{
  "type": [poster | infographic | profile | thumbnail | ad | lookbook],
  "subject": [main visual subject],
  "style": [art style + lighting + medium],
  "composition": [layout, framing, focal point],
  "text_elements": {
    "headline": [exact text in quotes],
    "body": [exact text in quotes],
    "language": [en | ja | zh | ko]
  },
  "details": [specific colors, props, atmosphere, brand tokens]

{
  "type": "exploded view product diagram poster",
  "subject": "VR headset",
  "style": "clean high-tech 3D render, studio lighting, glowing accents",
  "background": "{argument name=\"background color\" default=\"soft purple and blue gradient\"}",
  "header": {
    "logo": "∞ {argument name=\"product name\" default=\"Meta Quest 3\"}",
    "subtitle": "{argument name=\"main catchphrase\" default=\"まったく新しい現実を、まったく新しい構造から。\"}"
  },
  "layout": {
    "centerpiece": "vertically stacked exploded view of a VR headset showing 9 distinct layers of internal components: outer shell, camera sensors, motherboard with chip, pancake lenses, internal frame, battery packs, side straps, top strap, and facial interface cushion.",
    "callout_labels": {
      "count": 8,
      "left_side": [
        "Snapdragon® XR2 Gen 2\n圧倒的な処理性能でリアルタイムな体験を。",
        "調整可能なIPD機構\n幅広いユーザーに快適なフィット感を。",
        "精密設計されたヘッドストラップ\n快適さと安定性を追求したエルゴノミクス。"
      ],
      "right_side": [
        "フェイスプレート\n洗練されたデザインと最適な重量バランス。",
        "トラッキングカメラ\n高精度な位置トラッキングと環境認識を実現。",
        "パンケーキレンズ\n薄型設計で広い視野角と鮮明な映像を提供。",
        "高性能バッテリー\n長時間駆動を支える最適化された電源設計。",
        "柔らかなフェイスインターフェース\n長時間でも快適な装着感を実現。"
      ]
    },
    "footer": {
      "left_text_block": {
        "headline": "{argument name=\"bottom headline\" default=\"体験は、構造から進化する。\"

{
  "type": "illustrated map infographic",
  "style": "{argument name=\"art style\" default=\"watercolor and ink hand-drawn illustration on vintage parchment\"}",
  "title_section": {
    "text": "{argument name=\"city name\" default=\"成都\"} {argument name=\"map title\" default=\"吃货暴走地图\"}",
    "mascot": "cartoon red chili pepper wearing sunglasses and giving a thumbs up"
  },
  "border": "{argument name=\"border decoration\" default=\"vine of green leaves and red chili peppers\"}",
  "layout": {
    "background": "textured beige parchment paper with yellow roads, blue rivers, and green park areas",
    "sections": [
      {
        "title": "landmarks",
        "count": 6,
        "illustrations": ["traditional pavilion", "traditional monastery", "modern skyscraper with climbing panda", "tall TV tower", "traditional gate", "industrial buildings"],
        "labels": ["人民公园", "文殊院", "IFS", "339电视塔", "宽窄巷子", "东郊记忆"]
      },
      {
        "title": "food_spots",
        "count": 12,
        "illustrations": ["mapo tofu", "dumplings in chili oil", "skewers in pot", "sticky rice balls", "egg baking cake", "nine-grid hotpot", "sweet potato noodles", "cold skewers", "spicy mixed dish", "covered tea bowl", "ice jelly dessert", "spicy rabbit heads"],
        "labels": ["1 陈麻婆豆腐", "2 钟水饺", "3 春熙路", "4 宽窄巷子·三大炮", "5 建设路·叶婆婆蛋烘糕", "6 玉林路·小龙坎火锅", "7 香香巷·肥肠粉", "8 武侯祠大街·钵钵鸡", "9 东郊记忆·冒椒火辣", "10 人民公园·鹤鸣茶社", "11 锦里古街·冰粉", "12 双流老妈兔头"]
      },
      {
        "title": "图例",
        "position": "bottom-right",
        "count": 5,
        "items": ["red dot", "green house", "green tree", "blue line", "yellow double line"],
        "labels": ["美食地点", "地标景点", "公园绿地", "河流湖泊", "主要道路"]
      }
    ],
    "centerpiece": "giant panda sitting and eating bamboo",
    "bottom_right_extras": ["vintage compass rose with N, S, E, W", "disclaimer text '温馨提示：吃辣需谨慎，肠胃要保护~' with a red chili pepper icon"]

{
  "type": "live stream UI mockup",
  "subject": {
    "description": "portrait of {argument name=\"host name\" default=\"Elon Musk\"}, smiling, wearing a black t-shirt with a white technical schematic graphic",
    "background": "left side shows a screen with '{argument name=\"left background logo\" default=\"SPACEX\"}' text, right side shows a red '{argument name=\"right background logo\" default=\"Tesla T logo\"}' and a dark car"
  },
  "ui_overlay": {
    "top_header": {
      "host_info": "avatar, name '{argument name=\"host name\" default=\"Elon Musk\"}', subtext '55.6万本场点赞', red '关注' button",
      "rank_badge": "gold coin icon with '全站第1名'",
      "viewer_stats": "3 top viewer avatars with '12.3w', '8.6w', '5.7w', total '68.7万', 'X' close button",
      "right_links": "'更多直播 >', '礼物展馆 0/24' with blue '经典' tag"
    },
    "mid_left_gifts": {
      "count": 2,
      "items": [
        "avatar '科技爱好者', '送小心心', heart icon x 1314",
        "avatar '星辰大海', '送火箭', rocket icon x 666"
      ]
    },
    "bottom_left_chat": {
      "system_message": "level 37 badge '宇宙漫游者 加入了直播间'",
      "message_count": 7,
      "messages": [
        "小火箭: 马斯克！未来可期！🚀",
        "future: 特斯拉Model 2什么时候出？",
        "星空梦想家: SpaceX今年能上火星吗？",
        "AI探索者: Neuralink进展如何？",
        "帅气的网友: 马总好！",
        "Mars: 第一次来你的直播，超激动！",
        "用户123: 讲讲AI吧，会取代人类吗？"
      ]
    },
    "bottom_right_product_card": {
      "hot_tag": "orange '热卖 x 1888'",
      "image": "Tesla Cybertruck",
      "title": "{argument name=\"product name\" default=\"特斯拉Cybertruck 电动皮卡\"}",
      "price": "{argument name=\"product price\" default=\"¥ 1,618,000\"}",
      "button": "red '抢' button",
      "floating_animation": "translucent hearts floating up the right edge"
    },
    "bottom_bar": {
      "input_field": "'说点什么...'",
      "icons": ["smiley face", "three dots", "shopping cart", "gift box", "share"]

{
  "type": "evolutionary timeline infographic",
  "instruction": "Using REFERENCE_0 as a structural base, transform the flat vector design into a highly realistic 3D infographic. Replace the smooth ramps with distinct stone steps and upgrade all organisms to photorealistic 3D models.",
  "style": {
    "background": "{argument name=\"background style\" default=\"vintage textured parchment paper\"}",
    "staircase": "{argument name=\"staircase material\" default=\"realistic textured stone blocks\"}",
    "subjects": "{argument name=\"organism style\" default=\"highly detailed photorealistic 3D renders\"}"
  },
  "layout": {
    "main_title": "{argument name=\"main title\" default=\"人类演化\"}",
    "sections": [
      {
        "position": "left sidebar",
        "count": 8,
        "labels": ["L0: 单细胞生命", "L1: 多细胞生物", "L2: 动物界", "L3: 脊索动物", "L4: 上陆革命", "L5: 哺乳纲", "L6: 人科演化", "L7: 智人纪元"]
      },
      {
        "position": "top right",
        "title": "获得的功能 / 失去的功能",
        "description": "Legend with plus and minus icons"
      },
      {
        "position": "bottom center",
        "title": "演化关键里程碑",
        "count": 6,
        "description": "Timeline with a silhouette graphic of 6 figures showing ape-to-human evolution"
      }
    ],
    "centerpiece": {
      "description": "Winding stone staircase with 25 numbered steps featuring specific organisms.",
      "count": 25,
      "notable_elements": [
        "Step 07: Jellyfish",
        "Step 09: Ammonite",
        "Step 10: Trilobite",
        "Step 24: Walking human",
        "Step 25: {argument name=\"future evolution concept\" default=\"glowing cosmic silhouette with a question mark\"}"
      ]

2x2 grid, 16:9 do this for {argument name="number of potters" default="4"} famous master potters   input:   [{argument name="potter data" default="four master potters & their glaze chemistry charts"}]

Create a {argument name="aspect" default="vertical"} cinematic tutorial comparison poster showing the same {argument name="subject" default="urban street scene"} repeated in five horizontal panels, each panel demonstrating a different film genre color grading style. The scene is a busy small city street at sunset, with cars, motorcycles, cyclists, shop buildings, electric poles, tangled overhead wires, and warm evening sky. Keep the camera angle exactly the same in every panel, like a fixed street photography shot.
<p>Each horizontal strip should have a different cinematic mood and color tone:</p>

ultra-realistic IMAX-grade cinematic action shot, extreme high-angle perspective looking down from a massive height, 9:16 vertical aspect ratio, a {argument name="subject" default="man or woman"} matching the exact reference face and hairstyle climbing the side of a modern glass skyscraper, body stretched dynamically across the reflective facade, positioned on the right side of the frame, one leg raised gripping the glass while the other is bent for support, both palms pressed tightly against the glass surface creating tension and realism, wearing {argument name="glasses" default="futuristic clear-framed glasses"} with subtle reflections, outfit: {argument name="outfit" default="premium black fitted t-shirt, black tactical pants, futuristic black gloves"} with protective padding and bright green LED accents glowing softly, black tactical climbing boots with gold detailing and strong grip texture, a sleek black vest or harness securely fitted over the torso adding realism and safety gear detail, expression: determined and slightly tense with focused eyes and head slightly tilted forward, face lock: maintain exact facial structure, proportions, skin tone, hairstyle, and identity from reference with 100% accuracy, preserve micro-details and natural imperfections, no beautification, facial rendering: soft natural skin with visible pores, smooth tonal transitions, subtle subsurface scattering, no smoothing or artificial glow, environment: towering skyscraper with ultra-reflective glass panels showing the subject’s shadow, sky reflections, and a detailed cityscape far below including intricate walkways, a lush green circular park, and distant street traffic with tiny moving cars, strong sense of depth and scale, lighting: bright natural daylight casting sharp directional shadows, high contrast reflections on glass surface, crisp highlights with controlled roll-off, color science: ultra-clean cinematic color grading with high color separation, natural saturation, deep contrast, HDR dynamic range preserving both sky and ground detail, lens: full-frame Sony A7R, 24mm wide-angle lens to exaggerate height and perspective, sharp foreground subject with slight depth falloff into the city below, realism: extreme photorealistic detail, realistic reflections, natural perspective distortion, micro-contrast textures, no HDR overprocessing, no artificial sharpening<br>

[Information Input Field]<p></p>
<p>Character Name: [{argument name="character name" default=" "}] (Required)</p>
<p>Additional Notes: [{argument name="additional notes" default="optional"}] (Enter if there is anything you want to tell the AI)</p>
<hr>
<p>[Image Generation Instructions]</p>
<p>Based on the character in attached image 1, dress them using the devil transformation set in attached image 2.</p>
<p>Read the character's appearance, atmosphere, age, expression, equipment, and personality traits from the input character name and attached image 1. Automatically devise a background, situation, posing, expression, composition, lighting, and a short phrase within the image.</p>
<p>Maintain the original character's hairstyle, hair color, eye color, physique, facial features, age, atmosphere, and character personality.</p>
<p>Reflect the design elements of the devil transformation set so they blend naturally with the original character. It should not just be layering a costume, but an integrated design showing the original character transformed into a devil.</p>
<p>Pay particular attention to the placement of horns and tails, depicting them to look anatomically and visually natural. Horns should sprout naturally from the head and not look like they are roughly placed on top of the hair. The base of the horns should be at the top of the head, near the forehead, or around the temples in a reasonable position, with balanced symmetry, orientation, length, thickness, and a proper sense of connection. The tail should sprout naturally from the lower back as an extension of the tailbone, and not from unnatural positions like the abdomen, chest, legs, or arms. Adjust the horns and tail to look natural according to the pose and costume, ensuring no awkward connections, floating bases, nonsensical numbers, unnatural curves, or strange growth patterns.</p>
<p>Construct a new background and situation as a scene that strongly conveys the character's charm, without relying on standard compositions. Make the character's expression, costume, pose, gaze, and gestures the main focus, rather than just flashy backgrounds.</p>
<p>Treat the expression as a high-priority item. Do not use expressionless, straight, flatly calm, or standard 'cool' faces. Create an impressive expression that looks like multiple emotions are layered, rather than a single simple emotion.</p>
<p>Add variety to the expression using eyebrows, eye direction, pupil highlights, corners of the mouth, cheeks, face angle, and neck tilt. Make it a natural expression that is slightly broken rather than perfectly symmetrical. Create an expression that makes viewers want to imagine the character's inner thoughts.</p>
<p>For posing, prioritize showing the entire costume while creating a dynamic composition that conveys the character's personality and the atmosphere after transformation. Do not use a pose where the character is just standing. Emphasize character traits using weapons, wings, horns, tails, chains, accessories, hand gestures, and gaze direction.</p>
<p>Utilize the eccentricity of the devil transformation set but do not crush the original character's individuality. Ensure the original character does not look like a different person.</p>
<p>In the top-left or bottom-right of the screen, automatically generate a title with decorations, with the first line being the '[Character Name]' and the second line being the title/nickname gained this time, placed at the same font size. The text should be a size that does not interfere with the image.</p>
<p>Only if there is content in the additional notes of the information field, reflect that content in the generated image.</p>
<p>Style:</p>
<ul>
<li>High-quality 2D animation</li>
<li>Language: Japanese</li>
<li>Genre: Dark fantasy leaning, but do not make the background too dark.</li>
<li>Delicate costume design</li>
<li>Character-focused</li>
<li>Impressive expressions</li>
<li>Dramatic lighting</li>
</ul>

Using the provided reference image as the character and car base, transform it into a lively hand-drawn Japanese anime character-reference collage on a white sketchbook-style background. Keep the same person, black outfit, camera, white open-top car with red seats, and round roadside sign recognizable, but reinterpret everything with expressive manga linework, soft gray shading, cute proportions, sparkles, hearts, musical notes, and handwritten Japanese annotation doodles.<p></p>
<p>Layout: Create exactly 11 character/car vignettes around the page:</p>
<ol>
<li>A large upper-left bust portrait wearing round black sunglasses.</li>
<li>A small top-center drawing of the white convertible driving near the road sign.</li>
<li>A large upper-right excited smiling head portrait.</li>
<li>The main central full-body standing pose in front of the car, holding the camera.</li>
<li>A mid-left seated back-view scene looking toward the water/landscape with the camera beside them.</li>
<li>A small left chibi holding the camera up near their face.</li>
<li>A lower-left chibi driving the white convertible.</li>
<li>A lower-center bust portrait looking over the shoulder.</li>
<li>A tiny bottom-center chibi standing still with sunglasses.</li>
<li>A right-middle chibi seated in a folding chair beside the car.</li>
<li>A lower-right walking side-view pose holding the camera, with motion lines.</li>
</ol>
<p>Additions: Fill the empty space with casual handwritten Japanese notes, arrows, checkboxes, tiny hearts, stars, birds, clouds, music notes, and energetic sound-effect marks. Include one checklist card on the right titled in Japanese, styled like a travel packing memo. Add small decorative labels such as {argument name="main handwritten title" default="ちびロドちゃん"}, {argument name="top praise text" default="最高〜っ!!!"}, and short travel-themed notes about driving, coffee, sunglasses, and taking photos.</p>

Goal: Create an anime character design reference sheet for {argument name="character name" default="a cute Japanese high school girl"}, with the character’s face intentionally obscured by a soft square mosaic blur in every view.<p></p>
<p>Canvas: Wide horizontal white canvas, clean character-sheet layout, thin pink dashed horizontal divider across the middle. Use delicate modern anime line art, soft cel shading, natural proportions, and plenty of white space.</p>
<p>Main character details: A petite teenage schoolgirl with short wavy light ash-brown bob hair, small ahoge strands, pale skin, and red eyes only faintly visible where the side view is not fully obscured. Outfit is a navy blazer with gold buttons, white shirt, red ribbon bow, brown pleated skirt, black knee-high socks, and black loafers. She carries a navy rectangular school shoulder bag with strap and small metal details.</p>
<p>Top turnaround section: Show exactly 3 full-body standing views evenly spaced from left to right: 1) front view standing neutrally with the navy school bag over one shoulder, 2) left side profile view with the bag hanging at her side, 3) rear view showing the blazer back, skirt, legs, and bag strap. Keep faces obscured with the same mosaic blur.</p>
<p>Bottom pose section: Add a small pink flower icon followed by the Japanese label 「ポーズ設定」 near the left above the bottom row. Show exactly 5 pose illustrations across the bottom row: 1) riding a cream-and-navy retro scooter while wearing a cream helmet with red stripes and carrying the school bag, 2) standing while holding a sheet of paper and looking flustered with small sweat marks, with a speech bubble saying 「その話、初耳なんですけど！」, 3) seated at a classroom desk eating or drinking while holding something near her mouth, with a bento box, pink lunch pouch, cup or thermos, and small dish on the desk, 4) standing assertively with one finger raised and one hand on hip, with a speech bubble saying 「うちのシステムを使わないからこういう事になるんですよ」, 5) energetic half-body pose holding a red megaphone and raising one fist, with motion lines.</p>
<p>Visual style: Cute polished Japanese anime reference-sheet style, thin black outlines, muted navy/brown/red school uniform palette, watercolor-like soft shadows, crisp details on clothing folds and accessories, no background scenery.</p>

Goal: Create a premium vertical sports poster design for {argument name="athlete name" default="Riyad Mahrez"}, styled like an Adidas football campaign, with a bold editorial collage aesthetic.<p></p>
<p>Canvas: Vertical poster, 2:3 aspect ratio, clean white background with high-contrast black, grey, and red graphics. Use a polished commercial sports-design look with sharp typography, grain texture, and layered depth.</p>
<p>Layout: Center a full-body male footballer walking forward, slightly left of center, wearing an all-black casual athletic outfit: black bomber jacket, black polo shirt, black slim trousers, and white sneakers. His pose is relaxed and confident, one hand in pocket, studio-lit with soft shadows on the floor. Behind him, place a giant black-and-white cropped portrait silhouette of the same athlete’s head filling most of the background. Overlay very large vertical uppercase typography reading {argument name="main vertical word" default="MAHREZ"} along the left side, partially transparent and integrated over the background portrait. Add the small vertical text {argument name="side name text" default="RIYAD"} near the upper-left edge. On the right side, include one large red geometric shape: a tilted red block/circle-like form with a wide white diagonal stripe, partially cropped off the bottom-right corner. Add one small red diamond shape near the top-right corner.</p>
<p>Text content: Include exactly 5 distinct text/logo elements: 1) the huge vertical word “MAHREZ” on the left, 2) the small vertical word “RIYAD” at upper left, 3) a red handwritten signature reading {argument name="signature text" default="Mahrez"} with the number “26” beneath it near the lower left, 4) small uppercase caption text reading “RIYAD MAHREZ / ALGERIA NATIONAL TEAM / WINGER” below the signature, and 5) a black Adidas logo at the bottom-left corner.</p>
<p>Visual style: Modern sports poster design, monochrome photography mixed with bold red accent shapes, gritty halftone/grain texture, strong contrast, clean negative space, luxury brand campaign feel, editorial magazine composition, crisp sans-serif typography, realistic athlete photo treatment.</p>

type: image_generation_prompt<p></p>

SUNSCREEN AD, “{argument name="headline" default="THE INVISIBLE SHIELD"}”<p></p>
<p>Luxury skincare advertising masterpiece, a colossal premium sunscreen bottle standing on a pristine tropical shoreline at golden hour, powerful beams of sunlight crashing down from the sky and splitting apart upon contact with a transparent protective energy dome radiating from the sunscreen, millions of sparkling UV particles dissolving into golden dust before reaching flawless skin, crystal clear ocean reflections, flowing water suspended in mid air around the product, microscopic droplets catching cinematic sunlight, ultra realistic textures revealing every detail of the bottle surface, luxury beauty campaign aesthetics, dramatic volumetric lighting, glowing atmospheric haze, premium {argument name="color palette" default="white and gold"} color palette, futuristic protection technology visualized as elegant light waves, hyper detailed environment, commercial photography perfection, award winning advertising design, photorealistic rendering, 16K ultra resolution, global skincare brand campaign, masterpiece quality.</p>
<p>Text Overlay:<br>{argument name="product" default="SUNSCREEN"}</p>

Goal: Create a luxury Swiss wristwatch advertisement for {argument name="brand name" default="VANTORÉ"}, featuring a single stylish male model in a premium fashion pose.<p></p>
<p>Canvas: Square 1:1 luxury magazine ad, warm beige and charcoal palette, high-end editorial photography mixed with refined graphic design. Split composition: model on the left, product branding and watch details on the right.</p>
<p>Layout: Left half shows one handsome male model standing in front of minimalist Mediterranean-style beige architecture with tall rounded arches and strong late-afternoon shadows. His face is covered by a centered soft-edged square blur in warm brown tones, while his dark wavy hair remains visible. He wears a tailored {argument name="suit color" default="taupe gray"} suit, a dark brown/black open-collar shirt, matching pocket square, and one hand in his trouser pocket. His other hand adjusts his jacket lapel so the luxury wristwatch on his left wrist is clearly visible. Right half is a dark charcoal vertical panel with elegant premium typography and a product watch render near the lower right.</p>
<p>Text content: At the top of the right panel, place a minimalist gold monogram logo shaped like a stylized V, then the brand name "{argument name="brand name" default="VANTORÉ"}" in large spaced gold serif letters, with "SWISS MADE" below in small spaced caps. Center headline reads "{argument name="headline text" default="TIME REDEFINED"}" in large white high-contrast serif capitals, split across two lines. Add a thin gold divider line below. Under it, write "CRAFTED FOR LEADERS" in small spaced gold capitals, then "Swiss Made Collection" in small italic white type. Beneath that, write "PRECISION • PRESTIGE • PERFORMANCE" in tiny spaced gold capitals.</p>
<p>Product details: Include exactly 2 visible watches: one real watch on the model’s wrist and one isolated product watch render on the lower right. Both watches have a black dial, rose-gold case and hands, slim indices, and a black leather strap. Under the isolated watch, write "VANTORÉ HERITAGE" in small gold spaced capitals and "AUTOMATIC" in smaller white spaced capitals.</p>
<p>Bottom feature row: Along the bottom left, include exactly 3 small gold line icons with white labels: 1 shield icon labeled "5 YEAR WARRANTY", 1 water drop icon labeled "5 ATM WATER RESISTANT", and 1 Swiss cross icon labeled "SWISS MOVEMENT".</p>
<p>Visual style: Premium watch campaign, cinematic warm sunlight, crisp suit tailoring, realistic fabric texture, shallow depth of field, elegant arch shadows, minimal clutter, refined gold and white typography on charcoal, luxury editorial mood.</p>

Goal: Create a fictional weekly Japanese manga magazine cover in a bright summer shonen style, like a glossy newsstand issue, featuring an ocean-beach illustration as the main cover art and many energetic cover lines.<p></p>
<p>Canvas: Portrait magazine cover, approximately 2:3 aspect ratio, full bleed, saturated cyan-blue sky and sea, bold yellow-and-blue typography, high-density print layout.</p>
<p>Main cover art: A single anime-style teenage girl stands on a sunny tropical beach, seen from behind and slightly turned, holding a wide straw hat with a blue ribbon as wind blows her medium brown hair to the right. She wears a plain white short-sleeve T-shirt tucked into a high-waisted white summer skirt with pale blue floral patterns. Her face is obscured by a rectangular censor-like blur. The background shows sparkling turquoise ocean waves, white foam on sand, distant green island cliffs, a bright blue sky, puffy summer clouds, and palm leaves entering from the top right.</p>
<p>Magazine masthead and top area: Huge distressed italic masthead {argument name="magazine title" default="Mushin"} across the top in bright yellow with dark navy outline and rough halftone texture. Add a small weekly label at top left, a short Japanese-style tagline across the top, and a small release-day badge at top right. Issue information on the upper right should show {argument name="issue number" default="No. 28"}, {argument name="issue date" default="2025.7.2"}, and a price line of 550 yen.</p>
<p>Large main headline: On the right side, place a tall vertical Japanese summer headline reading {argument name="main cover headline" default="夏が呼んでる。"} in large white characters with blue shadow, plus a smaller pink vertical side phrase suggesting the dazzling smile of summer.</p>
<p>Inset feature boxes: Include exactly 3 inset feature panels. Panel 1 is on the left upper-middle: a dark blue action manga hero with spiky hair and a glowing blue fist, face blurred, framed in white, with bold blue Japanese feature text. Panel 2 is on the left middle: a pastel lavender-haired anime girl portrait with purple eyes, framed in white, with pink and blue Japanese feature text. Panel 3 is on the lower right: a faux gravure/interview promo showing a young woman in a white dress inside a glasshouse or garden setting, face blurred, with ornate serif title styling and floral decorations; include text implying an exclusive interview.</p>
<p>Other cover text: Add a left column with exactly 5 smaller serialized-title blurbs in stacked blue Japanese text, ending with a small pink “and more!!” style line. At the bottom, create a large campaign banner with a pink starburst badge on the left and the headline {argument name="bottom campaign text" default="人気キャラ総選挙2025 開催中!!"} in big blue, pink, and black lettering, followed by a smaller yellow-and-white voting call-to-action strip.</p>
<p>Visual style: High-resolution polished anime magazine art, energetic shonen cover design, bright summer palette, thick outlines, halftone print textures, glossy highlights, dramatic overlapping typography, sticker-like badges, drop shadows, and dense editorial layout. Keep the composition crowded but readable, with the central beach girl dominating the page.</p>

Goal: Create a studio fashion lookbook collage for a women's casual streetwear tracksuit, emphasizing fabric, fit, and multiple poses.<p></p>
<p>Canvas: Wide horizontal 16:9 image, clean editorial layout with thin white dividers between panels. Use a warm beige seamless studio background, soft diffused lighting, realistic photography, natural shadows, high detail.</p>
<p>Layout: Use exactly 5 photo panels. Panel 1 is a tall left panel showing a full-body walking pose. Panel 2 is a small upper-middle portrait crop from waist to head. Panel 3 is a lower-left seated full-body pose. Panel 4 is a lower-middle back/three-quarter view from thighs to head. Panel 5 is a large right-side close-up portrait crop occupying about half the canvas, showing the hoodie shoulder, hood, neckline, hair, and upper torso.</p>
<p>Subject details: A young adult woman model with {argument name="hair style" default="dark brown curly hair in a messy high bun with loose tendrils"}, wearing a matching {argument name="tracksuit color" default="dusty blue"} oversized hoodie and jogger cargo sweatpants. The hoodie has a large padded hood, dropped shoulders, ribbed cuffs, metal-tipped drawstrings, and soft fleece texture. The joggers have elastic cuffs, relaxed fit, and cargo-style side pockets. She wears {argument name="shoes" default="chunky white sneakers"} and subtle small earrings with a delicate necklace visible in the close-up.</p>
<p>Panel pose count and descriptions: Include exactly 5 distinct poses: 1) full-body side walking pose with one foot forward, 2) upper-body front pose with one hand near the hoodie drawstring, 3) seated floor pose with one knee raised and one leg folded, 4) rear three-quarter standing pose showing the back of the hoodie and cargo pocket, 5) large close-up three-quarter portrait showing the hood, shoulder seam, drawstrings, and tousled hair.</p>
<p>Face treatment: In every panel, cover the model's face with a simple soft-edged rectangular skin-toned blur block, preserving the anonymous editorial styling. Do not show facial features.</p>