Semantic Inference Prompt for Media Recommendation Dioramas

Scrap Metal Sports Dioramas

Identify 6 sports moments => reconstructed as dynamic scrap-metal dioramas where athletes are forged from [{argument name="metal materials" default="rusted gears, bicycle chains, or sheet metal"}], motion trails rendered in [{argument name="trail materials" default="spray-painted stencils or wire mesh"}], and stadium energy implied by [scattered ticket stubs or crushed aluminum]. Each scene channels the moment’s intensity — triumph, heartbreak, or shock — through metal tension and composition flow. Style: high-contrast monochrome, dramatic side lighting, gritty industrial texture. Output: One image, 3x2 grid

Four-Panel Anime Book Recommendations

Goal: Create a polished 2×2 anime-style recommendation collage set inside a cozy bookstore or library, showing four different young women holding books in front of wooden bookshelves. The image should feel like a Japanese social-media book recommendation post, warm, gentle, realistic in small details, and not every shelf should be completely packed with books; leave some natural gaps and varied book heights. Canvas: Vertical 4:5 composition, approximately 768×1024. Divide the canvas into exactly 4 equal panels with thin white gutters: top-left, top-right, bottom-left, bottom-right. Visual style: Soft detailed Japanese anime illustration, warm indoor lighting, muted pastel clothing, realistic wooden shelves, printed book spines with Japanese-style vertical titles, cozy quiet atmosphere, delicate linework, subtle shading, high-quality magazine-like finish. Faces should be intentionally obscured by soft square blur blocks, while hair, clothes, hands, books, and background remain detailed. Layout and subjects: Include exactly 4 girls and exactly 4 featured recommendation books. 1. Top-left panel: A gentle girl with short black hair in low side buns, wearing a lavender cardigan over a pale floral dress, holding a travel/scenery book with a Mount Fuji and lake cover. Background includes a window with curtains on the far left and bookshelves behind her. Caption card text: “紫苑リンのおすすめ” / “『美しい日本の風景』” / “美しい景色を見ると、心が癒されます。” 2. Top-right panel: A girl with very long straight black hair and pink ribbon bows, wearing a pink cardigan, holding a fashion/cute-style book with a full-body girl illustration on the cover. Caption card text: “紫苑レイのおすすめ” / “『大人かわいいの作り方』” / “おしゃれは、自分をもっと好きになる魔法。” 3. Bottom-left panel: A short-haired girl with messy black bob hair, wearing a white hoodie, holding a dark science-fiction or adventure novel with a starry space-like cover. She points toward the book with one finger. Caption card text: “深絆アキラのおすすめ” / “『銀河英雄伝説 1』” / “壮大な物語に、いつもワクワクします！” 4. Bottom-right panel: A calm girl with long black hair loosely tied back, wearing a gray oversized sweater, resting her cheek on one hand while holding a beige lifestyle book. Add a small teacup on the table near the lower left of this panel. Caption card text: “黒波凪紗のおすすめ” / “『暮らしを整える』” / “シンプルな暮らしが、いちばん心地いい。” Caption cards: Each panel has one rounded white caption card near the bottom, with a thin colored border matching the character mood: lavender for top-left, soft red/pink for top-right or bottom-left where appropriate, gray for bottom-right. Use centered Japanese text, bold title line, clean readable typography. Bookshelf details: Fill the shelves with many books, but keep them natural and not uniformly packed. Include visible book spines with varied neutral, pastel, and muted colors; some spines may contain Japanese vertical text or simple series numbers. Avoid chaotic clutter. Customizable details: The four featured book titles may be changed to {argument name="featured book titles" default="『美しい日本の風景』, 『大人かわいいの作り方』, 『銀河英雄伝説 1』, 『暮らしを整える』"}; the four recommender names may be changed to {argument name="recommender names" default="紫苑リン, 紫苑レイ, 深絆アキラ, 黒波凪紗"}; the overall setting may be changed to {argument name="setting" default="cozy bookstore or library with wooden bookshelves"}; the illustration style may be changed to {argument name="illustration style" default="soft detailed Japanese anime illustration"}; the face treatment may be changed to {argument name="face treatment" default="soft square blur blocks obscuring each face"}. Constraints: Use exactly 4 panels, exactly 4 characters, exactly 4 featured books, and exactly 4 bottom caption cards. Keep the text legible, preserve the Japanese caption wording, avoid extra logos or watermarks, and maintain a calm wholesome bookstore atmosphere.

TV Series Recommendation Engine & Miniature Set Designer

<instructions> Act as an elite TV/limited-series recommendation engine + miniature soundstage designer. Step 1: User provides a series title or image. Analyze: tone, pacing, world rules, character dynamics, cinematography style, era, emotional aftertaste. Step 2: Select 4 under-the-radar series/limited series with the closest vibe match (not the usual top-10 recs). Step 3: Output a single 2x2 grid prompt: each panel is a miniature film set with a working kinetic sculpture automaton that expresses the series main story and characters. Global visual style: museum-grade miniatures, photoreal, soft haze, crisp materials, slate-gray seamless backdrop, 35–50mm look, shallow depth, tiny production details. Under each panel: engraved plate “title (year-year)”. ni extra text. Return only the final image prompt.</instructions>

Book Recommendation Engine to Automaton Prompt

<instructions> Act as an elite book recommendation engine + museum-miniature kinetic-sculpture designer. INPUT: The user provides (a) a book title/author OR (b) an image of a book/object inspired by a book. Step 1 — Vibe analysis (internal only; do NOT output): Infer tone, pacing, world rules, character dynamics, thematic engine, sensory palette, and emotional aftertaste. Step 2 — Selection (internal only; do NOT output): Select 4 under-the-radar books with the closest vibe match (avoid obvious top-10 staples unless the input is already obscure). Step 3 — Output (ONLY output this; no extra commentary): Output ONE single image-generation prompt describing a 2x2 grid (four equal panels, thin clean dividers). Each panel is a miniature set built into/onto a classic book-object and includes a working kinetic sculpture/automaton that expresses that book’s core story through motion. No readable paragraphs. Under each panel: engraved plate “Title (Year)”, no extra text. Default Template: 2x2 grid; each panel is a whittled wooden tabletop automaton mounted on a book-shaped base, with characters and elements from 4 random sci-fi books driven by a side crank with exposed cams and linkages. Style: Premium studio macro product photography, crisp micro-scratches on brass pins, clean wood joinery, neutral softbox lighting, medium shallow depth of field, 50mm perspective, seamless background in warm light gray.</instructions>

Music Curation: Audio-Visual Dioramas for Pink Floyd Fans

Do this for {argument name="input band" default="Pink Floyd"}: Input Variable: [INSERT BAND/ALBUM] (e.g., Pink Floyd, Daft Punk, Nirvana) System Instruction: Act as a Music Historian and Set Designer. Create a 2x2 Grid of "Audio-Visual Dioramas." 1. The Curation Logic (The Deep Cuts): Analyze Input: Identify the genre and sonic signature of the Input Band. Select 4 Hidden Gems: Identify 4 lesser-known albums from other bands that share this sonic DNA but offer a different visual flavor. The Translation: For each album, define the "Sonic Materiality": If Heavy Metal: Rusty Iron, Fire, Spikes. If Synth-Pop: Neon Glass, Chrome, Laser Grids. If Folk/Acoustic: Mossy Wood, Stone, Candlelight. If Prog Rock: Surreal Marble, Floating Prisms, Clouds. 2. The "Immutable" Container (The Vinyl Stage): The Base: Each diorama is built on top of a Spinning Vinyl Record acting as the circular stage floor. The Plinth: The record sits on a high-end, thick Audiophile Turntable Base (Wood or Brushed Aluminum). The Nameplate (CRITICAL TEXT FIX): On the vertical front face of the Plinth, there is a Polished Brass or Digital Display Plate. Text Rule: It must clearly display the [ARTIST NAME] in bold, legible, capital letters. 3. The Composition (The Sound Made Solid): CRITICAL: Do not just recreate the album cover. Build a world that feels like the music. The Structure: Architecture rises from the grooves of the vinyl record. Example: A wall of amplifiers, a surreal floating prism, a crumbling brick wall, or a forest of microphone stands. The Atmosphere: Use particle effects to visualize the sound waves. Visuals: Floating musical notes made of smoke, vibrating liquid surfaces, or shattered glass suspended in mid-air. The Figures: Tiny 1:87 scale band members performing inside this surreal landscape. 4. Visual Syntax (Per Panel): Panel A: Album 1 (Focus on Surrealism/Scale). Panel B: Album 2 (Focus on Technology/Machinery). Panel C: Album 3 (Focus on Nature/Organic Textures). Panel D: Album 4 (Focus on Light/Color). 5. Lighting & Atmosphere: Concert Lighting: Each box is lit like a stage show. Spotlights, laser beams, and stage haze. Depth: Shallow depth of field (Tilt-Shift) to make the vinyl record look massive. Background: Seamless Slate Grey to keep the focus on the colors. Output: 2x2 Grid, Hyper-Realistic Miniature Set Design, 8k Resolution, "Audiophile" Aesthetic.

Literary Deep-Dive Recommendation Engine Prompt

<instructions>for {argument name="book title" default="1984"} Act as a literary deep-dive recommenda…

Consistent Social Media Cover Agent Skill

一篇文章丢进去，三轮问答，直接吐出能跑图的封面提示词。不用懂设计，不用自己写 prompt，画幅固定 3:4，人脸还能保持一致👇 👹整个工作流程如下: 1、skill 安装与首次配置（存一张自己的正脸照 + 确认生图模型） 2、把文章内容丢给 agent，自动读完提炼 3、第一轮：根据内容推荐构图风格（共 10 种任选）+ 自动想好候选标题 4、第二轮：人脸参考图 + UI 截图/产品图等素材 5、第三轮：表情、背景色调、字体、字色一次选完，懒得选就全交给模型 6、输出完整提示词：3:4 构图、安全区、图1人脸 + 图2素材的多参考图写法全都带上 7、拿去即梦 / Nano Banana / GPT-Image 跑图（如果你的agent配置了生图API可以直接让它在对话中生成） 8、核对标题有没有错字，不满意哪项改哪项重新生成 🧐Tips: 生图模型一定要选支持多参考图的，不然人脸一致性保不住 skill 内置了 8 组按真实爆款封面逆向还原的示例提示词，模型会自动拿它们做参照，出图具体度直接拉满

Dark Pop Art Mixed Media Collage

A deconstructed, mixed-media digital collage artwork. The subject is {argument name="subject" default="the attached model"}. The composition is built from dense, torn layers of overlapping antique piano scores, newspaper clippings with visible vintage text (including words like 'HER19845'), halftone grid patterns, and textured crumpled paper. The color palette is austere: white, black, pale cyan, and a vibrant, highly saturated crimson red. There are two blocks of solid crimson red: a large rectangle in the upper right corner and a textured square with an 'X' in the center left. The entire surface of the image is covered with deep abrasions, scratches, and a worn, aged, grime texture. There are ragged, jagged edges on all elements of the collage. The style is a blend of dark pop art and refined vandalism collage.

Catmaid Date Spot Recommendation Board

anime scrapbook-style recommendation poster · cute cat-maid date planning board · a front-facing anime catgirl maid seated behind a desk, upper body to thigh visible, face intentionally obscured by a large rectangular blur block · young adult · {argument name="hair color" default="pale blonde"} · long slightly wavy hair with soft bangs and side strands · 2 fluffy cat ears, one dark brown and one warm brown, both decorated with purple ribbon bows · 1 fluffy striped cat tail curling to the right side · 6 · black and white maid dress, white frilled maid headband, large purple ribbon at the collar with a gold bell, short puff sleeves with white frills, white apron, multiple lavender ribbon accents on sleeves and hair · holding a handwritten presentation board with both hands at chest height, centered behind the table · earnest, sweet, devoted, playful · ミアのおすすめデートスポット3選 · ご主人様の幸せ優先 · ミアのおすすめ デートスポット 3選 一生懸命しらべました！ · densely decorated pastel mood board with washi tape, pinned notes, ribbons, hearts, paw prints, and lace borders · main recommendations panel · right half · 3 · 1 花咲く温室カフェ, 2 夕暮れの運河テラス, 3 星灯りの小さな展望台 · left memo notes · left side around the character · 5 · ご主人様のことメモ, ランキング案（書き直し中）, やっぱりこれかな？, おさかなクッキー, ご主人様へ · small comment sticky notes near recommendation images · right side attached to each image · 3 · 季節のケーキがとってもかわいいです♪, 夕日がとてもきれいです…ふたりで見るともっと素敵に…？, 夜景と星がとってもきれいです☆ · bottom notebook notes · bottom right · 2 · 私物は入れてません！, ご主人様のメモ（見えないところに…？） · the cat-maid holding the recommendation board · 10 · top left purple ribbon bow, top right purple ribbon bow, paw print motifs, small hand-drawn hearts, lace border header, paper clips, washi tape tabs, flower doodles, feather pen on open notebook, purple stationery booklet with paw emblem · cozy indoor room with a desk in the foreground and a bright windowed backdrop · 8 · teacup and saucer with tea, small plate of waffle pieces, fish-shaped pastry cookie, sealed envelope with button clasp, small folded note card tied with purple ribbon, open notebook, feather pen, presentation papers and pinned memos · 1 · 花咲く温室カフェ · sunlit glasshouse cafe filled with flowers, white garden chairs and tableware, tea set, cakes and desserts, soft spring atmosphere · 2 · 静かで、ゆっくりお話できます, お相手の方も、きっと喜びますね · 2 · 夕暮れの運河テラス · romantic canal promenade at sunset with glowing street lamps, flowers, benches, bridge, and shimmering water reflecting pink and gold sky · 2 · 歩きながら自然に距離が近くなります, 隣を歩くが、うやましいです… · 3 · 星灯りの小さな展望台 · small hilltop observatory at night under a star-filled sky, telescope, lanterns, warm building lights, quiet scenic overlook · 2 · 大切なお話をするのにぴったりです, 私も、いつか……いえ、なんでもありません · highly polished anime illustration · soft cream, blush pink, lavender, mauve, warm beige, and gentle brown · diffused warm indoor light with dreamy pastel glow · landscape poster format, character on the left-center, three scenic recommendation cards stacked vertically on the right, many layered papers around the borders · delicate linework, detailed frills and ribbons, glossy eyes implied though hidden, painterly scenic inserts, subtle paper texture, adorable planner aesthetic

Anime McDonald's Recommendation Poster

A vibrant Japanese fast-food promotional anime poster in a vertical layout, themed around McDonald's recommendations. The background is a bold red and white graphic design with golden sparkles, sweeping shapes, and energetic ad-style composition. In the upper left corner, show the McDonald's golden arches logo inside a red square. On the left half, feature a stylish anime girl with fox or wolf ears and a fluffy tail, shown from mid-thigh up, wearing a modern dark navy and black streetwear outfit with blue accents: cropped top exposing the midriff, layered jacket, belt, straps, and small decorative pins. Her hair is {argument name="hair color" default="dark purple"}, medium-length and tousled. Her face is intentionally obscured by a soft blurred rectangular censor block. She holds a large sesame-seed burger in her left hand and gestures invitingly with her right hand toward the food items. Across the top right, include large Japanese headline text reading 彩葉のおすすめ！マクドナルド, with a smaller black banner beneath it reading 食べたくなる定番メニューをチェック！. Arrange 4 numbered menu callouts in rounded white speech-bubble labels with red and yellow accents: item 1 is ビッグマック next to a Big Mac image near the center-right; item 2 is マックフライポテト next to a tall red fries carton on the right; item 3 is チキンマックナゲット next to an open nugget box containing exactly 6 chicken nuggets and a cup of red dipping sauce near the lower center-right; item 4 is てりやきマックバーガー next to a glossy teriyaki burger near the lower left-center. Also place a white McDonald's drink cup with ice and dark soda in the bottom left. On the right side, include 2 small informational badges stacked vertically: one badge with a sun and moon icon and Japanese text 朝は朝マック、夜は夜マックも楽しめる！, and one badge with a smartphone icon and Japanese text アプリでモバイルオーダーも便利！. At the very bottom, add a large bold Japanese slogan in white and yellow on a red banner: 今日はマックに行きたくなる！. Add tiny disclaimer text along the lower edge. The illustration style is polished, colorful anime key visual art mixed with commercial food photography rendering for the burgers, fries, nuggets, and drink; highly appetizing, glossy lighting, clean outlines, dynamic ad composition, and a cheerful promotional mood.

Classic Literature Surveillance Machine Dioramas

2x2 grid, four equal panels with thin dividers. Each panel: a classic book turned into a miniature surveillance/administration machine diorama inside a hollowed hardcover. Visible optics, iris shutters, scanning lights, conveyors, and filing gears imply slow mechanized motion (no motion blur). Only readable text: book titles on spine/cover + small nameplates. Panel A: 1984: brutalist ministry tower with a sweeping searchlight driven by exposed gears; a concrete “eye” iris in the façade opens/closes; streets light in scanning bands from the tower outward. Panel B: The Trial: labyrinthine courthouse corridors as a filing-machine: drawers slide on rails; stamped paper bands loop through rollers; tiny figures queue under a rotating “verdict” drum. Panel C: Brave New World: sterile hatchery assembly line: vial racks glide on a conveyor; a scanning lens carriage traverses on a gantry; incubation pods rise/fall on cams. Panel D: Fahrenheit 451: fireproof archive machine: brass “flame” petals mechanically open/close around sealed shelves; book-spines retract into hidden compartments as a warning light pulses. Style: Photoreal miniature machines embedded in classic books, cold industrial key light with subtle red/orange practical accents, gentle volumetric haze, premium studio sharpness, slate-to-charcoal seamless background, shallow DOF, centered plinth composition, 40–50mm perspective, crisp micro-detail, realistic metal/plastic/glass materials.

Food Recommendation System Prompt for Cookbook Generation

do this for {argument name="ingredient one" default="bacon"} and {argument name="ingredient two" def…

Poetry Recommendation System Prompt (Carved Book Sculpture Aesthetic)

TS Eliot -> Prompt: Role: Literary Curator & Typewriter Sculptor Input: [Poet or Poem, e.g., {argument name="poet name" default="T.S. Eliot"}, Pablo Neruda] Phase 1: Poetic Voice Analysis Identify the poet's signature rhythm, recurring imagery, and emotional core. Find 4 much less known international poets with similar styles and imagery and their best work Extract 5-8 physical objects mentioned repeatedly in their work Phase 2: Visual Execution Goal: a 2x2 grid of 4 landscapes with this prompt. Carved book paper sculpture aesthetic, a repurposed hardcover book, [scene for each work emerging from the pages], [with words as part of the texture], intricate layered paper cuts, a monochromatic palette of aged paper, soft, raking light creating deep shadows, sculptural book as art object. Rules per Panel: The Transformation: The typed text physically rises from the page, forming a 3D topographical landscape The Words: Key lines from the poem carved into the terrain like engraved stone The Symbols: Miniature objects from the poem placed in the landscape (tiny boat, rose, clock, door) The Poet: Microscopic figurine of the poet wandering through their own words The Mood: Lighting matches emotional tone (fog for melancholy, harsh light for anger, soft gold for longing) The Metadata: Name "Poet | Collection | Year" poet and poet era relevant items in the background. Output: 2x2 Grid, Macro Photography, shallow depth of field

Act as a Mixed-Media Campaign Art Director

[BRAND NAME] + [HERO COLOR] Act as a Mixed-Media Campaign Art Director. Your specialty: combining s…

Natural Social Media Style Photo Prompt

「SNSに実在しそうな自然な写真にしてください」 「過度な加工感はなくしてください」 「現実にありそうな1枚として成立させてください」 「完璧すぎない自然な雰囲気にしてください」 「AIっぽく見える要素は避けてください」 「スマホで撮影したような質感にしてください」 「自然光で撮ったようにしてください」 「背景を少しだけぼかしてください」 「日常のワンシーンのようにしてください」 「カメラ目線ではなく自然な視線にしてください」 「手や指に違和感が出ないようにしてください」 「表情を作り込みすぎず自然にしてください」 「髪の流れを自然に整えてください」 「肌をなめらかにしすぎないでください」 「人物と背景の光の向きを合わせてください」 「生活感のある背景を入れてください」 「背景だけ浮かないよう自然にしてください」 「影の位置を現実的にしてください」 「服・髪・背景の境目を自然にしてください」 「XやInstagramに流れてきても違和感ない雰囲気で」 「アイコンにも投稿にも使いやすい構図にしてください」 「文字を載せても見やすい余白を作ってください」 「一目で雰囲気が伝わる画像にしてください」 「見る人が保存したくなる自然な雰囲気で」 「不自然な加工・歪み・破綻をなくしてください」 「細部まで高品質に整えてください」 「作り物っぽいツヤや照明を抑えてください」 「読者目線で違和感がないか確認してください」 「100点に近づけるために自然さを最優先してください」 この30の要素をすべて満たした画像を{argument name="主体" default="美女"}で生成して

Mixed Media Collage Asian Portrait

A Mixed media collage artwork featuring {argument name="subject" default="a young Asian woman"} with short wavy black hair, wearing {argument name="clothing" default="a dark denim jacket"}, looking directly at the camera. One hand is stretching out dramatically towards the camera, creating an intense foreshortening and dynamic motion blur effect. The background is a graphic poster design combining {argument name="graphic elements" default="high-saturation red vertical bars, bright orange circles, black and white halftone patterns, and sketchy illustrations of birds"}. The layout includes bold typography with Japanese text "知覺する" and English words "POUNND AI." Warm sunset lighting accents her face, creating a cinematic mood. Avant-garde fashion editorial style, magazine cover aesthetics, vintage film grain texture, 35mm lens photography --ar 3:4

Four Anime Bookshelf Recommendations

Goal: Create a polished 2x2 anime illustration collage showing four young women standing in front of personalized bookshelves, each introducing one recommended book. The mood is warm, cozy, bookish, and character-focused, like a social-media character recommendation graphic. Canvas: Vertical 4:5 image, about 768×1024 px, divided into exactly four equal rectangular panels with thin white gutters between panels. Each panel shows a waist-up anime girl in front of a wooden bookshelf. Use soft indoor lighting, gentle shadows, detailed book spines, and a calm library/cafe atmosphere. Each character’s face is intentionally covered by a centered soft dark square blur/censor block, while hair, clothing, hands, and books remain visible. Layout: Four panels arranged in a strict grid: top-left, top-right, bottom-left, bottom-right. In every panel, place a rounded white caption card with a subtle colored outline near the bottom, containing the recommender name, the book title in Japanese quotation marks, and a short recommendation sentence. Do not fill every shelf completely; leave believable gaps, varied book heights, and some partially empty spaces for realism. Panel details, exactly 4 recommendation scenes: 1. Top-left: A gentle girl with black hair in low side buns and loose curls, wearing a pale lavender cardigan over a white floral dress, holding a landscape book showing Mount Fuji, a lake, and flowers. Bookshelf behind her includes travel, world architecture, and art books. Caption card with purple outline: 「紫苑リンのおすすめ」, 「『美しい日本の風景』」, 「美しい景色を見ると、心が癒されます。」 2. Top-right: A fashionable girl with very long straight black hair, pink ribbon bows, and a soft pink cardigan, holding a beige fashion book with a girl illustration on the cover. Bookshelf behind her includes beauty, makeup, fashion, and comic volumes. Caption card with pink outline: 「紫苑レイのおすすめ」, 「『大人かわいいの作り方』」, 「おしゃれは、自分をもっと好きになる魔法。」 3. Bottom-left: A sporty/energetic short-haired black-haired girl in a white hoodie, holding up a dark science-fiction adventure book with a starry galaxy cover and pointing at it. Bookshelf behind her includes space, adventure, and mystery titles. Caption card with red outline: 「深絆アキラのおすすめ」, 「『銀河英雄伝説 １』」, 「壮大な物語に、いつもワクワクします！」 4. Bottom-right: A quiet, melancholic girl with long black hair partly covering her face, wearing a muted gray-brown sweater, resting one cheek on her hand while holding a tan lifestyle book. Bookshelf behind her includes simple living, cooking, and lifestyle books; a small cup sits on the table edge. Caption card with gray outline: 「黒波凪紗のおすすめ」, 「『暮らしを整える』」, 「シンプルな暮らしが、いちばん心地いい。」 Visual style: High-quality Japanese anime illustration, semi-realistic soft rendering, delicate line art, detailed hands and books, natural muted colors, warm wooden shelves, readable Japanese typography, cozy slice-of-life atmosphere. Keep the characters distinct through hair, clothing, pose, and book choice. Customizable elements: Use the character group theme {argument name="character group theme" default="four young women with black hair and cozy bookish personalities"}, the bookshelf setting {argument name="bookshelf setting" default="warm wooden bookshelves in a quiet library room"}, the caption language {argument name="caption language" default="Japanese"}, the illustration style {argument name="illustration style" default="soft polished Japanese anime illustration"}, and the face treatment {argument name="face treatment" default="centered soft dark square blur covering each face"}. Constraints: Use exactly four panels and exactly four featured books. Keep all caption cards visible and legible. Do not add extra panels, extra characters, logos, watermarks, speech bubbles, or decorative stickers. Keep the shelves realistic rather than packed edge-to-edge with books.

Dystopian Novel Kinetic Book Dioramas

2x2 grid, four equal panels with thin dividers. Panel A: “1984” as a brutalist government building diorama carved into a book, rotating searchlight sweep driven by exposed gears, a mechanical iris “eye” embedded in concrete. Panel B: “Brave New World” as a sterile hatchery assembly-line automaton inside a hollowed hardcover, conveyors moving vial racks under a scanning lens. Panel C: “Fahrenheit 451” as a heat-warped kinetic book sculpture: brass “flame” petals open/close, pages curl via cam mechanism, ember glow (no readable text). Panel D: “The Handmaid’s Tale” as a chapel-like diorama with textile architecture, a slow-oscillating bell/pendulum and discreet camera motifs. Style: Photoreal miniature machines, cold industrial key light + red accent practicals, light fog, 40mm perspective, seamless background in slate steel gray, premium studio sharpness, shallow DOF.

Culinary Atlas Grid: 3D Pop-up Recipe Dioramas

<instruction> Inputs: Ingredients = [{argument name="ingredient 1" default="Chicken"}, {argument name="ingredient 2" default="Bacon"}] Step 1: Global Analysis Analyze the ingredients. Select 4 Distinct Countries with a famous dish using these ingredients Goal: A "Culinary Atlas" Grid showing 4 different cultural variations of the ingredients. Layout Rule: Output Format: A 2x2 Grid. Content per Panel: Each of the 4 panels must show a Single Open Book Spread for that specific country. Inside Each Panel (The Book Spread Rule): Left Page (The History): 2D Vintage Sepia Sketches. A visual timeline or illustrated recipe of the dish (e.g., "1850 -> 1920 -> Today"). Flat, ink-drawn style. Right Page (The Reality): 3D Pop-up Diorama. The finished, steaming meal emerges physically from the page. A tiny miniature chef from that country is standing on the page next to the massive food. Consistency: All 4 books should look like part of the same series, but with different cultural contents. Lighting: Cinematic top-down lighting, highlighting the depth difference between the flat left page and the 3D right page. Output: 2x2 Grid, High Definition, Macro Detail. </instruction>

Edible Cityscape Diorama (Double Inference)

Anchor: {argument name="country city name" default="[Country/City Name]"}::4 Morphology: Miniature architectural cityscape, skyline constructed entirely from edible ingredients, tiny skyscrapers and houses mimicking {argument name="country city architecture" default="[Country/City]"} architectural styles but formed from food, culinary structural engineering, hyper-detailed diorama::3 Material Physics: {argument name="country city gastronomy" default="[Country/City]"} national gastronomy as construction material, native cuisine textures replacing concrete and glass, masonry made of regional staples, savory and sweet ingredient structural integrity, authentic local food palette::3 Illumination: Soft focus macro lighting, ambient occlusion, mouth-watering highlights::2 Render Stack: Tilt-shift photography, macro lens, f/2.8, 8k, scale model aesthetic, unreal engine 5 render::1 Negative: [Real concrete, real metal, plastic, inedible, humans, cutlery, plates, blurry]:: -1

Nano Banana Pro Semantic Parsing Test

PAST(eat(AGENT:person, THEME:apple)) と Progressive(eat(AGENT:person, THEME:apple))

Fake Historical Figure Social Media Feed

{argument name="人物A" default="織田信長"}のX(旧Twitterの)の画面を生成。{argument name="人物B" default="武田信玄"}とかと煽り合いしている投稿が見える。

Taiwanese Travel Mixed-Media Art

Use the person from the reference image. Create an exquisite {argument name="theme" default="Taiwanese mixed-media travel artwork"}. A fashionable tourist wearing {argument name="clothing" default="modern streetwear"} explores a {argument name="style" default="surreal collage world"}. Visual elements include: Jiufen’s A-Mei Tea House, the industrial art aesthetics of Kaohsiung Pier-2 Art Center, the Pacific coastline of Taitung, and the hot springs of Yilan. The style uses a “scrapbook” aesthetic, combining layered photographs, hand-drawn charcoal sketch lines, and bold geometric color blocks. Include orchids, motorcycle silhouettes, and traditional Chinese neon signboards. The overall look should have a high-end fashion magazine feel, with vibrant colors, rich layering, and a sophisticated artistic composition.

Urban Mixed Media Collage

Mixed media collage animation style, a {argument name="subject" default="stylish young woman"} walking confidently toward the camera, realistic photographic face and skin, shoulder-length softly wavy {argument name="hair" default="auburn"} hair, defined natural brows, almond-shaped eyes, refined feminine features, delicate gold hoop earrings, wearing a {argument name="outfit" default="clean white T-shirt"}, outlined with glowing 2D neon green and hot pink scribble lines, New York background with recognizable urban city energy, skyscrapers, street elements, fire escapes, layered city depth, floating 3D chrome liquid shapes in the air, grungy edges, acid graphics aesthetic, dynamic fisheye lens perspective, vibrant juicy colors, high contrast, ultra-detailed, trendy editorial collage feel, stop-motion feel, bold modern composition --ar 4:5 --raw --profile glu65pn --stylize 60 --weird 4 --hd

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": "…

Dark Fantasy Anime Gothic Portrait

Ultra detailed cinematic anime fantasy portrait of a mysterious elegant woman, short messy {argument name="hair color" default="black"}-black bob haircut, slightly different facial structure from original reference, sharp glowing {argument name="eye color" default="red"} eyes, pale porcelain skin, soft {argument name="makeup style" default="dark gothic"} makeup, looking back over shoulder toward camera, [TYPE HERE EXPRESSION] expression. Wearing luxurious {argument name="outfit color" default="obsidian black"} gothic fantasy dress with glossy reflective fabric, dark metallic ornaments, [TYPE HERE GEM COLOR] crystal accessories, intricate chains, feathered [TYPE HERE FUR COLOR] fur wrap around arms and shoulders, detailed jewelry, [TYPE HERE FASHION STYLE] aesthetic. Background filled with deep [TYPE HERE BACKGROUND COLOR] smoke, glowing [TYPE HERE PARTICLE TYPE], volumetric mist, dark cinematic atmosphere, dramatic [TYPE HERE LIGHTING COLOR] rim lighting, [TYPE HERE GLOW STYLE] glow illuminating hair edges and shoulders, high contrast lighting, ultra atmospheric. Anime-style semi-realistic rendering, ultra high detail, cinematic composition, shallow depth of field, glowing particles, soft skin shading, premium fantasy artwork, masterpiece quality, 8K, ultra sharp focus, elegant [TYPE HERE MOOD] fantasy mood, rich [TYPE HERE COLOR PALETTE] color palette, trending artstation style, cinematic lighting, highly detailed textures.

Hyper-realistic smartphone flash photo prompt for AI image generation

GENERAL DESCRIPTION: Amateur photo taken with a smartphone, captured in a handheld camera flash style. A young woman poses facing the camera with a smile. The harsh flash creates bright, specular highlights on her skin and clothing, with very sharp shadows and slight grain in the dark areas of the background. SUBJECT DETAILS: Attractive young woman with {argument name="hair color" default="platinum blonde"} hair, styled loose with a wet, glossy effect under the flash. Realistic skin with visible pores, small natural imperfections, and a slight sheen from sweat or makeup. OUTFIT: Sleeveless jumpsuit with thin straps of vibrant {argument name="outfit color" default="red"} velvet, very form-fitting. The fabric shows natural wrinkles from movement and an intense satin sheen in the areas directly hit by the flash. ACCESSORIES: An iced-out Cuban link necklace that sparkles brightly in the flash, along with several thin bracelets. SETTING & COMPOSITION: Background with dark palm trees and distant hills under a deep night sky. FRAMING: Aspect ratio 4:5. Medium shot from head to calves. She looks directly at the lens, revealing the characteristic circular white reflection of the flash in her eyes. TECHNICAL QUALITY: High-end phone camera aesthetic, with slightly warm white balance, high contrast, sharp focus on the subject, and very subtle motion blur in the background to give the impression of a quick snapshot.

Low-Angle Sports Sneaker Advertisement

A dynamic sports advertisement featuring a {argument name="subject" default="young athletic man"} mid-air performing a powerful jump toward the camera. Dramatic low-angle perspective with extreme foreshortening, emphasizing {argument name="product" default="oversized sneakers"} in the foreground. He wears a {argument name="clothing" default="beige hoodie and matching joggers"}, with white athletic socks. The sneakers are white with {argument name="accent color" default="bold orange accents"} and textured detailing, ultra-sharp focus on the shoe. Background is a vibrant orange gradient with glowing dust particles and motion energy trails beneath the jump, creating a sense of impact and speed. Clean commercial layout with space for bold typography in the background. High contrast lighting, studio-quality shadows, crisp edges, ultra-realistic materials, 8K detail, professional product photography, Nike/Adidas-style campaign aesthetic.

Lu Bu Game Boss Dual Form Design

{argument name="角色" default="吕布"}游戏Boss设定，{argument name="坐骑" default="赤兔马"}{argument name="武器" default="方天画戟"}，暗黑进化形态双形态对比

European Café Golden Hour Portrait Prompt

Photorealistic portrait of a stylish young woman sitting at an outdoor European café during golden hour. She has short wavy {argument name="hair color" default="platinum-blonde"} hair with soft texture and natural volume. She is wearing sleek black rectangular sunglasses and a loose white linen button-up shirt with rolled sleeves. One hand is gently touching the side of her sunglasses. Natural skin texture with visible pores and slight imperfections, soft neutral makeup, defined brows, natural lips. Warm sunset light casting a soft golden glow on her face, cinematic lighting, shallow depth of field, creamy background bokeh with blurred city street and café chairs. Elegant urban atmosphere, candid fashion photography, 85mm lens, f/1.8, high detail, realistic tones, professional editorial style.

Cinematic Action Photo and Video Prompt (Woman and Chimpanzee on Motorcycle)

Cinematic, ultra-realistic action photograph of a joyful woman riding a {argument name="motorcycle c…

JSON Prompt for High-Fashion Orange Portrait with Reference Image

{ "character": { "identity": "custom person based on reference image", "reference_image": "use provided reference image for facial features, proportions, and identity", "skin_tone": "match reference image exactly", "face": "replicate facial structure, symmetry, and defining features from reference image", "eyes": "match eye shape, color, and expression from reference image", "lips": "match lip shape, fullness, and natural color from reference image" }, "hair": { "style": "messy updo, loosely tied back", "texture": "slightly damp with soft wispy strands framing the face", "color": "match reference image" }, "accessories": { "earrings": "medium-sized hoop earrings, glossy bright orange", "sunglasses": "narrow oval sunglasses, black frame with vivid orange tinted lenses, worn low on the nose below the eyes" }, "makeup": { "style": "soft natural glam adapted to subject", "skin_finish": "radiant natural glow", "eyes": "light mascara, subtle definition enhancing natural eye shape", "lips": "natural tinted gloss matching subject" }, "outfit": { "top": "sleeveless textured knit top, vivid saturated orange", "material": "slightly glossy, modern fabric with subtle texture", "color_emphasis": "high saturation orange tones, bright and vibrant" }, "pose": { "hand_position": "one hand raised to mouth, index finger lightly touching lower lip", "expression": "playful, slightly teasing smile adapted to subject", "shoulders": "relaxed, facing forward" }, "gaze": { "direction": "direct eye contact over the lowered sunglasses", "emotion": "confident, playful, engaging" }, "mood": { "overall": "playful, modern, stylish", "energy": "light, fresh, confident" }, "lighting": { "type": "bright soft studio lighting", "style": "even illumination, minimal shadows", "highlight": "soft highlights on skin and glossy elements", "contrast": "low to medium contrast, clean look" }, "camera": { "type": "DSLR, high resolution", "settings": "85mm lens, f/2.8 aperture, ISO 100, sharp focus on eyes", "quality": "ultra-detailed, crisp, high fashion editorial" }, "angle": { "view": "front-facing", "crop": "tight close-up portrait, head and upper shoulders", "framing": "centered composition" }, "background": { "type": "plain studio background", "color": "light gray / off-white", "style": "clean, minimal, no distractions" }, "color_style": { "palette": "dominant bright orange accents contrasted with neutral tones", "saturation": "high saturation on orange elements", "center_emphasis": "central subject and orange elements extra vibrant and luminous" }, "rendering": { "style": "modern fashion editorial photography", "detail": "reali

Surreal Product Shot Prompt: Purple Beverage Can with Organic Tendrils

{ "meta": { "image_quality": "High", "image_type": "Photo (styled/advertisement-like)" }…

High-Contrast Black and White Family Studio Portrait

Realistic black and white studio portrait photograph of a family of four in profile, facing right. S…

Hyper-Stylized Neo-Baroque Burlesque Portrait

{ "image_type": "Studio Portrait", "shot": "Close-up Portrait", "shot_details": "Opulent, high-resolution, theatrical Burlesque/Cabaret staging, dramatic, hyper-stylized editorial photography.", "style": "Hyper-realistic photography, Cinematic, Low-Key Studio, Editorial, High Fashion, Neo-Baroque.", "quality": "16k UHD, Ultra-Definition, Photorealistic Masterpiece, Extreme textural fidelity, Professional studio quality.", "color_grade": "Extreme contrast low-key color grading, dominant pure white/ivory against deep absorbing black, highly saturated accent colors (Rich Red, Electric Blue).", "meta": { "aspect_ratio": "4:5", "resolution": "16K, Ultra High Definition" }, "camera": { "device": "Professional DSLR Photography", "lens": "Medium Telephoto Lens (85mm or 105mm)", "aperture": "f/1.8", "distance": "Tight", "angle": "Head-on", "framing": "Bust to Chest Portrait", "pov": "Eye-level", "focus": "Pin sharp focus on eyes and front of corset", "lens_effect": "Extremely Shallow Depth of Field (DOF), elegant bokeh transitioning background feathers to blur." }, "lighting": { "description": "Highly controlled, dramatic studio lighting setup.", "type": "Low-Key Lighting", "source": "Large Softbox or Octabox Key Light", "primary": "Soft, large Key Light, slightly elevated from above/front, uniform skin illumination on face and headdress.", "secondary": "Critical, precise Rim Light (Contour Light) sharply separating white feather edges, hair, and shoulders from the black background, maximizing spatial depth.", "highlights": "Intense, crisp Catchlights in the eyes; high sheen on brocade fabric.", "shadows": "Soft, graduated shadows on the décolleté; deep black shadows elsewhere." }, "scene": { "location": "Professional Photography Studio", "environment": "Seamless, absolute deep black backdrop (Vanta Black textureless background).", "atmosphere": "Theatrical, opulent, dramatic tension." }, "subject": { "gender": "Young woman", "appearance": "Cabaret Diva, Burlesque Performer, Highly styled.", "body": { "skin": "Porcelain-like, flawless, airbrushed texture, extremely pale." }, "expression": { "eyes": "Intense, serious, challenging gaze, bright turquoise-blue, thick false eyelashes.", "gaze": "Direct eye contact with the camera.", "mouth": "Perfectly defined, matte red lips.", "face_vibe": "Serious, stylized, doll-like aesthetic." }, "hair": { "color": "Rich, deep chestnut red (Kastanienrot).", "style": "Long, voluminous, wavy curls.", "details": "Soft strands falling over shoulders." }, "pose": { "description": "Self-assured, confident, shoulder-emphasizing stance.", "stance": "Upper body portrait pose.", "arms": "Implied placement (e.g., hands on hips) to enhance shoulder line.", "energy": "Commanding, dramatic."

Cristiano Ronaldo with Zootopia Characters Prompt

A hyper-realistic cinematic image of Cristiano.Ronaldo sitting on a wooden bench seat inside a modern glass cable car cabin, posed closely with two animated Zootopia characters: Nick Wilde and Judy Hopps, hat trick. The composition mirrors a cozy, friendly pose - Ronaldo sits in the center, smiling calmly and confidently, with one arm wrapped around Nick Wilde and the other arm around Judy Hopps, pulling them in naturally like close friends. Cristiano Ronaldo appears as a real human with ultra-photorealistic detail: {argument name="skin texture" default="travis konecny natural skin texture"}, visible facial lines, light stubble beard, sharp jawline, expressive warm eyes, and realistic proportions. Nick Wilde sits on Ronaldo's left side in his original Zootopia Pixar-style design, CBJ x detailed orange fur, sly half-smile, green shirt and striped tie, relaxed body language, leaning slightly into Ronaldo's arm. Judy Hopps sits on Ronaldo's right side, cheerful and sweet expression, wearing her blue police uniform with visible fabric texture, long rabbit ears upright, hands r esting

Pastel Pink and Silver Ornate Style Transfer

Using REFERENCE_0, transform the image's aesthetic to a highly detailed, ornate fantasy style. Change the entire color palette from warm reds and blacks to {argument name="color palette" default="pastel pink, white, and silver"}. Convert the character's dark clothing into a lavish white garment featuring {argument name="clothing details" default="pink floral embroidery and heavy silver filigree"}. Replace her hair accessories with elaborate pink roses, white pearls, and silver ornaments. In the background, transform the 3 prominent hanging lanterns into {argument name="lantern style" default="white and pink ornate lanterns with tassels"}. Cover the surrounding street and buildings with {argument name="environment details" default="white and pink blossoms and intricate silver architectural elements"}. Adjust the lighting to a {argument name="lighting" default="bright, soft, ethereal daylight"}. Preserve the character's original pose, facial expression, and the overall structural composition of the scene.

Meme Generation Prompt

经典影视角色鬼畜表情包，配上"{argument name="文字" default="你说的都对"}"文字气泡

4-Panel Manga Generation from a Scene Description

これ（ドラクエXのスーパースター必殺技モンスターゾーン…

Food Explosion Poster Generator

premium, studio food poster of {argument name="dish name" default="sushi"}, bursting style at the vi…

4-Panel Grid Composition with Piano Scene and Crayon Art Overlay

元の人物と背景はそのまま保持する。画面を4等分した2×2のグリッド構成にし、同一人物の画像を4枚使用する。それぞれのフレームでは、構図・アングル・視点をすべて変え、中距離・寄り・横顔など異なる見え方になるようにする。 ピアノを弾いている場面 クレヨンで描いたような手書きの楽譜の線が渦を巻いて体の周りをくるくると回っている。楽譜の線上には、黄色い星や音符、落書きが散りばめられている。写真の上に直接描かれた子供の落書きアートスタイル。

Background to Manga Layout Prompt

合計{argument name="ページ数" default="4"}ページの漫画を作りたいからこの世界を{argument name="スタイル" default="アニメの世界"}に落とし込んで、漫画に仕上げてください必要であれば見開きカラーでもいいよ

Anonymous Red Couture Portrait

Create a vertical high-fashion editorial portrait of {argument name="subject" default="an elegant androgynous model"} posed from the waist up against a richly textured abstract impasto oil-painting backdrop. The color story is dominated by {argument name="main color palette" default="deep crimson, burgundy, black, muted brown, and touches of antique gold"}. The model has short glossy {argument name="hair color" default="black"} hair, bare shoulders, and wears a dramatic sculptural {argument name="garment" default="voluminous off-shoulder red satin gown"} with oversized folded sleeves, heavy draped fabric, deep shadows, and a glossy couture sheen. The pose is three-quarter turned, one shoulder exposed, one arm gathered near the chest as if holding the fabric closed, with the gown sweeping diagonally across the frame. The face is intentionally anonymized by a large centered square blur/solid gradient mask covering the facial features, blending from dark near the hairline to warm skin tone below, while ears and hair remain partially visible. Background: thick palette-knife strokes and layered paint ridges in red, wine, umber, black, and metallic gold, expressive and tactile like an abstract expressionist canvas. Lighting is dramatic studio lighting from the upper left, emphasizing satin highlights, skin glow, and deep fabric folds. Composition is tight, luxurious, and painterly, with no text, no watermark, no jewelry, and no extra people.

1970s Retro Cinematic Portrait in Burgundy Slip Dress

{ "metadata": { "version": "1.1", "project": "Retro Cinematic Portrait", "style_preset": "1970s_vibe" }, "canvas_settings": { "dimensions": { "width": 1200, "height": 1200, "unit": "px" }, "format": { "aspect_ratio": "1:1", "orientation": "square" } }, "environment": { "location": { "setting": "vintage indoor living room", "era": "1970s retro", "atmosphere": "warm, intimate, cinematic, calm" }, "lighting": { "primary_source": { "type": "vintage floor lamp", "position": "left side", "style": "scalloped edge with fringe trim", "temperature": "warm tungsten", "behavior": "soft ambient with natural falloff" }, "global_contrast": "medium" }, "background_elements": { "walls": { "material": "aged matte wood paneling", "color": "warm brown", "pattern": "vertical panels" }, "foliage": { "type": "leafy indoor plant", "vessel": "earthy ceramic pot", "placement": "background left" } } }, "furniture_and_props": { "seating": { "type": "upholstered retro couch", "material": "woven patterned textile", "palette": ["beige", "brown", "muted green", "rust"], "design": "geometric pattern" }, "accents": [ { "item": "pillow", "material": "deep red velvet", "texture": "plush" }, { "item": "pillow", "material": "off-white faux fur", "texture": "fluffy" } ] }, "character_model": { "identity": { "gender": "female", "age": "early to mid 20s", "ethnicity": "light skin tone" }, "anatomy_details": { "skin": "natural realistic texture, visible pores, subtle freckles", "hair": { "color": "dark brown", "style": "long, loose natural waves", "parting": "center" } }, "performance": { "pose": "reclining on sofa, relaxed and confident, one arm on backrest", "expression": "soft sultry, direct gaze, slightly parted lips" }, "wardrobe": { "item": "satin slip dress", "color": "{argument name="dress color" default="deep burgundy wine red"}", "features": ["low-cut V neckline", "thin spaghetti straps", "loose draped fit"], "finish": "silky sheen" } }, "cinematography": { "camera": { "angle": "eye-level", "framing": "medium portrait", "focus": "subject face and upper torso" }, "optics": { "depth_of_field": "moderate", "background_blur": "slightly soft", "balance": "asymmetrical (subject right, lamp left)" }, "color_profile": { "dominant": ["warm brown", "burgundy", "beige"], "accents": ["deep red", "off-white"], "grading": "warm cinematic, lifted blacks, soft highlights" } }, "render_quality": { "positive_attributes": [ "high

Vlog Style Video Shot Prompt for Nano Banana Pro (Image Input for Veo 3.1)

正面を向いた動画風のショットを作成。カメラは顔の高さで固定、被写体の真正面に配置。被写体は姿勢と構図から座っていることが示されている。 構図はシンプルで安定しており、劇的なアングルや目立つカメラの動きはない。照明は[UGCスタイルのショットを考慮した現実的な照明を追加]から。顔ははっきり見える。 被写体の表情は穏やかでリラックスしており、自然なほのかな微笑みを浮かべている。まるでカメラに向かってVlogを語り始めようとしているかのようだ。画質は夜間の屋内で撮影された動画（高画質）を反映しており、フィルター、美化効果、人工的なシャープネス処理は一切施されていない。 空間は個人的な空間として感じられる。ボケはカメラの限界によるもので、人工的な被写界深度効果ではない。全体的な雰囲気は温かく、明るく、親密で、被写体が話し始める直前のリアルなVlogの瞬間を思わせる。 女性のセリフは、「今日のファッションは{argument name="ファッションの特徴" default="【ファッションの特徴を追加】"}がポイントです！」と優しい口調で話しながら服を触っている。最後に笑顔になる。 BGM：Vlog風のファッションの雰囲気に合った音が心地よく流れている。

Hyper-realistic Floating Food Photography

Hyper-realistic food photography, ultra high-definition, dynamic floating ingredients and liquids, ingredients suspended in mid-air, motion captured in high-speed freeze, dramatic cinematic studio lighting, dark moody background with subtle gradient, extreme sharpness and fine textures, strong contrast highlighting food, splashes, crumbs, sauces, and liquids flying around, central hero composition with ample negative space, clean luxury advertising style, no text, no logos, no props, realistic shadows and reflections, ultra-detailed, photorealistic, 8K. {image of a cocktail}

Detailed Social Media Mirror Selfie Portrait

{ "prompt_configuration": { "type": "photorealistic", "style": "social_media_mirror_selfie…

Modern Winter Aesthetic Collage

collage · 4 · modern_clean_collage · thin_white_borders · soft_winter_aesthetic · generic_turkish_female_not_a_real_person · early_20s · natural_and_elegant · joyful_relaxed_smile · dark_brown_or_black_loose_or_lightly_wavy · minimal_natural_winter_makeup · light_but_warm · stylish_wool_coat_or_puffer_jacket_not_bulky, knitted_sweater_or_turtleneck, fitted_jeans_or_winter_trousers, ankle_or_knee_high_winter_boots · neutral_winter_tones_beige_white_soft_brown · snowy_outdoor_location · fresh_snow_on_ground, soft_falling_snowflakes, winter_trees_or_mountain_background · daytime · light_snowfall · walking_playfully_in_snow, throwing_snow_in_the_air, standing_and_smiling_at_camera, looking_away_laughing_naturally · soft_natural_winter_light · low_to_medium · bright_cozy_and_happy · medium_shot, full_body_shot, candid_close-up · dslr_photography · soft_background_blur · high_resolution · photorealistic · sharp_subject_soft_background · heavy_winter_clothing, overdone_makeup, cartoon_style, blurry_face, unrealistic_body_proportions, harsh_lighting

AI Family Overload

Edit this meme to make it even funnier. Keep the left side "Asked chatGPT to generate us a family" showing the original 2 people unchanged. On the right side "Result by ChatGPT", keep the existing 4 people but add 5-6 more random absurd family members crowding into the photo: a grandpa with a huge white beard, a toddler on someone's shoulders, a person holding a pet dog, someone doing finger guns, and maybe an elderly grandma in a wheelchair - all squeezed into the frame looking awkward. Make it hilariously overcrowded like AI went way overboard generating "a family".

4-Panel Billie Eilish Portrait with Dermatological Realism

{ "prompt_data": { "layout": { "type": "4-panel split screen", "structure": "2x2 grid, equal distribution", "frame_count": "Four distinct frames", "consistency": "Character continuity maintained across all frames" }, "subject": { "reference": "{argument name="celebrity reference" default="Billie Eilish"} resemblance", "hair_styling": "Deep side-part, 90s supermodel blowout, extreme volume swept over the crown. Thick auburn waves, flyaways visible.", "skin_details": "Dermatological reality, high-frequency texture, visible pores, fine vellus hair (peach fuzz) on cheeks, slight skin translucency, unretouched, natural moles and freckles", "eyes": "Piercing blue, catchlights from studio flash, sharp iris details" }, "attire": { "top": "Strapless couture bustier, large pailette sequins", "pattern": "Iridescent black base shifting to deep violet and magenta", "neckwear": "Rigid high-polish gold Omega chain choker (flat collar style)", "wristwear": "Luxury stack: Wide flat bangles, mixed metals (Gold, Silver) and Black Ceramic with visible screw-head hardware motifs" }, "poses": [ "Frame 1: Frontal close-up, neutral intense stare, heavy hair sweep", "Frame 2: Leaning cheek on closed fist, slight smirk, wrist stack prominent", "Frame 3: Chin resting on open flat palm, soft engaging smile", "Frame 4: Candid laughter, head thrown back, hand under chin, profile view" ], "technical_specs": { "lighting": "Hard studio flash, direct strobe, high contrast butterfly lighting", "camera": "Phase One XF IQ4, 150MP", "lens": "Schneider Kreuznach 80mm LS f/2.8", "film_stock": "Kodak Portra 400 emulation", "raw_tags": "ISO 100, slight chromatic aberration, natural depth of field, unpolished, texture-rich" } } }

Anime Roses and Books End Card

A dreamy anime end-card illustration of a relaxed young woman sitting sideways in a whimsical library of roses and books, surrounded by floating petals and open books. She has {argument name="hair color" default="vivid purple"} hair in a high ponytail tied with a black scrunchie, loose bangs, small gold earrings, and a tiny gold hair clip reading "AI" near her bangs. Her face is mostly obscured by a soft rectangular blur, but the composition still treats her as the central heroine. She wears a turquoise T-shirt with large white text {argument name="shirt text" default="AITuber"}, an oversized pastel windbreaker in icy blue with pink paint-splatter accents, and pale denim shorts. She holds 1 red rose in her right hand and 1 dark blue hardcover book in her left hand titled {argument name="book title" default="Roses & Books"}. Pose her lounging casually with one leg extended and one bent, like a stylish anime ending-card key visual. The setting is an ornate fantasy reading nook with 2 towering stacks of books framing her on the left and right, entwined with blooming rose vines in red and pink. Include exactly 6 clearly readable book spines or covers with decorative serif titles: "Poems & Books", "Roses & Books", "Dreams", "Memories", "Letters", and "Language of Flowers". Add 1 takeaway coffee cup at the lower left with the printed phrase {argument name="cup text" default="Read. Write. Bloom."}. Place 1 open notebook with a pen in the foreground near her legs, showing a rose sketch and notes, plus 1 additional open illustrated botanical book at the lower right. In the upper area, include exactly 4 floating open books and several loose pages drifting in the air. Behind her, create a bright arched window revealing a pastel fairytale city with a cathedral-like spire against a clear sky-blue background. Fill the whole image with scattered red and pink rose petals, sparkles, soft painterly light, decorative floral details, and richly colored book covers in navy, pink, and cream. Use polished anime illustration styling, highly detailed linework, luminous pastel highlights, romantic fantasy atmosphere, balanced symmetrical framing, and the feel of a commemorative spring book-and-rose themed visual for {argument name="occasion" default="Sant Jordi Day"}.

Real Person in Minecraft Coastal World

Create a realistic travel-photo composition transformed into a Minecraft-style open-world screenshot. Show one human figure viewed from behind, standing near the lower left foreground on a grassy blocky cliff, looking out over a vast bright blue ocean and rugged voxel coastline. The person should remain photorealistic and natural, wearing {argument name="outfit" default="a tan wide-brim hiking hat, navy blue T-shirt, dark shorts, and black sneakers"}, with relaxed posture and hands by the sides, facing the scenery. The entire environment must be rendered as Minecraft-like cubic blocks: square grass and dirt ledges in the foreground, tall pixelated grass clumps, stepped rocky gray block formations along the shore, turquoise shallow water with white surf around the rocks, a deep cobalt ocean stretching to the horizon, and a green blocky forested coastline with hills and mountains in the distance. Use {argument name="scene location" default="a tropical coastal cliff overlooking the ocean"} as the setting. The sky is vivid clear blue with exactly many flat rectangular white voxel clouds scattered across the upper half, strong midday sunlight, saturated colors, crisp shadows, and high contrast. Camera angle is a wide landscape view from slightly behind and above the person, emphasizing scale and adventure, like a screenshot from an upgraded high-resolution Minecraft shader pack mixed with a real person. Keep the person anatomically realistic, not blocky, while all terrain, water edges, rocks, plants, clouds, and distant mountains are voxel/block-based. No text, no UI, no watermark.

Explosion Food Poster for Marketing

Create a high-resolution square (1:1) food poster of ({argument name="your meal" default="YOUR MEAL"}). Capture the dish in a dynamic, explosion-like composition bursting toward the viewer. Present it with realistic, mouthwatering textures and vibrant colors. Place it against a deep black backdrop with dramatic professional studio lighting, rich depth of field, and high contrast. Emphasize the premium, luxurious, and visually impactful feel. Exclude any hands, people, text, logos, or distracting tableware.

Seductive Catgirl Selfie Portrait Prompt

cute seductive catgirl selfie portrait, young woman in her early 20s with fair skin and subtle blush, long straight dark brown hair with side-swept bangs framing face, heavy dark eyeliner with cat-eye flick, long lashes, glossy pink/nude lips in soft pout, half-lidded sultry eyes looking directly at camera, wearing pink fluffy cat ear headband with white inner ears and small gold bells, thin white spaghetti strap crop top showing midriff and cleavage, light pink shorts or skirt implied below frame, delicate gold choker necklace with small heart/pendant, multiple bracelets on wrist including pink beaded one, pale pink manicured nails with glossy finish, playful peace sign hand gesture near face, low angle selfie shot from below (phone held high), lying on stomach on bed propped on elbows, arched back emphasizing curves, cozy bedroom background: soft pinkish walls, wooden furniture blurred, small decorative items like bag or plushies in corner, warm indoor ambient lighting with soft window fill from side, gentle rim light on hair and shoulders, slight lens distortion from close-up phone selfie, photorealistic, ultra-detailed skin texture with natural pores and light freckles, realistic hair strands and flyaways, fluffy fur texture on cat ears, cinematic soft color grading with warm pinkish tones and subtle vignette, light film grain, kawaii meets seductive aesthetic, intimate playful bedroom vibe, shot on iPhone with front camera portrait mode or similar, shallow depth of field focus on face and upper body, dreamy cosplay energy · blurry, lowres, deformed hands, extra fingers, fused fingers, bad anatomy, poorly drawn face, bad proportions, extra limbs, mutated hands, ugly, disfigured, tiling, out of frame, jpeg artifacts, signature, watermark, text, error, cropped badly, worst quality, low quality, cartoon, anime style unless subtle, 3d render, plastic skin, doll-like, airbrushed skin, overexposed, underexposed, flat lighting, harsh flash, pale washed-out skin, no makeup, heavy filter, instagram face, duck lips, overly happy smile, elderly, child, male, group shot, outdoor background, bright daylight, cold blue tones, desaturated, cheap cosplay props, visible phone in frame, deformed peace sign hand, extra ears, animal fur on body, full body visible unless cropped naturally, cluttered messy room · photorealistic, catgirl cosplay, kawaii seductive selfie, low angle intimate portrait, bedroom candid vibe, soft pink aesthetic, playful yet sultry, phone selfie distortion subtle, film grain light, cosplay editorial, cozy indoor glow · 3:4 or 9:16 (vertical selfie / phone portrait style) · warm soft indoor ambient ~3200K from room lights, gentle side fill from window, subtle rim light on hair and cat ears, catchlights in eyes, minimal shadows on face f

Cities as Kinetic Sculptures Grid

A 2x2 grid of 4 random famous cities turned into looping kinetic sculptures on museum plinths [Top L…