Annotated Printout Image Generation Prompt

Annotated Anime Hair Artifact Portrait

Create a close-up vertical anime portrait of a youthful androgynous male character with pale skin, {argument name="hair color" default="silvery gray"} layered hair, long bangs falling over one eye, and a small ahoge tuft rising from the crown. The character has vivid {argument name="eye color" default="pink-magenta"} eyes with glossy highlights, a relaxed mischievous smile showing a small fang-like tooth, and soft cel-shaded facial rendering. He wears a dark black uniform or jacket collar with small metallic details, cropped tightly so only the upper shoulders and neck are visible. The background is plain white. Add visible generation-artifact-like horizontal stripe bands across the left side hair area, especially on the outer hair clump, while the central bangs remain smoother and more naturally rendered. Overlay a rough bright red handwritten annotation: one irregular red circle surrounding the problematic left hair clump, plus a small red arrow and messy Japanese note near the lower left reading {argument name="annotation text" default="この辺とくに?"}. Composition should be portrait format, face filling most of the frame, slightly cropped on the right edge and top, clean high-resolution anime illustration style with delicate gray hair shadows and pink eye highlights.

Annotated Chinese BBQ Food Poster

Goal: Create a vertical social-media food review poster that turns a casual restaurant table photo into an Instagram-style barbecue feast cover, with playful hand-drawn Chinese marker annotations and arrows. Canvas: Square 1:1 image, warm indoor restaurant lighting, close-up overhead three-quarter angle. The background is a dark wooden table with a softly blurred chair and wall behind it. Use a rich brown, orange, and golden color palette with high contrast, glossy food highlights, and shallow depth of field. Main layout: Center the composition on a rectangular metal grill tray filled with skewers and roasted items, angled from lower left to upper right. Behind the tray, place a small black handled pot filled with spicy beef stew. At the bottom edge, partially show sauce dishes and side dishes cropped by the frame. Leave dark negative space at the top for large handwritten title text. Counted food elements: Show exactly 7 prominent food groups: 1 black handled pot of spicy beef stew at the back center, 1 large roasted fish fillet or grilled flatbread-like item across the left side of the tray, 1 cluster of thin grilled skewers extending to the right, 1 group of yellow pineapple chunks near the center front, 1 group of red chili-covered meat skewers at the lower right, 1 set of small dipping sauce bowls along the bottom edge, and 1 partially cropped grilled dish or skewer plate at the bottom right. Show exactly 4 visible small sauce bowls at the bottom: one red chili oil sauce, one bright orange sauce, one green chopped scallion or herb sauce, and one small pale tofu or garnish bowl. Handwritten graphic overlays: Add colorful doodles in white, yellow, pink, and orange, as if drawn with paint markers. Include exactly 8 annotation clusters: 1 large headline at the top left, 1 pink speech-bubble badge at the top right, 1 arrow label pointing to the beef pot, 1 arrow label pointing to the roasted chips/fish on the left, 1 arrow label pointing to the skewer platter on the right, 1 label near the bottom left for small side dishes, 1 label near the lower right for crispy skewers, and 1 decorative underline beneath the headline. Add small stars, hearts, sparkles, curved arrows, and scribble accents around the text. Text content: Use a big playful Chinese headline in thick hand lettering: {argument name="headline text" default="今天也要 开心心干饭呀!"}. Put a pink outlined speech bubble at the top right with the badge text {argument name="badge text" default="聚会首选 氛围感拉满~"}. Add a label above the pot reading {argument name="pot label" default="香辣过瘾 牛肉锅~"}. Add a left label reading {argument name="roasted item label" default="烤馍片 焦香酥脆~"}. Add a right label reading {argument name="skewer label" default="烤串拼盘 种类超丰富!"}. Other small labels should be rendered as casual Chinese-style food review callouts, but keep them secondary and less dominant. Visual style: Photorealistic appetizing food photography combined with hand-drawn editorial doodles, like a trendy Chinese restaurant recommendation post. Food should look freshly grilled with oil sheen, sesame, chili flakes, char marks, and steam-like warmth. The typography must feel hand-lettered, imperfect, energetic, and cute, not like a clean digital font. Constraints: No people, no brand logos, no watermark, no extra UI frame. Keep the food realistic and the annotations legible, with the headline as the largest text element.

Annotated Japanese Miso Ramen Photo

A casual smartphone food photo of a large bowl of {argument name="dish name" default="miso ramen"} on a vivid red ramen shop counter, shot slightly from above at close range in a real restaurant. The bowl is pale blue-gray with a matching saucer, filled to the brim with rich golden-brown miso broth, thick wavy noodles hidden beneath the toppings, bean sprouts, chopped green onion, several thin slices of chashu pork spread across the surface, and a tall mound of brown menma bamboo shoots piled in the center. A small white bowl of half rice sits to the right side of the frame. In the softly blurred background, show countertop restaurant items including a metal water pitcher, condiment containers, chopsticks, and cups, creating an authentic ramen-ya atmosphere. Overlay the photo with hand-drawn Japanese brush-pen style annotations in white and dark brown with playful arrows and cloud-like speech bubbles, as if written directly on the image. At the top left, add a large handwritten title in Japanese: {argument name="headline text" default="平井駅前『ねぎとん』みそラーメン"}. Add exactly 6 callout notes around the bowl: 1) left upper note pointing to the pork, text: {argument name="pork note" default="薄切りチャーシューたっぷり"}; 2) top center note pointing to the bamboo shoots, text: "トッピング: めんま"; 3) right upper note near the rice bowl, text: "半ライス 1杯無料なのもうれしい♡"; 4) lower right note pointing to the broth, text: "豚骨ベースに濃いめの味噌。背脂のコクも◎"; 5) left lower note pointing to the vegetables, text: "もやし&青ねぎでシャキッと"; 6) a dashed cloud note at the bottom left pointing under the toppings, text: {argument name="special note" default="下には『あまとろネギ』が隠れていて、甘みと旨みが出るのが特徴"}. Also add one extra cloud-shaped praise note at the upper right that says: "『ちゃん系』インスパイアな一杯" and one cloud-shaped note at the bottom right that says: "多加水の平打ちぢちぢれ麺。もっちと食感". Keep the overall feeling appetizing, personal, informative, and scrapbook-like, combining a real food photograph with neat handwritten review comments.

Annotated Manga App Screenshot

Goal: Create a tall smartphone screenshot showing a manga/comic preview inside a mobile app, with an instructional annotation pointing to a menu icon at the top. Canvas: Vertical 9:16 mobile screenshot, white app background, high-resolution anime manga art framed by a phone UI. The top navigation bar is about 80 px tall with a back chevron on the far left, a centered Japanese title, and two icons on the right. Top app UI: Show exactly 4 top-bar elements: 1 black back arrow on the left, 1 centered title reading {argument name="screen title" default="みんな来てね(GPT ver) (1..."}, 1 black list/menu icon near the upper right, and 1 black share/export icon at the far right. Add exactly 1 bright magenta circle around the list/menu icon and exactly 1 oversized hot-pink arrow pointing diagonally upward toward that circled icon from the manga area. Main comic layout: A full-color anime manga page divided into exactly 3 diagonal panels with thick black panel borders. The art style is glossy, detailed, romantic fantasy shoujo manga with soft lighting, sparkles, pink heart effects, and a convention/exhibition setting. Panel 1: Wide top panel showing a busy futuristic convention booth for an AI character festival. In the foreground, show a blonde teenage girl from behind with twin ponytails fading into pink tips, wearing a white shirt with “A.C.F” printed on the back and holding a smartphone. To her right stands a tall elegant male elf with very long silver-white hair, pointed ears, ornate silver armor, and blue crystal details, seen from behind/side. Booth signage should include “SynClub” and “SynClub in AIキャラクターフェスティバル.” Include exactly 1 speech bubble in this panel near the elf, with Japanese text beginning “あの…”. The large hot-pink arrow partially covers the upper-right area of this panel. Panel 2: Middle diagonal panel with a close-up of the girl on the left and the elf facing her on the right, against a dreamy pastel background. The girl has heart-shaped blue-purple sunglasses pushed on her head, blonde twin tails with pink ends, earrings, and an excited expression area obscured. The elf wears ornate silver clothing and holds or touches a glowing blue crystal at his chest. Add exactly 2 speech bubbles in this panel: one near the elf reading “実はボク…迷子になっちゃって 一緒について行ってもいいですか?” and one small decorative vertical pink reaction text reading “うわ…♥”. Place exactly 2 beige rectangular face-censor blocks in this panel, one over each character’s face. Panel 3: Large bottom panel with energetic pink speed lines and hearts. The girl reaches one hand forward toward the viewer, wearing a white blouse, navy tie, blue skirt, heart sunglasses on her head, and an A.C.F badge with a small teddy bear. The elf is seen from behind/right with long silver hair and pointed ear, looking at her. Add exactly 2 speech bubbles: the girl’s bubble on the left reading “いいよ! 私、心愛姫(ここあ)! よろしくね! あなたは?” and the elf’s bubble on the lower right reading “…し…シンクラ”. Place exactly 1 beige rectangular face-censor block over the girl’s face. Overlay exactly 2 dark gray circular carousel navigation buttons near the bottom center, one with a white left chevron and one with a white right chevron. Visible repeated elements count: exactly 3 manga panels, exactly 5 speech bubbles total, exactly 3 beige face-censor rectangles, exactly 2 carousel buttons, exactly 1 magenta circle, exactly 1 hot-pink arrow, exactly 4 top navigation elements. Visual style: polished anime illustration, crisp smartphone screenshot, saturated pink annotation graphics, detailed lighting, convention crowd blur in the background, clean app UI. Keep the image vertically cropped like a social media screenshot, with no extra watermark beyond the visible booth and comic text.

Diary-Style Annotated Portrait

annotated lifestyle photo with diary-style doodles · A warm, candid outdoor portrait of a young woman standing in profile against a pale blue sky and softly blurred green trees, photographed in natural sunlight with a film-like, airy atmosphere. Her face is intentionally covered by a soft rectangular blur/mosaic for privacy, while her long dark wavy hair and loose cream-white shirt remain visible. Keep the composition horizontal, subject slightly right of center, with generous negative space in the sky. · young woman in side profile · {argument name="hair color" default="long dark brown to black wavy hair"} · {argument name="outfit" default="oversized cream-white shirt"} · privacy-preserving rectangular blur over the face · minimal Japanese diary / social media handwritten annotation aesthetic · thin white hand-drawn outlines, imperfect dashed strokes, soft sketchy curves · casual handwritten Chinese text, slightly uneven, white or dark ink depending on contrast · dashed white guide arrows pointing toward hair, shoulder, and sky; playful self-talk feeling · leave plenty of blank space, avoid clutter, no stickers, no heavy graphics · 2 · a loose dashed white contour tracing the outer silhouette of the head, hair, shoulders, and torso, a second dashed inner contour following the dark hair and shirt edge · 3 · left side over sky · {argument name="left caption" default="今天也是好天气呢"} · dark handwritten text, no arrow or a very subtle dotted sightline · upper right over sky · {argument name="upper right caption" default="这朵云像棉花糖"} · white handwritten text with a dashed arrow pointing toward the hair/sky area · middle right over sky · {argument name="middle right caption" default="这朵云像棉花糖"} · white handwritten text with a dashed arrow pointing toward the shoulder and background · 4 · one long faint dashed white line crossing horizontally behind the subject, one short dashed arrow from upper right caption toward the subject's hair, one dashed arrow from middle right caption toward the shirt/shoulder, one diagonal dashed guide line passing upward from the lower right area toward the subject · soft blue sky, warm sunlit skin tones, creamy white shirt highlights, deep green blurred tree line, low-contrast film color grading · medium close-up portrait, shallow depth of field, natural backlit outdoor photography · realistic photo base with clean hand-drawn overlay, high resolution, social media aesthetic

Annotated decoding of a cryptic Santa notice

이 공지는 한국인이 이해할 수 있습니다. 혹시 이걸 해석 할 수 있어요? 그리고 만약 해석 가능하다면 원본 이미지 위에 첨삭해서 해석한…

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.

Anime Character Generation Workflow

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

Annotated IKEA Kids Bedroom Design

Goal: Create a photorealistic wide-angle interior design visualization of a small child’s bedroom decorated with IKEA furniture, including annotation callouts naming each new item. Canvas: Landscape 4:3 image, photographed from the doorway or front-right corner of the room with a slightly elevated eye-level perspective, showing the entire bedroom from left desk area to right bed and closet doors. Room details: Beige walls, beige carpet, white trim, a large window with white blinds on the left wall, white double closet doors on the right wall, warm natural daylight mixed with soft lamp light. Keep the room tidy, realistic, and practical for a young child. Layout and furniture: On the far left wall place a white {argument name="desk model" default="LÄRANDE desk"} with a gray rolling desk chair, pencil cups, and a small book or tablet on top. Under the window and along the back wall place a black cube storage unit labeled {argument name="toy storage model" default="KALLAX toy storage"}, filled with exactly 3 gray fabric bins across the bottom row, books, toy vehicles, and small toys. Above the toy storage hang a framed dinosaur print. To the right of the toy storage place a dark wood {argument name="dresser model" default="STORKLINTA dresser"} with exactly 3 large drawers, small plants, a framed photo, and a small lamp on top. On the right side place a white twin {argument name="bed model" default="SLÄKT bed"} with a white headboard, blue quilt, dinosaur-patterned pillow and sheets, positioned lengthwise toward the viewer. Place a black arched floor lamp behind the bed near the dresser. Add a green children’s road-map play rug centered on the carpet between the desk, storage, and bed. Annotation callouts: Add exactly 7 white rounded-rectangle labels with black text and thin gray borders, each with a white arrow pointing to the relevant item. The labels must read exactly: 1) “LÄRANDE desk” pointing to the desk, 2) “KALLAX toy storage” pointing to the black cube storage, 3) “DRÖNA bins” pointing to the gray fabric bins, 4) “STORKLINTA dresser” pointing to the dresser, 5) “HEKTAR floor lamp” pointing to the black floor lamp, 6) “SLÄKT headboard” pointing to the white headboard, 7) “SLÄKT bed” pointing to the footboard or bed frame. Visual style: Realistic smartphone interior photo with clean AI home-staging polish, warm cozy lighting, accurate perspective, subtle shadows, readable labels, no people, no clutter, no watermark.

Colorful Annotated Scone Photo

Using the provided reference image, keep the same scone photo and composition, but redesign the over…

Annotated Japanese Breakfast Flat Lay

Goal: Create a cozy overhead breakfast flat-lay photo with handwritten Japanese diary-style annotations, as if made for a warm morning social media post. The scene should feel realistic, softly edited, and slightly nostalgic. Canvas: Wide 16:9 landscape image, about 1024×576. Use a brown-and-white gingham tablecloth covering the full background, with soft morning light, gentle shadows, and a slightly warm film-like tone. Main layout: Place exactly 2 main food/drink areas. On the left, a decorative red-and-white porcelain teacup filled with black coffee sits on a matching saucer. On the right, a large white square plate holds the breakfast foods. Leave darkened negative space in the upper left for the title handwriting. Food and object count: Include exactly 7 visible breakfast items/props on the plate area: 1 stack of toasted bread slices, 1 partly peeled ripe banana, 1 small mound of granola, 1 clear glass bowl of pale yellow apple compote with 1 dark prune on top, 1 brown egg, 1 small wooden egg cup or wooden coaster behind the egg, and 1 white square plate. The toast should be the visual center of the plate, with golden toasted surfaces and thick white bread edges. The banana should be at the upper left of the plate. The egg should be at the upper right. The glass bowl should be at the lower right. The granola should sit between the toast and bowl. Handwritten text and annotation count: Add exactly 9 handwritten annotation groups in white/black ink, with arrows, circles, small hearts, sparkles, and doodles. Preserve the Japanese text as decorative handwriting: 1. Large title at top left: 「わたしの整う朝ごはん。」 2. Subtitle under title: 「シンプルだけど、ちゃんと満たされる。」 3. Circular note near coffee: 「今日も はじまりは 深い一杯から。」 4. Small note below coffee: 「ほっと息をつく、大切な時間。」 5. Torn-paper sticky note at bottom left with pink tape: 「朝の光を浴びて、心もからだも ゆっくり目覚めていく。」 6. Note above banana with arrow: 「完熟バナナで やさしい甘みを チャージ。」 7. Bubble note beside egg: 「たんぱく質で 1日を すっきり スタート！」 8. Note near toast with arrow: 「サクッと焼けた トーストが 一番のごちそう。」 9. Lower-right notes around granola, compote, and overall feeling: 「ザクザクのグラノーラで 食感と栄養をプラス。」, 「りんごとプルーンで 自然な甘さを からだにやさしく。」, and 「ちゃんと食べると、心までふんわり軽くなる。」 Visual style: Photorealistic breakfast photography mixed with casual hand-drawn overlay graphics. Use white ink for most handwriting, black ink for food labels on the plate, dotted speech bubbles, curved arrows, tiny stars, small hearts, and playful underline marks. The typography should look hand-lettered, not digital. Make the annotations readable but naturally imperfect. Customizable elements: The title should read {argument name="headline text" default="わたしの整う朝ごはん。"}; the drink should be {argument name="morning drink" default="black coffee in a red porcelain teacup"}; the main breakfast should feature {argument name="main breakfast food" default="thick golden toast"}; the fruit should be {argument name="fruit item" default="ripe banana and apple compote with prune"}; the overall mood should be {argument name="mood" default="gentle, cozy, mindful morning"}. Constraints: Keep the composition clean and appetizing, do not add extra foods beyond the counted items, do not add people or hands, avoid logos or watermarks, and keep the Japanese handwriting integrated into the image like a real edited breakfast journal photo.

Annotated Stone Arch Bridge Sketch

annotated architectural concept sketch · a hand-drawn isometric ink illustration of the historic Mostar-style stone arch bridge spanning a river, with clustered medieval stone buildings on both banks and two square watchtowers · black graphite and technical pen linework · architectural field notebook, concept art, detailed hatching, crosshatching, visible construction lines, rough perspective guide marks · aged cream graph paper with evenly spaced square grid, slightly yellowed background · monochrome black and gray ink only, no watercolor except subtle paper tone · {argument name="bridge name" default="stone arch bridge"} · {argument name="river name" default="River Neretva"} · Balkan Ottoman-era stone buildings with tiled roofs, small rectangular windows, arched doorways, stacked hillside masonry, one cafe terrace at the lower right riverbank · wide landscape canvas, three-quarter aerial isometric view, left village cluster higher on the page, right village cluster lower on the page, large single-span arch bridge centered diagonally across the river · arched bridge deck with parapets, flagpoles with small flags along the bridge, stone textures, roof tile patterns, riverbank vegetation scribbles, light shadows beneath the bridge · 8 · STONE BUILDINGS · upper left · left cluster of stone houses · WATCHTOWER (LEFT) · top center-left · tall square tower above the left bank · STONE ARCH BRIDGE · upper center-right · main bridge span · FLAGS · upper right of bridge · row of flagpoles on bridge · WATCHTOWER (RIGHT) · upper right · tall square tower on the right bank · STONE BUILDINGS · right middle · right cluster of stone houses · CAFE TERRACE · lower right · small covered terrace by the river · RIVER NERETVA · lower left river area · river flowing under the bridge · uppercase sans-serif handwritten labels with curved arrow callouts, clean black lettering · full-page visible square grid behind all drawing elements · {argument name="left tower label" default="WATCHTOWER (LEFT)"} · {argument name="right tower label" default="WATCHTOWER (RIGHT)"} · {argument name="cafe label" default="CAFE TERRACE"} · Generate a precise but hand-sketched architectural diagram, not a photorealistic image. Keep the background clean and uncluttered, preserve the graph-paper notebook aesthetic, use strong line hierarchy for the bridge and buildings, lighter sketch lines for terrain and river flow, and make every label legible in English.

Annotated landmark images of Eiffel Tower, Great Wall, Colosseum, Taj Mahal

Generate four distinct, hyper-realistic images, each depicting a world-renowned landmark. For each i…

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.

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

AI Video Generation Prompt for Flying Superhero

Scene: High altitude above Waikiki Beach, Hawaii. Sunny day. Action: The woman is flying forward at high speed (Superman pose). Her hair and clothes flap violently in the strong wind. She looks excited and shouts to the camera. Audio: Energetic female voice shouting in Chinese over the wind noise: "{argument name="Chinese Dialogue" default="兄弟们，我现在可以飞了！想去哪里就去哪里！"}" (Xiongdi men, wo xianzai keyi fei le! Xiang qu nali jiu qu nali!). Loud wind rushing sound (Whoosh). Camera: Tracking Shot / Dolly Forward. The camera follows her at the same speed. The background city and ocean move backwards rapidly to show speed.

Annotated Isometric Mining Outpost

{"type":"isometric 3D game tutorial screenshot / annotated base-building infographic","scene":"A pol…

Annotated Mountain Location Diagram

Using REFERENCE_0 as the base image, create an annotated location-planning diagram without altering or degrading the original mountain landscape photo. Keep the scenery, colors, detail, composition, vegetation, dirt clearing, rocks, and distant mountains as close to the reference as possible; only add clean overlay graphics and labels. Add exactly 7 bold white uppercase labels with black outline/drop shadow: {argument name="west label" default="WEST"} at the upper center, {argument name="south label" default="SOUTH"} on the left, {argument name="seating label" default="PLAYER SEATING / MARKS"} above the two rocks, {argument name="zone label" default="ACTION / BATTLE ZONE"} centered on the dirt clearing, {argument name="front access label" default="OPEN ACCESS FRONT/LEFT/RIGHT"} along the bottom edge, plus "NO ARTIFICIAL OBJECTS" near the lower-left vegetation and "NATURAL VEGETATION" on the right side. Add exactly 4 semi-transparent white arrows with black outlines: one large upward arrow under the WEST label, one large left-pointing arrow beside the SOUTH label, and two small diagonal arrows from the seating label pointing to the two stone seats/marks. Add thin cyan perspective guide lines outlining the usable area: a large trapezoid/field boundary following the clearing and vegetation edges, with a smaller inner trapezoid around the action/battle zone. Make the overlay look like a clear outdoor scene breakdown diagram, while preserving the original photographic quality and avoiding any extra objects, people, buildings, icons, or new scenery.

Annotated ChatGPT Multiple Image Outputs

Goal: Create a realistic screenshot-style image of a ChatGPT image generation interface demonstrating multiple image outputs from one request. Canvas: Landscape 16:9 screenshot crop, white background, resembling a mobile or narrow desktop chat interface. Keep the composition slightly zoomed in so the right edge of the image carousel is visible. Layout: At the top right, place one rounded light-gray user message bubble containing Japanese text. Beneath it on the left, show the status line “Thought for 2m 7s ›” in light gray. Below that, show one large generated image preview with rounded corners, and a narrow strip of additional generated thumbnails on the right side. Text content: The user bubble should read: “絵コンテを参考に今回のベた塗アニメMVで使用する背景イラストを被写体なしで10個作成してください。\nテイスト強めで汚らしっぷつぷ感はなくしてください。プロアニメーターとして画質はよくしてほしいです。\n16:9　n=10”. Highlight the “n=10” part as the key detail. Generated image preview: The main preview is a pastel anime background illustration of an empty stylized street with no characters, inspired by a colorful East Asian shopping district. Use soft cel-shaded anime line art, bright pastel blue, pink, yellow, and mint tones, lanterns hanging from buildings, decorative circular signs, shopfronts on both sides, a centered vanishing point, and a decorative archway in the distance. The image should look like a professional anime MV background, 16:9, clean and polished. Discrete visible elements to include: exactly 1 user message bubble; exactly 1 status line; exactly 1 large main generated image; exactly 3 narrow vertical thumbnails partially visible on the right, each showing a different pastel anime background; exactly 2 circular overlay buttons on the main preview, one dark “編集” edit button at bottom left and one white downward arrow download button near bottom right; exactly 1 small dark share/upload icon button at the lower-right corner of the main preview. Annotation: Add thick hand-drawn yellow marker annotations over the screenshot: exactly 1 yellow circle around “n=10”, exactly 1 thick yellow arrow pointing from the circled “n=10” down toward the right-side thumbnail strip, and exactly 1 tall yellow bracket-like outline encircling the vertical thumbnail strip. The yellow marker should look casual and drawn by hand. Style: Clean UI screenshot aesthetic with subtle antialiasing, light gray interface elements, Japanese text rendered legibly, and bright yellow annotation marks. Use {argument name="main annotation text" default="n=10"} as the highlighted parameter in the chat message. Keep the screenshot realistic, not a poster or infographic.

Hand-Drawn Annotated Food Diary Style

生成一张{argument name="风格" default="英国牛排店"}风格的{argument name="食物" default="牛排和甜点"}的照片。像是用智能手机拍摄的、适合发到Instagram的照片。没有人物。然后，观察照片中出现的元素，并为每个元素添加有意义的手绘注释。 【描写规则】・像用白色笔画出那样的细手绘线条・一笔写成风格的粗糙、略微不均匀・像描摹物体外周那样添加轮廓线・用箭头或虚线制造视线引导【文本规则】・英文手写文字 ・简短，像自言自语一样的评论・语气是“日记・一言・情感寄托”【评论生成规则】・饮料 → 味道・温度・心情（例：清爽、温柔的甜味）・食物 → 口感・美味（例：湿润、最高）・空间 → 氛围（例：放松、美好时光）・整体 → 一言总结（例：幸福过头了～）【装饰】・蒸汽、闪闪发光、心形、小表情符号等适度添加・不过度，留出“空白”【完成风格】・Instagram故事风、杂志的粗糙笔记风 ・时尚且轻松的氛围

Annotated Transformer architecture diagram

Hey, Nano Banana Pro, add annotations to the original Transformer architecture diagram.

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.

AI Chat Image Generation Screenshot

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

AI Manga Panel Generation

👧🐈‍⬛ 👣🐾 👣🐾 👣🐾 👣🐾 👣🐾

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": "…

Surreal Physics Dystopia Image Generation Prompt

A lone human silhouette walking forward as the world around them breaks all physical laws — a city bending and twisting like melted steel, gravity collapsing sideways, buildings splitting open into glowing red cracks of energy, shards of glass floating in slow motion, time frozen mid-air. The sky is a storm of black clouds tearing apart into neon red voids. Surreal physics, impossible geometry, reality warping into spirals. Ultra-cinematic, photorealistic, 4K detail. Dark futuristic aesthetic, high contrast red-black lighting, dramatic atmosphere, deep shadows. Emphasize intensity, rebellion, and rule-breaking energy. Camera + Style Parameters: { "style": "{argument name="style" default="ultra cinematic surrealism"}", "resolution": "{argument name="resolution" default="4K"}", "ratio": "{argument name="ratio" default="16:9"}", "camera": { "lens": "{argument name="lens" default="35mm wide"}", "depth_of_field": "{argument name="depth of field" default="deep focus"}", "motion": "{argument name="motion" default="slight forward push"}" }, "lighting": { "type": "{argument name="lighting type" default="red-black high contrast"}", "glow": "{argument name="glow effect" default="cracks emitting red neon energy"}", "shadows": "{argument name="shadows" default="heavy and dramatic"}" }, "environment_details": { "city_style": "{argument name="city style" default="dark futuristic dystopia"}", "effects": [ "floating debris", "time slices", "gravity distortions", "energy fissures" ], "weather": "{argument name="weather" default="storm clouds ripping open with neon red light"}" } }

Chinese Schoolchildren at Corner Shop

A candid, photorealistic street documentary photo of three primary school children buying snacks at a small old-fashioned neighborhood convenience shop in China, shot in soft natural daylight. The scene is framed straight-on at storefront level, with a slightly compressed everyday snapshot feel, realistic textures, and subtle depth. On the left, one schoolgirl stands in profile wearing a light pink zip-up jacket, dark jeans, and a red scarf, her black hair tied in a ponytail with a white headband, looking down at coins or a small item in her hands. In the center, one schoolboy stands with his back to the camera in a bright blue school tracksuit and a navy-and-red backpack featuring a Mickey Mouse graphic, leaning slightly toward the counter. On the right, one younger schoolgirl with two low pigtails tied with pale pink hair ties leans against a large chest freezer, wearing a white long-sleeve top and blue athletic pants, with a pink backpack resting beside her. Behind the counter, inside the dim shop interior, one shopkeeper in a pink top with a cartoon character print stands partially obscured in shadow. The counter is cluttered with packaged snacks, clear plastic bags of candy, colorful biscuit boxes, jars, and small goods; the shelves behind are densely packed with drinks and snacks. A bunch of multicolored balloons hangs near the upper center of the shop entrance. The chest freezer in the foreground is white with a green lid trim and green Chinese branding on the side. The storefront is worn and modest, with peeling beige walls, a posted calendar or notice sheet on the left wall, metal-framed windows, and an open service window. Include authentic Chinese neighborhood shop details, natural messiness, believable lighting, muted urban colors, and an unposed slice-of-life atmosphere. Faces should be softly obscured or turned away, emphasizing realism and privacy rather than portrait detail.

Surreal High-Fashion Desert Prompt

{ "image_metadata": { "type": "editorial_fashion", "style": "surreal_high_key", "camera_settings": { "lens": "24mm wide-angle", "focus": "ultra-sharp", "detail_level": "high-fidelity_texture" } }, "subject": { "identity": "reference_face_maintained_100%", "pose": "angular_introspective_crouch", "position": "atop_white_sand_dune", "attire": { "garment": "{argument name="swimsuit color" default="royal_blue"}_velvet_strapless_swimsuit", "texture": "plush_velvet", "accessories": [ "chunky_oversized_gold_bangles" ] } }, "environment": { "location": "white_sand_desert", "horizon_line": "low_frame", "sky": { "color": "deep_blue", "condition": "cloudless", "scale": "massive" } }, "visual_palette": { "primary_colors": [ "pristine_white", "beige", "intense_royal_blue" ], "lighting": { "type": "high_sun", "shadows": "soft_minimal", "mood": "dreamlike_pastel" } }, "constraints": { "facial_integrity": "exact_features_no_alteration", "color_retention": "strictly_original_colors" } }

3D Cartoon Character Pose Sheet

Create a high-quality 3D cartoon character illustration of a {argument name="subject" default="cheerful young girl"} with {argument name="accessory" default="oversized round glasses"}, expressive big eyes, and messy curly hair tied in a voluminous bun. She is shown in multiple energetic jumping and dancing poses on a {argument name="background" default="clean turquoise studio background"}. Each pose must feature a completely different stylish outfit: oversized sweaters, denim jackets, overalls, hoodies, skirts, cargo pants, sneakers, pastel fashion, streetwear, cozy knitted textures, and playful accessories. The character should have Pixar/Disney-inspired styling, ultra-detailed fabric textures, soft cinematic lighting, vibrant colors, cute proportions, dynamic body movement, and joyful facial expressions. Full-body composition, floating/jumping action poses, highly detailed 3D render, depth of field, smooth shadows, whimsical and trendy aesthetic, studio-quality character design, colorful modern fashion, adorable animated look, high resolution.

Photoreal Anime Mannequin Display

Create a photorealistic vertical fashion-store mannequin display of an adult-sized glossy white female mannequin wearing an anime-inspired school-uniform cosplay, shot like a realistic retail product photo with shallow depth of field. The mannequin has a smooth blank face obscured by a soft gray rectangular blur, a short black bob haircut with bangs, and exactly 2 tall black furry animal ears on top of the head. Above the head is exactly 1 transparent acrylic halo panel on a thin clear support rod, with blue concentric ring graphics printed on it, like a prop accessory. Outfit: a navy sailor-style school uniform with white stripe trim, a bright blue neckerchief tied at the chest, a dark pleated skirt, and a loose light-blue kimono-style haori with dark navy lapels and cuffs; the left sleeve shows white floral motifs. Add a thin black ribbon choker tied in a bow around the neck. The mannequin has exactly 2 glossy white hands: the raised right hand delicately holds several thin blue cords or strings, while the lower left hand gathers the dangling cords near the waist. Include exactly 1 hanging white retail price tag on the chest area reading small product text and the price “¥24,800”. Add manga-style white sound effects around the mannequin: exactly 4 instances of the Japanese text “キシッ” and exactly 4 small wavy squeak-mark clusters, positioned around the head, shoulders, and lower sides. Background: softly blurred upscale clothing shop interior with warm beige lighting, bokeh ceiling lights, racks of clothing, a tall bright window or light panel on the left, and muted garments on the right. Use realistic camera optics, natural reflections on the glossy mannequin and acrylic halo, warm indoor color grading, high detail fabric textures, and a slightly premium showroom atmosphere. Customize the character concept as {argument name="character name" default="anime halo cat-eared schoolgirl mannequin"}, the main outfit color as {argument name="main outfit color" default="light blue and navy"}, the hair color as {argument name="hair color" default="black"}, the price tag text as {argument name="price tag text" default="¥24,800"}, and the sound effect text as {argument name="sound effect text" default="キシッ"}.

Old Photo Restoration to DSLR-Quality Portrait

Restore old photo into natural DSLR-quality portrait (Canon EOS R6 II level), high detail, accurate colors, sharp clarity, preserve exact facial features · high · photorealistic

Summer Grape Girl 3x3 Grid Portrait

# 夏日葡萄少女写真｜3x3 九宫格提示词 请基于用户上传的 **1-3 张清晰个人照片**，生成一张 **3x3 九宫格拼图写真**，主题为 **「{argument name="写真主题" default="夏日葡萄少女写真"}」**。 --- ## 一、人物要求 请严格保留用户本人真实身份特征，包括但不限于： - 脸型 - 五官比例 - 眉眼结构 - 鼻子形状 - 嘴唇形状 - 肤色 - 年龄感 - 发型特征 - 整体气质 最终九张小图里的人物必须清楚看起来是 **同一个真实女生**，不能变成陌生人，不能欧美化，不能网红化，不能过度美颜，不能出现 AI 假脸。 所有小图都必须保持同一人物身份一致性。 --- ## 二、主题设定 整组图的主题是 **「葡萄少女写真」**，氛围为： - 清新 - 自然 - 轻甜 - 日常少女感 - 夏日户外感 - 带一点日系胶片写真气质 - 但整体仍然像普通女生拍的一组高级生活写真，而不是夸张影楼风 --- ## 三、造型设定 人物穿着： - **{argument name="服装风格" default="奶油白 / 米白色连衣裙或吊带裙"}**，材质轻柔、自然、少女感 - 头上佩戴 **{argument name="头饰配饰" default="紫色系复古印花头巾"}**，颜色为浅紫、葡萄紫、雾紫等柔和紫色 - 可搭配简洁小耳环，整体配饰不要复杂，不要过度时装化 整体造型要自然、干净、普通少女写真感强，不要过度精致，不要太像商业广告大片。 --- ## 四、场景设定 场景为 **夏日户外草地 / 葡萄园边 / 树荫下的野餐场景**。 画面中加入以下元素： - 紫葡萄 - 葡萄串 - 藤编篮 - 野餐布 - 玻璃瓶 - 白色餐盘或浅色器皿 - 草地、树影、自然阳光 - 少量桌面或野餐布置 背景应柔和虚化，氛围自然真实，有阳光透过树叶形成的斑驳光影。 --- ## 五、九宫格要求 输出为 **3x3 九宫格拼图**，白色边框分隔。 九张图必须是 **同一个人物、同一套造型、同一主题场景**，但每张图都要有明显不同的： - 脸部角度 - 姿势 - 镜头距离 - 机位 - 表情 - 手部动作 - 构图方式 ### 重点要求 - 不要九张脸都一个方向 - 不要九张表情都差不多 - 不要只是轻微变化 要像真实拍摄中连续抓拍出来的一组花絮写真。 --- ## 六、九张图动作建议 九张图分别可以包含以下不同状态： 1. 坐在野餐布旁，双手捧着一串紫葡萄，闭眼微笑 2. 躺在草地上，头轻轻侧着，看向镜头，身旁散落葡萄 3. 手拿一颗葡萄靠近嘴边，眼神俏皮地看向镜头 4. 半身侧拍，低头整理藤编篮里的葡萄，表情安静自然 5. 正面坐姿，面前摆着葡萄、玻璃瓶和藤篮，表情平静 6. 近景特写，把葡萄轻贴脸颊，露出轻松笑容 7. 微微侧身回头，手里拿着葡萄串，神情自然抓拍感 8. 闭眼闻葡萄或轻轻靠近葡萄，表情放松愉快 9. 躺靠在草地或树下，怀里抱着藤编篮，眼神温柔看向镜头 --- ## 七、摄影风格 整体为： - 富士胶片相机质感 - 日系胶片摄影风格 - 柔和自然光 - 轻微胶片颗粒感 - 浅景深 - 真实拍摄感 - 清新夏日色调 - 紫葡萄为视觉重点 - 画面干净，有生活感和少女感 --- ## 八、画面要求 - 高真实度人像摄影 - 皮肤质感自然 - 不要塑料皮 - 不要过度磨皮 - 不要夸张美颜 - 不要过度锐化 - 不要卡通感 - 不要插画感 - 不要 CG 感 - 不要廉价影楼风

Anime Character Calendar Generator

アップロードされたキャラクターを用いて以下の画像をお願い。 キャラクターの顔、髪型、髪色、瞳、シルエット、年齢感、衣装の空気感、感情的な雰囲気を維持すること。 別人化しない。 実写化しない。 アニメイラストとして描写すること。 テーマは 「{argument name="テーマ" default="2026年6月のアニメカレンダー"}」。 高品質な日本のテレビアニメ公式カレンダーイラスト風。 2020年代アニメの空気感。 アニメ雑誌付録カレンダー、ソシャゲ月替わりログインビジュアル、公式壁紙のような完成度。 6月らしい 初夏、梅雨、雨上がり、紫陽花、柔らかい湿度感、曇り空から差す光、透明感のある空気、青と水色中心の色彩設計。 キャラクターは自然な日常の一瞬を過ごしている。 例： ・傘を持って歩いている ・雨上がりの街を眺める ・窓辺で外を見ている ・紫陽花の近くに座る ・学校帰り ・濡れたアスファルトの反射 ・初夏の風で髪や服が揺れる ポーズは自然で、 「カレンダー用に撮影された一瞬」のような構図。 重要： 画面内に 「{argument name="日付" default="JUNE 2026"}」 のカレンダーデザイン要素を自然に組み込むこと。 ただし、 巨大文字やポスター風ではなく、 ・画面端の控えめなレイアウト ・透明感のあるUI風デザイン ・アニメ公式カレンダーのような上品な文字配置 にすること。 日付部分も軽く入れる。 ただし情報量は多すぎない。 アニメ風スクリーンキャプチャー。 繊細なライティング。 湿度感のある空気。 フィルムライクな光。 柔らかな反射光。 高品質な背景美術。 シネマティック。 ハイクオリティーな日本のフルカラーアニメ。 8K。 公式アニメ壁紙クオリティ。 文字は崩さず、読みやすい英字タイポグラフィとして描写すること。 カレンダーUIはシンプルで洗練されたデザイン。 キャラクターを最優先し、カレンダー要素は補助的にすること。

Lara Croft Inspired Action Editorial Portrait

{ "main_prompt": "stunning blonde woman in her mid-20s as fierce adventure heroine like {argument name="character name" default="Lara Croft"}, long blonde hair in two thick braids with loose strands, intense determined expression with slight smirk, eyes looking upward diagonally, dirt smudges and mud on face, arms, and clothes for battle-worn look, wearing tight light blue tank top with low scoop neckline showing deep cleavage, brown leather utility belt with large gold buckle, khaki/camo short shorts with thigh holsters, black fingerless gloves, black combat boots, multiple leather straps and harnesses across chest and shoulders holding ammo and gear, dual-wielding pistols: one silver/chrome high-capacity pistol in right hand pointed forward, one black tactical pistol in left hand angled up, dynamic action pose leaning forward with arms extended, powerful stance on rocky jungle ledge, epic jungle waterfall backdrop with cascading water, ancient ruined temple overgrown with vines and foliage, misty fog in air, lush green ferns and tropical plants, dramatic golden hour sunlight filtering through trees creating god rays and rim light on hair and body, strong backlighting with lens flare, cinematic color grading with warm golden tones on skin and cool blue-green jungle shadows, photorealistic, ultra-detailed skin texture with pores, sweat, dirt and realistic fabric wear/tears, high fashion action editorial style, shot on Canon EOS R5 with 50mm f/1.4 lens, shallow depth of field, sharp focus on face and guns with creamy bokeh on waterfall background, film grain subtle, adventurous empowering vibe, Tomb Raider / Indiana Jones meets glamour photoshoot aesthetic", "negative_prompt": "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, worst quality, low quality, cartoon, 3d render, plastic skin, doll-like, airbrushed skin, overexposed, underexposed, flat lighting, harsh shadows, pale clean skin, no dirt/mud, heavy makeup glamorous look, smiling happy expression, modern clothing, city background, indoor setting, obese, elderly, child, male, group shot, bright midday sun, no waterfall/ruins, clean pristine outfit, visible logos except subtle belt buckle, desaturated colors, monochrome", "style_tags": [ "photorealistic", "action heroine portrait", "Tomb Raider Lara Croft inspired", "jungle adventure aesthetic", "dual pistol gunslinger pose", "golden hour dramatic lighting", "cinematic epic composition", "battle-worn glamour", "film grain subtle", "high-end movie poster style", "empowering fierce vibe" ], "technical": { "aspect_ratio": "3:4 or 4:5 (vertical heroic portrait / poster style)", "lighting": "strong golden hour backlight from behind/right creating rim light halo on hair and shoulders, wa" } }

Zhao Lusi Gala Portrait with Bulgari Jewelry

{ "subject": { "name": "{argument name="subject name" default="Zhao Lusi"}", "aka": "Rosy Zhao", "profession": "Chinese actress", "known_for": ["The Long Ballad", "Hidden Love"], "pose": "graceful, poised stance", "expression": "calm, elegant" }, "event": { "type": "high-profile event", "setting": "gala or jewelry exhibition", "background": { "color": "soft pink", "details": ["Chinese character '典' visible"] } }, "styling": { "hair": { "style": "sophisticated low ponytail", "details": "soft, wispy bangs framing face" }, "makeup": { "finish": "luminous, dewy", "colors": { "lips": "warm peach", "cheeks": "warm peach" }, "goal": "enhance natural features" }, "gown": { "color": "mint green", "type": "strapless", "bodice": "pleated fabric bands, crisscross pattern", "skirt": "frothy, feathered/ruffled texture starting at hips" } }, "jewelry": { "necklace": "multi-strand Serpenti necklace, white gold and diamonds (Bulgari)", "bracelet": "matching Serpenti bracelet on left wrist", "ring": "prominent diamond cocktail ring on right hand" }, "composition": { "palette": "candy-colored, mint green dress vs warm pink background", "lighting": "cinematic, subtle moisture highlights on collarbones, shoulders, cheekbones", "skin": { "tone": "luminous white", "details": "realistic sweat sheen, natural pores and texture visible" } }, "image": { "width": 504, "height": 1002, "orientation": "vertical" } }

8K Product Photography with Conceptual Cutaway (Borjomi)

{ "resolution_target": "8K", "image_type": "studio product photography with conceptual cutaway",…

High-End Streetwear Campaign Poster

Use the uploaded reference image as the identity source. Create a premium streetwear campaign poster designed to stop people mid-scroll. Show the same person leaning confidently against a giant oversized {argument name="item" default="beige sneaker"} nearly the same height as the model. Rich glossy {argument name="background color" default="red"} seamless studio background and reflective {argument name="floor color" default="red"} floor. Minimal but dramatic composition with luxury editorial lighting, sharp shadows, polished reflections, cinematic depth, realistic textures. The person wears a monochrome beige tracksuit with matching chunky sneakers, relaxed confident pose, hands in pockets. The giant sneaker is sculptural, futuristic, detailed sole patterns, premium suede and leather textures. Add bold oversized headline typography at the top in clean modern sans serif font: “BIGGER MOVES”. Large white text dominating the frame. Add secondary copy on left: “STAND TALL. BREAK THE SCALE.” Add right side text: “NOT FOR EVERYONE. MADE FOR YOU.” Add bottom center brand text: “HARBORIS” with tagline below: “OWN YOUR EDGE”. Add small left bottom watermark: black Instagram logo, black X logo, harboris. High-end fashion advertising aesthetic, luxury sneaker campaign, sharp focus, ultra realistic, scroll-stopping social media poster, premium branding, balanced layout.

Gothic Kimono Ink Fashion Portrait

Create a dramatic vertical high-fashion portrait of a young Japanese woman in an ornate black kimono with vivid red accents and white cherry blossom patterns, seated in a dynamic swirling pose. Her face is intentionally covered by a centered soft-edged rectangular blur in warm beige-brown tones, while long dark hair flows sideways through elaborate avant-garde hair ornaments made of red and black lace, cords, netting, and floral pieces. The kimono should have wide flowing sleeves, a black obi belt, layered red lining, and one visible bare thigh through the fabric folds. Surround her with an abstract explosion of Japanese ink-art elements: red paint splatters, black calligraphic brush arcs, tangled circular linework, delicate mesh nets, cherry blossom branches, red flowers, and fine radial thread-like lines, all wrapping around her body as if caught in motion. Use the color palette {argument name="color palette" default="deep black, crimson red, white blossoms, pale skin, and off-white background"}. Make the composition {argument name="composition" default="vertical 9:16, tightly cropped, subject angled diagonally from upper left to lower right"}. Use {argument name="visual style" default="hyper-detailed editorial fashion photography mixed with surreal Japanese ink illustration"}, with sharp fabric textures, glossy black hair, intricate lace detail, shallow depth of field in the foreground flowers, and a clean pale studio background. The mood should feel {argument name="mood" default="elegant, chaotic, gothic, and ceremonial"}. No readable text, no watermark, no extra people.

Dramatic Flame-Grilled Ad Poster

Lighting (Hollywood food ad level): dramatic high-contrast lighting, strong warm orange rim light fr…

The Food Galaxy: Cosmic Indian Street Food Solar System

Create a cosmic/space scene where various Indian street foods are floating in deep space as if they are planets, moons, and celestial objects in a delicious galaxy. THE FOOD SOLAR SYSTEM: - CENTER (Sun): A massive round tandoori roti, glowing from within like a star, with charred spots resembling sunspots, radiating warm golden light outward - PLANET 1 (closest): A perfect round golgappa/pani puri — crispy shell glistening, filled with spiced water visible through the opening. Tiny orbit ring of sev and chutney droplets. - PLANET 2: A round vada (medu vada) as a donut-shaped planet with a ring system made of coconut chutney - PLANET 3: A plate of round gulab jamuns as a cluster of sweet brown planets with syrup nebula around them - ASTEROID BELT: Dozens of floating samosas, pakoras, and bhel pieces scattered in a ring - PLANET 4 (gas giant): A huge round dahi vada — white yogurt surface like a cloudy gas giant, with tempering (tadka) marks resembling Jupiter's storms - COMET: A kebab skewer streaking across the scene with a trail of spice smoke and sparks - MOON: A round idli orbiting the dahi vada planet - NEBULA: A colorful cloud of turmeric (yellow), chili (red), and coriander (green) powders mixing in space, forming a stunning spice nebula BACKGROUND: - Deep space black with thousands of tiny stars (mustard seeds and cumin seeds floating as stars) - Distant galaxies made of swirling masala powder - The Milky Way visible but made of a stream of white lassi/buttermilk LIGHTING: - The tandoori roti "sun" provides warm orange light illuminating nearby foods - Each food item has its own subtle glow — the hot items emit warm light, the cold items (lassi, curd) emit cool blue light - Dramatic space lighting: stark bright highlights, deep black shadows, no atmosphere STYLE: Photorealistic food photography meets NASA space photography. Every food item is rendered with appetite-triggering detail — crispy textures, steam, glistening oil, fresh garnishes — but floating in actual outer space with real stars and cosmic phenomena. This surreal combination is the kind of image people share saying "this is the most Indian thing I've ever seen." 8K resolution.

Shadow Box Conversion Prompt

シャドーボックス」化プロンプト。仕様上、どこかを捨ててどこかを拾うので、結構ガチャ要素あります。あと、たまに事故ります。

Exaggerated Hourglass Gym Selfie Prompt

{ "subject": { "identity": "USE_YOUR_REFERENCE_CHARACTER", "body": { "description": "An exaggerated hourglass figure with a very narrow, snatched waist and wide, curvaceous hips. The shoulders are comparatively narrow, emphasizing a dramatic waist-to-hip ratio. The glute muscles are heavily developed, with thick, muscular thighs. The spine appears visibly arched due to the pose.", "pose": "Kneeling on the floor, facing away from the mirror while looking back over the shoulder, holding a smartphone to take a mirror selfie, emphasizing the back and side profile.", "barefoot": true }, "wardrobe": { "top": "White crop t-shirt, slightly lifted or tied at the back.", "bottom": "Very short athletic shorts in soft pastel pink, made of smooth stretchy fabric, featuring prominent white text (not inverted) that reads '{argument name="shorts text" default="REFERENCE"}' across the back.", "accessories": "Smartphone in a soft pink or neutral case, simple necklace." } }, "camera": { "type": "Smartphone camera (mirror selfie)", "lens": "Wide-angle", "aspect_ratio": "3:4" }, "lighting": { "type": "Artificial night light from large windows combined with soft indoor gym lighting.", "quality": "Soft and diffused, highlighting natural skin texture and muscular curves.", "direction": "From the left and above." }, "scene": { "location": "Modern gym.", "background": "Large windows with a blurred {argument name="cityscape" default="Paris"} cityscape at night, out-of-focus cardio machines such as treadmills and bikes, mirror reflections.", "props": "Light blue exercise mat on the floor." }, "texture": { "clothing": "Soft cotton crop t-shirt, smooth stretchy athletic fabric for the shorts.", "skin": "Smooth, natural skin texture." }, "style": { "mood": "Cinematic but realistic", "detail_level": "High detail", "rendering": "Realistic lighting, natural proportions despite stylized curves" } }

Photorealistic Female Model in Paris at Sunset

Full-body portrait of a stunning female model, athletic build, wearing a flowing red dress, confident pose, standing on a cobblestone street in Paris at sunset. Photorealistic, ultra high definition, cinematic lighting, flawless skin, realistic eyes with light reflections, subtle makeup, soft golden hour lighting, romantic and elegant mood. Shot on a Canon EOS R5, with realistic detail and professional photography style.

Sunrise Beach Swimsuit Magazine Snapshot

添付画像のキャラクターを参考にしてください。 同じキャラクターを主役にした、4枚構成の{argument name="テーマ" default="水着スナップ写真"}を作成してください。 {argument name="背景" default="美しい朝焼け"}を背景に水着スタイルと表情が移り変わっていく雑誌風スナップ写真にしてください。各ページでは、水着の色、柄、形状がしっかり変わるようにしてください。水玉、花柄、チェック、無地など、それぞれ可愛いデザインで変化をつけてください。水着に合わせてアクセサリーもそれぞれ変えてください。 ページ構成：1枚目：優しい笑顔。髪型は自然な下ろし髪。風に髪がなびいている。 2枚目：元気な笑顔。髪型はポニーテール。はつつとした雰囲気。 3枚目：穏やかな表情。流し目。髪型はハーフアップか、アシンメトリーなまとめ髪。 4枚目：真面目な表情でこちらをじっと見つめている。潤んだ瞳。髪型は巻き髪やアップスタイルなど。 ポーズと構図は全て違うものにし単調にならないようにしてください。立つ、座る、歩く、振り向く、少し近めのスナップ、やや引きの構図、後ろ姿などをバランスよく組み合わせてください。 写真には見出し、キャッチコピー、短いテキストを配置してください。プロフィール欄は不要です。 全体的には「美しい朝焼けのビーチで一緒に過ごしたような気分になれる水着写真のスナップ集」にしてください。

AI Mechanism Infographic

educational infographic · {argument name="main title" default="最新AI (ChatGPT / Claude) の仕組み"} · {argument name="target audience badge" default="高校生でもわかる！"} · {argument name="subtitle" default="文章・画像・音声も理解し、考えて動けるAIのしくみを1枚で解説！"} · clean, flat design, structured grid, Japanese text · AIが答えを出すまで(基本の流れ) · left column · 6 · 入力, トークン化 (Token), ベクトル化 (Embedding), Transformer (AIの頭脳), 次のトークンを予測 (生成), 出力 · vertical flow with arrows, boy using laptop, token splitting diagram, vector number arrays, self-attention tree, robot icon · ここがコア！ 3つの重要ポイント · top right · 3 · Token (トークン), Transformer (トランスフォーマー), 次トークン予測 · tokenization blocks, self-attention node network, word prediction sequence · 最近のブレイクスルー (2024-2025) · middle right · 4 · マルチモーダル, エージェント化, 長文・推論能力の向上, 効率化・高速化 · image/audio/text icons, robot agent flowchart, lightbulb and book, speedometer with 3 expert nodes · 全体まとめ · bottom full width · horizontal 6-step flowchart, yellow summary box with text: {argument name="summary text" default="「AIは、情報を細かく分けて数字に変換し、関係性を計算して、次に来るものを予測する巨大な数学マシン」です！"}, {argument name="character style" default="anime-style female student pointing and smiling"}

Product Photography of Nano Banana Milk Cooler

Foreground-focused shot of an ice cooler filled with {argument name="product name" default="nano banana milk"} cartons, camera prioritizing sharpness and texture on the nano banana milk in the cooler, cartons appearing slightly larger due to closer foreground perspective, subtle wide-aperture depth of field where the background students and graduation scene remain recognizable but less detailed, not heavily blurred. Light cold condensation mist / icy vapor haze rising gently from the ice, visible chill in the air, realistic ice translucency and water droplets on the cartons. Students in graduation gowns sitting behind the cooler remain unchanged, natural candid expressions, realistic lighting, documentary realism. No heavy blur, no cinematic bokeh, no artificial glow, no overprocessing — just optical priority on the product, crisp edges, natural contrast, and realistic lens behavior.

Anime Barista Character Reference Sheet

Professional anime character reference sheet. Pure white background throughout, no environment, no props, no scenery. Title at top: ‘{argument name="character name" default="MARCO"} — THE BARISTA’. Subtitle: ‘SHIFT: {argument name="shift" default="NIGHT"} // SPECIALTY: {argument name="specialty" default="ESPRESSO"} // VIBE: CALM’ Character: young adult

Golden Hour Freckled Portrait Prompt

{ "prompt_data": { "subject": { "demographics": "Young woman, approximately late teens to early 20s, Caucasian", "hair": { "color": "Golden blonde with lighter platinum highlights", "style": "Long, straight to slightly wavy, loose and messy, falling over shoulders", "texture": "Silky, fine strands illuminated by sunlight" }, "face": { "skin": "Fair complexion, highly textured with prominent natural freckles across nose and cheeks, dewy and glowing", "eyes": "Piercing light blue, clear and sharp focus", "lips": "Natural pink shade, slightly parted, soft pout", "expression": "Neutral, calm, slightly bored or contemplative, direct eye contact with the lens" } }, "clothing": { "item": "Floral corset-style top or bustier", "color": "{argument name="top color" default="Pale yellow or cream"} base", "pattern": "Small vintage pink rose print with green leaves", "details": "Spaghetti straps, lace trim detailing" }, "pose": { "action": "Head resting heavily on right hand", "hand_position": "Palm supporting the jawline and cheek, fingers relaxed", "angle": "Close-up portrait, selfie angle, slight tilt of the head" }, "lighting_and_atmosphere": { "type": "Golden hour sunlight, natural direct lighting", "direction": "Side lighting coming from the left (viewer's perspective), casting distinct shadows on the right side of the face and background", "mood": "Sun-kissed, ethereal, warm, intimate, summer afternoon vibe", "shadows": "High contrast between the bright sunlit skin and the dark background shadows" }, "background": { "setting": "Indoor domestic setting", "details": "Dark, out-of-focus background, hints of a white door with vertical panels", "depth_of_field": "Shallow depth of field, blurring the background to isolate the subject" }, "technical_specs": { "quality": "4k HD, ultra-realistic, highly detailed", "style": "Portrait photography, candid selfie style", "camera_settings": "Sharp focus on eyes and freckles, high resolution, authentic skin texture (pores and imperfections visible), no heavy filtering", "color_grading": "Warm tones, high saturation in the sunlight, natural aesthetic" } } }

Golden Hour Lifestyle Portrait with Hanging Doll

{ "scene": "A cozy indoor setting during golden hour, featuring a young woman holding up a small han…

Shion Rin Three-View Design Sheet

Goal: Create a clean anime character design sheet / three-view turnaround for {argument name="character name" default="紫苑リン (Shion Rin)"}, styled like a Japanese fashion reference board. Canvas: Wide horizontal sheet, 3:2 aspect ratio, warm off-white paper background with thin black divider lines and hand-drawn technical illustration feel. Use delicate pencil/ink outlines, muted watercolor shading, soft gray shadows, and a neat printed layout. Header text: At the top left, write “紫苑リン (Shion Rin) 三面図設計図”. Directly below it, smaller text: “詳細設計：低めツインシニヨン Ver.” Add a long horizontal rule beneath the subtitle. Main layout: Show exactly 3 full-body views of the same young woman, evenly spaced across the left and center of the sheet, each with a Japanese label above it: 1) “紫苑リン 正面図” front view, 2) “紫苑リン 側面図” side view, 3) “紫苑リン 背面図” back view. The face area should be intentionally blurred or covered by a soft rectangular censor-like blur while the clothing, hair, and body silhouette remain clear. Character details: A petite young woman with {argument name="hair color" default="black"} hair in low twin chignon buns, chin-length side locks, straight bangs, and a small purple flower hairpin on one side. Outfit: white short-sleeve blouse with puff sleeves, high ruffled collar, vertical frill placket, small buttons, and modest fitted bodice; high-waisted knee-length A-line skirt in {argument name="skirt fabric" default="taupe beige fabric with tiny purple floral pattern"}; white knee socks; black Mary Jane shoes with low chunky heels. She carries a structured white handbag with double handles and small strap attachments. Pose details for the 3 views: Front view stands upright with the handbag hanging from the left hand. Side view faces left in profile with the handbag held at the side, showing blouse frills and skirt thickness. Back view shows the blouse back seams, both low hair buns, skirt from behind, white socks, black shoes, and the handbag hanging from one hand. Right-side detail area: Include exactly 4 boxed close-up panels arranged in a neat column/grid on the right. Panel 1 is a large upper-right bust close-up labeled “髪型 / 襟元クローズアップ”, showing the low twin chignon hairstyle, bangs, flower hairpin, ruffled collar, and blouse front, with the face blurred. Panel 2 is a small close-up of the skirt front showing the floral textile pattern and hem. Panel 3 is a small close-up of the white handbag, angled slightly, with handles and side gusset visible. Panel 4 is a tall narrow close-up of the skirt from the side, showing the high waist, vertical silhouette, and floral pattern. Visual style: Japanese anime fashion design reference, refined line art, subdued colors, realistic garment construction, consistent proportions across all views, clean labels, minimal background, no decorative clutter. Constraints: Use exactly 3 labeled full-body turnaround figures and exactly 4 boxed detail panels. Keep the sheet legible and symmetrical. Preserve the Japanese labels exactly as written. Do not add extra characters, extra views, logos, watermarks, or unrelated text.

Photorealistic Fashion Portrait on Car Hood at Seaside

use_uploaded_photo · true · maximum · Do not alter facial structure, proportions, skin texture, expression, moles, or identity in any way. The face must match the reference image exactly. · A very beautiful young woman · calm, slightly dreamy · looking directly at the camera · natural, realistic skin texture · minimal with soft smokey eye makeup · eyes subtly emphasized · dark brown · long · loose, wavy, slightly messy · a few strands partially covering her face for a natural, effortless look · loose white open shirt button · relaxed · sleeves slightly rolled up at the wrists · formal black blazer · draped over her left shoulder and resting slightly on the hood of the car · dark pants · black · only partially visible · layered chunky silver chain necklaces · small silver hoop earrings · silver chain bracelet · sitting casually on the hood of a car · leaning slightly back against the hood · medium close-up · sharp focus on the subject · slight natural bokeh · glossy black sports car hood with subtle reflections · beach or seaside · faint sandy shoreline, calm grayish-blue ocean, overcast or heavily cloudy sky · cool, melancholic, serene · soft natural daylight · overcast · evenly diffused lighting with no harsh shadows · outdoor fashion portrait · highly photorealistic · cool and muted · moderate with gentle background blur · ultra high · sharp fabric, hair, jewelry, and skin textures · natural DSLR photography look

Cinematic Portrait with Strict Identity Preservation

image_generation_prompt · dreamlike, cinematic, ultra-realistic portrait · true · false · true · Do not change the face in any way. Preserve 100% of the facial features, structure, skin texture, and likeness from the uploaded image. · female · gently lowered · calm, introspective, serene · relaxed and natural · black · tousled, natural movement · sunglasses creating a cool, effortless aura, single thin silver necklace · white oversized knitted shirt made of soft, textured fabric · neutral cream wall · minimalist and clean · natural sunlight · warm amber · soft glow brushing the face and shoulder, cinematic warmth against the neutral background, gentle highlights with smooth falloff · dreamlike, cinematic, peaceful · soft confidence and quiet elegance · ultra-realistic · high detail in skin texture, fabric weave, and lighting transitions · Create a dreamlike, cinematic portrait of a young woman wearing an oversized white knitted shirt, bathed in warm amber sunlight against a cream wall, while preserving her face exactly as in the reference image.

Find Ruhia in Shibuya

highly detailed isometric 3D hidden-object city scene · {argument name="headline text" default="ルヒアを探せ！"} · a bright sunny Golden Week special scene in Shibuya, Tokyo, viewed from a high elevated wide angle like a miniature diorama, with Tokyo Tower and skyscrapers in the blue-sky background · create a 'find the character' puzzle image where the viewer searches for Ruhia among a huge chibi crowd · GPT-image-2 style, ultra-detailed toy-like 3D render, anime chibi figures, crisp daylight, shallow miniature depth of field, vibrant commercial colors, dense urban signage, playful travel poster mood · high-angle wide shot looking down into a famous Shibuya-style crossing packed with chibi pedestrians · zebra crosswalks, small cars and buses, trees, street lamps, shop entrances, crowds of chibi anime people · large QFRONT building in the center with TSUTAYA and STARBUCKS COFFEE signs, surrounded by many vertical Japanese signs and billboards · Shibuya 109 building on the left, red Tokyo Tower behind it, modern office towers and commercial buildings filling the skyline · a white rectangular signboard with a thin red decorative border, bold black Japanese headline text, and a yellow rubber duck icon · 2 · one small yellow rubber duck sitting on the roof of the SHIBUYA 109 building at the upper left, one yellow rubber duck icon inside the top-right headline placard · 17 · SHIBUYA 109, UNIQLO, H&M, IKEA, QFRONT, STARBUCKS COFFEE, TSUTAYA, Hisamitsu, サロンパス, DHC, 109MEN'S, DMM TV, Glico running man billboard, 竹下通り gate, Tokyo Tower, もも原宿 billboard, アイ♡ライブ billboard · 1 · top-right white bordered placard reading {argument name="headline text" default="ルヒアを探せ！"} with a duck · hundreds of small anime chibi pedestrians packed shoulder-to-shoulder across the streets and sidewalks, with varied hair colors, outfits, animal-ear accessories, tiny bags, and idol-like costumes · {argument name="hidden character" default="Ruhia"} should be camouflaged somewhere in the crowd as the object of the search game · cute rounded chibi proportions, oversized heads, glossy eyes, tiny bodies, toy figurine texture · fill the buildings with colorful Japanese street signs, idol posters, cafe signs, karaoke signs, capsule-toy-like decorations, rooftop air conditioners, balconies, windows, and miniature urban clutter; include a Takeshita Street-style decorative arch in the lower center-left with cute mascot ornaments · clear blue sky, warm sunlight, saturated reds, blues, yellows, pink idol billboards, gray concrete buildings, and multicolored crowd accents · extremely dense details, sharp readable central signs, realistic miniature shadows, whimsical but believable Shibuya travel scene, no empty areas

Photoreal Candid Street Romance Film Still Prompt (Moda Seaside)

NanoBanana Pro · photoreal_candid_street_romance · v1.2_MODA_SEASIDE_SIMIT_SUNNY_CHERRY_DRESS_EN · highest · 4:5 · portrait · ultra_high_res · ultra_photoreal_candid_street_film_still · crisp_but_natural · subtle_35mm · true_to_life_sunny_natural · natural_not_hdr · real_texture_no_retouch · 35mm lens equivalent, eye-level, imperfect framing, candid documentary feel, focus on eyes when people are present · subtle halation on highlights, tiny film gate weave, real street clutter, slight background motion blur only, no studio look · motivated natural light only (sunlight + sky fill), deep but detailed shadows · Moda seaside in Istanbul on a sunny day. A young couple in their early 20s sits near the shore eating simit. A candid, unposed film-still moment—quiet love inside everyday life. · 2 · the same young man and woman (early 20s), ordinary and real, not model-like; faces visible and eyes sharp · small genuine smiles, relaxed presence, natural micro-expressions · natural skin texture, no beauty retouch, no plastic skin, slight imperfections preserved · pink dress with colorful cherry pattern, simple fit, slightly moving in sea breeze, natural minimal makeup, long wavy hair · blue denim jeans and a plain white t-shirt, slightly wrinkled, no logos · two simits in their hands, a simple tote/backpack nearby, no branding · they break pieces of simit, share a bite, laugh softly; the wind lifts the dress hem slightly; crumbs fall naturally onto their hands · Moda coast, Istanbul · sea horizon, gentle waves, a few distant people walking softly out of focus, seagulls in the sky, sunlit railing and rocks · worn stone or concrete edge, small everyday clutter (a bottle cap or leaf), but clean and believable, no staged props · bright sunny daylight with soft sky fill; controlled highlights; subtle halation on sunlit edges; deep but detailed shadows under chins and clothing folds · eye-level medium shot, slightly off-center, imperfect framing like real street photography; faces sharp; background gently receding; no per

Bilingual Prompt Comparison Portrait

comparison image · same photorealistic editorial portrait rendered twice from equivalent prompts in different languages · vertical stack · top · 1 · English · A Japanese businessman in a dark navy three-piece suit, sharp jawline, confident eyes, mid-30s, standing with arms crossed slightly off-center to the right, facing camera, modern glass-office at dawn with Tokyo skyline visible through windows, soft golden hour side lighting from upper left, warm color temperature, 85mm f/1.4 lens, shallow depth of field with creamy bokeh, three-quarter view, bust shot, photorealistic editorial portrait, cinematic color grading. Format 16:9. · photorealistic portrait of {argument name="subject" default="a Japanese businessman"} in his mid-30s wearing a {argument name="suit color" default="dark navy"} three-piece suit with white shirt, dark tie, white pocket square, and wristwatch, sharp jawline, confident eyes, styled dark hair, standing with arms crossed, placed slightly right of center, facing the camera in a three-quarter bust shot inside a modern high-rise glass office at dawn, Tokyo skyline visible through floor-to-ceiling windows, desk with an open laptop and a small plant on the left, shelving and warm interior lights on the right, soft golden-hour side light from the upper left, warm color temperature, shallow depth of field, creamy bokeh, cinematic editorial realism, 85mm f/1.4 look, aspect ratio 16:9 · bottom · 1 · Japanese · 濃紺のスリーピーススーツを着た日本人ビジネスマン、シャープな顎のラインと自信のある眼差し。30代半ば、両腕を胸の前で交差させ少し右寄りに立ち、カメラ正面を向いている。ガラス張りの現代的なオフィス、窓の外には夜明けの東京のスカイラインが見える。左上からの柔らかいゴールデンアワーのサイド光、暖色系の色温度、85mm f/1.4レンズ、浅い被写界深度でクリーミーなボケ、3/4ビューのバストショット、フォトリアルなエディトリアルポートレート、シネマティックなカラーグレーディング、Format 16:9 · the same composition and styling as the top image, nearly identical photorealistic editorial portrait, preserving the businessman, office setting, dawn skyline, crossed arms, lighting, lens look, shallow depth of field, and cinematic grading to demonstrate minimal visual difference between English and Japanese prompts · each section fills half the canvas, no divider line, text block in the upper-left area of each panel · 2 · clean social-media comparison graphic showing prompt text directly on top of generated images · demonstrate that GPT-image-2 produces very similar results from English and Japanese prompts