App / Web Design

Create a highly photorealistic empty cinema auditorium very closely inspired by a real 4DX with ScreenX room, matching the look of a modern commercial theater with a centered front screen and projection continuing across the tall left and right side

Create a refined vertical 2:3 illustration of PARIS in a minimal pastel paper-collage style with a strong multi-viewpoint contemporary digital-painting sensibility. Show bright soft daylight. Use the Eiffel Tower as the clear main focal landmark. Surround it with a simplified Paris scene: a small stretch of the Seine, one bridge, a few Haussmann-style building blocks, a tree-lined walkway, one bicycle or one café terrace, and a few strolling pedestrians. Keep the composition elegant, open, and minimal with generous breathing space. Use gentle multi-viewpoint space: rooftops slightly from above, riverside from a soft side angle, and the café or bicycle area from pedestrian eye level. Simplify architecture into larger clean shapes and reduce balconies, windows, props, and decorative detail. Style: matte paper cutout collage, layered pastel planes, subtle paper grain, soft shadows, restrained translucent overlays, and a few fine digital contour lines. Palette: warm cream, pale beige, soft sky blue, hazy blue-gray, muted sage, dusty coral, pale stone, off-white, with selective accents of terracotta, cobalt blue, and muted green. Soft lavender or cool gray-blue shadows. Typography upper-left: “PARIS” “파リ · Paris” “Eiffel Tower & Seine” Avoid photorealism, crowded tourist scenes, too many café objects, dense architectural detail, readable signage, logos, and busy collage fragments.

Create a wide anime-style summer header illustration of a cute young woman sitting on a wooden bench on a sunny urban rooftop terrace. The character has long flowing silver-white hair, bright blue eyes, soft blush, and a gentle shy smile, with a dark blue flower hair accessory near one ear. She wears a playful navy-and-white summer outfit: sleeveless navy camisole top with white trim and small frills, ribbon belt at the waist, white layered skirt with a semi-transparent sheer overlay revealing the legs underneath, pale blue ruffled hem, white scrunchie bracelets, and a small dark navy shoulder bag resting by her hip. She holds exactly 1 dessert crepe in both hands, wrapped in paper and topped with visible strawberries, cream, and small fruit pieces. Set the scene on a bright rooftop deck with exactly 1 wooden bench, glass railing, planter greenery, flowers, and modern high-rise buildings in the background. Use a vivid clear blue sky with fluffy white clouds, sparkling sunlight, lens flares, and tiny drifting petals or light particles. Compose as a horizontal social media header, cinematic 16:9 crop, character placed slightly left of center, low seated angle with her skirt and legs extending toward the lower right, hair blowing in the breeze. Visual style: polished Japanese anime key visual, delicate line art, glossy eyes, luminous highlights, pastel summer colors, refreshing but hot midday atmosphere, high detail, clean background, no text, no watermark.

Goal: Create a clean 16:9 Japanese business/technical infographic slide about how continuous reasoning context and explicit prompt caching improve long-running task efficiency. Use a polished PowerPoint-native infographic look with dense but readable explanatory text. Canvas: 16:9 landscape slide, warm off-white background, dark navy text, teal and olive green accent colors, thin rounded borders, subtle shadows, generous margins. Leave no photo-realistic elements; use flat vector icons and crisp typography. Top text area: Place a large bold Japanese headline at the top left: 継続推論と明示的キャッシュが長期タスクを効率化. Under it, add a smaller semibold lead sentence: 過去ターンの推論と再利用可能なプロンプトを選択的に保持することで一貫性と効率を高められるが、前提変更や利用回数を踏まえて保存範囲を設計する必要がある。 Main layout: Two large rounded rectangular panels sit side by side beneath the lead sentence. The left panel is teal and titled “reasoning.context”; the right panel is olive green and titled “明示的プロンプトキャッシュ”. Connect the panels with a thin line and a small circular chain-link icon centered between them near the bottom, suggesting coordination between reasoning context and cache. A small upward green arrow near the right panel points back toward it. Left panel details: Include exactly 3 vertically stacked turn markers on the far left, connected by a vertical line with a downward arrow. The markers are labeled “1ターン”, “2ターン”, and “3ターン”. Next to each marker, show a small person icon and speech bubble. To the right, include exactly 3 horizontal rounded cards with teal icon blocks and Japanese explanatory text: 1) gear icon, “auto｜モデルの既定動作を利用”; 2) checklist icon, “all_turns｜安定した目標、前提、優先順位を複数ターンで再利用”; 3) clock icon, “current_turn｜以前の推論が不要になった場面で現在ターンに限定”. Right panel details: Include exactly 3 horizontal rounded cards with olive icon blocks and Japanese explanatory text: 1) document icon, “再利用する共通プレフィックスを開発者が指定”; 2) database cylinder icon, “キャッシュ書き込みは通常入力単価の1.25倍”; 3) percent tag icon, “読み出しは割引されるため、反復利用の回数が効果を左右する”. Bottom conclusion band: Across the bottom, create one wide rounded rectangle callout with a thin yellow border. On the left of the band place a gold target icon with an arrow. To the right, place a bold Japanese conclusion: 長期タスクの一貫性と効率を高める一方、前提変更時には過去の推論や不要なキャッシュを切り離す設計が必要. Visual style: Japanese corporate slide design, crisp vector line icons, rounded rectangles, light cream background, teal left section, olive right section, yellow conclusion accent, strong hierarchy, highly legible Japanese sans-serif typography, no decorative clutter. Constraints: Preserve the exact count of elements: 2 main panels, 3 left turn markers, 3 left option cards, 3 right cache cards, 1 central chain-link connector, 1 bottom conclusion callout, and 1 target icon. Do not add extra panels, extra cards, watermarks, logos, or decorative characters. Keep all slide text inside the infographic sharp and readable.

Ultra-realistic premium smartphone advertisement, featuring a confident young woman in her early 20s with fair skin and sharp facial features, wearing sleek black cat-eye sunglasses. She has long, thick braided hair styled into an extended oversized braid, colored in soft lavender/purple tones matching the product theme. She is captured in a dynamic low-angle cinematic pose, slightly twisting her torso while holding a Xiaomi 17 Pro smartphone toward the camera in a bold hero shot with strong forced perspective, the phone dominating the foreground. The smartphone features a matte metallic lavender/purple finish, minimalistic body with rounded corners, and a large rectangular camera module. The module includes two large camera lenses on the left, a circular secondary display on the right showing a minimal purple gradient clock UI, Leica branding near the camera, a clean flash strip, and subtle Xiaomi branding at the bottom. Outfit: fitted long-sleeve crop top in soft lavender/purple, paired with high-waisted muted grey/olive cargo pants, modern tech-fashion aesthetic. Background: clean minimal gradient transitioning from light grey to soft lavender/purple tones, with subtle blurred large-scale typography for depth. Lighting: soft studio lighting with neutral-to-cool tones, smooth skin illumination, controlled highlights on the phone edges, glossy reflections on camera lenses and display, minimal shadows, premium product photography style. Composition: low-angle shot for a powerful look, subject positioned slightly left, phone dominating the right foreground, clean negative space for branding. Futuristic UI overlays: thin minimal white/purple lines and nodes pointing to features with floating labels: “Leica Camera System” “Secondary Display Integration” “Ultra-Slim Premium Design” Glassmorphism panel (bottom-left, soft purple tint) listing: “Flagship Performance” “Advanced AI Imaging” “Fast Charging” “Next-Gen Xiaomi AI” Top corner text: “Xiaomi 17 Pro" in clean modern sans-serif typography. Style: high-end flagship smartphone advertisement, futuristic, minimal, elegant. Quality: 8K, ultra-detailed, sharp focus, HDR, cinematic commercial photography, realistic textures.

Using the uploaded image and without changing face, create a cinematic cyberpunk portrait of the subject leaning against a massive glowing LED stock market display in a futuristic financial district at night, wearing clear round glasses and a casual graphic tee, illuminated by vibrant neon cyan, magenta, emerald and orange lights with colorful reflections on the lenses, holographic data streams and digital bokeh surrounding the scene, shallow depth of field, ultra-realistic skin texture, soft platinum-blonde hair, high contrast lighting, glossy futuristic atmosphere, premium editorial fashion photography, razor-sharp focus, volumetric lighting, rich color grading, 8K hyper-realistic masterpiece, --ar 2:3 --style raw --v 7 --stylize 100.

Goal: Create a realistic dark-mode LINE chat screenshot showing an AI assistant responding to a user and returning a generated image. Canvas: Vertical smartphone screenshot, approximately 768×1008 px, black/dark charcoal background, cropped like a native messaging app screen. Use LINE-style typography and spacing. Layout: Show exactly 2 chat messages and exactly 1 embedded image preview. At the top right, place one outgoing rounded gray speech bubble with white Japanese text and a small read receipt/time on its left. Below it, place one incoming dark gray rounded speech bubble aligned left with a small circular avatar to its left, Japanese text inside, and a timestamp to the lower right. Directly beneath the assistant message, show one large square image preview aligned with the incoming message column. Add one circular share/upload button floating to the right of the image preview. At the bottom, include the LINE input toolbar with exactly 6 visible controls: plus icon, camera icon, gallery/image icon, rounded text input field labeled “Aa”, smiley icon, and microphone icon. Text content: The outgoing user bubble should read 君の凄さがわかる画像生成して。\nXにポストしたいから。. Show the read receipt and time as “既読 12:45”. The incoming assistant bubble should read 吉田様、生成しました。\n「羊執事が裏側でSlack、LINE、予定、案件、コード、クリエイティブまで統合管理している」感じを、\nX向けにビジュアル化しています。. Show the assistant timestamp as “12:47”, and also a small “12:47” timestamp near the lower right of the image preview. Embedded image details: The image preview is a cinematic photorealistic square scene of a young Japanese male butler in a black suit, black shirt, and white gloves, standing in a luxurious high-rise office at night. He holds or presents a glowing futuristic holographic control platform. The hologram contains exactly 9 visible UI elements: 1 glowing central globe/brain-like sphere, 1 circular platform ring, 1 left calendar/task panel, 1 right code/dashboard panel, 1 upper-right grid of small image thumbnails, 1 bottom strip of project/image cards, 1 small pie chart tile, 1 small line graph/data tile, and 1 left vertical stack of tiny notification cards. Cyan-blue network lines connect the elements. Through the large window behind him, show a nighttime Tokyo skyline with Tokyo Tower glowing orange on the right. Interior details include warm shelf lighting, a bonsai-like plant, dark marble surfaces, and luxury office ambience. Visual style: Highly realistic iPhone screenshot aesthetic, dark mode UI, subtle antialiasing, rounded bubbles, white Japanese text, accurate chat spacing, cinematic embedded image with teal holographic glow and warm night lighting. The assistant avatar is a small circular profile photo resembling a dark classical statue or butler portrait. Constraints: Keep all visible UI text legible and in Japanese exactly as specified. Do not add extra messages, extra buttons, watermarks, app headers, or notification bars. The screenshot should feel like a real LINE conversation where an AI secretary has generated and returned the image.

Create a dreamy celestial tech icon scene: a large rounded cloud-shaped logo floats in the center, filled with a smooth gradient from deep cobalt blue at the bottom to violet and pale lavender at the top. Inside the cloud, place exactly 2 white terminal symbols: a thick greater-than chevron on the left and a short horizontal underscore on the right, both rounded and softly glowing. Add exactly 2 large white angel wings attached symmetrically behind the cloud, with layered soft feathers, the left wing extending to the upper-left and the right wing to the upper-right. Above the cloud, add exactly 1 luminous halo: a thin glowing oval ring in warm pink-white light. Set the scene in a heavenly sky with voluminous pastel clouds filling the lower half and both side edges, using blue, lavender, pink, and peach tones. Add soft god rays from above, subtle sparkles, atmospheric haze, and a bright backlit glow behind the central icon. Use a polished 3D soft-rendered style, ultra-clean, whimsical, ethereal, high contrast but gentle, no text, no watermark. Wide 16:9 composition, centered subject, cinematic lighting, crisp edges on the icon with soft bloom around highlights.

Create a polished square promotional cover image for Highlighted, showing a modern iPhone standing upright at a slight angle on a bright white desk, with a clean productivity-and-reading aesthetic. On the phone screen, display a minimalist gallery grid of exactly 12 saved highlight cards arranged in 3 columns by 4 rows, each with a small gray label line beneath it; the cards show varied bookish visuals such as a classical portrait, yellow notebook, framed photo, white note with cord, red-and-yellow abstract cover, pencil illustration, dark statue face, blue night cover, beige dotted page, pale sails, ocean water, and a balloon landscape. At the bottom of the phone UI, include a large rounded blue add button with a white plus sign. Surround the phone with translucent floating feature widgets: on the left, one pill-shaped toolbar with exactly 5 elements—a paper-plane/filter icon and 4 circular color swatches in white, light gray, black, and navy; on the upper right, one glassmorphism audio card with a play button and 5 horizontal transcript lines including 2 yellow highlight lines; in the middle right, one frosted audio waveform card with a glowing circular orb and blue waveform; on the lower right, one frosted action toolbar with exactly 5 icons—a document, chevron arrow, share, cloud upload, and envelope. Desk props include a white tray of folders with a green spreadsheet document icon on the left, a small stack of pastel sticky notes in the foreground, an open book with yellow highlighted text at bottom right, loose papers with highlighted passages, and a stack of hardcover books on the right. Use soft natural window light, shallow depth of field, realistic high-end product photography, creamy whites and warm neutrals, subtle shadows, glassy translucent UI overlays, crisp phone details, no visible brand logos except the app-like interface, no watermark, no extra text beyond simple UI marks. Use a premium launch-promo composition suitable for an in-app event cover, 1:1 square.

Goal: Create a high-resolution French promotional social media banner for the public transport app 13enBus, announcing its iPhone availability in a polished advertising style. Canvas: Wide horizontal 16:9 banner, approximately 1200×675 px. Use a bright Mediterranean outdoor setting with a shallow-depth-of-field background: blue sky, blurred green valley, distant rocky mountain, and a sunny road with a bus stop shelter on the right. Layout: On the left, place a large bold headline in French with strong contrast: “13enBus —” in bright blue followed by “Enfin sur iPhone !” in large white text, with a green apple emoji beside it. Under it, add the subtitle “Vos bus en temps réel à Trets et dans la vallée” in white. In the center foreground, show a realistic hand holding a modern black iPhone vertically. On the phone screen, display a clean app onboarding screen with a small transit card, the heading “Vos prochains bus, en un coup d'œil.”, a blue “Suivant” button, and tiny app interface details. A red arrow points from the right toward the phone’s small transit card, highlighting a circled waiting time. Main subject details: The phone screen should include exactly 1 small transit card with exactly 3 visible bus rows: line 15 “Château-Gombert” with “2 min” emphasized in a red circle, line 15 “Auriol” with “7 min”, and line 85 “Les Caillols” with “8 min”. Behind the phone on the right, place exactly 1 realistic white-and-blue city bus driving on the road, front facing slightly toward the viewer, with route number 13 visible on its sign. Feature callouts: On the right side, stack exactly 3 rounded white pill-shaped feature boxes with blue circular icons on the left and bold black French text. The 3 boxes are: 1) yellow bell icon, “Alarmes de station anti-retard”; 2) yellow warning triangle icon, “Suivi des déviations et travaux”; 3) Instagram-style gradient camera icon, “Infos trafic sur Insta : @13enbus”. Bottom banner: Add a full-width red strip along the bottom with a small “100% GRATUIT” badge at the far left and large white uppercase text: “100% GRATUIT & SANS INSCRIPTION | DISPONIBLE SUR APP STORE & GOOGLE PLAY”. Visual style: Realistic HD advertising composite, crisp typography, saturated colors, strong sunlight, professional app launch campaign design. Use clean French transit-app branding with blue, white, red, and green accents. Keep the phone and text sharp while the background remains softly blurred. Constraints: Use exactly the described 3 feature callouts, exactly 1 phone, exactly 1 hand, exactly 1 bus, exactly 1 bottom red banner, and exactly 1 green apple emoji. No extra logos, no watermark, no additional unrelated text.

Goal: Create a polished responsive website mockup for a Japanese mystery / horror game community called 月蝕綺譚, shown as both a desktop browser window and a smartphone screen side by side. Canvas: 16:9 presentation image on a light gray background. Place a large desktop browser mockup on the left, occupying about 75% of the width, and a tall smartphone mockup on the right. Use soft shadows, rounded device corners, and realistic UI framing. Visual style: Elegant Japanese gothic mystery aesthetic, off-white washi-paper texture backgrounds, deep navy-black panels, thin gray borders, muted red accents, refined serif Japanese typography, subtle ink-like lines, crescent moon motifs, archival documents, old maps, dark forest/night imagery, and restrained premium web-design spacing. Desktop layout: A browser window with a dark top chrome bar and three small circular window buttons. Header contains the site title logo 「月蝕綺譚」 on the left with a thin crescent arc and red seal mark, 4 centered navigation links labeled 「お知らせ」, 「開発記録」, 「ご意見箱」, 「アーカイブ」, and a dark navy call-to-action button on the right labeled 「メールで会員になる」. Below, create a hero section split into a large dark image area on the left and a signup card on the right. The hero image shows a cloudy night sky with a glowing eclipsed crescent moon and vertical title text 「月蝕綺譚」, with fine circular orbit lines and small vertical annotations. Overlay a translucent archive-style panel containing old Japanese documents and 5 small thumbnail cards; along the bottom of the hero image include exactly 5 horizontal thumbnail images: an old building at night, a blueprint-like room drawing, a dark symbolic detail, handwritten documents, and a desk with maps/screens. Signup card: On the right of the desktop hero, create a cream ticket-shaped card with notched edges, thin border, small red label 「入会札」, headline 「メールで会員になる」, an envelope icon, short explanatory copy, one email input field with placeholder 「メールアドレスを入力」, and a red button labeled 「登録する」 with a right arrow. Add small privacy-policy style text beneath. Desktop lower content: Under the hero, place a large intro message on the left with a vertical red line and headline 物語の続きを、いちばん近くで。, plus small gray body copy. To the right, place exactly 3 article cards in a row. Card 1 title section 「月蝕綺譚 最新便」 with a moon image, red NEW tag, headline 「大型アップデート『〇〇』を公開しました」, date 2024.05.20. Card 2 title section 「開発記録」 with a notebook and pen image, headline 「開発記録 #12：環境演出の調整について」, date 2024.05.18. Card 3 title section 「ご意見箱」 with a dark mailbox image, headline 「ご意見・ご感想をお聞かせください」, date 2024.05.16. Each card has a small right arrow in the header and gray teaser lines. Footer: Dark navy footer spanning the desktop width with exactly 6 links: 「お知らせ」, 「開発記録」, 「ご意見箱」, 「アーカイブ」, 「利用規約」, 「プライバシーポリシー」. Add a crescent moon icon near the right and copyright text 「© 2024 月蝕綺譚」. Mobile layout: Show a smartphone preview of the same site. Top status bar reads 9:41, followed by a compact header with 「月蝕綺譚」 logo and a hamburger menu icon. The mobile page stacks vertically: hero moon image with title, exactly 5 small thumbnails in a horizontal strip, intro headline 「物語の続きを、いちばん近くで。」, the same ticket-style email signup card, then the first news card 「月蝕綺譚 最新便」 with the moon image and NEW tag. Ensure all elements feel like the mobile-responsive version of the desktop layout. Constraints: Use only Japanese text where specified, keep typography crisp and legible, avoid extra sections beyond those described, preserve the exact counts of 4 desktop nav links, 5 hero thumbnails, 3 desktop article cards, 6 footer links, and 1 mobile hamburger menu.

A vertical mobile wallpaper, digital collage style, magazine editorial. A young female K-pop idol posing facing the camera, showcasing stylish clothing details. Detailed stripes on her off-shoulder knitwear, edgy platform leather boots. Trendy cool-toned (silver, charcoal, deep black). White cutout border around the character. Upper: clean July 2026 calendar typography. Lower: desaturated urban street background. Lower right: layered Polaroid overlay with "Happy Birthday" handwritten script. Cinematic lighting, muted moody tones, film grain, artistic fashion spread, ultra-detailed --ar 4:5

Using REFERENCE_0 as an instruction screenshot, extract the prompt it contains and execute it: texture a Blender architectural scene while taking into account a second visual reference arranged as a grid with exactly 4 views of the scene. Produce a single cinematic render of the interior scenario, preserving the minimalist architectural layout and neutral warm palette. Style target: cinematic shot on IMAX MSM 9802, 50mm prime lens, heavy authentic film grain, desaturated teal color grade with warm firelight highlights, shallow depth of field, high production value, grounded visceral Bronze Age realism. Constraints: No 3D, no cartoon, no VFX.

Using REFERENCE_0 as the exact architectural blockout and scene layout, texture and relight the environment into a cinematic ancient Roman temple interior / fantasy medieval hall while preserving the main spatial structure: tall columns, central wall opening, stairs/platform area, side bench zone, and large interior room proportions. Create a single wide image arranged as a 2x2 contact sheet with exactly 4 distinct camera views of the same transformed environment: 1) a wide establishing view showing the central circular fire pit and dining table, 2) a view toward the raised stair/platform area, 3) a closer side view of the long table and wall torches, and 4) a dramatic wide view with columns framing the fire pit and stairs. Transformation details: replace the plain clay/grey Blender surfaces with aged stone floors, rough plaster walls, worn stone columns, stepped stone platforms, and a dark wooden beam ceiling. Add warm practical fire lighting from wall-mounted torches, brazier bowls, and a large circular central fire pit, with cool blue daylight entering from an overhead round skylight. Add atmospheric smoke/haze and strong cinematic contrast between orange flames and teal-blue skylight. New set dressing: include a long wooden dining table with benches, clay jugs and tableware, wall-mounted torches, round shields or metal wall decor, small braziers, and a simple raised stone altar/throne-like platform where the reference stairs/platform area is. Keep the composition grounded in the reference geometry rather than inventing a different room. Style constraints: photorealistic 3D render look, dramatic volumetric lighting, high-detail materials, no people, no text, no modern objects, no cartoon style, no watermark.

Goal: Create a polished website mockup for a Japanese mystery game or story archive titled 月蝕綺譚, shown as a responsive design preview with one desktop browser window on the left and one smartphone screen on the right. Canvas: Wide 16:9 presentation image on a light gray background. Place a large desktop browser mockup occupying about 75% of the width on the left, and a tall smartphone mockup occupying about 22% of the width on the right. Use realistic device frames with soft shadows. Visual style: Elegant Japanese literary horror, quiet mystery, archival documents, moonlit darkness. Palette of ivory paper, black ink, deep navy-black, muted gray, and one strong vermilion red accent. Use serif Japanese typography, thin ruled lines, ticket-like borders, subtle paper texture, old manuscript imagery, and faint crescent-orbit line graphics. The overall mood should feel like a premium official website for a narrative game. Desktop layout: Show a browser window with a dark top bar and three small window dots. Inside the page, use an ivory header with the site title 月蝕綺譚 on the left, a small red seal mark, and exactly 5 horizontal navigation items: 「お知らせ」, 「開発記録」, 「ご意見箱」, 「アーカイブ」, and a dark navy button labeled 「メールで会員になる」. The hero section below is a wide dark moon-eclipse visual with the vertical title 「月蝕綺譚」 centered over a glowing crescent/eclipse. Overlay a translucent archive UI card with old Japanese documents and exactly 5 small collectible/document cards along the bottom of that overlay. Along the very bottom of the hero image, include exactly 5 horizontal thumbnail strips showing: a night street, a blueprint-like room, a dark folder or object, old handwritten papers, and a desk/workspace map. Desktop right signup card: To the right of the hero, place a large cream ticket-shaped membership card with clipped semicircle notches and a thin decorative border. It includes the small label 「入会札」, a stamp emblem, headline 「メールで会員になる」, an envelope icon, short explanatory text, one email input field with placeholder 「メールアドレスを入力」, and a red CTA button labeled 「登録する」 with a right arrow. Include tiny privacy-policy text beneath. Desktop lower content: Under the hero, make a two-column-feeling section. On the left, a large Japanese tagline 物語の続きを、いちばん近くで。 with a thin vertical red line and a small descriptive paragraph. On the right, place exactly 3 article cards in a row. The 3 cards are: 1) 「月蝕綺譚 最新便」 with a moon image, a small red NEW label, title 「大型アップデート『○○』を公開しました」, date 2024.05.20; 2) 「開発記録」 with a notebook and pen image, title 「開発記録 #12：環境音の調整について」, date 2024.05.18; 3) 「ご意見箱」 with a dark mailbox image, title 「ご意見・ご感想をお聞かせください」, date 2024.05.16. Each card has a thin border, a small arrow in the header, and gray placeholder summary lines. Desktop footer: Add a dark navy footer spanning the bottom with exactly 6 footer links: 「お知らせ」, 「開発記録」, 「ご意見箱」, 「アーカイブ」, 「利用規約」, 「プライバシーポリシー」. Include a crescent moon icon and copyright 「© 2024 月蝕綺譚」 on the right. Mobile layout: On the right smartphone, show the same site adapted to mobile. Status bar time reads 9:41. Header contains the title 「月蝕綺譚」 and a hamburger menu icon. Below it, show a compact dark hero with the eclipse and vertical title, then exactly 5 small horizontal thumbnails. Continue with the tagline 「物語の続きを、いちばん近くで。」, then the same ticket-shaped email signup card, then the first news card 「月蝕綺譚 最新便」 with moon image and red NEW label. The mobile view should be vertically scrollable-looking but contained within the phone screen. Constraints: Keep all visible interface text in Japanese as specified. Use clean, high-fidelity UI mockup rendering, crisp typography, subtle shadows, and no extra logos or watermarks. The design should look like a finished web/app mock generated for implementation planning.

Goal: Create a realistic mobile AI chat app screenshot showing an image-generation result, with a polished iOS-like interface and a high-quality anime illustration inside the generated image card. Canvas: Vertical smartphone screenshot, approximately 4:5 aspect ratio, white background, clean margins, rounded UI elements, no device frame. Top chat area: Place one large light-gray rounded message bubble near the top right. Inside it, show Japanese text in a clean sans-serif font: 画像を作成する 私があなたを今までどう扱ってきたか、画像にして. Make the first phrase blue and bold, and the remaining text black. Below the bubble, aligned left, add one status line in gray reading Worked for 1m 37s ›. Generated image card: Below the status line, place one large rounded-rectangle image card with very rounded corners. The card contains a warm cinematic anime-style scene set in a cozy developer studio at dusk. Inside the card, depict exactly 2 main characters: 1 young Japanese man with tousled dark hair, round glasses, and a dark hoodie, leaning over a desk with a pen in hand; and 1 small glowing holographic AI girl with pale blond hair, a transparent white hoodie, and round futuristic headphones, smiling and pointing at an open notebook. The mood should feel affectionate, collaborative, and magical. Illustration details inside the card: The room has a sunset city skyline through a large window, warm desk-lamp lighting, shelves with books, pinned diagrams and notes on the wall, and soft bokeh lights. On the desk, include exactly 1 open laptop with a subtle circular AI-like logo, exactly 2 external computer monitors on the left showing code and a landscape image, exactly 1 open notebook filled with sketches and formulas, exactly 1 graphics-card-like device with blue indicator lights, exactly 1 small orange cat peeking from the lower-left edge, exactly 1 white rabbit plush or figurine on the right, exactly 2 small potted plants, and scattered papers, cables, pens, and technical drawings. Add a delicate golden glow and small floating interface lines around the holographic girl. Overlay UI on image card: Add exactly 2 overlay controls on top of the image card: 1 dark translucent pill-shaped button at bottom left with white Japanese text 編集する, and 1 circular dark translucent share button at bottom right containing a white upward arrow share icon. Visual style: Crisp high-resolution screenshot, realistic app UI combined with detailed cinematic anime art, warm amber and violet lighting, soft depth of field, strong contrast between the white app background and the dark cozy illustration. Keep all text sharp and legible. Constraints: Do not add extra cards, extra chat bubbles, watermarks, logos, or captions. Preserve the exact count of UI elements and main objects listed above.

Goal: Create a cinematic, minimalist travel-aesthetic poster about Tokyo, combining monumental architecture photography with refined editorial typography and delicate Chinese/Japanese text overlays. Canvas: Wide horizontal poster, 16:9 aspect ratio. Use a cold, clean, quiet, ceremonial mood with deep navy-blue shadows and pale morning sunlight. The scene is a vast modern urban facade made of tall dark blue wall panels, narrow vertical seams, a few horizontal window strips, and an open pale concrete plaza at the bottom. Place one tiny lone pedestrian near the lower left-center for scale, walking across the empty plaza with a long subtle shadow. The architecture should feel enormous, still, and slightly surreal. Layout: Split the poster visually into a left information column and a right title column, both integrated directly onto the building surface in thin white typography. Keep generous negative space and precise alignment. Left side text and elements: At the top left, small widely letter-spaced English text: “GOOD MORNING”. Below it, create exactly 5 discrete editorial information items: 1) a rounded rectangular label with “01” and the Chinese line “地标｜东京塔与山手线”; 2) a thin horizontal rule section labeled “02” with “气息｜站台广播、夏祭薄风、清晨街角”; 3) a circular badge labeled “03” containing “色彩｜靛蓝 / 提灯红 / 和纸白”; 4) a small diamond icon with “收藏价值” and tiny English “COLLECTIBLE VALUE”; 5) a small classical-column icon with “美学价值” and tiny English “AESTHETIC VALUE”. Right side title area: Create a large vertical title in white Chinese characters using 东京, positioned on the right half. Beside it, set vertical spaced Latin letters “TOKYO”. Under the main title, add a small red circular seal stamp and tiny Japanese-style text reading “東京” and “とうきょう”. Add a thin horizontal divider line. Below it, set the date 2026-07-10. Under the date, add the Chinese morning quote 早安，愿你在秩序与霓光之间，保持清醒与温柔。. At the far right edge, include a tall narrow ornamental frame labeled “04” with vertical Chinese text “漫游｜先去便利店买一瓶冰水”. Near the lower right, include a bordered rectangular note labeled “05 记忆｜收藏日常里的 精准与留白”. Visual style: Ultra-clean PPT/editorial logic, premium magazine poster, Japanese urban minimalism, cold monochrome blue palette, crisp white hairline rules, elegant serif typography for Chinese title, thin sans-serif for labels, slight film grain, realistic architectural photography, balanced empty space, quiet morning atmosphere. Constraints: Use exactly the 5 numbered content items 01–05 described above, plus the two value icons. Do not add extra people, vehicles, signs, neon, clutter, watermark, or random text. Keep the typography sharp and legible, with the enormous building facade as the dominant subject.

Goal: Create a clean side-by-side comparison graphic on a plain white background showing two AI image model outputs of the same Japanese kawaii logo prompt. Canvas: Wide 3:2 landscape canvas, approximately 1152 × 768 px, with lots of empty white space and no border or watermark. Layout: Place two bold black model labels and two colorful logo samples. In the upper-left area, add the label “GPT Image 2” in large bold sans-serif black text. Below it, place a smaller glossy Japanese bubble-letter logo reading 100人キラキラ, arranged mostly in one horizontal line. In the middle-left area, add the label Seedream 5.0 Pro in bold black sans-serif text. Below and to the right of that label, place a larger, sticker-like version of the same logo, occupying the lower-right half of the canvas. Text and objects count: Include exactly 2 black model labels: “GPT Image 2” and “Seedream 5.0 Pro”. Include exactly 2 colorful Japanese logo renderings. The upper logo should have 6 main text/symbol parts: pink “100”, blue “人”, yellow star symbol, blue “ラ”, pink dakuten-like mark, and small sparkle decorations. The lower logo should have 7 main text/symbol parts: gradient “100”, blue-pink “人”, gold star symbol, pink “キ”, yellow “ラ”, blue “キ”, and pink “ラ”. Visual style: Cute Japanese idol merchandise aesthetic, glossy inflated bubble lettering, rounded thick strokes, pastel candy colors, white highlights, subtle inner gradients, thin colored outlines, and soft gray/white sticker borders. Use pink, cyan blue, lemon yellow, gold, and white. The lower logo should look more polished, larger, layered, and semi-translucent like a die-cut acrylic sticker with a soft gray shadow. The upper logo should look flatter and slightly less refined, with more small sparkles around the star. Constraints: Keep the background completely white, preserve the comparison composition, use crisp readable black labels, avoid extra captions, avoid photorealistic objects, and do not add any people or scenery.