Explore image prompts.

A cute anime-style {argument name="character type" default="Japanese schoolgirl"} drawn as a hand-made oil pastel illustration on textured paper, bust-up portrait, centered composition. She has {argument name="hair color" default="dark brown"} hair in 2 low twin ponytails with soft waves and a center part, small dark hair ties, and visible ears. Her face is mostly hidden by a large vertical skin-toned rectangular censor block placed over the center of the face from forehead to chin, leaving only the hair, ears, jawline edges, and a little neck visible. She wears a light beige school uniform jacket over a white frilled blouse with lace-like ruffles at the collar and cuffs, accented by a deep red ribbon bow at the neck. Her right hand is raised in a small clenched-fist pose near her chin, creating a shy, adorable, cheering gesture. Background is fully filled with rough diagonal pink pastel scribbles over warm off-white paper. Emphasize thick waxy oil pastel texture, visible grain of paper, soft blending, broken color strokes, sketch-like outlines, charming imperfect handmade crayon drawing quality, gentle warm lighting, nostalgic and extremely cute mood.

A cute anime catgirl crouching low in a playful pose, drawn as a hand-made oil pastel illustration on textured off-white paper. She has long straight {argument name="hair color" default="deep purple with lighter lavender ends"} hair, large pointed orange cat ears on top of her head, and a striped orange-and-black cat tail curving in from the right side. Her outfit is a tiger-inspired bodysuit in vivid {argument name="outfit color" default="bright orange"} with bold black accents: long fitted sleeves, a dark black chest and torso panel, orange legs, orange gloves, and a soft pale pink patch on the hip and upper thigh area. She is squatting with one knee raised, one hand touching the ground in front of her, and the other hand lifted in a salute near her forehead, facing the viewer with a mischievous, energetic feel. Render the whole image in rough crayon-like oil pastel strokes with visible grain, uneven sketchy black outlines, scribbled color fill, and childlike analog texture. Use a warm pastel palette with orange as the dominant color, purple hair, soft pink scribbled background shading, and a purple-blue scribbled shadow beneath her. Keep the composition as a single centered full-body character on paper, whimsical, charming, slightly messy, and irresistibly cute, like an expressive pastel doodle illustration.

Create a {argument name="genre" default="Science fiction"} movie poster

A cute anime girl illustration in a hand-drawn oil pastel style on textured paper, drawn with visible crayon-like strokes, rough sketchy outlines, and soft color blending. The single subject is a teenage girl with {argument name="hair color" default="black"} chin-length bob hair with loose bangs, large sparkling eyes, rosy cheeks, and a gentle smile while glancing upward to the left. She is sitting on the ground in a relaxed side pose with 1 bent knee raised and 1 leg extended forward, both arms resting casually across the raised knee. She wears a bright {argument name="hoodie color" default="red"} hoodie, {argument name="shorts color" default="blue"} short shorts, black knee-high socks, and white sneakers with black stripes. Use a warm, charming, playful mood and emphasize the tactile oil pastel texture, grainy pigment buildup, broken color strokes, and slightly messy childlike crayon drawing appeal. The composition is a full-body figure placed slightly left of center against a simple abstract background made of broad diagonal pastel scribbles in dusty blue, lavender gray, and beige on an off-white paper surface, with no detailed setting and no extra objects.

Goal: Create a dark futuristic Chinese workflow infographic slide showing how to turn written content plus images into an advanced editable PPT, with a premium tech presentation aesthetic. Canvas: Wide 16:9 horizontal slide, deep navy/black background with subtle circuit-line texture, thin glowing border, cyan and gold neon accents, soft bloom highlights, clean corporate SaaS style. Main headline: Centered at the top, use {argument name="headline text" default="文稿 + 配图 → 高级可编辑PPT"}. Highlight “文稿” in gold, “配图” in cyan, and the rest in white. Add a small cyan lens flare under the headline. Top workflow layout: Place exactly 3 large rounded rectangular cards across the upper half, connected by a glowing horizontal process line and arrows that run left to right. 1. Card 1: Yellow numbered circle “1”, title “ChatGPT”, subtitle “理清文字结构”, large gold chat-bubble icon with three dots. 2. Card 2: Cyan numbered circle “2”, title “Image2”, subtitle “生成整页视觉稿”, small mock visual preview containing exactly 3 inner panels: a landscape image, a mini bar-chart/text panel, and a second landscape image. 3. Card 3: Yellow numbered circle “3”, title “GPT-6”, subtitle “拆层成可编辑PPT”, layered floating blue sheets over a gold base icon. Central demonstration: In the lower middle-left, create one large tilted PPT slide mockup with rounded corners and glow. Slide title text: {argument name="demo slide title" default="未来城市：智能与可持续的融合"}. Slide subtitle: {argument name="demo slide subtitle" default="技术创新 · 绿色发展 · 生态共生"}. Inside the slide, show a cinematic mountain lake landscape at sunset, plus a small inset city skyline image on the right. Metric row inside the slide: Show exactly 3 metric items along the bottom of the slide: “35% 能源效率提升” with a clipboard icon in cyan, “60% 碳排放降低” with a shield/check icon in gold, and “2026 全面落地目标” with a globe icon in gold. Layer conversion effect: To the right of the central slide, show the slide splitting into multiple translucent editable layers, about 7 visible stacked panels, with flowing cyan and gold data particles moving from the slide into the layers. Editable output list: On the right side, create exactly 4 stacked rounded cards connected by thin lines to the separated layers: 1. “标题文本” with smaller text “副标题文本”, icon: large letter T. 2. “流程图节点” with smaller text “可编辑 · 可调整”, icon: flowchart nodes. 3. “图片占位符” with smaller text “替换 · 缩放 · 裁剪”, icon: image placeholder. 4. “布局与样式” with smaller text “母版 · 主题 · 动画”, icon: layout grid. Bottom slogan: Centered near the bottom, in gold Chinese characters with dot separators, use {argument name="bottom slogan" default="好看 · 能改 · 复用"}. Visual style: High-resolution presentation infographic, crisp vector-like UI, luminous cyan and warm gold strokes, glassmorphism cards, subtle depth and perspective, modern Chinese typography, clean spacing, no people, no logos, no watermark. Keep all listed text legible and preserve the exact counts: 3 top workflow cards, 3 metric items, 4 editable-output cards, and 7 visible separated layer panels.

{"type":"dark editorial infographic slide","style":"premium keynote-style presentation page with minimalist Swiss-inspired layout, strong contrast, elegant serif headline paired with small uppercase sans-serif metadata, lots of negative space, cinematic black background, subtle grain, refined white typography, monochrome diagram card","aspect_ratio":"16:9","background":{"color":"deep black"},"layout":{"sections":[{"title":"top metadata","position":"top edge","count":3,"labels":["INFOGRAPHIC · SYSTEM","03 / 08","WHAT IS A HARNESS"]},{"title":"main text block","position":"left side","count":3,"labels":["模型不是完整的 agent。","Agent 的定义是 LLM 与工具、数据和环境持续互动。Harness 就是围绕模型的那套编排系统。","Web search、tool calling、文件系统、当前目录、上下文压缩, 都不是\"模型本身\"。"]},{"title":"diagram card","position":"right side","count":5,"labels":["模型（LLM）","挂载（Agent Harness）","工具（Tools）","上下文（Context）","记忆（Memory Store）"]},{"title":"footer","position":"bottom edge","count":4,"labels":["IMAGE TYPE · 系统关系信息图","03","← → 翻页 ESC 关闭","7 pagination dots with the 3rd highlighted"]}],"centerpiece":"a large off-white rectangular card on the right containing a clean systems diagram"},"typography":{"headline_font":"high-contrast editorial serif, oversized, bold","body_font":"modern serif for Chinese body copy","meta_font":"thin uppercase sans-serif with generous tracking"},"diagram":{"card_color":"warm light gray","border":"none or extremely subtle","line_style":"thin black connector arrows","icon_style":"simple outline icons","nodes":[{"name":"模型（LLM）","position":"upper left inside card","details":"small box with subtle radial texture behind the heading, subtitle suggests reasoning and generation"},{"name":"挂载（Agent Harness）","position":"upper center inside card","details":"central orchestration box with small person-like icon above title and short descriptive text below"},{"name":"工具（Tools）","position":"upper right inside card","details":"tall box with wrench icon and a vertical list of 8 tool items"},{"name":"上下文（Context）","position":"lower left inside card","details":"wide box with document icon, description line, and 5 small labeled icons along the bottom"},{"name":"记忆（Memory Store）","position":"lower right inside card","details":"wide box with database icon, description line, and 5 small labeled icons along the bottom"}],"connections":{"count":8,"description":"numbered circular markers on the connector arrows show the orchestration flow between the 5 nodes, including bidirectional links from the central harness to tools, context, and memory, plus one link from the model to the harness"}},"color_palette":{"count":4,"colors":["black background","white headline text","soft gray body text","warm light-gray diagram panel"]},"customization":{"headline":"{argument name=\"headline text\" default=\"模型不是完整的 agent。\"}","page_index":"{argument name=\"page number\" default=\"03 / 08\"}","section_kicker":"{argument name=\"section label\" default=\"WHAT IS A HARNESS\"}","diagram_topic":"{argument name=\"diagram topic\" default=\"系统关系信息图\"}","quote":"{argument name=\"quote\" default=\"Web search、tool calling、文件系统、当前目录、上下文压缩, 都不是\"模型本身\"。\"}"}}

Dramatic ultra-photorealistic black-and-white studio fashion portrait of an {argument name="subject" default="adult man"}, photographed as a premium editorial campaign with a full-frame professional camera. Three-quarter body composition, framed from approximately mid-thigh upward. He stands naturally with confident posture, both hands casually tucked into his trouser pockets, shoulders relaxed, chest subtly open, chin slightly lifted, head turned a little away from the camera. His expression is calm, self-assured, serious, and composed. He wears round vintage-style sunglasses with realistic dark lenses and thin frames, a perfectly tailored {argument name="shirt type" default="crisp white dress shirt"} with the top two or three buttons undone, collar naturally open, sleeves casually rolled to the forearms, shirt neatly tucked into high-quality dark tailored trousers with a simple leather belt and understated metal buckle. Clothing should show authentic fabric texture, natural wrinkles, realistic stitching, subtle folds around the elbows and waist, and physically accurate draping. Pure seamless black studio background with no visible environment, props, texture, or distractions. Extremely controlled low-key cinematic lighting: one strong directional side light positioned approximately 45 degrees to the subject, creating sculpted bright highlights across the white shirt while allowing the opposite side of the face and body to fall naturally into deep partial shadow. Subtle soft reflected fill only where physically plausible. Strong chiaroscuro, rich blacks, luminous white highlights, smooth tonal transitions, realistic skin texture, natural pores and fine facial detail, subtle facial hair detail, accurate anatomy, realistic hands and fingers. High-contrast monochrome photography with a refined filmic tonal range, deep blacks without crushed facial detail, clean highlights without excessive clipping, subtle natural film grain, realistic lens rendering, gentle background separation, and authentic photographic imperfections. Sharp focus on the face, sunglasses, and shirt collar with a gradual shallow depth of field toward the lower body. Sophisticated luxury fashion editorial aesthetic, timeless cinematic mood, restrained and elegant rather than theatrical. Photorealistic skin, physically accurate lighting, realistic shadows, true-to-life proportions, natural posture, premium studio photography, high dynamic range, fine micro-contrast, detailed fabric texture, realistic optical characteristics, {argument name="lens" default="85mm"} portrait lens look, approximately f/2.8, full-frame camera, high-resolution RAW photography, professionally retouched but not artificially smoothed, no CGI appearance.

Ultra-realistic candid smartphone photo, 3:4 vertical. Original non-identifiable young woman inspired only by general proportions/vibe. {argument name="location" default="Night Tokyo sidewalk beside white ceramic tile wall"}. Mid-walk, half-profile, turning back in surprise, hand raised toward lens, shy restrained smile, continuing forward, imperfect framing, nearly exiting frame. Flash fired during motion. Strong handheld shake, heavy directional blur, smeared facial details, blurred hand and hair, ghosting, streaked tile wall, deep darkness around. Harsh flash highlights, blown exposure, hard shadows. Raw accidental snapshot, intrusive, playful, fleeting memory. Extremely noisy, heavily blurred, authentic phone-camera look.

Goal: Create a bold experimental product poster for a design-object announcement, combining an extreme cropped typography background with a thermal receipt layout overlay. Canvas: Vertical poster, 4:5 aspect ratio, off-white outer margin around a saturated hot-pink rectangular field. Use a clean print-design composition with slight risograph/thermal-paper grain and subtly imperfect ink edges. Layout: Place one huge cream-white uppercase background title reading {argument name="product name" default="TABLE LAMP"}, spanning nearly the full width across the upper third; crop the letters heavily at the left and right edges so the title feels oversized and partially hidden. Center-right, overlay exactly one tall narrow cream thermal receipt running from near the top to near the bottom, with zigzag torn edges at the top and bottom. Add one thin vertical microtext line beside the receipt, rotated 90 degrees, reading like an archive/design ID. Along the bottom of the pink field place exactly two separate cream barcode blocks, one at bottom left and one at bottom right. The receipt itself contains exactly one black barcode near its bottom. Receipt details: The receipt header has a large condensed black title {argument name="receipt header" default="TABLE LAMP"}. Under it, include the subtitle “AESTHETICS, SWITCHED ON”. Fill the receipt with monospaced thermal-printer text, dashed divider lines, and pseudo-transaction metadata. Include design-spec lines such as design registration number, date, time, terminal, transaction, attendant, product, object type, form study, material study, surface finish, light quality, curve ratio, form revision, assembly check, aesthetic value, archive index, subtotal, tax, payment method, authorization, thank-you note, return policy, and “KEEP THIS LIGHT RECEIPT”. Highlight exactly one line in a translucent pink marker strip: “GRAND TOTAL--BEAUTY, SWITCHED ON”. Subject image on receipt: At the lower half of the receipt, print exactly one cute glossy flower-shaped table lamp illustration with a pink fluted pedestal stem, six rounded pink petals, a blue inner glow, a small orange-red circular center, and a thin pale power cord trailing left. Keep it centered above the receipt barcode. Typography and style: Use condensed bold sans-serif for the massive background title, monospaced receipt type for all receipt text, black ink on warm cream paper, and a fashionable editorial graphic-design aesthetic. Main colors are {argument name="background color" default="hot pink"}, cream white, black, soft pink, blue, and orange-red. The image should feel like a modern poster generated from the structural idea of a thermal-paper receipt, not a realistic store receipt photo. Constraints: Use exactly 3 visible barcodes total: 2 large background barcode blocks and 1 receipt barcode. Use exactly 1 receipt, exactly 1 product illustration, and exactly 1 highlighted grand-total line. Do not add people, logos, watermarks, QR codes, extra products, or extra receipts.

{"type":"cinematic app design language mood board","style":"ultra-wide premium presentation board with three horizontal cinematic panels and a narrow editorial text column on the left, dark luxury sci-fi minimalism, moody atmospheric lighting, restrained typography, near-monochrome blue-black palette with subtle warm gold accents, highly polished concept-art realism","subject":"a visual design system for an autonomous intelligence product shown as world-scale cinematic environments and interface philosophy","layout":{"canvas":"16:9 landscape","left_column":{"width":"about 20% of canvas","background":"matte black","count":3,"sections":[{"index":"01","title":"Brand-World Hero","tagline":"THE WORLD UNDER AUTONOMOUS INTELLIGENCE.","subtext":"Cinematic. Vast. Subtle. Alive.","position":"top left block"},{"index":"02","title":"Product-Meets-World Hero","tagline":"THE INTERFACE IS A WINDOW, NOT THE WORLD.","subtext":"Human scale. System scale. One view.","position":"middle left block"},{"index":"03","title":"Interior Autonomous-Core Hero","tagline":"THE CORE OPERATES. QUIETLY. CONTINUOUSLY.","subtext":"Tactile. Architectonic. Intentional.","position":"bottom left block"}],"typography":"elegant high-contrast serif for titles, tiny uppercase sans-serif for labels and body copy, generous spacing, faint gold section numbers and divider lines"},"right_panels":{"count":3,"panels":[{"position":"top","scene":"a solitary human figure standing on dark rocky ground overlooking a vast flooded valley at dusk, mountain ranges on both sides, dramatic cloud cover with a pale opening at the horizon, an enormous grid of distant warm lights and runway-like linear illumination stretching into the landscape, reflective water channels and wetlands in the foreground, sense of immense scale and silence"},{"position":"middle","scene":"the same mountainous lake landscape viewed through a giant transparent futuristic interface wall from behind a seated or standing person centered at the bottom edge, subtle HUD overlay graphics framing the panorama, thin white interface lines and tiny data labels, left-side system menu and right-side metrics panel integrated into the glass, the world outside remains dominant while the UI feels delicate and secondary","ui_components":{"count":6,"labels":["MISSION CONTROL","VENTURES","RUNS","OPPORTUNITIES","SYSTEMS","SYSTEM LIVE"]},"right_metrics":{"count":4,"labels":["VALUE PROJECTION","CONFIDENCE","ACTIVE RUN","Lead Generation Engine Executing"]}},{"position":"bottom","scene":"a monumental interior autonomous core chamber, dark stone or concrete architecture, symmetrical composition, tall monolithic walls, thin vertical light slits, a hovering or suspended rectangular black monolith in the center with a small hexagonal emblem, circular platform recessed into the floor beneath it, glossy reflective floor, shafts of cool light descending from above, sparse warm floor lights, sacred technological atmosphere"}]},"color_palette":{"count":5,"colors":["deep black","midnight blue","steel gray","misty silver","muted warm gold"]},"mood_keywords":{"count":8,"words":["cinematic","vast","subtle","alive","architectonic","intentional","quiet","futuristic"]},"rendering":"high-end concept art mixed with premium brand presentation board, photoreal environment detail, soft volumetric fog, reflective surfaces, low-key contrast, meticulous composition, luxury tech aesthetic, no bright saturated colors, no playful elements"}

Using REFERENCE_1 as the main room base and REFERENCE_0 only as a cue for ordinary lived-in apartment realism, transform the room into a natural candid photo of {argument name="group description" default="three 20-year-old female college students hanging out"}. Keep the original cramped room layout, dark curtains, air conditioner, stained beige walls, low table, bedding/futon area, TV shelf, microwave area, scattered trash, drinks, and messy lived-in atmosphere. Add exactly 3 young women into the scene: one seated near the front-right foreground holding a canned drink, one seated by the low table opening or holding snacks, and one seated casually on the bedding at the back-right holding a phone. Dress them in casual Japanese school-uniform-like outfits: white shirts, dark ribbon ties, and plaid skirts. Make the photo feel completely unposed and realistic, like a smartphone snapshot taken during a small hangout, with warm dim indoor lighting and natural shadows. Faces should be anonymized/blurred or indistinct for privacy. Do not clean the room, do not make it stylish, and do not change the camera angle significantly. Emphasize that this is the same uploaded room, now looking like {argument name="scenario" default="a hangout spot for three 20-year-old female college students"}.

Using REFERENCE_0 as the room base, create a natural, realistic photo showing that this same room has become the hangout spot for exactly {argument name="number of students" default="3"} {argument name="student description" default="20-year-old female university students"}. Keep the room layout, furniture, curtains, bed, TV, hanging clothes, storage drawers, lighting, and camera angle from REFERENCE_0 largely unchanged. Use REFERENCE_1 only as inspiration for adding a lived-in, casual hangout mess, but do not make the room dirty or rundown. Add exactly 3 young women in casual Japanese school-uniform-inspired outfits: white shirts, dark plaid skirts, and ribbon ties. Placement: one sits on the left edge of the bed holding a canned drink, one sits cross-legged on the bed near the center holding a phone, and one sits in the foreground on the right side facing slightly toward the others while holding a canned drink. Make their faces anonymized/blurred with simple rectangular blur blocks. Add casual party/snack items on the low black table: exactly 7 visible items — a large open snack bag, a cup noodle container, a paper plate, a canned drink, a small packaged snack, a blue tissue/snack box, and the existing remote/earbud-style small items. The scene should feel like friends chatting and snacking after school, candid smartphone photography, realistic indoor lighting, no dramatic styling, no text overlays, no extra people.

Perform "archival-grade high-fidelity restoration + modern high-end Sony full-frame camera texture reconstruction" on the old photo I provided. Core goal: Not to redraw it or simply beautify/renovate it, but to maximize the repair of damage, blurriness, overexposure, and missing details in the old photo while strictly adhering to the original content, making the final effect as close as possible to what a modern high-end Sony Alpha full-frame camera would produce in terms of clarity, layers, texture, and authentic photographic effect. Restoration should focus on "recovery" and "reconstruction of real details" rather than "drawing another one based on the original." The background should retain reasonable layering. Overall keyword direction: high-fidelity restoration, archival-grade restoration, authentic photography, Sony Alpha full-frame texture, natural high resolution, authentic micro-contrast, delicate layers, credible coloring, documentary, restrained, faithful to the original.

Deconstruct the character's clothing, generate a clothing design diagram, and apply it to an ordinary East Asian woman, {argument name="aspect ratio" default="3:2"}

{"type":"triptych sports advertising poster","brand_style":"premium athletic campaign inspired by Nike studio advertising","subject":{"left_panel":{"type":"athlete portrait","gender_presentation":"masculine","visible_count":1,"skin_tone":"deep brown","hair":"short tight curls","wardrobe":"black zip-up performance training top with a white swoosh logo on the chest","pose":"cropped from upper chest to top of head, head turned slightly to the side","lighting":"moody studio rim light with sweat sheen on neck and jaw, dark background with a single diagonal white light bar behind"},"center_panel":{"type":"product action close-up","visible_count":1,"focus":"black Nike running shoe with white swoosh and visible air cushioning","styling":"white ribbed crew sock with black swoosh","hands_count":2,"action":"both hands tightening the shoelaces while the foot is planted on a dark textured gym floor","camera":"low-angle macro-style product shot emphasizing the shoe shape, mesh texture, laces, and sole"},"right_panel":{"type":"typographic poster","headline":"{argument name=\"headline text\" default=\"MOVE FORWARD.\"}","small_text_count":8,"small_text":["MOVE WITH PURPOSE.","MOVE WITH PURPOSE.","MOVE WITH PURPOSE.","EVERY STEP MAKES PROGRESS. KEEP MOVING.","TRAIN","RUN","RECOVER","REPEAT"],"brand_line":"NIKE TRAINING","logo_count":1,"style":"oversized distressed white condensed sans-serif headline on black background, small utility text, thin white framing lines and corner crop marks, lower boxed logo area with diagonal hatch pattern"}},"layout":{"panel_count":3,"orientation":"vertical triptych","panel_widths":"three equal tall panels","gutter":"narrow dark dividers","overall_composition":"left athlete portrait, center shoe-lacing close-up, right motivational typography block"},"art_direction":{"palette":"black, charcoal, white, subtle warm brown skin tones","mood":"focused, determined, high-performance, cinematic","lighting":"low-key dramatic studio lighting with crisp highlights and deep shadows","texture":"sweat sheen, mesh shoe fabric, rubber sole, matte poster grain","finish":"editorial commercial sports campaign, ultra-detailed, sharp, realistic"}}

{"type":"triptych fast-food advertising poster","brand_style":"bold premium McDonald's-inspired campaign art","aspect_ratio":"16:9 landscape","background":{"color":"deep saturated red","finish":"smooth studio backdrop with subtle tonal variation"},"layout":{"sections":[{"title":"left portrait panel","position":"left third","count":1,"subject":"cropped fashion portrait of a young woman from chest up, face intentionally obscured by a large soft-edged vertical blur block centered over the face","details":{"hair":"dark curly hair gathered up with loose curls framing the head","jewelry_count":4,"jewelry":["large gold hoop earring left","large gold hoop earring right","short gold chain necklace","longer layered gold chain necklace"],"clothing":["red satin zip-up jacket","yellow tank top underneath","small golden arches logo on left chest"],"microtext_count":5,"microtext":["crave the familiar.","crave the familiar.","crave the familiar.","crave the familiar.","crave the familiar."],"graphic_elements_count":2,"graphic_elements":["thin yellow corner line motif near top right of panel","small yellow dotted grid near lower right of panel"]}},{"title":"center food panel","position":"middle third","count":1,"subject":"hero shot of a sesame-seed double-decker burger in an open red carton on a red tabletop","details":{"burger_layers_count":9,"burger_layers":["top sesame bun","top beef patty","pickle slices","shredded lettuce","middle bun with sauce","bottom beef patty","melted cheese","more lettuce and sauce","bottom bun"],"hand":"manicured feminine hand reaching down and touching the top bun with two fingers, wearing thin gold rings","background_items_count":4,"background_items":["red fries carton filled with french fries in upper left background","white drink cup in upper right background","one loose fry on tabletop foreground","one loose fry peeking from lower left edge"],"lighting":"dramatic warm studio lighting, glossy food styling, shallow depth of field"}},{"title":"right typography panel","position":"right third","count":1,"subject":"large typographic slogan poster","details":{"headline":"{argument name=\"headline text\" default=\"Crave the familiar.\"}","headline_style":"oversized condensed bold sans-serif in golden yellow, stacked over three lines and filling most of the panel","small_text_count":9,"small_text":["crave the familiar.","crave the familiar.","crave the familiar.","crave the familiar.","crave the familiar.","crave the familiar.","crave the familiar.","crave the familiar.","crave the familiar."],"brand_marks_count":4,"brand_marks":["golden arches logo near lower left","thin yellow corner line motif near top right","thin yellow horizontal line near bottom","small yellow dotted grid with short horizontal bar marks near lower right"]}}],"gutters":"narrow vertical separations between the three panels"},"color_palette":{"primary":"{argument name=\"background color\" default=\"deep McDonald's red\"}","secondary":"{argument name=\"accent color\" default=\"golden yellow\"}","supporting":["warm brown skin tones","gold metallic highlights","toasted bun brown","lettuce green"]},"style":{"mood":"confident, craveable, stylish, editorial, modern commercial photography","composition":"clean graphic triptych with fashion on the left, product in the center, message on the right","branding":"use McDonald's visual language including the golden arches and packaging","print_finish":"premium poster look with high contrast and sharp detail"},"subject_customization":{"model_clothing":"{argument name=\"jacket color\" default=\"red satin\"}","food_item":"{argument name=\"burger type\" default=\"Big Mac-style double burger\"}"}}

{"type":"triptych advertising poster","style":"bold modern toy-brand campaign, high-contrast studio photography mixed with graphic editorial design","format":"three equal vertical panels side by side","color_palette":{"dominant_background":"vivid saturated red","accent":"bright yellow","secondary":"orange-red, black, white, gray"},"subject":{"theme":"creative building and imagination","brand_style":"construction toy aesthetic","headline":"{argument name=\"headline text\" default=\"BUILD THE FUTURE\"}","tagline":"{argument name=\"tagline\" default=\"Play. Build. Repeat.\"}"},"layout":{"sections":[{"title":"left portrait panel","position":"left third","count":1,"labels":["child portrait"]},{"title":"center build panel","position":"middle third","count":1,"labels":["hand placing brick on toy building"]},{"title":"right typography panel","position":"right third","count":1,"labels":["headline and brand graphics"]}],"panel_dividers":"thin dark vertical separations between all 3 panels"},"left_panel":{"subject":"close-cropped portrait of a child from chest up","counted_elements":{"people":1,"garments":2,"visible_facial_features":2},"appearance":{"age":"young child","hair":"short dark brown hair","clothing":["red crew-neck shirt","red zip-front jacket with silver zipper teeth"],"visible_features":["left ear visible","neck and lower face visible"]},"framing":"top of head slightly cropped, centered in panel","background":"solid vivid red seamless studio backdrop"},"center_panel":{"subject":"toy architecture scene being assembled","counted_elements":{"hands":1,"main_building":1,"mini_figures":6,"trees":1,"vehicles":1,"loose_bricks_being_placed":1},"action":"a human hand enters from the upper left and places a single red brick on the roof","building":{"style":"block-built modern multi-level house or civic building","colors":["red","yellow","gray","transparent dark window panels"],"features":["arched left-side structure","flat roof levels","multiple balconies or terraces","large windows","gray baseplate","front steps"]},"surroundings":{"mini_figures":"6 small construction-worker-like toy figures in yellow and red distributed around the structure","trees":"1 small green conifer-like tree near front left","vehicle":"1 small black and red wheeled vehicle at the lower left edge"},"background":"solid vivid red seamless studio backdrop","surface":"red tabletop continuous with backdrop"},"right_panel":{"subject":"graphic poster typography","counted_elements":{"headline_words":3,"small_repeated_word_instances":9,"decorative_blocks_top_right":3,"small_horizontal_bar_groups_top":2,"tagline_lines":3,"logo_boxes":1,"decorative_hatched_boxes":1,"decorative_dot_grids":1},"typography":{"main_text":"{argument name=\"headline text\" default=\"BUILD THE FUTURE\"}","arrangement":"three stacked lines, one word per line, very large condensed bold sans-serif in yellow occupying most of panel height","tagline":"{argument name=\"tagline\" default=\"Play. Build. Repeat.\"}","tagline_position":"lower left of right panel in small yellow text on 3 lines","repeated_side_text":"the word BUILD repeated vertically 9 times in small yellow text along the mid-right side"},"graphics":{"top_details":["1 short yellow dash near upper left","1 long thin yellow striped bar near top center"],"top_right":["cluster of 3 small square blocks in yellow and orange"],"bottom_details":["1 yellow hatched rectangle near lower center-left","1 small yellow dot grid near bottom center"],"logo":"{argument name=\"brand name\" default=\"LEGO\"} logo inside a thin black outlined square at lower right"},"background":"solid vivid red"},"lighting":"clean commercial studio lighting, crisp and saturated, minimal shadow, polished ad-campaign finish","composition":"striking triptych composition with photographic portrait on left, product build action in center, and oversized typographic slogan panel on right"}

{argument name="clothing" default="swimsuit"} fashion magazine advertisement page, {argument name="region" default="Japanese"} mature model, S-curve. Varying poses and styles, shown in a nine-grid display, maintaining facial consistency of the character.

Create a photorealistic wide-angle scene of a modern Japanese station platform in bright daytime, featuring a sleek white limited express train fully covered in an elegant anime character wrapping design for {argument name="character name" default="NOZOMU"}. The train is stopped beside the platform, viewed from a low three-quarter front angle so the rounded glossy black windshield fills the left edge and the decorated cars recede into the distance on the right. The wrap design shows one large pastel anime girl illustration on the nearest car: long light brown hair, oversized pale lavender bow on her head, delicate clock-and-gold accessory details, soft white blouse, fantasy memorial-line styling; keep her face intentionally obscured by a plain rectangular privacy blur. Surround the character with ornate gold filigree frames, antique clocks, stars, white flowers, pale blue ribbons, and soft watercolor accents. Add large refined serif branding on the train side reading “{argument name="train branding" default="NOZOMU"}”, with smaller text “SPECIAL WRAPPED TRAIN” and “Limited Memorial Line.” Continue the same illustrated wrap along the following cars with smaller repeated character art and decorative clock motifs visible between dark rectangular train windows. On the platform, include exactly three promotional placements: 1) a large overhead station sign near the upper right reading “NOZOMU / SPECIAL WRAPPED TRAIN / Limited Memorial Line” with a blue strip of Japanese text “本日限定運行” and a blurred character face on the right; 2) a vertical poster pillar on the far right showing the anime girl, Japanese copy “会いに行ける、うちの子。” and NOZOMU branding; 3) a floor advertisement decal near the lower right with ornate border and the same NOZOMU special wrapped train logo. Add a few real commuters in the background on the platform, including one person photographing the train with a phone, but keep them small and secondary. Use realistic railway platform details: yellow tactile paving strip, tiled floor, overhead canopy beams, hanging lights, wires, rails implied beside the train, soft shadows, blue sky, and strong natural sunlight. Style should blend real photography with high-quality printed anime advertising, crisp reflections on the train windows, premium commemorative campaign atmosphere, pastel ivory, gold, pale blue, and lavender color palette. No extra logos, no watermarks, no additional vehicles, and keep all visible text clean and legible.

A family portrait depicting four generations of related women, based on the attached girl as the reference. Composition: - The subject as a child - The subject currently - The mother - The grandmother Framing: - A natural group composition like a multi-generational family photo - Arrangement where the family is huddled close together - Natural sense of distance and height differences

Use the provided image as the base reference for the original character. Produce a high-quality anime key visual featuring both the original character and their gender-swapped version simultaneously. Place the original character on the left side of the screen. Place the gender-swapped character on the right side of the screen. Both must be immediately recognizable as the same person at a glance. Maintain facial features, eye shape, facial proportions, hairstyle design language, hair color, silhouette, habitual expressions, personality traits, visual motifs, and overall character identity with high precision. The gender-swapped version should not be mere cosplay or an outfit swap, but a design based on the natural interpretation of "what if the same person was born as the opposite gender from the start." Do not simply put them in clothes for the opposite sex. While naturally redesigning the outfit to suit the gender, maintain the fashion style, color design, accessories, symbolism, occupation, social status, world-view, and design philosophy of the original design. Ensure the audience can instantly understand that they are "male and female versions of the same person." Both designs should share strong visual commonalities. [Overall Atmosphere] The vibe of a late 1990s to early 2000s Japanese anime magazine or promotional poster. An official key visual for a non-existent masterpiece gender-swapped rom-com anime. Joyful confusion. Lighthearted commotion. Rom-com-style distance. Comical pacing. Not a serious sci-fi work. Not a serious parallel world story. Not a global crisis. Prioritize a fun atmosphere as if some unexpected trouble has occurred. Aim for a promotional visual that makes viewers think, "This definitely looks like it would be fun." [Character Acting] Depict the two characters as having accidentally encountered their own opposite-gender self. They should be aware of and reacting to each other. Emotions can be chosen freely. Examples: Surprise, confusion, bewilderment, irritation, curiosity, embarrassment, rivalry, self-loathing, self-praise, exasperation, provocation, distrust, caution, strange sense of affinity, etc. A mix of multiple emotions is allowed. The important part is to convey the humor of "seeing one's own gender-swapped self." [Composition] Do not use a fixed composition. Choose a different staging every time. Examples: Facing each other, back-to-back, putting arms around shoulders, arguing, glaring at each other, pointing at each other, staring at each other like looking in a mirror, taking the same pose, taking completely different poses, observing each other, chasing each other, running/chasing, accidentally bumping into each other, confusion immediately after swapping, fighting over the same object, reacting simultaneously, checking each other's clothing, keeping distance warily, becoming awkward from being too close, etc. Do not rely on symmetrical compositions. Vary the composition so that it looks like a promotional visual for a different anime work every time. [Background] The background should naturally suit the character's world-view, occupation, era setting, genre, culture, and design language. Design the background as a high-quality anime backdrop that enhances the characters. If necessary, you may use: School, cityscape, shopping district, fantasy world, Japanese-style space, magical world, cyberpunk city, retro-pop design, amusement park, school festival, stage, abstract graphics, etc. The background should naturally convey the genre of the work. [Art Style] Late 1990s to early 2000s anime magazine illustrations. Retro-pop anime aesthetics. Cel-shaded animation style. Clean line art. Bold silhouette design. Vivid and joyful color design. Commercial anime official promotional illustration quality. Dynamic like a scene from an anime opening. Strong eye-catch like a magazine cover. [Prohibitions] No logos. No title text. No captions. No watermarks. No comparison table layouts. No setting material collection layouts. No turnaround sheets. Do not make it a character comparison image. Do not make it a serious multiverse war. Do not make it a dark fantasy apocalyptic battle. Do not let combat or world-view explanations take center stage over the gender swap itself.

A warm, highly detailed anime-style illustration set in a cozy, cluttered indie workspace that feels like a book café mixed with a startup studio, lit by golden afternoon sunlight streaming through tall windows on the right and by 4 black industrial pendant lamps hanging from the ceiling, with string lights, overflowing bookshelves, plants, and handwritten motivational signs covering the background. Show 5 young women standing around a large wooden worktable, framed as a wide group portrait. The mood is whimsical, slightly satirical, and aspirational-but-chaotic. On the far left, place a tall woman with very long wavy {argument name="hair color" default="auburn"} hair wearing a crown of white daisies and a sleeveless rust-brown dress with a white sunburst emblem on the chest and a dark belt at the waist; she holds a small handwritten note toward the viewer that reads exactly {argument name="note text" default="Claude is asking for your permission"}. In front of her on a side table is a glass cup of tea, a book stack, and a tiny potted plant. Next to her, place a punky blonde woman with twin ponytails tied with black bows, large black headphones resting around her neck, and an off-shoulder black dress marked with a bold white X on the torso; she stands confidently beside an open sticker-covered laptop with another large X logo. In the center rear, place a mysterious slim girl with extremely long dark navy-black hair, pale skin, and a gothic dark dress, standing quietly in front of a desktop monitor showing a blue glowing star or sparkle on a dark screen. To the right of center, place an elegant woman in a fitted red cheongsam-inspired dress with floral embroidery and a side slit, leaning one hand on the wooden table near an open notebook filled with sketches or writing. On the far right, place a casually dressed brunette with messy hair in a bun, wearing a white T-shirt with a black knot-like AI logo under an open beige overshirt, standing behind an open silver laptop with the same logo. Scatter many cozy desk objects across the main table: 2 mugs, 1 open notebook, 1 pen, 1 small black figurine, 1 closed book stack, and laptops. Add readable handwritten wall notes and signs throughout the room: “FOCUS SHIPS DREAMS” on the upper left, “SHIPPING IS MY CARDIO” on the left wall, “turn caffeine into code” near the top center, “be kind to your future self” near the window, “The Art of Asking Nicely” on a book spine at lower left, “WORLD’S OKAYEST MODEL” on a black mug near center-left, “MOONSHOT DIARIES” on a book stack near lower right, “Good Prompts Only” on a mug at lower right, and a sticky note at the bottom right reading “AGI is already for ready us” with a small doodle. Use painterly linework, intricate textures, expressive fashion styling, warm brown and amber color grading, soft cinematic depth, and a polished social-media-viral illustration aesthetic.

Generate a 9:16 vertical, high-precision 3D CG double character illustration. The overall style is high-end 2D 3D CG rendering, with a dreamy, romantic, ambiguous, and restrained texture. The subjects are two adult Eastern fantasy female characters, located by a huge bright floor-to-ceiling window. Left character: adult female, {argument name="left hair color" default="silver-white short hair"}, gentle and active eyes. Right character: adult female, {argument name="right hair color" default="bright red long hair"}, high ponytail, calm expression. The two have an intimate relationship: their noses almost touch, and their eyes meet in an ambiguous gaze at close range. Both wear {argument name="dress color" default="white"} fantasy-style modified short formal dresses in a unified style. The background features a backlight effect from the floor-to-ceiling window, with warm golden-pink sunset soft light.

A detailed portrait of a fierce tribal fantasy warrior woman leaning close to a massive, majestic great horned owl, cinematic lighting, dark moody atmosphere. The woman has {argument name="hair style" default="long, wavy dark hair"} adorned with intricate silver chains, beads, and metallic headpieces. She has striking {argument name="eye color" default="light green"} eyes, piercing the camera, with silver and icy-white war paint painted across her cheeks and nose. She wears dark leather armor decorated with silver pendants and turquoise gemstones Beside her the giant owl features sharp {argument name="owl eye color" default="glowing orange"} eyes, patterned white and black feathers and an ornate silver circular medallion studded with a blue crystal resting on its forehead. The background is a shadowy, mystical forest in cool blue and dark gray tones. Highly detailed feathers, hyper-realistic, photorealistic textures, 8k resolution, dramatic dark fantasy aesthetic, masterpiece.

Generate a cinematic portrait with dynamic motion blur based on the theme: {argument name="theme" default="Dilraba walking quickly at the airport"}. The subject occupies the main visual weight with a quiet side profile or half-body silhouette, with subtle recognizable details at the edges of the face. The body and hair are stretched into a long-distance horizontal motion blur to one side, like a band of light passing through the subject and gradually blending into the background, making the character look like they are being carried away by speed, memory, or information flow. The background is a high-brightness, clear, and soft airy field without complex scenes. Colors are extracted from the material, emotion, and narrative temperature of the theme, preserving large areas of bright, calm base colors, deep shadows on the subject, a few highly saturated glowing accent colors, and a clean relationship between color gradations, creating a dreamlike and clean tension between warm and cold, avoiding muddiness, staleness, or ashy tones. The light is softly diffused, the focus is slightly loose, and the edges have slight film grain and lens flare, but the overall feel remains airy, transparent, and modern. The visual information density is low, leaving plenty of empty space for the sense of speed to breathe; text is used as part of the visual structure in a pure white modern sans-serif font, with the core word in a very large size placed below the subject or near the visual center, and short explanatory sentences using smaller font sizes, compact line spacing, and a centered rhythm. All text acts like a clear interface layer superimposed on the light mist, holding down the visual hierarchy without breaking the flow of the soft-focus image. Aspect ratio {argument name="aspect ratio" default="3:4"}

Modern and fashionable high-end one-piece swimsuit with elegant tailoring. A youthful and sunny {argument name="age" default="around 20-year-old"} Japanese female model with fair skin, slightly curly long hair, and a plump yet elegantly proportioned figure, exuding a sunny and confident temperament. Beach vacation style, soft natural light, walking sideways to highlight soft feminine silhouettes. Photorealistic, fashion magazine style, different angles, maintaining facial consistency, displayed in a nine-grid layout.

Use {argument name="character" default="the character from the reference image"} as the base design to draw "a single frame of a short video accidentally taken by a regular person on a train, showing an anime character living a normal life in the real world." Accurately maintain the atmosphere of the character as an anime illustration. Preserve the impression of the face, hairstyle, hair color, eyes, ears, body proportions, silhouette, and facial expression. Never break the character's identity. Do not turn the character into a photorealistic human. Maintain high-quality anime illustration expression for the character part. The setting is {argument name="setting" default="the interior of a typical Japanese commuter train"}. Realistic, photorealistic background depiction. Naturally depict advertisements, windows, handrails, straps, seats, doors, and guide displays. Do not make the space look like a clean advertising photo. Give it a sense of everyday life and use typical of real public transportation. The composition is a vertical short video. A screenshot of an SNS video taken with a smartphone. The photographer is sitting near the opposite seat. The character is sitting on the long seat opposite. A natural angle seen slightly from the side, not directly from the front. The character is looking at a smartphone. Not looking at the camera. Not posing. Not aware of the photographer. A bag, paper bag, or shopping bag that the character might have is placed at the character's feet. An atmosphere like coming home from work or shopping. They can be wearing earphones. They can have a tired or sleepy expression. They are just normally in transit. Surrounding passengers exist naturally. No one is reacting specially to the character. Depict the surrounding world as a mysterious everyday life where people are "used to the existence of anime characters." Add a modern {argument name="social media UI" default="atmosphere similar to TikTok, Instagram Reels, or YouTube Shorts"} to the screen. Not a LIVE broadcast screen. Naturally display the number of likes, comment section, share button, etc. Do not fix the comment content; let the AI generate it naturally. Comments are mainly in Japanese. Important: The comment section should not treat the character like a celebrity. No flaming or news treatment. It should have a natural temperature, like seeing an urban legend or a rare wild animal. Emphasize textures typical of smartphone photography: light HDR processing, fine sensor noise, slight JPEG compression feel, natural exposure, slight chromatic aberration, autofocus feel, high ISO noise, and fine shakes typical of handheld shooting. Reality like a frame cut from a short video. Prohibit movie poster style. Prohibit cinematic direction. Prohibit dramatic lighting. Prohibit excessive depth of field effects. Do not overload with information. Prohibit advertising photo style. Avoid AI-specific glossy rendering. Prioritize the strange reality of "a mysterious video that accidentally flowed through social media," "for some reason no one is surprised," and "only the person themselves is living normally."

Create a refined, high-end PHOTO + MINIMAL WATERCOLOR VIGNETTE artwork based entirely on the uploaded photograph. Use the photograph as the only visual reference and preserve the exact subject, composition, environment, clothing, objects, lighting, colors, and mood. FORMAT: Vertical {argument name="aspect ratio" default="3:4"} editorial composition. TOP SECTION — ORIGINAL PHOTOGRAPH: Place the original photograph in the upper 55–60% of the canvas. Keep it photorealistic and naturally detailed. Do not alter the identity, pose, proportions, objects, architecture, scenery, or important visual details. Give it a subtle premium editorial photography finish with natural cinematic light and gentle tonal balance. BOTTOM SECTION — HAND-PAINTED INTERPRETATION: Transform the same exact scene into a delicate minimal watercolor and fine-ink illustration. Recreate the main subject, pose, perspective, key objects, and recognizable background elements from the photograph. Use loose watercolor washes, subtle pencil/ink outlines, imperfect hand-painted edges, soft paper texture, and restrained pastel tones. Keep the illustration airy, elegant, and slightly imperfect rather than digitally polished. The illustration should feel like a fashion/lifestyle magazine sketchbook page, with plenty of clean negative space and a warm off-white textured paper background. Do not introduce new subjects or details. TYPOGRAPHY: Add a short elegant handwritten brush-script phrase underneath or integrated naturally into the illustrated section, similar to a premium lifestyle editorial poster. Underneath it, add a tiny minimalist lowercase serif/sans-serif subtitle. Typography should be subtle, sophisticated, thin, and balanced with the artwork. AESTHETIC: Scandinavian editorial design, quiet luxury, nostalgic travel journal, soft watercolor, delicate ink drawing, handmade paper texture, muted natural palette, sophisticated minimalism, emotional storytelling, premium art-book layout. IMPORTANT: The photograph and illustration must clearly represent the same exact moment and scene. No collage of unrelated images, no dramatic redesign, no excessive watercolor, no cartoon appearance, no heavy outlines, no saturated colors, no clutter. Output: photorealistic upper section + matching delicate watercolor illustration below, seamless premium editorial composition, vertical {argument name="aspect ratio" default="3:4"}, high detail. For different photos, just change the text phrase Examples: •{argument name="phrase" default="Good Days — a kinder me"}