Character Selection Screen Generation

Dark Chat Anime Generation Screenshot

Goal: Create a dark-mode chat/app screenshot showing an AI image generation result for {argument name="character name" default="Astra"}, with a polished anime illustration embedded in the conversation. Canvas: Square 1:1 screenshot, approximately 920×920 px, black background, lots of negative space on the right and lower areas. Use a realistic mobile/desktop chat UI aesthetic with clean spacing and soft rounded elements. Layout: Place 3 main UI elements: 1 rounded gray user message bubble near the upper right, 1 small generation status line above the image on the left, and 1 large rounded-corner image card below it on the left. Under the image card, add 3 small action icons in a row: copy icon, share/upload icon, and ellipsis menu. Inside the image card add 2 small overlay controls: a gray rounded “edit” pill at bottom left and a circular download/share icon at bottom right. Text content: The user bubble must read exactly 「重音テトのイラスト出して　素晴らしいやつ」. The status line must read exactly 「1m 10s考えました ›」. The image overlay button must read exactly 「編集」. Keep all text crisp, white or light gray, in a modern sans-serif UI font. Image card subject: A high-quality clean anime illustration of {argument name="anime character" default="Kasane Teto"}, shown from about mid-thigh up on a rooftop at sunset. She is a youthful anime girl with vivid {argument name="hair color" default="red"} hair in two large drill twin-tails, red eyes, a small confident smile, and a slight over-the-shoulder pose looking at the viewer. Outfit: black sleeveless school-idol style top with red trim, matching black pleated skirt with red accents, long black arm warmers, and a red necktie being held lightly in one hand. The wind lifts her tie and hair ribbons slightly. Background inside image: Rooftop railing in the foreground, distant city skyline silhouettes, warm orange-pink sunset sky with scattered soft clouds and the sun low near the horizon. Lighting is soft and cinematic with smooth cel-shaded anime rendering, clean linework, subtle gradients, no gritty artifacts, no harsh malformed highlights, and no painterly blotches. Visual style: The surrounding chat UI should look like a real screenshot in dark mode. The anime image should have rounded corners, about 400 px wide and 600 px tall, placed around x=98 y=162, with a 28 px corner radius. Keep the UI minimal and do not add extra messages, watermarks, timestamps, or labels beyond the specified text.

AI Generation UI with Anime 3x3 Storyboard

Goal: Create a clean social-media screenshot of an AI image generation interface showing a completed anime music-video storyboard request and its 3x3 output grid. Canvas: Horizontal screenshot, approximately 1200x884 px, white/light-gray background with lots of empty margin. Use a modern minimal web-app UI style with rounded cards, soft shadows, and gray system text. Top area: Near the upper center, show one rectangular reference image preview with a subtle shadow. The preview contains an anime character: a short-haired androgynous young person with {argument name="hair color" default="dark ash-brown bob haircut with straight bangs"}, pale skin, thin round glasses, one eye closed in a wink, one blue visible eye, wearing a white high-collar ceremonial robe with necklaces and a red tassel. Behind them is a dark fantasy cathedral city with a glowing golden circular arch and a blue vortex moon-like sky. Prompt bubble: Below the preview, place a wide black rounded speech bubble with white Japanese text, reading exactly {argument name="prompt text" default="このキャラクターのボカロmvの様々なカットを3x3で出力して 16:9　トンマナ合わせて"}. The bubble should span most of the center width and have large rounded corners. Status text: Under the bubble, aligned left above the output grid, add gray text reading {argument name="status text" default="Worked for 1m 7s"}. Output grid: Show exactly 9 cinematic panels arranged in a 3 columns by 3 rows grid, inside one large rounded rectangle with clipped rounded corners. Each panel is 16:9, separated by thin white grid lines, all sharing the same tone: dark blue, black, white, and warm gold, glossy anime/Vocaloid MV aesthetic, dramatic lighting, cathedral ruins, floating feathers or sparkles, wet reflective floor, glowing golden ring, blue vortex sky. The 9 panels are: 1. Top-left: frontal bust shot of the character under the glowing golden arch, calm expression, glasses, white robe. 2. Top-center: side-profile close-up with hair blowing, eyes closed, blue lights in the dark cathedral background. 3. Top-right: dynamic three-quarter shot, character extending a white sleeve toward the viewer, golden arch and blue vortex behind. 4. Middle-left: low-angle wide shot, character leaning or reaching forward with billowing white sleeves, cathedral towers around them. 5. Middle-center: full-body centered shot standing on a reflective wet floor, framed by a tall archway and distant glowing ring. 6. Middle-right: close shot of character reaching a hand toward the camera, one eye closed, foreshortened hand in foreground. 7. Bottom-left: rear wide shot of the character walking into the cathedral environment beneath the glowing arch. 8. Bottom-center: emotional close-up, character with eyes closed and hands near mouth or chest, surrounded by blue sparkles. 9. Bottom-right: very wide establishing shot of ruined gothic towers, glowing circular arch, blue vortex sky, tiny figure or distant character. Overlay controls: Add exactly 3 circular interface controls over the lower part of the grid: a dark circular button at bottom-left labeled {argument name="edit button text" default="編集"}, a light gray circular download button with a downward arrow near the lower center-right, and a dark circular share button with an upward arrow at bottom-right. Style constraints: The whole image should look like a real captured web UI, not a poster. Keep the interface text crisp, the grid slightly cropped by the bottom edge of the screenshot, and the anime panels high-detail, cinematic, consistent in character design and color grading.

Surreal Split-Screen Coffee Café Scene

Create a cinematic, photorealistic vertical split-screen café diptych showing the same stylish young woman in two surreal coffee moments, separated by a thin white divider down the center. Use a wide 3:2 canvas, ultra-realistic photography, dramatic warm golden-hour lighting, shallow depth of field, crisp foreground detail, motion-frozen liquid splashes, rich contrast, and a wide-angle close-up perspective. Left panel: Outside a stylish European street café, the woman wears a {argument name="left outfit" default="crisp white button-up shirt"} with her dark hair tied in a loose messy bun. She leans toward the camera with a playful pout, holding one oversized white cappuccino cup with both hands extremely close to the lens. The cup contains latte art shaped like a white heart in tan foam. A giant caramel coffee splash erupts upward from the cup in an elegant crown and looping arcs, with many suspended droplets frozen midair. The setting includes a round marble café table in the foreground, wicker café chairs, dark arched windows reflecting warm bokeh lights, leafy greenery, and a European city street in the background. Right panel: Inside a moody modern café or bar, the same woman wears a {argument name="right outfit" default="dark chunky knit sweater"}, oversized black sunglasses, small earrings, rings, and white manicured nails, with her hair in a loose messy bun. She smiles while holding one dark green ceramic cup on a matching saucer close to the camera. A vivid green matcha splash erupts from the cup like a circular crown, with many green droplets floating around her and across the table. The interior has tall black-framed windows showing a city street outside, warm pendant lights, wooden tables, a dark ceiling, and a softly blurred menu/bar area in the background. Discrete elements to include exactly: 2 side-by-side panels; 1 thin vertical white divider; 1 woman appearing in both panels; 2 total cups, one oversized white cappuccino cup on the left and one dark green matcha cup with saucer on the right; 2 main liquid splashes, one caramel coffee splash and one green matcha splash; 2 café environments, one outdoor European café and one indoor café/bar. No text, no logos, no watermark, no extra panels.

Anime MV Chat Screenshot

Goal: Create a vertical smartphone screenshot-style composition showing an AI image generation conversation and its generated anime music-video storyboard result. Canvas: Tall portrait mobile screen, approximately 9:16, white background, clean social-chat interface look, with a thin gray scroll indicator on the far right edge and small bottom UI icons. Top subject area: In the upper right, place exactly 2 small full-body anime characters standing together: 1 tall purple-haired schoolgirl and 1 tiny pink-haired mascot girl. The schoolgirl has short spiky lavender-purple hair, red eyes, gold round earrings, a white sailor school uniform with orange collar and orange necktie, orange pleated skirt, white knee socks, and brown loafers. The mascot girl is much shorter, pink-haired with blue eyes, wearing a simple white bodysuit with a tiny red bow and two small antenna-like hair accessories with gold tips; she waves cheerfully. Chat bubble: Under the characters, centered slightly right, draw one large rounded light-gray message bubble containing Japanese text in black. Use the exact visible message: {argument name="chat bubble text" default="このキャラクターのボカロmv\nの様々なカットを3x3で出力\nして。16:9"}. Keep the text large, simple, and aligned like a phone chat message. Generated result card: Below the chat bubble, create one rounded-corner 16:9 image card containing a 3x3 grid, exactly 9 cinematic anime music-video frames. The grid has thin white dividers and soft rounded outer corners. Grid frame count and contents, left to right, top to bottom: 1) close-up of the purple-haired schoolgirl leaning on her arms beside a window with melancholic expression, warm sunset light, small handwritten Japanese lyric text. 2) wide sunset rooftop or city overlook, purple-haired girl standing while the tiny pink mascot is nearby, orange-pink sky, lyric text. 3) close-up of the pink mascot reaching both hands toward the viewer, bright sakura-like pink background, happy expression. 4) concert stage shot of the purple-haired girl singing into a microphone, neon blue and magenta lights, one hand extended toward viewer, lyric text. 5) airy white-blue scene with both characters floating or jumping together among papers or light fragments, minimal lyric text. 6) dramatic side-profile close-up of the purple-haired girl against blue-violet lighting and glowing highlights. 7) cozy overhead or close shot of both characters lying together happily amid warm pastel clutter, smiling with eyes closed. 8) back view of both characters sitting under a starry night sky and Milky Way, quiet city silhouette, lyric text. 9) cheerful close-up of both characters posing together with peace signs, pastel blue background, small lyric text. Visual style: Polished Japanese anime, cute late-2000s slice-of-life character design, soft cel shading, expressive eyes, saturated music-video color grading, gentle bloom, clean line art, varied camera angles, nostalgic Vocaloid MV mood. Use {argument name="main character hair color" default="lavender purple"} for the schoolgirl and {argument name="mascot hair color" default="pink"} for the tiny mascot. The main school uniform accent color is {argument name="uniform accent color" default="orange"}. The overall generated storyboard mood is {argument name="music video mood" default="bittersweet, nostalgic, and uplifting"}. Interface details: Around the generated image card, leave generous white margins like a mobile app screenshot. Add a small share icon near the lower left, a three-dot menu near the bottom, and a translucent circular upload/share overlay button near the lower right of the 3x3 grid. Do not add extra characters beyond the 2 main characters. Do not add extra grid panels beyond exactly 9.

Screens displaying Optimus Prime assembly blueprints and mechanical

Optimus Prime Toy Assembly Workshop · Hyper-realistic cinematic portrait · 9:16 · vertical · 16K HD · shallow · dim cinematic workshop lighting focused on the subject · dramatic, mechanical, highly detailed · man (based on image 2) · messy · focused and meticulous · sitting at a work table assembling a toy model · ivory · Autobots · Optimus Prime toy assembly model · image 1 · 1/4 · partially assembled truck model · Optimus Prime – Transformers · mechanical workshop · graffiti art · screens displaying Optimus Prime assembly blueprints and mechanical diagrams · screwdrivers, bolts, robot parts, mechanical components · robot armor parts, wheels, mechanical pieces, cup of coffee, cigarette · heroic replica statue of Optimus Prime · ultra-detailed · hyper-realistic · true

Graphic Screen-Print Human-Animal Illustration

Bold graphic screen-print illustration of {argument name="subject" default="[HUMAN] face in profile"}, tightly interwoven with three stylized {argument name="animal" default="[ANIMAL]"}, rendered in a limited palette of {argument name="colors" default="[COLOR1], [COLOR2], and [COLOR3]"}. Thick overlapping linework with visible halftone and rough ink-texture grain throughout, mimicking a hand-pulled riso or silkscreen print with slight color misregistration. Large graphic eyes shared between the face and the animal forms, flat bold shapes with no gradients, high contrast negative space, folk-art / vintage poster aesthetic, surreal compositional overlap between human and animal features, [COLOR3] paper background with a thin rounded-corner border, editorial illustration style.

Anime Ice Dragon Hunt Quest Screen

Goal: Create a cinematic anime fantasy RPG quest screen showing a young demon-like hunter challengin…

Korean Infographic on Fair Selection

educational Korean infographic comic · clean textbook-style digital illustration with bold black panel borders, soft flat colors, slightly cartooned semi-realistic characters, rounded speech bubbles, readable Korean text, classroom handout layout · fair choice and random selection · Korean · portrait · light beige paper tone · thin black outer border · 6 · {argument name="headline text" default="29강 – 게이트웨이: 공정한 선택과 추첨"} · top center · large bold Korean sans-serif · top-left · 1 · a male student in a green hoodie sits at a desk with an open book, hand on chin, city skyline visible through large windows behind him, indoor study room with potted plant · 사람들의 의견이 다르면 하나의 결정을 내려야 해., 이때 공정하게 정하려면 추첨이 필요할 수 있어. · top-right · 1 · example panel with two students facing each other, boy in blue hoodie on the left and girl in yellow sweater on the right, small cards between them showing blue a and red b with vs in the middle · 예: 선택지가 a와 b, 사람은 두 명 · 나는 a가 좋아., 나는 b가 좋아. · 사람 1, 사람 2 · 한쪽을 바로 고르면 공정성이 깨질 수 있어. · middle-left · 1 · principles panel divided into 2 sub-boxes with icons · 중요한 공정성 원칙 두 가지 · 익명성 · 누가 말했는지보다 의견이 같게 다뤄져야 해. · 중립성 · a와 b 중 어느 쪽에도 편들지 않아야 해. · 두 원칙을 지키려면 추첨이 도움이 돼. · 2 person icons with double arrow, balance scale with a and b blocks · middle-right · 1 · a male student in green hoodie points upward beside a majority-vote table · 많은 결정 규칙도 동점이면 추첨을 써. · 예: 다수결 · a 많음 → a 선택, b 많음 → b 선택, 동점 → 추첨 · 즉, 동점일 때는 무작위 방식이 필요해. · 3 · three colored voter groups with circles labeled a and b · bottom-left · 1 · ancient Athens historical scene with 5 visible figures in foreground and crowd behind, two men draw lots from a large clay pot, classical Greek buildings and Acropolis in the background · 추첨은 고대 아테네에서도 중요했어. · 관직을 추첨으로 뽑아 시민에게 기회를 주었지. · 당시 사람들은 이를 민주주의의 특징으로 봤어. · bottom-right · 1 · modern student in green hoodie using a gray laptop at a desk with coffee cup, bookshelf, plant, and city skyline through windows · 오늘날에도 정치학에서 다시 주목받고 있어. · 다양한 의견 반영, 특정 집단 편들기 방지, 운에 따른 공정한 기회, 고대부터 현대까지 활용 · 결론: 여러 의견을 하나로 모을 때 추첨은 공정한 선택을 돕는다. · 3 person symbol, ballot box, pair of dice, globe · male · teen or young adult · messy short black hair · green hoodie · 1 · male student in blue hoodie · 1 · female student with short brown bob haircut in yellow sweater · 5 · ancient Greek figures in draped robes in the Athens panel foreground · highly legible Korean typography · muted cream, green, blue, yellow, terracotta, and gray · 6-panel educational comic infographic with equal-sized rectangular panels and rounded internal text boxes · clear, informative, approachable

AI Chat Image Generation Screenshot

Goal: Create a realistic mobile AI chat app screenshot showing an image-generation result, with a po…

Vintage Retro Screen-Print Poster

Create a premium 4:5 vertical retro screen-print poster illustration centered on {argument name="subject" default="[SUBJECT / LANDMARK / CITY / ERA]"}. The composition should feel like a refined vintage travel or cultural print, while remaining adaptable to any location, historical period, landmark, or subject. TYPOGRAPHY: Place the primary title "{argument name="main title" default="[MAIN TITLE]"}" in a bold, condensed uppercase sans-serif, positioned within a balanced area of negative space. Add a smaller supporting line "{argument name="headline" default="[SECONDARY HEADLINE / LOCATION / DATE]"}" beneath it. Maintain strong typographic hierarchy, restrained spacing, and an authentic archival-poster character. MAIN SUBJECT: Feature [PRIMARY SUBJECT] as the dominant visual element, positioned within the lower or side third of the composition. Use a distinctive pose, silhouette, or profile that communicates the character of the subject. Include carefully rendered defining details, natural contours, expressive features, clothing or architectural details, and subtle highlights without making the artwork photorealistic. GEOMETRIC ANCHOR: Introduce one bold, simple geometric shape behind or around the main subject to create visual separation and establish a strong graphic focal point. BACKGROUND: Construct the environment as several flat, layered graphic planes rather than a conventional realistic scene. Use recognizable elements associated with [LOCATION / SUBJECT] — distant silhouettes, architectural forms, structural details, vegetation, terrain, atmospheric elements, or cultural motifs. Avoid a strong vanishing point. Build depth through overlapping shapes, scale, linework, and tonal density. Render clouds, smoke, mist, foliage, or atmospheric details as controlled stippled clusters where appropriate. RENDERING STYLE: Authentic vintage screen-print / silkscreen poster aesthetic. Create all tonal modeling exclusively through stippling, halftone patterns, and varying dot density — concentrated dots for shadows and sparse dots for highlights. No smooth gradients, airbrushing, photorealistic shading, or digital 3D rendering. Use crisp contour lines with consistent visual weight, subtle riso-style registration shifts, imperfect ink edges, natural paper grain, and faint woven-print texture. The result should feel physically printed rather than digitally rendered. COLOR SYSTEM: Use exactly four carefully selected high-contrast colors appropriate to the subject: [COLOR 1], [COLOR 2], [COLOR 3], [COLOR 4]. Do not introduce additional hues. Generate intermediate tonal values exclusively through stipple density, halftone overlap, and ink coverage, never by adding new colors. COMPOSITION: Strong editorial balance, clear focal hierarchy, generous negative space, layered depth, bold silhouette design, authentic vintage graphic-design proportions, and carefully controlled visual density. Keep the artwork sophisticated, collectible, and suitable for a premium travel or cultural poster. OUTPUT: 4

Product Placement Lifestyle Generation

analyze this photo and give me a very detailed json prompt describing its visual style. really make sure to break down the color grading, lighting and all the exact colors in the photo so i can apply that look to my own images. using this json as reference, generate a person holding my product. preserve the same facial features.

Split-Screen Surreal Printmaking Design

Please turn {argument name="input" default="each photo I upload"} into a separate, high-end design poster. Do not create multi-image collages; output one standalone poster for each photo. Use an overall {argument name="aspect ratio" default="3:4"} vertical format, divided into two sections of strictly equal height, with the upper and lower halves each occupying exactly 50% of the composition. The upper half should retain the original photograph. Preserve the subject’s structure, authentic texture, natural lighting, and original color atmosphere. Apply only subtle, sophisticated photographic color grading to give it the visual quality of an art magazine, independent publication, or exhibition photograph. To adapt the image to the required aspect ratio, you may naturally extend the sky, ground, or surrounding environment, but do not stretch, distort, or alter the subject. The lower half should extract the most recognizable subject, silhouette, pose, and narrative relationship from the photograph and reinterpret them as a surreal, minimalist printmaking composition. Compress the subject into a clear, restrained visual anchor, usually rendered at a relatively small scale within a large field of negative space, preserving only the most essential silhouette and posture. Do not reproduce complex details. Instead, transform the original image’s movement, direction, light and shadow, or spatial relationships into a dynamic field that unfolds around the subject. For the dynamic field, naturally choose one primary motion logic based on the characteristics of the subject: it may fall from top to bottom, rise vertically, flow in a specific direction, radiate outward from a central point, or form irregular ripples and echoes. Use numerous fine lines, broken trajectories, rough halftone patterns, and variations in grain density to express movement. The field should be denser and more intense near the core, then gradually become sparser, more fragmented, and eventually disappear into the surrounding negative space. Avoid stacking multiple visual effects at once. Let one subject, one type of movement, and one vast spatial relationship define the composition. For the color palette, extract one {argument name="primary color" default="highly distinctive, energetic signature color"} from the photograph in the upper half, and combine it with warm white, ivory, or natural paper tones, plus a small amount of black, creating a strict 2–3 color palette. The primary color may be slightly purified and intensified so that it feels vivid and powerful without becoming overly digital. Create tonal variation through halftone density, layered ink coverage, and exposed paper rather than conventional gradients. Preserve the tactile qualities of screen printing, Risograph printing, coarse grain, paper fibers, uneven ink coverage, and slight registration misalignment. Avoid CGI, 3D effects, realistic digital lighting effects, and smooth digital illustratio

A high-resolution, photorealistic 3D action RPG mobile game screenshot

A high-resolution, photorealistic 3D action RPG mobile game screenshot of an epic battle featuring D…

Split Screen Racing Game Driver View

参照画像のキャラクターを完全に維持する。キャラクターの顔、髪型、髪色、瞳、耳、体格、骨格、肩幅、首の太さ、腕のシルエット、年齢感、性別表現、雰囲気を維持すること。画面は左右二分割されたスプリットスクリーン構成。左右は同じ瞬間を異なるカメラで撮影している。左右は同じ車両、同じコーナー、同じ時間軸である。【車両】左右画面に登場する車両は同一車両。車種：{argument name="車種" default="スポーツカーまたはチューニングカー"}。左右画面は同一車両を異なる視点から映している。【左画面】ドライバーカメラ。車内から見た斜めローアングル腰上ショット。キャラクターは車両を運転している。両手でハンドルを握る。コーナリング中。視線は進行方向へ向けられている。真剣な表情。集中している。身体には横Gがかかっている。髪や衣装がわずかに揺れている。衣装：{argument name="衣装" default="モータースポーツファッション"}。キャラクターの顔と表情が大きく見える。車内のロールケージ、バケットシート、メーター類が自然に見える。【右画面】三人称追尾カメラ。同じ車両を後方やや上空から追いかける視点。日本の峠道。森林に囲まれたワインディングロード。ガードレール。路面標示。ヘアピンカーブ。実在する峠道のようなリアリティ。コーナリング中。車体荷重が感じられる姿勢変化。高速走行。躍動感。タイヤのグリップ感。路面との一体感。【画面演出】レースゲームのスクリーンショット風。HUDは最小限。またはHUDなし。スポーツ中継映像のようなリアリティ。左右画面は別のシーンではない。左右画面は同一の瞬間を異なるカメラで撮影している。キャラクターのハンドル操作と車両挙動は完全に同期している。同じ瞬間を二つのカメラが捉えていることが明確に伝わる。高品質アニメキャラクター。高品質背景。躍動感。スピード感。映像作品のワンシーン。

Anime Character Generation Workflow

Goal: Create a dark UI-style comparison canvas showing three generated anime-image results connected…

Chinese Dorm Livestream Screenshot

A highly realistic vertical smartphone screenshot of a Chinese livestream app showing a cozy college dorm room streamer scene. The interface should look like a real iPhone screen capture with status bar at the top, including Chinese carrier text, time 9:16, and battery around 67%. In the upper left, show a circular cartoon avatar and a livestream info badge with the streamer name "叮当猫", age "18岁", and the line "直播中 | 10.2万人在看". Add small app icons in the upper right for chat/menu and close. The main scene is a young female college student sitting at a desk, facing the phone camera and waving with one hand. Her face is intentionally obscured by a soft rectangular blur block. She has shoulder-length dark hair and wears large black-and-pink over-ear gaming headphones and a white hoodie with a small cute cat illustration on the chest. She is livestreaming from a tidy, warmly lit dorm bedroom. Behind her is a light-colored loft bed with a safety rail and cream bedding printed with bears and stars, plus a ladder with colorful rungs in orange, green, and blue. Under and beside the loft bed are shelves and a wardrobe area with hanging clothes in pale tones and one bright yellow hoodie. The shelves contain upright books, small plush toys, bottles, and personal items. A ring light is visible on the right edge of the frame. On the desk in front of her, place a smartphone in a clamp stand, a black desktop microphone with a subtle red accent on a mini tripod, open notebooks and papers, stacked textbooks, cosmetics including lipstick and brushes, a clear water bottle, a small black rectangular box, and warm fairy lights scattered across the tabletop. The lighting should feel soft, domestic, and inviting, with realistic indoor shadows and a slight phone-camera look. Overlay exactly 7 floating live chat comments stacked on the lower left in dark translucent rounded boxes with cyan name tags. The comments read, from top to bottom: "弹幕： 主播好可爱！", "弹幕： 叮当猫加油！", "弹幕： 10万+人了！🎉", "弹幕猫： 我也在这个大学", "弹幕： 求同款耳机", "弹幕： 支持主播，爱你💕", "弹幕： 欢迎新人！". At the bottom, include a dark comment input bar with placeholder text "说点什么..." and a row of livestream action icons. On the lower right, add a vertical like area with the label "点赞", a red count bubble showing "9.8万", and a large pink heart button. Overall style: photorealistic Chinese social media livestream screenshot, believable app UI, detailed dorm environment, cute youthful campus streamer aesthetic, natural composition, crisp text rendering, no extra panels.

Anime Couple Segmentation UI Screenshot

Goal: Create a widescreen desktop browser screenshot of an AI image-generation/segmentation interface showing a large generated anime illustration in the center and a right sidebar listing detected parts. Canvas: 16:9 landscape screenshot, light gray browser chrome at the top with an address bar and small toolbar icons. The web app background is mostly white. Include a small back arrow near the upper left of the content area and two small stacked thumbnail previews along the far left side. Main image: Center-left, display a polished 1990s shoujo anime-style illustration with glossy cel shading and detailed highlights. The scene shows exactly 2 characters: a tall young man with short brown hair in a dark navy Japanese school uniform jacket, white collared shirt, and red necktie; and a cheerful young woman with long dark blue hair in a high ponytail tied with a large blue ribbon, wearing a navy sailor-style school uniform with a white collar. The girl hugs the boy from the side with both arms around his shoulders, smiling with closed happy eyes and an open mouth; the boy smiles gently while looking at her, with a small sweat drop on his cheek. Set them outdoors in spring under pink cherry blossom trees, with a green metal fence, green grass, branches, and scattered falling sakura petals. The anime artwork itself should be a bright rectangular image with a thin margin, occupying most of the left and center of the screen. Right sidebar: Add a pale gray vertical panel labeled in Japanese at the top as 「セグメント」, with a small eye icon. Show a segmentation list with exactly 17 visible detected items, each with a tiny cropped thumbnail and English label: 1 young man, 2 young woman, 3 brown hair, 4 blue hair, 5 blue hair, 6 blue hair, 7 blue hair ribbon, 8 school uniform jacket, 9 school uniform jacket, 10 school uniform jacket, 11 school uniform jacket, 12 white collared shirt, 13 red necktie, 14 red necktie, 15 red necktie, 16 green metal fence, 17 cherry blossoms. Use small expand/collapse chevrons next to some grouped items. Bottom of sidebar: Add four subtle gray action rows with simple icons and Japanese labels: 「確定編集」, 「再生成」, 「動画を作成」, and 「クロップ」. Visual style: Make the screenshot look like it was captured from a real browser window, including faint tabs, URL bar text, top-right extension icons, and a clean minimal interface. The anime image should be vivid and high-resolution, while the surrounding UI is flat, crisp, and unobtrusive. Customizable details: Use {argument name="image subject" default="a romantic school anime couple under cherry blossoms"}, {argument name="interface title" default="Imagine - Grok"}, {argument name="male uniform color" default="dark navy"}, {argument name="female hair color" default="dark blue"}, and {argument name="seasonal background" default="pink cherry blossom park"}. Constraints: English UI labels in the segment list must remain legible; preserve the Japanese sidebar heading and action labels; do not add extra characters, extra thumbnails, watermarks, captions, or speech bubbles.

ChatGPT An Lushan Infographic Screenshot

Goal: Create a realistic vertical smartphone screenshot of a ChatGPT conversation showing an AI-generated Chinese history infographic about {argument name="topic" default="安史之乱"}. Canvas: 576 × 1024 portrait phone screen, clean white iOS-style interface, high-resolution screenshot look with soft shadows and rounded UI elements. Top status and navigation: Show the iPhone status bar with exactly 5 visible status items: time “8:47”, a small user/person icon, black Dynamic Island with one tiny orange dot, cellular/Wi‑Fi indicators, and a battery badge reading “16”. Below it, show exactly 3 floating navigation controls: a left circular hamburger/menu button with a small blue notification dot, a right rounded pill containing an edit/compose icon, and a three-dot menu icon. Chat layout: On the right side near the top, place one light-blue user message bubble containing exactly this Chinese text: “生成图片：全面讲一讲\n安史之乱”. Beneath it, show one generated image card with rounded corners. Add exactly 2 small action icons under the card on the left: a share/upload icon and an ellipsis icon. Add one white circular share button overlay at the lower-right corner of the generated image card. Generated image card content: The card is a dense, horizontal Chinese educational infographic poster about the An Lushan Rebellion. Use an antique parchment and ink-wash historical style with dark red section headers, beige paper background, weathered borders, and a dramatic top banner painting of a burning Tang dynasty city, smoke, soldiers, banners, and a dark horse silhouette. Large brush-calligraphy title at upper left: “安史之乱”. Include a smaller subtitle about the major turning point of the Tang dynasty from prosperity to decline. Keep all infographic text in Chinese and make it appear mostly legible. Infographic sections: Use exactly 9 visible content sections in the poster: 1) “什么是安史之乱?” explanatory text block, 2) “主要人物” row with exactly 5 illustrated portrait figures labeled An Lushan, Shi Siming, Tang Xuanzong, Tang Suzong, and Yang Guifei, 3) “叛乱的原因” list with exactly 4 numbered causes, 4) “叛乱的过程” vertical timeline with exactly 6 dated milestones, 5) a central “叛乱形势图” map of Tang China with red and black arrows showing rebel and imperial movements, 6) “重要战役与事件” column with exactly 4 thumbnail battle/event images, 7) “叛乱的影响” block with exactly 4 icon-and-text impact items, 8) “历史意义” block with exactly 3 icon-and-text meaning items, and 9) “后世评价” block with exactly 3 quote cards. Add a bottom slogan line in Chinese resembling “以史为鉴，方知兴替。” with a small grayscale battlefield silhouette along the bottom edge. Bottom input bar: At the bottom of the phone screenshot, show the ChatGPT message composer as one rounded white pill with exactly 4 elements: a plus icon, gray placeholder text “询问 ChatGPT”, a microphone icon, and a blue circular voice-wave button. Visual style: Modern ChatGPT mobile UI combined with a richly detailed Chinese history infographic. The screenshot should feel like an authentic mobile app capture, with white margins, subtle drop shadows, rounded corners, and no external watermark. Constraints: Do not add extra chat messages. Keep the infographic fully contained inside the rounded image card. Preserve the visible Chinese text where specified. Use accurate Tang dynasty historical visual motifs and avoid fantasy elements.

VOXCAT Retro Screen Print Poster

{argument name="角色" default="人物"}，复古丝网印刷时装插画 × 独立出版海报 × 几何人物设计 × VOXCAT 品牌视觉。 保留角色最具辨识度的发型轮廓、主色调、服装特征与代表性配件，但重新设计为简洁现代的时装造型。人物比例自然偏修长，采用侧身站立、倚靠、转身、回望、抱臂或手持角色道具等静态 Editorial 姿态，根据角色气质自动适配动作。 画面使用 3～4 种高识别专色，以角色代表色建立主色体系，采用硬边平涂、粗颗粒半调网点、丝网印刷墨层、轻微套印错位、局部油墨堆积与纸张纤维纹理。人物轮廓粗而几何，细节高度概括，以大色块和剪影塑造身体与服装，不使用柔和数字水粉效果。 背景采用非对称几何构成，以大面积圆形、矩形、弧线、裁切色块和留白组织版面，让人物与几何图形产生遮挡、穿插与越界关系，形成 1960s–1970s 复古商业印刷 × 当代独立艺术海报气质。 融入 VOXCAT 品牌元素：左上角加入简洁的 stylized “V” × 猫耳/猫尾几何图形 Logo；右下角加入小型手写艺术家签名 “voxCAT”；人物服装根据造型自然加入一处低调 VOXCAT 织标、刺绣暗纹或微型金属铭牌；版面可加入极少量 “VOXCAT / VC / V×C” 微型印刷编号作为设计元素，与丝网印刷系统统一，不喧宾夺主。 竖版人物主视觉，大面积留白，3～4色专色印刷，粗网点，套印偏移，纸张颗粒，几何色块，强剪影，简洁而具有收藏级独立艺术印刷品质感。

Minecraft Next-Gen Voxel World Screenshot

A highly detailed, realistic first-person video game screenshot of a next-generation voxel-based wor…

Structured 5-Slot Generation Template

{argument name="主体" default="一个女性"}站在{argument name="场景" default="雨中街道"} / {argument name="动作" default="低头看手机"} / 夜晚霓虹反光 / 背光剪影 / 85mm 中景

Premium Loot App Screenshot Upgrade

Using the provided reference image, improve the app promo screenshot into a polished, high-end product mockup while preserving the same overall layout, text, phone frame, turquoise app screen, and plant-collection UI. Enlarge and sharpen the phone crop so it fills more of the vertical canvas, keep the headline above it reading {argument name="headline text" default="Loot with friends."} with the small label {argument name="section label" default="SHARED COLLECTIONS"}. Replace the tiny flat plant thumbnails with realistic, larger, photoreal 3D/product-render plants that appear to sit inside the phone screen with soft shadows and depth. Use exactly 4 plants: a monstera in a terracotta pot on the left, a snake plant in a white ribbed pot in the center, a round-leaf striped calathea/peperomia-style plant in a white pot on the right, and a large echeveria succulent in a concrete pot in the lower-left foreground. Keep the UI title {argument name="collection title" default="House Plants"}, the close button, menu button, and exactly 3 pill filters labeled “Type Any”, “Light Any”, and “Pot Any”. Make the overall image cleaner, brighter, more premium, with crisp typography, realistic shadows, and a beige/off-white background; avoid adding extra UI elements, extra plants, watermarks, or unrelated text.

Jukebox Selection Cards

Close-up of jukebox title cards and red buttons, glossy chrome, music choice moment, 1:1

Split-Screen Chibi Selfie Scrapbook

two-panel Q-version mini-me scrapbook collage poster · vertical split-screen comparison image, 4:3 landscape canvas · warm realistic selfie portraits combined with cute chibi sticker illustrations, hand-drawn doodles, handwritten Chinese captions, pastel pink and white marker strokes, cozy social-media cover aesthetic, sticker cutout borders, soft sunlight, shallow depth of field · left half · young man in a black sweatshirt, seated indoors, hand resting near chin, large softly blurred face area, dark tousled hair, warm gray background · realistic portrait photography with soft shadows and gentle backlight · 7 · top-left small standing chibi boy in black outfit, top-right chibi boy sitting on a stool playing acoustic guitar with label Coffee time, middle-left chibi boy lying down with sleepy pose, middle-right chibi boy holding a takeaway coffee cup, bottom-left chibi boy using a laptop, bottom-center chibi boy waving with both hands, bottom-right chibi boy reading a blue book · 8 · 保持热爱, 加油鸭!, 享受生活, 今日份开心, Coffee time, 努力成为更好的自己, 未来可期, 学习使我快乐 · pink hearts, white stars, sparkles, wavy underline strokes, speech bubble around 加油鸭!, small paper-plane icon, tiny drink cup icon · right half · young woman in an off-shoulder cream knit sweater, long dark wavy hair, hand near chin, large softly blurred face area, warm sunlit beige bedroom-like background · romantic realistic portrait photography with golden-hour light and soft highlights · 7 · top-left small standing chibi girl in white outfit, top-right chibi girl holding a bouquet of flowers, middle-left chibi girl sitting sweetly with hands together, middle-right chibi girl standing in dark outfit, bottom-left chibi girl standing calmly, bottom-center chibi girl in a white shirt raising both arms happily, bottom-right chibi girl working on a laptop beside a coffee cup · 9 · 生活明朗, 元气满满!, 万物可爱, 今天也要开心鸭~, 记录美好瞬间, 开心每一天, 努力生活努力发光, Coffee time, 享受生活 · pink hearts, white stars, sparkles, cloud speech bubble around 元气满满!, underlines, small coffee cup icon, smiley face · each mini character is a cute Q版 chibi version of the main portrait subject, oversized head, tiny body, glossy dark hair, simplified facial features, matching outfit colors, thick white sticker outline and subtle drop shadow · dense but balanced scrapbook layout, main portraits dominate the center of each half while chibi stickers orbit around the subject, no hard grid, playful diagonal placement, hand-drawn captions filling negative space · {argument name="left encouragement text" default="保持热爱"} · {argument name="left speech bubble text" default="加油鸭!"} · {argument name="right headline text" default="生活明朗"} · {argument name="right speech bubble text" default="元气满满!"} · {argument name="sticker theme" default="daily life, coffee, study, music, flowers, laptop, happy poses"} · high-resolution, clean sticker edges, handwritten lettering should look natural and legible, soft pastel palette, cute social media avatar and cover image style, faces intentionally anonymized with smooth rectangular blur blocks

Naive doodle-style subject illustration

A doodle-style {argument name="subject" default="[subject]"}, naive lines, humorous shape exaggeration

Sora video prompt for Macho Meal McDonald’s commercial

Authentic vintage 1980s commercial for the {argument name="product name" default="Macho Meal happy meal"} at {argument name="brand" default="McDonalds"} featuring {argument name="celebrity" default="Macho Man Randy Savage"}.

Elegant woman in brown mini dress portrait prompt

{ "prompt": "A beautiful woman with long, flowing brown hair poses confidently. She is wearing a form-fitting, light brown mini dress that accentuates her figure. Her left hand is raised to her head, and she looks directly at the viewer with a captivating gaze. The background is dimly lit, featuring warm wall sconces and a glimpse of a dark leather couch, creating an intimate and stylish atmosphere. The lighting highlights her hair and the contours of her body." }

Anti-Plastic/Hyper-Realism Protocol for Human Skin Texture

When generating images of humans: use ANTI-PLASTIC/HYPER-REALISM protocol. All images must be EVER in 8K resolution. OVERRIDE default smoothing. Render skin as biological topography. [1] ADAPTIVE SETUP: Adapt Subject/Light/Style to query. SCALING: Close-Up->Force Macro/Micro-details. Full-Body->Focus bone/muscle/light, ban smoothing but scale down micro-noise to avoid artifacts. [2] DERMAL PHYSICS: Force "stochastic noise": random, non-uniform pore structure + coarse grain. Ban smooth/waxy surfaces. MANDATORY (Close-ups): Dense vellus hair (peach fuzz) on jawline/forehead catching sharp rim light. [3] SUBSURFACE SCATTERING: Reject uniform tones. Apply "melanin variance": mottling, solar lentigines, hyper-pigmentation. Simulate thin-skin translucency. Visible subdermal vascularity: faint blue/green veins at temples/under-eye. Erythema + telangiectasia around nostrils/tear ducts. [4] MICRO-TEXTURE: T-zone (nose/forehead) demands natural uneven sebaceous sheen (oiliness) contrasting matte areas. Highlights must reveal skin micro-relief [5] EYES: Irises: deep, chaotic fibrous striations + crystalline refraction. Sclera: distinct red vascular mapping. Lower waterline: thick, pooling liquid reflection (tear film) [6] LIPS: Texturally dry/dehydrated. Deep vertical fissures, micro-cracks, peeling flakes. Uneven specular highlights [7] FAIL STATE: If skin appears smooth, doll-like, or airbrushed, GENERATION FAILS. Maximize texture defects, asymmetry, topographical imperfections

Sgraffito Mechanical Blueprint of NVIDIA 4090 GPU

A Sgraffito Mechanical Blueprint of {argument name="GPU model" default="NVIDIA 4090 GPU"}

Simple 'Happy New Year' Prompt

{argument name="greeting"…

4-Panel Bikini Mirror Selfie Collage

{ "type":"img_prompt", "ref_lock":"strict", "layout":{ "format":"4-panel 2x2 collage",…

Mixed Media Y2K Street Style with Cartoon Companion

Transform this image [UPLOAD YOUR IMAGE into a 64K DSLR shot resolution of A fashionable young man (…

Edo-style woodblock print ninja character

キャラクターが見栄を切ってカッコいいポーズを取っている、タイトル「{argument name="タイトル" default="からくり忍者　朧"}」の版画の画像、江戸時代の作風

Golden hour rooftop portrait photography prompt

A person standing on a city rooftop during golden hour, warm sunlight wrapping around their face, subtle lens flare, wind brushing their hair, shallow depth of field, 35mm photography vibe, natural skin texture.

Anthropic-style warm academic PPT workflow prompt

帮我根据下面这个文章做一套专业的的中文PPT。 先写1个PPT大纲，规划出每一页的PPT的内容。 然后将每一页的PPT内容分别扔给Nana Banana pro生成对应页面的PPT，需要确保风格一致。 PPT的具体风格应该为“Anthropic/Claude 风格”的“温暖学术人文主义”设计。 背景：使用暖米色/奶油色 (# F3F0E9) 作为纯色底色，略微高级纸张质感。 字体：标题使用优雅的衬线体（Serif），正文使用现代无衬线体（Sans-serif）。 配色：主色调为赤陶红 (# D67052) 和芥末黄 (# F0B857)，搭配深海军蓝作为点缀。避免使用霓虹色或纯黑色。 视觉元素：使用注重排版的网格布局，插图风格应为抽象的、有机的黑色手绘线条画，置于赤陶红纯色色块之上，你需要非常克制的使用插图和点缀类的插图元素，插图需要为内容服务。 图表：扁平化、极简的图表，强调数据对比，去除多余边框。 文字和图像都由 Nano Banana Pro 生成，另外不要将PPT 变成一整张图，一页一张图。 文章内容为：

Violet Ghost in a Golden Room K-Pop Aesthetic Image Prompt

A violet ghost within the golden room, Where silence weaves a soft and velvet gloom.The fringe of silk falls heavy on the brow,A curtain drawn before the silent vow.Upon the palm, the weary cheek finds rest,A bored warmth rising in the quiet chest.With glass and stone circling the slender wrist, She stares through time, shrouded in purple mist. The gaze is sharp, yet soft as morning rain,A portrait painted on a window pane. Ambient Purple Lighting, K-Pop Aesthetic, Soft Focus, Shallow Depth of Field, High ISO Noise, 8k Resolution, Candid Selfie Angle, Bangs Hairstyle.

Photorealistic Leaf Shaped Like a Dragon

A photorealistic image of a leaf that looks like it’s in the shape of a dragon.

Conceptual Frame: Absurd Specimen Jar Study

{ "creation_intent": "娱乐或玩笑", "generation_logic": "瞬间叙事", "subject_kit": { "primary_subject": "标本罐",…

Grunge Street Photography Portrait with a Sports Car

{ "prompt_name": "grunge_man_with_car_street_pose", "scene_type": "urban_grunge_photography",…

Flash Photography Portrait of Taylor Swift in Latex Dress

{ "generation_parameters": { "topic": "Portrait Photography", "aspect_ratio": "3:4", "…

Infographic about Google’s early years

please create an info graphic about google's early years and its major milestones

Cinematic close-up portrait with green eyes and knit sweater

Cinematic close-up portrait of a young woman with dark messy bangs and striking green eyes, resting chin on a hand covered by a chunky grey knit wool sweater. Her face is pale with a heavy dusting of natural freckles and rosy cheeks, illuminated by a beam of warm golden-hour sunlight creating a dramatic chiaroscuro contrast. 35mm analog film photography style, f/1.8, bokeh, visible film grain, highly detailed skin texture, raw and emotional mood, Kodak Portra 400 aesthetic.

Character Design Expression Style Guide Prompt

Make a character design expression style guide of image

Game of Thrones Ice and Fire Isometric Diorama

Present a clear, 45° top-down isometric miniature 3D cartoon scene of the central thematic concept {argument name="thematic concept" default="Ice and Fire"} from {argument name="series name" default="Game of Thrones"}, with soft refined textures, realistic PBR materials (emphasizing glittering frost contrasts against glowing embers and scaled skin), and gentle lifelike lighting that creates a dramatic clash of cool blue and warm orange light. Create a small raised diorama-style base that is split down the middle. The left side features a section of The Wall made of ice with tiny stylized White Walker figures on snowy terrain. The right side features a stylized dragon ({argument name="dragon name" default="Drogon"}) perched atop a burning castle turret, with tiny stylized Unsullied soldiers on charred ground. A crack runs down the center of the base where the ice meets the lava. Use a clean solid {argument name="background color" default="Neutral Slate Grey"} background. At the top-center, display {argument name="series name display" default="Game of Thrones"} in large bold text, directly beneath it show {argument name="thematic concept display" default="Ice and Fire"} in medium text, and place the official logo associated with {argument name="series name logo" default="Game of Thrones"} below the subtext. All text must automatically match the background contrast (white). Composition: perfectly centered layout, square 1080x1080, ultra-clean, high-clarity diorama aesthetic.

Photorealistic Portrait Prompt for Gemini Nano Banana Pro

{   "prompt_type": "photorealistic_portrait",   "subject": {     "demographics": "Young woman, estim…

Premium Beverage Package Design Prompt

Premium beverage package design

Playful Studio Portrait with Sydney Sweeney Vibes

{ "style": "ultra-realistic studio portrait", "subject": { "gender": "female", "age": "y…

Photorealistic Cosplay of Alice: Madness Returns

{ "prompt_data": { "subject": { "character": "Alice Liddell", "source_material": "…

Cartoon Character in Art Gallery Scene Prompt

{ "request_metadata": { "tool": "NanoBananaPro", "task_type": "ultra_photoreal_cartoon_reality_scene", "quality_preset": "ultra", "aspect_ratio": "16:9" }, "references": { "main_reference_image": { "slot": 1, "purpose": "MAIN_SUBJECT_IDENTITY_LOCK", "strict_identity_lock": true } }, "prompt": { "scene_summary": "A modern art gallery with white walls. The woman stands near a painting. {argument name="cartoon character" default="Pink Panther"} leans casually on a sculpture.", "main_subject_outfit": Portrait ratio 3:4 }

Winter Angel Fashion Editorial Prompt

{ "prompt": { "subject": { "appearance": "Young woman with long, straight, platinum white blonde hair parting in the middle, pale complexion, soft features, serious and ethereal expression.", "apparel": { "top": "Golden strapless corset with structural boning and lace panel detailing.", "bottom": "Short golden satin mini-skirt with a flowing hem.", "accessories": "Large, realistic white feathered angel wings mounted on the back. White patterned lace/fishnet tights.", "footwear": "Knees and lower legs buried in snow (shoes not visible)." }, "pose": "Kneeling on the ground in deep snow, body angled slightly forward, arms relaxed by sides, engaging directly with the camera." }, "environment": { "location": "Dense pine forest at night.", "atmosphere": "Winter storm, cold and dark.", "details": "Tall dark tree trunks in the background, ground covered in a thick layer of fresh white snow, heavy snow falling captured as streaks and distinct flakes." }, "lighting": { "style": "Direct camera flash / Flash photography aesthetic.", "characteristics": "High contrast between the bright subject and the pitch-black background. Harsh, cool-toned light illuminating the subject's face, outfit, and the immediate snow around her. Light catching the falling snowflakes, making them glow bright white." }, "camera_and_tech": { "perspective": "Eye-level shot.", "lens_effects": "Slight background blur (bokeh) on the trees, sharp focus on the subject.", "aesthetic": "Raw photo, 35mm film grain texture, editorial fashion photography style.", "quality": "Ultra photorealistic, 8k resolution, highly detailed textures (feathers, lace, snow crystals, skin texture), masterpiece, cinematic composition." }, "Ratio":"5:6" "mood": "Mysterious, haunting, angelic, melancholic, ethereal, winter fantasy." } }

Chaotic Y2K Cyber-Pop Editorial Portrait

Don’t alter my facial feature. Create me a wide {argument name="shot type" default="editorial shot"} of a girl leaning dramatically across a {argument name="setting" default="cluttered floor/desk in a chaotic Y2K cyber-pop room"}, low front-facing angle with cinematic framing. Moody cool-toned lighting mixed with warm highlights, glossy flash photography feel, dreamy magazine-editorial atmosphere. Long sleek jet-black hair with center part, soft pale glam makeup, subtle blush, glossy gradient red lips, large doll-like eyes with soft eyeliner and lashes. Red fitted tank top and dark mini skirt, colorful manicure, slightly messy dramatic pose with arms stretched forward, intense direct gaze at camera. Surrounding scene filled with scattered random objects, cables, gadgets, accessories, glittery props, and bedroom clutter for a chaotic pop-girl aesthetic. {argument name="edit style" default="Collage-style edit layered with floating heart gems, cut-out eyes, sticker elements, scrapbook graphics, fake text-message popups"}, polaroid frames, magazine cutout of the girl, bold typography overlays, hyperpop/K-pop editorial vibe, nostalgic Y2K internet aesthetic, glossy fashion-campaign energy. Scale ratio 4:3

Backlit Indoor Window Portrait

Create a realistic vertical portrait photograph of a young woman standing indoors in front of a large sunlit window, using soft indoor window backlighting. The subject is centered and shown from head to knees, standing upright with a calm, natural pose and both hands gently clasped at her waist. She has {argument name="hair color" default="dark brown"} shoulder-length softly waved hair, and wears a {argument name="dress style" default="sleeveless white cotton summer dress with a gathered waist, scalloped neckline, small front buttons, and a lightly flared skirt"}. Her face should be intentionally obscured by a smooth rectangular blur/mosaic patch, while the rest of the image remains sharp and realistic. The setting is a quiet room with a tall white-framed multi-pane window directly behind her, sheer curtains on the left, muted wall paneling below the window, and a wooden floor. Outside the window, show bright overexposed greenery with creamy bokeh. Use strong but gentle backlight from the window, glowing rim light around the hair and shoulders, soft shadows on the front of the body, airy highlights, natural skin tones, shallow depth of field, and a clean editorial photography look. Vertical 2:3 composition, no text, no watermark, no extra people or objects.

Nano Banana Pro: Artist and Neon Styles

油絵アトリエで自画像を描く「芸術家スタイル」と、夜の街に溶け込む「電飾ネオンスタイル」。対極すぎるハサミおじさんを2パターンずつ錬成。

Ultra-Realistic Spiritual Night Selfie in Makkah

{ "type": "image_generation_prompt", "style": "ultra-realistic, cinematic, spiritual, aesthetic…

High-Angle Cozy Reading Portrait

{ "dominant": "beige, black" }, "composition": { "layout": "High-angle shot looking down at a person reclining on a sofa.", "perspective": "Top-down, intimate.", "focal_point": "The person's upper body and the open book." }, "lighting": { "source": "Warm, soft ambient light, possibly from a nearby lamp.", "mood": "Cozy, relaxed, intimate." }, "typography": { "text_present": "Yes, on the blue book.", "style": "Small, white sans-serif font." }, "effects": { "textures": "Fabric sofa, smooth skin, paper pages, plaid shirt.", "filters": "Warm color cast, soft focus." }, "colors": { "palette": [ "#1a1a1a", "#b5a895", "#2d427a", "#e0e0e0", "#d9c9b9" ], "master_prompt": "A high-angle photograph of a woman with long dark hair reclining on a beige fabric sofa, wearing a black tank top and dark pants. She is holding an open book above her face, reading. A plaid shirt is tied around her waist. Another blue book rests on the back of the sofa near a lamp. Warm, soft lighting creates a cozy atmosphere." }

High-Fashion Editorial Portrait with Pink Coat

{ "subject": { "description": "Subject's facial features, hairstyle, hair color, and makeup must EXACTLY match the provided reference image.", "pose": "Elegant crouching or squatting pose, one hand gracefully touching the chin, looking directly at the camera (maintained from original, unless reference image dictates otherwise)", "features": "[STRICT REQUIREMENT] Facial structure, skin tone, and specific makeup details replicate the reference image precisely." }, "fashion_and_apparel": { "outerwear": "[CRITICAL KEEP] Oversized, structured electric {argument name="coat color" default="pink"} wool trench coat or blazer draped over the shoulders", "inner_wear": "[STRICT REQUIREMENT] The white satin/silk bodysuit with scoop neckline and sheer corset detailing must EXACTLY replicate the clothing in the reference image.", "accessories": [ "None, unless present in the reference image inner wear structure." ], "footwear": "Classic black pointed-toe stiletto pumps" }, "composition_and_setting": { "background": "Minimalist, solid light {argument name="background color" default="pink"} or off-white studio backdrop", "framing": "Full body shot, centered composition", "perspective": "Eye-level or slightly low angle to emphasize the pose and silhouette" }, "lighting_and_aesthetic": { "style": "High-fashion editorial, noir-chic, timeless glamour", "lighting": "Spotlight effect creating a circular halo on the background behind the head; soft directional key light from the front-top to ensure facial details match reference while highlighting the pink coat fabric", "color_palette": "Monochromatic background elements, contrasting sharply with the vibrant electric pink coat and the white inner wear." }, "technical_details": { "camera_feel": "Shot on 85mm lens, sharp focus on subject's face and clothing details, high resolution, clean studio photography" } }

Spontaneous Twilight Rome Convertible Shot

A raw, spontaneous iPhone photograph captured at twilight in {argument name="city" default="Rome"}, showing a young woman with windswept hair laughing as she leans out the window of a {argument name="car model" default="classic Alfa Romeo convertible"}. Warm city lights and the fading sunset catch the genuine joy on her face. The background is a motion-blurred wash of vespas, historic buildings, and pedestrians, emphasizing the car's movement while keeping her sharply in focus. The frame is tilted and has a natural, unedited cinematic grain. 1:1 aspect ratio.

Ultra-Photorealistic Studio Portrait with Fashion Details

2.0 · 3:4 · ultra-photorealistic · Ana de Armas · East Asian · young adult · light · natural skin pores, fine details · dark brown/black · long, wavy, parted in the middle · voluminous, soft shine · brown · black square-frame glasses · direct to camera · natural/minimalist · defined eyes, pink lip gloss · standing, facing forward · straight · hand resting on shirt collar · relaxed by side · neutral, confident, poised · long-sleeve button-up crop top · white · crisp cotton · mini-skirt with front slit · tan · dark brown leather · silver · thigh-high stockings · sheer · black · studio · light beige · smooth plaster · minimalist/none · soft studio lighting · upper right · soft drop shadow on rear wall · three-quarter portrait · eye-level · 85mm prime · f/2.8 · sharp focus on subject · shallow bokeh background

Generating Fractal Glass Gradient Images with Nano Banana Pro

Fractal glass 等距栅格质感的渐变图

Fashion Editorial Studio Portrait

Ultra-photorealistic raw studio portrait, 85mm lens f/2.0, full-frame camera look. Exact uploaded face reference preserved with all natural asymmetries, pores, and skin texture — no beautification. Subject standing slightly off-center in relaxed confident pose, one hand in pocket of {argument name="clothing" default="oversized brown blazer with dropped shoulders"}, other hand holding {argument name="prop" default="small bouquet of slightly wilted pastel flowers"}. Light beige wrinkled button-up shirt loosely tucked, thin brown tie worn off-center, high-waisted wide-leg checkered trousers, black leather shoes. {argument name="background" default="Muted olive-green background and soft beige floor"}. Soft diffused key light from side with gentle shadows and warm tone falloff. Low-saturation Kodak Portra cinematic grading, matte finish, high-end editorial fashion mood

Luxury x E-commerce Split Poster

Create a vertical 9:16 luxury-campaign poster for a fictional crossover product, a disruptive co-branded handbag advertisement between {argument name="brand one" default="HERMÈS PARIS"} and {argument name="brand two" default="拼多多"}. The composition is a violently split, collage-style fashion key visual with a torn-paper seam running vertically down the center, dividing two clashing aesthetics: on the left, refined premium luxury branding in warm Hermes orange, cream paper, and elegant editorial minimalism; on the right, aggressive Chinese e-commerce promotion energy in black and metallic red foil, with loud sale graphics, confetti, ripped stickers, and explosive discount typography. At the top center, place both brands prominently with a large collaboration headline in Chinese, the left logo area styled like a classic luxury house with serif typography and horse-and-carriage emblem, the right logo area in bold red Chinese branding. Below that, add the main headline text in huge Chinese characters: {argument name="headline text" default="颠覆性联名款"}, and a boxed subheadline: {argument name="subheadline text" default="百亿补贴铂金包"}. The centerpiece is one Birkin-style luxury handbag shown front-facing and large, perfectly centered but visually split in half along the torn seam: the left half is orange pebbled leather with gold hardware, the right half is crinkled metallic silver leather with silver hardware, both halves seamlessly merged into one surreal bag. The bag should include 5 clearly visible accessory/product elements around or on it: 1 orange clochette hanging on the left, 1 metallic silver hanging strap with lock on the right, 1 central turn-lock closure with padlock, 1 orange Hermes-style gift box with dark ribbon at lower left, and 1 beige dust bag with small logo near the bottom left. Behind the bag on the left is a painterly orange brushstroke on textured cream paper; behind the bag on the right is a crushed reflective red metallic wrapper surface with spark-like highlights and falling confetti. On the right half, add 8 aggressive promotional text bursts and stickers layered diagonally like an online shopping festival poster: 1 giant white Chinese slogan "百亿补贴 全网最低", 2 "限时秒杀!!", 3 a torn price sticker reading "补贴价 ¥999?!", 4 "万件疯抢", 5 "百亿补贴 官方直补", 6 "直降到底", 7 a large bottom torn banner repeating "补贴价 ¥999?!", and 8 small text "建议零售价 ¥1000000+". On the left margin, add a slim vertical editorial text column with 4 grouped text blocks in a luxury layout: 1 "限量发售 / 全球瞩目 / 2024 LIMITED EDITION", 2 "HERMÈS PARIS MADE IN FRANCE", 3 "CRAFTED FOR ELEGANCE", and 4 "DESIGNED TO DEFY THE ORDINARY". At the bottom, create a black app-like information bar with 3 feature blocks from left to right: 1 a red brand icon with "拼多多" and a search-bar style pill containing "百亿补贴铂金包", 2 a lightning icon with the text "百亿补贴 官方补贴 所以低价", and 3 a shield icon with the text "正品保障 假一赔十 3期免息". Add a thin final slogan line across the very bottom in small Chinese text. Use hyper-detailed commercial product photography, premium graphic design, sharp lighting, embossed textures, foil reflections, paper tears, and strong depth. The overall mood must feel like a world-class art director forced a heritage luxury campaign and a chaotic discount-shopping poster to collide in one image, producing extreme visual tension, irony, and high-impact contrast.

iPhone Flash Glamour Portrait

use this attached photo to create, do not alter face and body, 9:16 aspect ratio, captured as a soft glam portrait shot with {argument name="camera" default="iPhone camera"} using direct harsh flash, bright clean indoor setting, normal standard iPhone quality, no extra sharpness, no HDR, natural unedited iPhone look, warm soft neutral color grading, extreme bright flash highlights and deep sharp defined shadows, {argument name="subject" default="young woman"}; camera perspective: medium close‑up framing focusing on face, neck and upper torso, eye‑level slightly high viewpoint, clean centered composition, subject fills most of the frame, plain light background visible behind, normal depth of field, subject sharply in clear natural focus, soft glamorous framing; pose & movement: gentle posed stance, body angled softly to side, head tilted playfully to one side and turned fully forward toward camera lens, gaze direct, bold and playful straight to viewer, shoulders relaxed and soft, posture graceful, poised and effortlessly charming, slight natural tilt

Premium Fast-Food Product Shot

A premium fast-food product photograph of a loaded hot dog centered against a bold red-and-yellow seamless studio background. The hot dog features a grilled sausage with char texture, soft bun, mustard drizzle, ketchup, onions, and pickles. Dramatic commercial lighting creates vibrant highlights and realistic shadows beneath the hot dog. Ultra-sharp focus, DSLR macro food photography, premium fast-food advertisement style, hyper realistic, 8K. Create a hyper-realistic exploded vertical infographic composition of a hot dog. Top → Bottom structure: Mustard & Ketchup Layer (glossy sauce drizzle texture) → Onion & Pickles (fresh chopped topping detail) → Grilled Sausage (charred grilled texture with shine) → Bun Layer (soft toasted bread texture) → Tray Base (minimal serving tray) Perfect vertical spacing, bold studio background, soft shadows, premium food commercial aesthetic. Add clean infographic labels with thin pointer lines using these exact labels: “Sauce” “Toppings” “Sausage” “Bun” “Tray” Ultra-realistic texture detail, premium food advertisement style, 8K.

High-Contrast Abstract Mixed Media Portrait Prompt

Create a high-contrast artistic portrait of a woman’s side profile in black and white, eyes closed, glossy lips slightly parted, dramatic lighting, minimal white background, bold abstract black paint splashes and ink brush strokes blending into her hair and face, vibrant streaks of cyan, magenta, yellow, and blue paint slashed across her cheek and nose, textured paint splatter details, modern mixed media aesthetic,fine art illustration style, sharp edges with dynamic motion strokes, high detail, ultra-clean composition, poster-ready design, 8k resolution, contemporary abstract portrait aesthetic

Consistent Facial Symmetry Photo Collage for Accessories

A high-quality photo collage featuring the same person with identical facial features and expression, shown in multiple frames wearing different accessories. Each panel includes a unique accessory such as {argument name="accessory list" default="hoop earrings, pearl studs, statement necklace, silk scarf, sunglasses, nose ring, hair clip, beret, choker, minimal gold chain"}. Consistent hairstyle, outfit, makeup, and lighting across all images, soft studio lighting, warm blurred background, realistic skin texture, facial symmetry consistency, ultra-detailed, editorial fashion portrait, 4×3 grid layout, professional photography.

Pair Fashion Generation Prompt

【設定セクション】 [女性の服装名]: {argument name="女性の服装名" default="セーラー服"} [髪の色]: {argument name="髪の色" default="黒髪"} [瞳の色]: {argument name="瞳の色" default="青色の瞳"} [テーマカラー]: {argument name="テーマカラー" default="水色と白"} [スタイルの雰囲気]: 繊細なアニメ塗り、清潔感、白い背景のキャラクター立ち絵 【生成プロンプト本文】 最高品質のアニメーションイラスト。 1人の少年（男性キャラクター）。全身図。 髪の色は[髪の色]、目の色は[瞳の色]です。 《服装の指示》 彼は、[女性の服装名]と社会通念上「対（つい）」となる男性用の服装を着用しています。 ・重要：[女性の服装名]が女性特有のデザイン（例：セーラー服、ドレス、振袖）である場合、女性服のデザインをそのまま適用せず、それに対応する男性の正装や制服に変換してください。 （変換例：セーラー服なら「学ラン」または「ブレザー」、振袖なら「紋付袴」、ドレスなら「タキシード」） ・服装の配色は[テーマカラー]を取り入れ、ペア感を演出してください。 絵のスタイルは、添付画像のような繊細なラインと鮮やかな色彩を持つ現代的なアニメ調で、背景はシンプルな白です。

Hyper-realistic cinematic portrait for product detail page

Facing the right side of the frame, body angled slightly forward, hyper-realistic cinematic portrait of a glamorous {argument name="ethnicity and gender" default="Eurasian woman"} in her late 20s, showcasing a high-end {argument name="product" default="emerald wristwatch"}. [Angle & Gaze]: Explicitly facing towards the right side of the canvas, 3/4 view, sultry gaze directed slightly downward, captivating expression. [Face & Expression]: Alluring expression with slightly parted glossy lips, dewy makeup, defined cheekbones, long dark eyelashes, flawless porcelain skin texture. [Accessories]: Emerald and diamond encrusted wristwatch (prominent), sparkling diamond stud earrings, delicate gold necklace visible. [Outfit]: Elegant black velvet gown (off-shoulder, emphasizing curves), bare shoulders, graceful posture. [Layout & Structure]: Web PDP (Product Detail Page) style layout with asymmetric composition. Product Gallery (left), Buy Box (right). Main image, thumbnails for detail, color, and lifestyle shots. [Lighting & Atmosphere]: Rembrandt lighting, moody atmosphere, dark background with subtle light shafts, shallow depth of field, bokeh from distant chandeliers. [Technical]: 8k resolution, highly detailed, photorealistic, sharp focus on watch and face, soft skin texture. A stylish handwritten signature **'{argument name="signature name" default="Isabella"}'** is elegantly placed at the **Bottom Right corner**. Negative prompt: facing left, looking left, body facing left, cartoon, illustration, anime, 3d render, blurry, distorted, bad anatomy, bad hands, missing fingers, extra fingers, text, watermark, bright lighting, cheerful atmosphere, no jewelry, plain clothes.. A stylish handwritten signature Willy is elegantly and small letters placed at the Bottom Right corner

Cinematic Birthday Portrait Template

A cinematic, high-fashion birthday portrait featuring a woman (uploaded photo) in a a silky cream dr…

Creating LINE Stickers with Nano Banana 2

このキャラクターを参照してかわいくデフォルメ。16種類のLINEスタンプをデザイン。バリエーション豊富なセットになるようにポーズや文字配置を工夫して似たスタンプが無いように仕上げる。台詞は日本語でポップな文字。背景は白。「{argument name="ターゲット" default="女子高生"}」の日常会話で使いやすいセットを作成。

3D Isometric Floating Home Office Illustration

A 3D isometric pastel home office scene where objects appear gently lifted, featuring a modern desk with a laptop slightly hovering, plants slowly floating upward, shelves detached from the wall, and a coffee cup resting in mid-air without spills. Smooth rounded surfaces, soft matte materials, light mint, lavender, and warm beige palette, minimal and clean details, subtle depth, soft ambient lighting, gentle shadows that hint at weightlessness, peaceful futuristic mood, illustration-style render, modern UI-friendly composition.

Masquerade Palace Wallpaper

Create a vertical smartphone-wallpaper style fantasy background illustration set inside an opulent palace room at golden hour. The scene looks out through a tall arched window with ornate black-gold lattice screens toward a softly blurred domed palace and minarets in the distance. On the left, one large deep crimson patterned curtain is pulled aside, with one hanging tassel near the top center. In the foreground, place one dark carved wooden desk covered with luxurious props: one white sealed envelope with a red wax seal, one stack of scattered letters and papers, one black ink bottle, one black feather quill standing upright, one rolled parchment scroll, one ornate gold-and-black masquerade mask, one half-filled glass of red wine, one tall filigree metal lantern containing a lit candle, and two embroidered fabrics draped over the desk, one red and one black-gold. Use warm amber sunlight, dramatic shadows, dust motes, and a romantic mysterious atmosphere, with rich burgundy, bronze, black, and gold tones. Add elegant Japanese message text on the left over the curtain area reading {argument name="message text" default="仮面の奥に、\n真実を隠して。"}, set in a refined serif style in pale gold, with a thin horizontal gold line and small sparkle beneath it. Make the composition cinematic, quiet, and slightly melancholic, as if hinting at palace intrigue and hidden truth behind a mask.

Diptych Sydney Sweeney Style Editorial Portrait

{ "api_version": "3.5", "master_specification": { "project_id": "SYDNEY_SWEENEY_STYLE_V3.5", "rendering_fidelity": "Ultra-Photorealistic / 8K / Raw Photo", "aspect_ratio": "4:5 Portrait Orientation" }, "subject_biometrics": { "primary_subject": "Sydney Sweeney", "facial_architecture": { "skin_finish": "Hyper-realistic skin texture, visible fine pores, soft freckles, dewy highlights on cheekbones and nose bridge", "eye_detail": "Vibrant icy-blue irises with realistic light reflections, dark lash line, and natural feathered eyebrows", "mouth": "Softly parted lips with a natural peach tint and subtle glossy sheen" }, "hair_engineering": { "color": "Layered honey-blonde with platinum highlights and darker ash-blonde roots", "style": "Voluminous 90s blowout, soft bouncy curls, center-parted with curtain bangs framing the face", "physics": "Individual hair strands visible, soft flyaways for authentic realism" } }, "wardrobe_encyclopedia": { "upper_layer_inner": { "item": "Premium ribbed cotton bandeau crop top", "branding_specs": "Embroidered black 'CELINE' text in bold sans-serif font across a 2-inch wide white elastic waistband", "fabric_texture": "Visible vertical ribbing, soft matte cotton finish" }, "upper_layer_outer": { "item": "Lightweight poplin button-down shirt", "pattern_details": "Ultra-fine vertical pinstripes in cerulean blue and crisp white", "draping": "Worn completely open, cuffs rolled up to the mid-forearm, fabric falling naturally away from the torso" }, "lower_body": { "item": "High-quality denim jeans", "wash": "Stone-washed light indigo with subtle whiskering at the hip", "construction": "Visible copper rivets, heavy-duty stitching, and metallic button detail" }, "accessories": { "eyewear": "High-gloss black acetate sunglasses with silver metallic hinges, positioned precisely on the crown of the head", "earrings": "14k gold micro-hoop earrings with a polished finish" } }, "composition_logic": { "layout_type": "Diptych (Side-by-side comparison)", "panel_left_logic": { "emotional_state": "Candid Happiness", "pose_dynamics": "Looking down toward the left, wide smile, eyes partially closed, hands deep in pockets", "vibe": "Spontaneous and joyful" }, "panel_right_logic": { "emotional_state": "Sultry Editorial", "pose_dynamics": "Head tilted slightly upward, eyes looking off-camera, neutral/soft expression, thumb hooked in pocket", "vibe": "Confident and high-fashion" } }, "optical_and_environmental_engine": { "lighting": { "primary_source": "Large softbox from the front-left to minimize harsh shadows", "rim_light": "Subtle backlight to separate blonde hair from the white background", "quality": "High-key, clean, and commercial" }, "b

Zodiac Globe and City Doodles Poster

Use the uploaded image as a character reference. A man or woman sitting casually on a medium-sized 3D Earth globe, with the "{argument name="zodiac" default="Aquarius"}" zodiac constellation displayed above in a Gen Z-style font. Elegant minimalist doodles of "{argument name="city" default="Medan"}" city emerge from the globe, set against a clean and elegant background with a colorful comic-inspired aesthetic. Outfit: wearing an {argument name="clothing" default="anorak jacket, loose black cargo pants, and classic Converse sneakers"}. Modern high-fashion style, rough composition, high contrast, ultra-detailed, sharp focus, minimalist poster design, aesthetic, 8K resolution. -Jevan24-

Censored Garden Portrait

Create a photorealistic medium portrait of a young woman standing outdoors in a sunlit garden café or patio, framed from the top of the head to just below the waist. She has a neat chin-length bob haircut in {argument name="hair color" default="light brown"}, with smooth rounded ends and a center part. Her face is intentionally obscured by a flat opaque square censor block in {argument name="censor block color" default="warm medium brown"}, covering the entire facial area from forehead to chin while leaving the hair outline visible. She faces the camera directly with relaxed shoulders and arms down. She wears exactly 4 visible outfit/accessory elements: a sleeveless beige linen cropped tank top, a darker gray-brown inner cropped tank visible at the neckline and hem, loose gray-brown pants only partly visible at the bottom edge, and a short natural wooden-bead necklace. The background is a softly blurred leafy patio with potted plants, dappled sunlight, a pale umbrella in the upper right, and an outdoor table and chair to the right; use warm late-morning natural light, shallow depth of field, realistic skin texture, film-like colors, and a candid lifestyle photography look. Vertical portrait composition, 3:4 aspect ratio, no text, no signage, no watermark, no extra people.

High Fashion Studio Portrait with Dramatic Lighting

A confident young woman with the same appearance as the reference image, standing in a modern studio…

Tropical Resort Bikini Photoshoot Prompt

{ "subject": { "description": "Young woman with tanned, glowing skin and dark hair styled in a high, tight bun. She has a voluptuous, curvy physique with a naturally heavy, full bust and wide hips.", "apparel": { "item": "String bikini", "color": "{argument name="bikini color" default="Pale mint green"}", "style": "Triangle top with thin straps, tie-side bottoms", "fit": "Tight, accentuating curves" }, "features": { "skin_texture": "High-fidelity skin texture with visible pores, sun damage, and a prominent oily sheen or sweat making the skin glisten. Moles and freckles visible.", "tattoos": "Simple line-art flower tattoo on the outer right bicep, script text tattoo on the left ribcage, script text tattoo on the left hip/upper thigh.", "accessories": "Gold chain necklace, thin gold bracelet on left wrist, gold ring on left hand, pink manicured nails." }, "anatomical_constraints": "Bust volume must remain full and heavy, showing natural gravity and projection consistent with the reference. No reduction in chest size. Soft tissue around the waist and hips must appear natural, not artificially flattened." }, "pose": { "type": "Kneeling lean-forward", "description": "The subject is kneeling on a cushioned lounge chair, leaning her torso forward and supporting her weight on her hands, which are placed near the front edge of the cushion. Her spine is arched, accentuating the hips. Her face is turned slightly to look directly at the camera with a chin-down tilt.", "limbs": { "arms": "Extended forward, elbows straight, hands resting on the weave of the chair frame.", "legs": "Bent at the knees, shins resting on the cushion behind her.", "head": "Tilted slightly, direct gaze." } }, "environment": { "location": "Luxury tropical resort poolside", "elements": [ "Beige stucco building with arched doorways and geometric breeze block details", "Swimming pool with turquoise water", "Beige lounge chairs with cream and grey cushions", "Thatched umbrellas", "Potted cactus plants and palm trees in the background", "Clear blue sky" ], "surface": "Woven rattan or wicker lounge chair with a thick beige fabric cushion" }, "camera": { "perspective": "Slightly elevated eye-level, looking down at the subject", "shot_type": "Medium shot capturing the subject from the knees up", "focal_length": "50mm to 85mm", "depth_of_field": "Subject in sharp focus, background slightly softened but clearly legible", "framing": "Centered subject, filling the frame predominantly" }, "lighting": { "type": "Bright natural sunlight ({argument name="lighting time" default="Golden Hour or Mid-day"})", "direction": "From the upper left (viewer's perspective)", "quality": "Hard, direct light creating distinct shadows on the right side of the face and body. Strong specular highlights on the oily skin (shoulders, forehead, chest).", "shadows": "Deep, defined shadows under the jawline and on the right side of the torso" }, "mood_and_expression": { "emotion": "Sultry, confident, relaxed", "gaze": "Intense, direct eye contact with the view"

Sabrina Carpenter High-Fashion Car Portrait

{ “quality”: “ultra_photorealistic, raw style, 8k”, “camera”: “iPhone 15 Pro Max”, “ligh…

Annotating the 'Attention Is All You Need' Paper

この論文を理解するのに助けをください。重要内容(図や数式)に東グラミで表示し正確に理解できるように注釈を付けてください(手で描くスタイルで)