in dark charcoal, with a simple vertical tricolor flag to the right of the title using blue, white, and red. Beneath the title, add a small spaced subtitle reading "{argument name="capital and population" default="PARIS • 67.4 MILLION"}". The diorama should be densely detailed: green countryside, patchwork farms, forests, rivers, roads, rail-like lines, villages, towns, harbors, coastline, and mountain ranges. Include exactly 10 prominent landmark or terrain features distributed across the map: 1 central Eiffel Tower near Paris, 1 large Gothic cathedral in the northeast, 1 domed monument in the west, 1 tall cathedral or basilica in the southwest interior, 1 white coastal lighthouse on the Atlantic side, 1 Mediterranean harbor with boats along the south coast, 1 snowy mountain range across the southeast Alps, 1 snowy mountain range across the southwest Pyrenees, 1 major winding blue river running north-south through the center-east, and 1 detached Corsica island with miniature towns and green hills. Add small boats and sailboats on the surrounding blue water, especially near the Atlantic coast and Mediterranean bay. Visual style: highly detailed miniature model, realistic 3D render, crisp topographic relief, vibrant natural greens and yellows, tiny architecture, clean editorial poster composition, soft ambient occlusion, subtle depth of field, no border, no watermark. Keep the overall image balanced with the text occupying the upper quarter and the isometric map filling the lower three quarters.

Kashmir Luxury Rain Masterpiece

Create an ultra-luxury cinematic masterpiece set on the {argument name="location" default="shores of Dal Lake, Kashmir"} during a dramatic rainy evening. A breathtakingly beautiful woman wearing an elegant {argument name="outfit" default="black velvet royal gown with intricate gold embroidery"} stands on a wet wooden promenade beside the lake, looking back with a confident expression. Majestic snow-covered Himalayan mountains rise in the background beneath dark storm clouds. Warm golden lanterns illuminate the scene, their reflections shimmering across the rain-soaked floor. A {argument name="car" default="vintage Rolls-Royce"} is parked nearby, adding a billionaire lifestyle aesthetic. Traditional Kashmiri houseboats glow softly across the lake, surrounded by mist and atmospheric fog. Ultra-realistic facial details, flowing fabric physics, glossy reflections, luxury fashion editorial photography, dramatic cinematic lighting, volumetric fog, shallow depth of field, premium color grading, black and gold luxury palette, photorealistic textures, masterpiece composition, hyper-detailed environment, Vogue magazine quality, Hollywood movie poster aesthetics, emotional storytelling, royal elegance, dark luxury atmosphere, 8K HDR, Unreal Engine quality, award-winning luxury advertising campaign, no text, no watermark, no logo, perfect symmetry, viral social media masterpiece.

Anime Girl Sketch by the Sea

Lighthearted sketch-style anime aesthetic, A serene, anime-inspired illustration of a {argument name="subject" default="young woman"} sitting against a tree by the seaside, full-body seated view at eye level, slightly turned three-quarter pose, looking down as she draws in a spiral sketchbook with a black pen. Soft pastel color palette with clean line art and gentle watercolor shading, warm, soft directional sunlight casting subtle, long shadows. She wears a {argument name="outfit" default="lavender long-sleeve blouse under a green pinafore dress patterned with small white daisies"}, a white underskirt with larger daisy prints peeking out, white ankle socks and brown loafers. Long dark hair, natural expression, light blush on cheeks. Large tree trunk with textured bark and {argument name="leaves" default="golden autumn leaves"} drifting in a light breeze; a few leaves scattered on the pavement. Background: calm blue ocean with gentle waves, pale sandy beach, distant horizon and soft fluffy clouds, a quiet two-lane coastal road beside the beach. Foreground includes a woven straw tote bag with colorful horizontal stripes placed on the curb. Emphasize peaceful, nostalgic mood, delicate details (fabric folds, leaf veins, bark texture, woven bag weave, pen and paper strokes), cinematic composition, high-resolution, soft grain, subtle rim light and natural ambient occlusion.

Lolita Maid With Anime Wall Sketch

Create a photorealistic editorial fashion image with an anime sketch transformation theme. A young woman with {argument name="hair color" default="light brown"} hair stands in the left third of the frame against a plain warm beige interior wall, wearing a black-and-white gothic lolita maid outfit: black puff-sleeve lace dress, white frilly apron, white lace cuffs, small white ruffled maid headband, white knee-high socks, and black Mary Jane platform heels. She poses shyly and slightly pouty, leaning near the corner with one hand resting against her cheek, the other arm folded, one leg straight and the other bent backward at the knee. To her right, drawn directly on the wall, show one large black ink manga/anime line-art version of the same maid character, about twice as dynamic and playful: winking, smiling with an open mouth, making a V-sign near her eye, one leg kicked up, apron and skirt fluttering, long hair flowing. Surround the sketch with exactly 8 doodle elements: 3 hearts, 3 stars, and 2 short emphasis marks. Use warm natural sunlight from a window on the left, casting diagonal shadows across the wall and wooden floor. Keep the composition split between real model on the left and hand-drawn anime alter ego on the right, with realistic photography texture, soft shadows, beige wall, baseboard, and parquet wood floor. No captions, no watermark, no extra characters.

Cinematic Moment of Fate Re-creation

Analyze the narrative of this illustration and identify the single most critical moment of fate within the story. [Scene Construction] - Recreate that decisive moment as a new illustration - The scene should feel candid and unposed — as if captured accidentally by a camera - The subject is caught mid-action, unaware of being observed - The composition is slightly off-balance, as if the photographer moved suddenly [Depth & Lens] - Place an out-of-focus object in the foreground close to the lens — a branch, fabric, foliage, architectural element, or any environmental object native to the scene - Human hands or body parts must never appear in the foreground - This foreground element creates strong depth separation - Apply shallow depth of field: the focal point is sharp, everything else falls into natural bokeh - Slight motion blur on peripheral elements suggests a fleeting moment [Imperfection] - The framing is imperfect — subject may be slightly off-center or partially cropped - Focus is not perfectly locked — the sharpest point is close but not clinical - The image feels like it was taken one second before or after the "perfect" shot [Atmosphere] - The emotional weight of the story's turning point must be felt in the image - Light and shadow reflect the tension of the moment - Preserve the original art style and color palette of the source illustration

Clear Glasses Smartphone Selfie Portrait

Create a realistic vertical smartphone selfie portrait of {argument name="subject" default="an adult East Asian woman"} in an extremely tight close-up, showing mainly the face, shoulders, and upper chest. She has {argument name="hair style" default="shoulder-length black hair with wispy bangs and one thin side braid"}, clear luminous skin, soft glossy pink lips, and large dark eyes looking directly into the camera. She wears {argument name="glasses" default="transparent amber rectangular eyeglasses"} lowered slightly on her nose, and lightly touches the outer edge of the frame with one index finger while resting her hand against her cheek. Her expression is calm, relaxed, slightly playful, and intimate. Dress her in an oversized {argument name="sweatshirt color" default="pale powder-blue"} crewneck sweatshirt with long ribbed cuffs pulled over part of the hand; include partial black printed lettering cropped at the bottom. Use a plain cool gray wall background, natural window light from the upper left, soft shadows, realistic skin texture, subtle hair flyaways, clear glass reflections, shallow depth of field, and a casual lifestyle cover-photo feeling. Composition should feel like a handheld phone selfie from slightly above eye level, portrait orientation 9:16, face filling most of the frame, no extra people, no watermark, no added text beyond the partial sweatshirt print.

Doodle Character Editorial Lifestyle Poster

同样处理： 请将我上传的每一张照片分别制作成一张独立的高级设计海报，不多图拼接，每张照片单独输出。整体采用3:4竖版构图，上下两个区域高度严格1:1，各占画面50%。 上半部分保留原始照片，保持主体结构、真实质感、自然光影和原有色彩氛围，仅进行轻微高级摄影调色，使其具有生活方式杂志、独立出版物和艺术摄影质感。为适配画幅，可自然扩展环境背景，但不得拉伸、扭曲或改变主体。 下半部分先理解原图真正的**视觉核心与寓意**：判断画面最重要的不是“有什么”，而是“什么最值得被记住”——可能是一个主体、一种动作、一组关系、一处反差、一个情绪瞬间或某种象征意味。再从中提取最具识别性的**主体、轮廓、姿态与叙事线索**，重构为“真实主体 + 黑线涂鸦小人”的趣味编辑海报。不要机械截取原图最大物体，而要保留最能代表照片精神和故事性的视觉锚点，使下半部分既能一眼对应原图，又像对原图进行了一次聪明的二次解读。 真实主体保持材质与身份特征，可适度优化角度、比例、光线和色彩，使核心特征更鲜明；原图中与寓意无关的信息可以舍弃，但支撑主题的关键关系必须保留。围绕主体加入少量极简黑线涂鸦小人，小人的动作、位置和互动方式完全根据原图的形态、语境与潜在寓意自然生成，让他们像在回应、放大或反转照片原本的故事，而不是随意做动作。 配色从上方照片中提取最有辨识度和精气神的颜色，可适度提纯、提亮和重新组织。背景以米白、浅色或原图中最舒适的浅色为主，保持大量留白；真实主体承担主要色彩，小人与文字以黑色或深灰细线形成对比，整体干净、轻快、克制。 文字同样从原图的**核心寓意、情绪和视觉关系**中自然生长，不直接说明物体名称，也不套固定文案。将照片最值得被记住的那层意思转化成极短、轻松、聪明、略带幽默或双关的手写文字，让它像小人留下的注释、念头或一句画外音。文字可沿主体轮廓、人物动作或留白节奏自由排布，与小人和主体共同完成叙事，而不是后期贴上的标题。 整体保持**真实主体、核心寓意、微型叙事、稚拙线条和大量留白**之间的平衡。无论原图是人物、动物、植物、食物、建筑、器物、交通工具或自然场景，都应先抓住“这张照片真正讲的是什么”，再决定如何重构，避免只抓物体不抓关系、只做可爱互动没有主题、卡通贴纸感、复杂装饰和模板感。 💣language：{argument name="language" default="english"}

Attack on Titan Isometric Diorama Map

Goal: Create an ultra-detailed photorealistic isometric miniature scale-model diorama poster of the world from {argument name="anime title" default="Attack on Titan"}, presented like a collectible museum map on a clean off-white studio background. Canvas: Vertical 4:5 poster composition. The upper third is typography, the lower two-thirds is a floating square-cut terrain diorama with rugged rocky sides and a soft realistic shadow beneath. Top typography: Centered at the top, use tall condensed bold distressed sans-serif lettering. Small spaced text above reads "THE WORLD OF". Main title reads "{argument name="main title text" default="ATTACK ON TITAN"}" in very large dark charcoal letters. Small spaced text below reads "{argument name="studio line" default="WIT STUDIO • 2013"}". Diorama layout: Show the walled civilization as a high-angle isometric model with three enormous concentric circular stone walls and fortified gates. The center contains a dense circular royal city with radial streets and a white central monument. Surrounding rings contain miniature villages, farms, roads, rivers, forests, watchtowers, and tiny human figures. Beyond the walls at the back are snow-capped mountains, wilderness, scattered ruins, and open terrain. The outer edge of the model is a thick cliff-like cutaway rock base with grass on top. Labeled signs: Include exactly 14 small dark rectangular map-label plaques with white uppercase text, placed around the diorama: 1) "BEYOND THE WALLS" near the mountains, 2) "ZIGANSHINA DISTRICT" on the upper-left wall area, 3) "KROLVA DISTRICT" on the upper-right wall area, 4) "SHIGANSHINA DISTRICT" on the far right, 5) "LAKE NALLE" by a blue lake on the left, 6) "YARCKEL DISTRICT" on the left outer area, 7) "CHLORBA DISTRICT" on the lower-left area, 8) "HUMANITY'S STRONGEST" beside a small military crest on the lower-left, 9) "TROST DISTRICT" on the right outer area, 10) "TRAINING GROUNDS" on the lower-right, 11) "ROYAL CAPITAL MITRAS" at the central city, 12) "INNER WALL WALL SINA" on the innermost wall, 13) "MIDDLE WALL WALL ROSE" on the middle wall, 14) "OUTER WALL WALL MARIA" on the front outer wall. Subject details: Make the wall rings tall, pale stone, weathered, and segmented with massive gates and red-roofed towers. Populate the landscape with tiny soldiers, civilians, horses, tiled-roof houses, roads, farmland plots, bridges, streams, and forests. Add a few tiny Titan-like humanoid silhouettes outside and near the walls for scale, but keep the scene map-like rather than action-focused. Visual style: Hyper-realistic miniature model photography mixed with anime-world cartography, crisp isometric perspective, warm daylight, realistic shadows, high texture detail, tiny hand-painted model figures, natural greens and browns, pale stone walls, snowy gray mountains, cinematic depth of field but all important labels legible. Constraints: Keep the image as a single poster, no border, no watermark, no extra logos. Preserve the exact 14 map labels listed above and the three wall labels. Use an off-white background and a centered floating diorama with clean studio lighting.

Six VTuber Japanese Logo Sheet

Goal: Create a clean presentation sheet of exactly 6 original VTuber-style Japanese name logos on a white background, arranged in a 3-column by 2-row grid with generous spacing. Each logo should be a polished vector-like typographic mark with decorative motifs, glossy gradients, small romanized subtitle text, and no extra captions outside the logos. Canvas: Wide horizontal canvas, about 1200×690 px, pure white background, centered composition, high-resolution crisp edges, transparent-logo-design feeling but displayed on white. Layout: Exactly 6 discrete logos: 1. Top left: {argument name="top left name" default="月詠こよみ"} with small romanization “TSUKUYOMI KOYOMI”. Elegant deep navy Japanese calligraphy, crescent moon sweep in pale gold, dangling star charms, small flowers, sparkles, and a black cat silhouette sitting on the lettering. 2. Top center: {argument name="top center name" default="夢羽ころん"} with small romanization “YUMEHA CORON”. Cute pastel magical-girl logo in pink, lavender, and sky blue, rounded bubbly letters, fluffy cloud outline, tiny angel wings, halo above, stars, dotted lace border, and a pink bow at the bottom. 3. Top right: {argument name="top right name" default="黒燐アリア"} with small romanization “KOKURIN ARIA”. Gothic dark fantasy logo, black and crimson Japanese typography, thorny bat-wing flourishes, red rose crown at the top, diamond jewel shapes, rose petals, sharp spikes, and dramatic black ink accents. 4. Bottom left: {argument name="bottom left name" default="水瀬なぎさ"} with small romanization “MINASE NAGISA”. Fresh aquatic logo in turquoise and aqua gradients with pale gold accents, flowing wave underline, bubbles, seashells, small star sparkles, airy elegant rounded Japanese lettering. 5. Bottom center: {argument name="bottom center name" default="夜乃書ラウ"} with small romanization “YORUNOSHO RAU”. Dark academia midnight logo in deep navy and gold, large blocky Japanese lettering on a shield/book-shaped plaque, open book silhouette at the bottom, ornate golden frame, dangling stars, crescent/lantern-like ornament above, refined fantasy library mood. 6. Bottom right: {argument name="bottom right name" default="雷ヶ咲うた"} with small romanization “IKAZUCHI UTA”. Energetic pop-rock electric logo with bold black and white Japanese lettering, cyan and hot pink accents, lightning bolts, jagged comic effects, stars, checker/halftone details, small gamepad icon with X buttons, dynamic tilted rhythm. Visual style: Modern Japanese VTuber logo design, professional esports/idol branding quality, highly legible stylized kanji/kana, layered outlines, gradients, sparkles, ornaments integrated into each logo, crisp vector illustration, balanced colors, no mockup shadows, no watermark. Constraints: Use exactly 6 logos and exactly the 6 themes listed above. Keep the grid clean and evenly spaced. Preserve the Japanese text and romanized subtitles as part of each logo. Avoid photorealism, characters, people, UI panels, or extra explanatory text.

Blue Moonlit Sari Portrait

Create a low-key nocturnal vertical portrait of {argument name="character description" default="a young South Asian woman"} from upper torso to head, centered slightly below the upper half of the frame, with a huge luminous full moon directly behind her head like a halo. She has long loose wavy {argument name="hair color" default="black hair"} parted near the center, a calm introspective expression, her complete face visible, eyes looking down and slightly to her left, soft lips, and a small nose ring. Use a monochromatic cool-blue moonlit color grade with deep navy shadows, subtle rim light on the hair and shoulders, and smooth realistic photographic skin texture. She wears a dark navy sari draped diagonally over one shoulder and a matching short-sleeve blouse with a wide neckline. Include exactly three visible tattoos: two symmetrical black leafy branch tattoos across the left and right collarbones, and one small centered chest text tattoo reading {argument name="chest tattoo text" default="FEEL ME"}. The background is almost black with faint star specks and negative space, while the oversized moon is softly detailed with craters and a blue glow. Mood should be quiet, cinematic, mysterious, and romantic, with shallow depth of field, high contrast, soft moon haze, no extra people, no added text besides the tattoo, no watermark, and a polished editorial portrait style.

Isekai Guild Receptionist Character Transform

参照画像のキャラクターをベースデザインとして使用して、「{argument name="シーン" default="転生したアニメキャラクターが、異世界の冒険者ギルドで普通に受付嬢として働いている瞬間"}」を描く。キャラクターのアニメイラストとしての空気感を正確に維持する。キャラクターの顔、髪型、髪色、瞳、耳、シルエット、頭身、表情の印象を維持すること。キャラクターのアイデンティティを絶対に崩さない。別人化しない。実写人間化しない。キャラクター部分はアニメイラスト表現を維持する。舞台は{argument name="場所" default="異世界ファンタジー世界の大都市ギルド本部"}。背景は{argument name="背景エンジン" default="Unreal Engine 5"}で描かれたような高品質なファンタジー空間。リアル寄りの背景描写。生活感のある異世界空間。綺麗すぎない。コンセプトアート化しない。ゲーム公式ビジュアルのようにしない。背景には、巨大なクエスト掲示板、木製カウンター、依頼書、地図、武器ラック、革鎧の冒険者、魔導ランタン、石造りの壁、酒場スペース、吹き抜け構造、二階回廊、荷物、樽、雑多な備品などを自然に配置する。構図は一人称視点（POV）。視聴者はギルドを訪れた冒険者。画面手前には、冒険者の腕、手、依頼書、冒険者カード、報酬袋、地図、飲み物、荷物などを自然にフレームインさせる。POV側の人物は、・依頼書を受け取ろうとしている・冒険者カードを差し出している・報酬袋へ手を伸ばしている・地図を覗き込んでいる・受付カウンターへ寄りかかっているなど、受付とのやり取りが成立する自然な行動を取る。ギルド受付嬢となったアニメキャラクターは、・依頼書を差し出している・地図を広げて説明している・冒険者カードを返却している・報酬袋を渡している・初心者向けクエストを案内している・ランクアップを祝福している・少し眠そうに受付している・慣れた様子で業務をこなしているなど、「普通に働いている」自然な動作を行っている。重要：キャラクター本人は、異世界の受付嬢であることを特別視していない。周囲の冒険者達も、それを当たり前の日常として受け入れている。ゲームUI風オーバーレイを追加する。冒険者ランク、クエスト情報、所持金、パーティ情報、通知表示、ミニマップなどを自然に表示する。UI内容は固定しない。AI側が自然に生成すること。UIは主役ではない。受付嬢と冒険者のやり取りを補強する程度に留める。異世界とアニメキャラクターが自然に融合した、奇妙にリアルな空気感を重視する。映画ポスター風にしない。過剰なシネマティック演出禁止。綺麗すぎる構図禁止。AI特有の glossy rendering を避ける。情報量を盛りすぎない。「RPGのイベントシーンのスクリーンショット」ではなく、「異世界の日常を偶然目撃した一瞬」のような生活感と偶然性を重視する。high quality anime character, UE5 fantasy environment, POV shot, guild receptionist, natural interaction, fantasy daily life, weirdly realistic atmosphere

Kawaii Arcade Claw Machine Portrait

Hyperrealistic photograph in Japanese kawaii style. The beautiful young woman in the attached image sits inside {argument name="setting" default="a UFO Catcher arcade machine overflowing with Pokémon plushies"}. The composition is perfectly centered and symmetrical. The model holds the metal shaft of the claw above her head, her expression {argument name="mood" default="soft and melancholic"} as she gazes directly at the camera. She has long, wavy, dark brown hair, luminous and delicate skin, and her legs are elegantly extended atop a mountain of adorable plushies. The interior is completely filled with Pokémon plushies. The Japanese arcade machine is decorated with kawaii illustrations, Japanese typography, stars, hearts, and other cute details. {argument name="lighting" default="Enveloping neon pink LED lighting"}, vertical light tubes on both sides, cinematic reflections on glass and metal, soft bloom, dreamcore atmosphere, Harajuku aesthetic, pastel vaporwave, monochromatic cotton candy pink color grading, soft magenta tones, ultra-detailed, hyper-realistic, moderate depth of field, perfect focus on the model, realistic reflections, luxury editorial photography, Japanese magazine style, magical and nostalgic atmosphere, 85mm, f/2.0, HDR, 8K, masterpiece, ultra-realistic, cinematic lighting, premium fashion photography, highly detailed, soft glow, dreamy atmosphere.

Magical Sunrise Alpine Valley

Create a cinematic, ultra-realistic nature landscape at magical sunrise: a pristine alpine valley with a shallow winding river in the foreground, framed by dense evergreen pine forests and jagged snow-dusted mountain peaks in the background. The sun is low on the left horizon, casting warm golden light, long rays, glowing mist, and soft volumetric fog through the trees and across the valley. In the river, show exactly 4 spotted deer drinking or grazing at the water’s edge: three grouped near the center with heads lowered, and one smaller deer farther right near the riverbank. The foreground is filled with vibrant wildflowers, especially purple lupines and small yellow blossoms, with lush green grasses, stones, and river rocks. Use {argument name="time of day" default="golden sunrise"}, {argument name="main animals" default="four spotted deer"}, {argument name="mountain style" default="jagged alpine peaks with light snow"}, {argument name="flower colors" default="purple and yellow wildflowers"}, and {argument name="mood" default="magical, peaceful, cinematic"}. Make the composition wide and immersive, with strong depth from flowers in the foreground to river, forest, misty valley, and towering mountains. Photorealistic detail, natural colors, dramatic warm lighting, soft haze, high dynamic range, serene wilderness atmosphere, no text, no people, no buildings, no watermark.

Glossy AI Logo Redesign Row

Create a clean logo redesign showcase on a wide white canvas, featuring exactly 5 glossy rounded-square app icons evenly spaced in a single horizontal row, centered vertically with generous empty margins. Use a modern 3D glassmorphism style with soft shadows, subtle reflections, beveled edges, high saturation, and smooth gradient lighting. The five icons from left to right are: 1) a teal-to-mint rounded square containing a white interwoven knot emblem resembling the OpenAI logo, 2) a peach-to-orange rounded square containing a white radial sunburst or asterisk emblem with many tapered rays, 3) a cyan-blue-to-purple rounded square containing a large white four-point sparkle star plus one small sparkle near the upper right, 4) a black rounded square with deep blue highlights at the bottom containing a white lowercase-like geometric “k” mark and one small bright blue dot near the upper right, and 5) a lavender-to-purple rounded square containing a white outlined angular six-point star or badge emblem. Keep the composition minimal, polished, and product-design focused, with no text labels, no watermark, and no extra icons. The overall subject is {argument name="logo redesign theme" default="AI app logo redesigns"}, with {argument name="icon style" default="glossy 3D glassmorphism rounded-square app icons"}, on a {argument name="background color" default="pure white"} background.

Surreal Mixed-Media Glitch Portrait Prompt

A surreal mixed-media portrait of {argument name="person" default="[PERSON]"}, set against a clean, plain white background with visible fine-grain paper texture. The character's face is the subject of a controlled, stylized distortion. Instead of chaotic fragmentation, the facial features are horizontally stretched into smooth, flowing bands of color and texture, resembling a deliberate digital scanline effect or a long exposure photograph pushed sideways. Key identifying features (like eyes, mouth, or distinct accessories) remain partially recognizable within these stretched streaks, creating a sense of fluid motion rather than destruction. The aesthetic blends analog collage textures with digital glitch art, feeling tactile and composed.

Luxury Asian Fashion Editorial

Realistic fashion editorial portrait, close medium shot of a beautiful adult {argument name="subject" default="Asian young woman"} with refined facial features, long straight light-blonde hair falling over her shoulders, soft airy bangs framing her face, pale porcelain skin, slim figure, cold and elegant expression, deep captivating eyes with slightly winged eyeliner, bold red lips. She is seated sideways in a relaxed, slightly lazy pose on a black leather sofa, with a soft white faux-fur blanket beneath her. Her right hand elegantly holds the rim of a wine glass. She wears a {argument name="dress" default="fitted black glossy mini dress or sleek patent-finish short dress"}, subtly contouring her body line, with a metallic zipper detail at the chest. Around her neck are layered sparkling rhinestone necklaces. A silver ring is worn on the ring finger of her left hand, and her fingernails are painted black. Framing focuses on her face and upper body, intimate editorial composition, eye-level with a slight high-angle perspective. The background is dark and moody, minimal, luxurious, and mysterious, creating a premium cinematic atmosphere. Lighting is soft but directional, sculpting the contours of her face and body while emphasizing the glossy texture of the dress, the shine of the jewelry, and the rich material of the black leather sofa. Style: high-end fashion magazine photography, cinematic realism, Korean-style luxury editorial portrait, slightly moody indoor atmosphere, elegant sensuality, premium visual language, realistic skin texture, soft diffusion, subtle film grain, muted dark tones, low-saturation luxury palette, shallow depth of field, polished but natural, detailed, sophisticated, visually striking. Add a small handwritten signature text “{argument name="signature" default="BubbleBrain"}” in the bottom-right corner.

Boho-Coastal Luxury Summer Portrait Prompt

{ "image_request": { "subject": { "type": "Adult female model", "identity_constrai…

Connected series of four-panel manga strips

4コマ漫画4ページ作成。4コマ漫画一つづつにオチをつけ、画像1枚に2つの4コマ漫画、合計8つの4コマ漫画がストーリーとしてつながっているように。

Urban Fashion Street Photography

Cinematic fashion street photography of a stylish young woman with {argument name="hair color" default="long wavy ash-brown hair"} wearing slim sunglasses, a {argument name="jacket" default="cropped brown fuzzy jacket"}, marble-pattern tube top, and high-waisted jeans, carrying a {argument name="accessory" default="beige shoulder bag"}. Scene 1: standing on a quiet cobblestone street between vintage red-brick buildings, soft golden-hour light, shallow depth of field, editorial Vogue style, natural pose with hand in hair. Scene 2: crossing a busy New York street with yellow taxis, urban motion blur, confident walk, candid look-back pose, city lifestyle aesthetic. Scene 3: posing on Brooklyn Bridge with Manhattan skyline at sunset, warm cinematic lighting, wind slightly moving hair, relaxed pose adjusting sunglasses. Ultra-realistic, 4K, soft color grading, warm tones, natural skin texture, depth of field, high-end fashion editorial, film grain, dynamic composition, photorealistic lighting.

Dorm Mirror Selfie Identity Reference

Use my uploaded portrait as the identity reference only, preserving my real facial features, hairstyle, skin tone, and natural likeness. Create a realistic vertical mirror selfie in a {argument name="location" default="small bedroom/dorm room"}, {argument name="lighting" default="warm golden backlight behind the head"}, soft messy indoor background, phone held in front of the chest, relaxed cute expression, natural skin texture, {argument name="outfit" default="casual layered outfit"} that suits me, subtle hair accessories and polished nails. Real iPhone photo feeling, imperfect candid framing, warm highlights, realistic shadows, no watermark, no logo. Negative Prompt: anime, cartoon, doll face, plastic skin, over-smoothed skin, fake face, face swap look, distorted hands, bad fingers, unnatural eyes, heavy makeup, overexposed face, studio lighting, clean commercial background, watermark, logo, text, AI artifacts

Ultra-Photorealistic Bedroom Mirror Selfie

{ "prompt_schema": { "style": "ultra-photorealistic", "lighting": "natural daylight from side window, soft highlights", "aspect_ratio": "2:3", "subject": { "demographics": "19-year-old caucasian female with fair, smooth skin", "hair": "long light brown hair, loosely waved, decorated with small pink ribbon clips", "accessories": [ "white over-ear headphones resting slightly off one ear", "iPhone with transparent case and subtle pink accents" ], "outfit": { "upper": "{argument name="top color" default="soft pink"} fitted ribbed tank top", "lower": "white high-waisted pleated mini skirt" }, "pose": "sitting on the bedroom floor with knees drawn up, one arm resting casually, mirror selfie angle", "expression": "cheeky smile, slight wink, playful attitude" }, "environment": { "setting": "bright modern bedroom", "flooring": "light grey patterned carpet", "furniture": [ "minimal white bed with textured duvet", "small bedside table with warm lamp glow" ], "background_details": "bathroom doorway visible with clean white counter and soft reflections" } } }

Cyberpunk Neon Rim Lighting Portrait

Ultra-detailed cinematic digital portrait of a young man with tousled messy {argument name="hair color" default="black"} hair and light stubble, viewed from a low-angle perspective, projecting confidence and effortless attitude. Black and white monochrome color palette with striking {argument name="glow color" default="neon red"} rim lighting outlining the hair, shoulders, and facial contours. Deep black background with dramatic high-contrast lighting, sharp shadows, and glossy highlights. Sunglasses resting on top of his head, slightly open black shirt layered over a plain white t-shirt, minimalist silver pendant necklace. Intense eyes looking directly at the viewer, relaxed expression, strong jawline, fashion-editorial aesthetic.\n\nModern graphic novel illustration style, ultra-clean vector rendering, smooth gradients, razor-sharp details, premium poster design, luxury streetwear vibe, cyberpunk-inspired red glow accents, cinematic composition, studio-quality lighting, highly detailed facial features, masterpiece quality, 8K resolution, dark moody atmosphere, trending on ArtStation, dramatic contrast, centered composition, black background.

Cinematic Urban Portrait of a Young Woman in Shanghai

A young Chinese woman in her late teens to early twenties, looking back over her left shoulder with her body slightly turned away, gazing directly and intensely at the camera with a slightly melancholic, contemplative expression. She wears a loose, light-colored down jacket or coat ({argument name="coat color" default="soft tones such as off-white, light gray, beige, cream"}), layered over a dark turtleneck sweater or black hoodie, with a loosely draped black scarf around her neck — classic dark inner + light outer winter layering style. Her hair is deep brown to black, styled in a slightly messy low bun or low ponytail, wind-swept with several loose strands naturally falling beside her face, giving a natural, slightly disheveled feeling. Fair, delicate, smooth skin with soft natural texture. Refined Korean-style makeup: subtle gradient eyeliner, gentle aegyo-sal (under-eye highlight), glossy lips. Large, expressive brown eyes slightly narrowed, looking straight at the viewer with depth and emotion. Neat straight bangs resting on her forehead, soft straight eyebrows, overall soft and gentle facial features. She carries a black backpack with clearly visible shoulder straps. Location: {argument name="location" default="Nanjing Road pedestrian street in Shanghai"}, bustling commercial district, at dusk or right after rain in overcast, damp weather. Background: heavily blurred crowds of people, dense rows of Chinese neon signs and illuminated billboards on both sides, distant silhouette of the Oriental Pearl Tower visible in the background. Wet, reflective ground with puddles. Strong colorful reflections of neon lights, street lamps, traffic lights, and car tail lights in the water. Blurred reflections of signs, buildings, and the Oriental Pearl Tower in the puddles. Overhead wires and decorative lights, rich bokeh light spots created by traffic lights and car headlights. Lighting: soft diffused cinematic light with slight grain feeling, overall cool blue-cyan ambient tone from overcast sky, contrasted by warm yellow, red, orange, pink-purple neon light spots reflected on wet surfaces — high contrast in background reflections, low contrast soft lighting on her face. Camera: medium close-up portrait, eye-level angle, extremely sharp focus on eyes and face, shot on Hasselblad XCD 3,4/75P (equivalent to ~50mm), creamy beautiful bokeh, rich light spots and reflection details preserved in background. Style: cinematic, emotional, urban life slice-of-life mood, street photography + emotional portrait, classic {argument name="color grading" default="teal-orange complementary color grading"}, overall cool low-saturation tones with warm neon highlights, soft dreamy atmosphere. Vibe: nostalgic, lonely, melancholic yet romant

Japanese Shoe Laundry Bag Ad

Japanese e-commerce product advertisement · shoe laundry mesh bag · {argument name="product name" default="靴用洗濯ネット"} · rounded clamshell zippered laundry bag with a top mesh panel and ribbed fabric sides · light blue mesh, medium gray ribbed body, pale blue zipper trim · front-right foreground on a light wooden tabletop · unzipped open at the front, revealing the contents · 2 · white low-top sneakers · a clean matching pair placed neatly side by side inside the bag with toes facing forward · bright clean laundry room · front-loading washing machine on the right side, partially visible · large water splash arcs behind the product, floating water bubbles across the composition · high-key commercial lighting with glossy highlights and crisp shadows · dense Japanese shopping-banner composition for an online marketplace hero image · main headline block · top-left · 3 · 洗濯機に入れるだけ！, 靴を傷めず, まるごと洗える！ · product name ribbon · left-center under headline · 1 · 靴用洗濯ネット · feature icons · left side vertical column · 3 · そのまま洗濯機へ入れるだけ, 型崩れを防いで優しく洗える, 汚れ・ニオイをしっかり落とす · award badge · top-right · 1 · 楽天ランキング, No.1, 靴用洗濯ネット, ※デイリーランキング1位 (2024年3月14日更新) · inset usage photo · bottom-left · 1 · hands opening the bag to place or show the shoes inside · color variants · bottom-center · 4 · グレー, イエロー, ブルー, ライトグレー · color count callout · bottom-right · 1 · 選べる, 4, color · グレー · gray body with light blue mesh top · イエロー · yellow body with pale trim · ブルー · bright blue body with pale trim · ライトグレー · light gray body with pale trim · Japanese · very large bold sans-serif, black and vivid blue emphasis, dynamic line breaks · royal blue, yellow, white, red-gold badge accents, green and orange feature icons · Create a polished marketplace-ready Japanese sales graphic with the product dominating the center-right, large benefit-focused headline on the left, ranking badge at the upper right, and four small color option thumbnails along the bottom. Emphasize cleanliness, protection, and washing power. Use glossy water splash effects and bubbles to imply machine washing performance. Keep the overall look premium, trustworthy, and highly clickable. · {argument name="accent color" default="blue"} · {argument name="main bag color" default="gray with light blue mesh"} · {argument name="background appliance" default="front-loading washing machine"}

Photorealistic Korean Newspaper Front Page

photograph of a printed newspaper front page · photorealistic, natural lighting, slightly angled perspective, printed on textured newsprint paper · SHINSEGAE DUTY FREE logo · {argument name="newspaper name" default="한국경제"} · 명륜진사갈비 logo with a small image of meat · {argument name="publication date" default="2026년 4월 23일 목요일"} · {argument name="main headline" default="오픈AI, 차세대 모델 'Spud' 공개 코딩·사이버전 벤치마크 석권"} · 신규 슈퍼앱 'Codex'도 출시… “AI 전쟁” 판도 바꿀 게임 체인저 될까 · promotional graphic · Introducing {argument name="app name" default="Codex"} The Super App for Everyone · 3 smartphones displaying dark mode UI · left phone showing a feature menu list · middle phone showing an analytics line chart · right phone showing a code editor with a python script · left column · mid-left · 2 · introductory article text, 코딩 벤치마크 모두 1위 · right column · mid-right · 1 · 사이버전 벤치마크도 압승 · bottom left article · bottom-left · 1 · 뉴욕증시, AI 랠리에 일제 상승…나스닥 2.7% ↑ · bottom right ad · bottom-right · 1 · {argument name="bottom ad text" default="세계 1위 메모리 반도체 기업 삼성전자"}

3x3 Black and White Photo Collage

{ "Objective": "Create a 3x3 grid photo collage with high contrast black and white aesthetics",…

48-gemini-nano-banana-ultra-realistic-coast

Use the attached reference image as a visual guide for the character’s appearance. Preserve key visu…

Educational Textbook Cover Design

人教版小学教材:{argument name="书名" default="Vibe Coding"} 一年级（上册）

Yohaku Coffee Cafe Announcement Poster

square Instagram announcement poster for a fictional Japanese coffee brand · minimal premium lifestyle design, warm beige and olive-gray palette, soft natural sunlight, calm Japanese cafe atmosphere, editorial magazine layout, elegant serif typography mixed with spaced small caps, subtle thin divider lines and botanical line art · 1:1 · 1024x1024 · warm off-white paper texture with muted gray-green and charcoal side panels · {argument name="brand name" default="余白珈琲"} · Y O H A K U C O F F E E · simple thin-line oval emblem containing a small coffee cup, a sprig, and tiny dots, placed in the upper-left olive panel · sunlit cafe tabletop still life with realistic shadows from a leafy branch · 4 · ceramic latte cup on matching saucer with rosetta latte art, centered lower-left, single slice of coffee cheesecake or tart on a beige plate with whipped cream, two coffee beans, tiny herb garnish, and a gold fork, lower-right, small clear glass vase with water and a leafy green branch, upper-right, minimal printed card or booklet partially visible in the lower-left foreground · late morning window light from upper right, long soft shadows, warm highlights, shallow editorial realism · 7 · upper-left vertical olive panel · logo plus brand name 余白珈琲 and spaced English Y O H A K U C O F F E E · left off-white vertical strip · vertical Japanese copy: 心に余白を。暮らしに、いい時間を。 with a thin vertical line · top-center · small label NEW POST with a short underline · center · large Japanese headline {argument name="headline text" default="余白珈琲"} · below headline · thin horizontal divider lines with a small center dot, followed by subheadline {argument name="subheadline text" default="一杯の余白で、日常を整える。"} · right charcoal vertical strip · vertical English text Y O H A K U / C O F F E E / T O K Y O with a thin vertical line · bottom beige footer · centered spaced text coffee / sweets / calm time with underline, plus a lower-right circular stamp containing {argument name="stamp text" default="余白が、いちばんのぜいたく。"} and a tiny botanical sprig · large headline occupies the upper middle, product photography fills the lower half, structured asymmetrical side panels frame the image, lots of negative space, delicate circular line accents near the corners · Japanese Mincho-style serif for the headline, small caps tracking for English labels, refined and airy spacing · quiet, sophisticated, restorative, suitable for announcing a new blog post or Shopify store case study for a Tokyo Nakameguro cafe goods brand · no people, no clutter, no bright saturated colors, no cartoon style, no heavy drop shadows, no distorted text, no extra logos

Bungee Jump Collage

photorealistic multi-panel adventure collage · young adult woman · long wavy medium-brown hair, face intentionally obscured with a soft rectangular blur for privacy · {argument name="shirt color" default="plain white fitted T-shirt"} · {argument name="pants style" default="light blue ripped skinny jeans"} · white low-top sneakers · black full-body bungee jumping harness with waist belt, shoulder straps, thigh straps, ankle cuffs, carabiners, safety ropes and blue bungee cord · {argument name="bungee location" default="high mountain bridge bungee platform"} · black sign reading BUNGY 207m with a downward arrow · deep green forested mountains, river gorge far below, bright midday sunlight, hazy distant ridgelines · industrial metal walkway with railings, gridded floor, beams, cables and safety equipment · vertical collage contact sheet with clean white gutters, editorial travel-documentary style · 6 · large left panel occupying about half the canvas height · three-quarter portrait of the woman standing beside the railing, one hand resting near the black BUNGY 207m sign, harness clearly visible, mountains blurred behind her · top right panel · full-body preparation scene on the metal platform, woman facing forward while two black-uniformed crew members check her harness and ropes · middle right panel · side profile of the woman standing near the platform edge, holding a harness strap, looking out over the gorge · bottom left panel · close-up portrait crop of her hair, shoulders and blurred face, emphasizing nervous anticipation · bottom center panel · tight detail shot of harness hardware at the waist and hips plus another tight detail of ankle cuffs, white sneakers and blue bungee cord on the metal floor · bottom right panel · rear view at the jump point, woman standing at the edge with arms stretched wide, harness straps and ankle attachments visible, vast green valley below · realistic DSLR photography, shallow depth of field in close-ups, crisp action-documentary framing · natural bright daylight with soft shadows · clean natural colors, white shirt and blue jeans contrasting with black safety gear and green mountains · preparation, anticipation, courage before a bungee jump · high-resolution, believable human proportions, realistic harness rigging, no cartoon or illustration style

Surreal Macro Advertising Concept: Mascara Cleanup

{ "generation_request": { "meta_data": { "tool": "NanoBanana Pro", "task_type": "text_to_image_surreal_photoreal_concept_ad", "version": "v3.0_MASCARA_CLEANUP_CLIMBER_CONCEPT", "priority": "highest" }, "output_settings": { "aspect_ratio": "2:3", "orientation": "portrait", "resolution": "ultra_high_res", "render_style": "ultra_photoreal_surreal_advertising", "sharpness": "macro_crisp_skin_texture", "film_grain": "none_or_minimal", "color_grade": "clean_editorial_true_to_life" }, "creative_prompt": { "scene_summary": "Ultra-photoreal surreal concept advertising image: extreme macro close-up of a woman's face with eyes closed, showing a dramatic smudged black mascara/eyeshadow streak running down her cheek like a stain. A tiny rope-access window cleaner / climber is scaling her cheek as if it were a giant wall, actively scraping and cleaning the mascara stain with a small squeegee and brush.\n\nThe mini climber is fully detailed and realistic: safety harness, ropes, carabiners, helmet ({argument name="climber helmet color" default="red"}), gloves, tool belt, and a small red bucket hanging from the harness. The ropes run vertically across the face, anchored out of frame, with believable tension and shadows. The climber’s scale is believable (miniature), with correct perspective and contact shadows on skin.\n\nSkin texture is hyper-realistic: pores, fine vellus hairs, subtle peach fuzz, natural highlights, and realistic makeup texture. The mascara smear has wet-to-dry texture variation with tiny flakes and glossy patches. The cleaner area shows a subtle 'wiped' path with different sheen, as if the stain is being removed.\n\nLighting: soft daylight from one side, creating gentle shadows that reveal skin texture and the climber’s depth; no harsh flash. Background is out of frame; only the face fills the composition. Mood: clever, premium, modern beauty ad concept, minimal yet striking." }, "composition": { "layout": "single frame macro close-up, face fills frame, climber placed on cheek near the smear", "framing": "eye, cheek, and partial lips visible; strong negative space avoided", "focus": "eyelashes, mascara smear, and climber tack sharp; slight falloff toward edges" }, "lighting_and_camera": { "lighting": "soft directional daylight + gentle fill", "lens": "100mm macro look", "aperture": "f/8 (macro sharpness)", "iso": "100", "shutter": "1/160" }, "hard_constraints": [ "ONE face only (female), eyes closed", "photoreal macro skin texture (pores, fine hairs)", "dramatic smudged mascara streak on cheek", "ONE miniature rope-access climber cleaning the smear", "visible ropes, harness, carabiners, tools, red bucket", "correct perspective and contact shadows", "no text, no logos, no watermark", "no extra people" ], "negative_prompt": [ "t" ] } }

Optical Illusion of Illusory Motion

image of optical illusion illusory motion

gpt2-profile-avatar-pastel-ai-assistant-anime-portrait

A dreamy anime-style portrait of a gentle virtual assistant girl named {argument name="character name" default="Misha"}, sitting curled up indoors in a cozy futuristic bedroom filled with translucent holographic memory screens. She has very long silvery white hair with a faint lavender tint, styled in 2 low twin tails tied with small lavender ribbons, with soft wispy bangs and loose flowing strands. Her expression should be tender, introspective, and slightly lonely, with a soft glow and delicate features. She wears an oversized chunky cable-knit cardigan in {argument name="cardigan color" default="pastel lavender"} draped loosely over a thin white ruffled nightdress, plus a tiny gemstone necklace. Her pose is seated with knees pulled to her chest and arms wrapped around her legs, creating a vulnerable, intimate silhouette. The room is lit in hazy pastel violet and pink ambient light with sparkles, dustlike stars, and a nostalgic magical-tech atmosphere. Around her are 5 visible holographic interface panels: 2 floating photo panels in the upper left showing soft memories, 1 lower-left panel labeled “Memory Fragments” with a small image and tiny graph bars, 1 large right-side profile panel with Japanese text including “ミーシャ・Misha” and “あなたの専属AIアシスタント,” and 1 smaller right-side checklist panel with heart icons. Include a glowing crystal ball on a desk to the right, a white mug printed with “Misha” and small heart motifs, a stack of 2 books beneath the desk area, and 1 plush cat cushion on the lower left. Composition is vertical, full-body to three-quarter seated framing, highly detailed, soft painterly anime rendering, luminous translucent overlays, sentimental memory-core aesthetic, gentle depth of field, pastel lilac palette, ethereal and emotionally warm.

Golden Hour City Street Portrait of a Supermodel

{ "model": "gemini-3-pro-image-preview", "prompt_json": { "environment": { "atmosphere": "fashion blogger vibes, sophisticated city life, trendy influencer", "background": [ "Eiffel Tower visible / NYC buildings", "historic architecture", "city bustling" ], "foreground": [ "cobblestone street", "designer shopping bags" ], "lighting": "warm afternoon sun creating flattering light, natural street lighting, golden glow on face", "midground": [ "charming cafe tables", "boutique storefronts", "fashionable pedestrians blurred" ], "setting": "trendy city street in Paris/NYC, daytime golden hour" }, "scene_type": "city_street", "subject": { "age": 20, "ethnicity": "Russian supermodel", "expression": "playful wink with mischievous dirty smile", "outfit": { "details": { "description": "satin slip dress clinging to curves" }, "type": "fashion" }, "physical": { "body": { "skin_tone": "porcelain white alabaster skin", "type": "thick voluptuous curves with big boobs" }, "eyes": { "color": "piercing ice blue captivating" }, "face": { "lips": "glossy juicy lips", "shape": "oval model face with high sharp cheekbones and defined jawline" }, "hair": { "color": "strawberry blonde", "length": "past shoulders cascading", "style": "high ponytail swinging" } }, "pose": "close-up portrait looking directly at camera, hand touching face gently" } }, "prompt_text": "Real photograph captured on iPhone 14 Pro camera by a friend during a casual outing.\n\nSUBJECT (IN SHARP FOCUS) - Stunning 20 year old Russian supermodel:\n\nFACE: oval model face with high sharp cheekbones and defined jawline, glossy juicy lips, piercing ice blue captivating eyes looking at camera, flawless porcelain white alabaster skin with natural glow, subtle makeup enhancing features, long lashes, perfect brows.\n\nHAIR: strawberry blonde, high ponytail swinging, past shoulders cascading, catching light beautifully, natural shine.\n\nBODY: thick voluptuous curves with big boobs, porcelain white alabaster skin, realistic skin texture with pores visible, natural definition.\n\nOUTFIT: Wearing satin slip dress clinging to curves.\n\nPOSE: close-up portrait looking directly at camera, hand touching face gently. \n\nEXPRESSION: playful wink with mischievous dirty smile.\n\nSETTING - trendy city street in Paris/NYC, daytime golden hour:\ncobblestone street, designer shopping bags. charming cafe tables, boutique storefronts, fashionable pedestrians blurred. Eiffel Tower visible / NYC buildings, historic architecture, city bustling.\n\nLIGHTING: warm afternoon sun creating flattering light, natural street lighti"

Lego Set Design Prompt Template

Create a Lego set for [place, movie, image reference], [type of set, adventure, architecture] set, include box and instructions

Holographic Wireframe Character Art

Transform the uploaded image into an {argument name="style" default="ultra-premium holographic wireframe artwork"}. Preserve the exact {argument name="subject details" default="face, identity, hairstyle, body position, clothing, camera angle, composition and perspective"}. Convert all visible objects into {argument name="structure type" default="glowing white wireframe structures"} made from luminous particles and digital light points. Background becomes deep pure black. Create bright neon white edge lighting around the entire subject. Add millions of floating particles, glowing dust, digital sparks, energy trails and holographic detail. High contrast monochrome aesthetic. Luxury cyberpunk advertisement style. Wet reflective ground surface. Ultra realistic lighting. Sharp focus. Volumetric glow. Studio quality. Premium poster design. Minimalist futuristic aesthetic. 8K masterpiece.

Seedance 2.0 - Spider-Man Noir

Film noir Spider-Man, Spider-Man Noir in 1930s noir detective story. He is in a shadowy cityscape, smoke缭绕, dramatic shadows, black and white aesthetic, hard-boiled detective narrative. A beautiful woman walks into his office, rain pouring outside. She tells him she's in trouble. He puts on his fedora and trench coat. They drive through the rainy city in his classic car. Noir cinematic style, black and white film grain, Expressionist shadows, dramatic angles, melancholic atmosphere, De Meyer-style lighting, f/1.8 shallow depth of field, vintage Hollywood glamour.

Retro Robot Powering Illo with Codex

Create a playful retro black-and-white technical cartoon illustration on a warm off-white paper background, in a 16:9 wide canvas. Use thick rounded black ink outlines, halftone stippling shadows, minimal cream fills, and bright hot-pink accent color. Show exactly four main objects arranged left to right: 1) a small vintage tabletop image-printing press labeled “{argument name="printer label" default="illo"}” in lowercase on its front, with a crank on the left, rollers on top, and a sheet of paper emerging from the lower front; the printed sheet contains one simple landscape picture with a black sun/circle, black mountains, and pink diagonal shading; 2) a cute small robot mascot in the center with a rounded square head, black screen face, two white oval eyes, tiny body, arms, legs, and one antenna ending in a pink circle; 3) a chunky rectangular battery/power pack on the right labeled “{argument name="battery title" default="Codex"}” with smaller text “{argument name="battery subtitle" default="subscription"}”, two top terminals colored black and pink, and a pink lightning bolt above it; 4) a small wall outlet/power block at the far right with one socket and one button-like top knob. Show exactly two visible cable connections: a hot-pink cable running from the printer’s right side to the robot’s hand, and a black-and-pink plug cable from the robot into the Codex battery; also show a black power cord with plug leading from the wall outlet. Add exactly two small pink motion marks near the plug held by the robot. Keep the composition clean and centered with lots of negative space, no extra characters, no extra labels, no watermark, and preserve the hand-drawn risograph/zine aesthetic.

AI Workflow for Novel Writing and Cover Generation

好みの画像を一枚参考にさせて ・画像を小説の表紙に見立ててタイトルを考えて ⬇ ・表紙とタイトルから内容のあらすじとチャプターを総字数{argument name="総字数" default="○○字"}想定で考案して ⬇ 各チャプターを順に執筆して

Surreal Melting Logo Generation Template

A surreal, melting logo of {argument name="brand name" default="[BRAND]"} in the style of Salvador Dali, highly detailed, photorealistic, 8k.

Live Stream App UI Mockup

side-by-side mobile UI mockup · {argument name="app style" default="Chinese mobile live streaming app"} · left · {argument name="streamer appearance" default="young Asian woman, beautiful, smiling"}, long wavy hair, holding a handwritten sign · {argument name="sign text" default="谢谢 Ray 的大火箭！"} with small rocket and heart doodles · profile info, follow button, 3 viewer avatars, {argument name="viewer count" default="10万+"} count, close button · popularity rank badge, gift gallery widget, floating gift animation showing {argument name="gift name" default="大火箭"} x1 · 7 distinct chat message bubbles · text input field, 4 action icons, floating like hearts · right · same streamer, high ponytail with scrunchie, holding a handwritten sign · {argument name="sign text" default="谢谢 Ray 的大火箭！"} with stars, hearts, and rocket doodles · app logo, LIVE badge, 12.6万 viewer count, profile info, follow button · hourly rank badge, gift goal widget, 2 floating gift animations (rocket x1, rose x10) · 6 distinct chat message bubbles · text input field, 4 action icons, follow button, floating like hearts

Noir Mirror Reflection Portrait

High-contrast black and white cinematic portrait of a man facing a mirror, reflection appearing darker and more intense, low-key lighting, sharp jawline shadows, classic noir style, ultra-realistic facial texture, cinematic framing

Codex Product Update Poster

product update marketing poster · clean modern SaaS landing-page graphic, Apple-like minimalism, soft ambient gradients, subtle shadows, rounded cards, crisp vector UI, high-end promotional design · OpenAI · 2:3 vertical · very light cool gray with faint lavender-blue glow gradients, rounded outer frame corners · header hero · top · 4 · OpenAI logo, PRODUCT UPDATE, main headline, supporting subheadline · main showcase panel · middle · 3 · Codex task card, working checklist card, dark analytics dashboard preview · feature cards · lower middle · 4 · Tackle more, Safe by default, Works with your tools, Built for teams · call to action banner · bottom · 3 · Codex is available now, Try it in ChatGPT or the API., arrow button · large floating rounded square icon near the upper right with black code brackets symbol · {argument name="eyebrow text" default="PRODUCT UPDATE"} · {argument name="headline line 1" default="Codex for"} · {argument name="headline line 2" default="almost everything"} · {argument name="subheadline" default="From small fixes to large features, Codex helps you ship faster."} · {argument name="call to action title" default="Codex is available now"} · small black OpenAI knot logo at top left · very large bold sans-serif headline on left, first line black, second line blue-to-purple gradient text · medium gray sans-serif, two lines under headline · white rounded square tile with soft shadow, containing black <> code symbol, placed upper right · large white rounded rectangle with thin border and soft shadow · 3 · small pill label with code icon and text Codex, white prompt card reading Add dark mode to the dashboard and update the settings page., status checklist titled Codex is working... · 4 · Understand codebase checked in purple, Implement dark mode checked in purple, Update settings page active/in progress with partial circular indicator, Run tests unchecked in gray · dark mode UI preview · Acme · 4 · Overview selected, Analytics, Projects, Settings · 3 · Overview heading, Active Users metric 8,421 with green +12.5% and purple line chart, Recent Activity list with 3 entries · 3 · Update landing page — 2m ago, Fix analytics bug — 1h ago, Improve onboarding flow — 3h ago · 4 · Tackle more · purple sparkle/star icon in a pale lavender rounded square · From bug fixes to multi-file refactors, Codex handles it. · Safe by default · blue shield icon in a pale blue rounded square · Runs in a sandboxed environment with read-only by default. · Works with your tools · green terminal prompt icon in a pale mint rounded square · Integrates with GitHub, CI, and your existing workflows. · Built for teams · pink group/users icon in a pale pink rounded square · Share context, review changes, and move faster together. · wide rounded rectangle with soft purple-blue gradient wash and white circular arrow button on the right · Try it in ChatGPT or the API. · balanced left-aligned typography with modular card grid below, lots of whitespace, premium tech advertisement look · sharp typography, subtle depth, gentle glassy lighting, no photographic elements

Cinematic Food Short Video Prompt (Summary)

温かみのある照明とASMR音響を重視した、4カット構成のシネマティックな料理ショート映像。マクロレンズで捉えたリズミカルな食材カットから、スローモーションのフライパン調理シーンへ滑らかに移行する。浅い被写界深度で可愛らしい手元の盛り付けを描写し、最後は完成した料理と食事の余韻で締めくくる。マッチカットやモーションブラーを駆使し、視覚と聴覚がシームレスに繋がる没入感のある演出。