Diagram / Chart

Create a premium commercial storyboard sheet for a luxury toothpaste advertisement in a clean A4 portrait layout. White background with elegant purple branding, minimal editorial design, premium typography, and creative agency presentation style. Top Header: • Title: FEISIDELIN POLISH • Subtitle: Bright White Teeth, Confident Smile! • Right info panel showing Duration (20s), Style (POV Hand, Photorealistic, Premium Commercial), Audience (18–40), Audio (Upbeat Pop), and Why This Style Works. Main Layout: • 8 storyboard frames arranged in a 4×2 grid. • Each frame has a purple number tab, timecode, realistic product photo, white handwritten notes, curved arrows, sparkle doodles, and a small voice-over caption. • Show: holding the toothpaste, front beauty shot, opening the cap, squeezing purple toothpaste onto a toothbrush, macro texture shot, product in a luxury bathroom, daily routine hero shot, and final recommendation shot. Bottom Section: • Detail Close-ups: Label, Cap, Texture, Ingredients. • Scale Reference with product dimensions. • Footer: Total Duration 20s • Format 9:16 • Style: POV Hand Premium Commercial. Style: Ultra-realistic, luxury product photography, premium bathroom lighting, shallow depth of field, clean grid layout, Apple-style presentation, Behance-quality storyboard, 8K, highly detailed, professional advertising pitch board, purple and white color palette.

Using REFERENCE_0 as the portrait photo, create a vertical Japanese appearance-consulting diagnosis sheet. Keep the original portrait recognizable and place it cropped on the upper-left side, while adding a clean editorial report layout around it. Goal: Turn the single portrait into a polished “face diagnosis report” infographic for men, like a professional styling/appearance consultation output. Canvas and style: Vertical A4-style report, cream/off-white paper background, thin black and gold decorative rules, navy section headers, small simple icons, neat Japanese typography, dense but readable magazine-consulting layout. Main headline: Use 顔面診断レポート at the top right, with a smaller subtitle below: 印象・似合う髪型・服装・カラー提案. Add a tiny note saying it is an estimated diagnosis from one photo. Layout: Create exactly 8 numbered diagnostic sections plus 1 final summary bar. Arrange them in bordered cards, with the portrait occupying the upper-left column and the analysis cards filling the right side and lower area. Sections to include, exactly 8: 1. Overall impression: mature, clean, direct gaze, cool and calm atmosphere, suitable for mode/smart casual styling. 2. Face type estimate: “adult × close to straight-line features,” explaining sharp eyes/contours and a balanced elegant impression. 3. Personal color estimate: ブルベ冬寄り; include two color rows: recommended deep/high-contrast colors and colors that may be difficult. Show exactly 12 color swatches total: 6 recommended colors labeled black, charcoal, navy, royal blue, burgundy, silver gray; and 6 difficult colors labeled yellowish beige, orange, mustard, yellow-brown, pastel yellow, and a similar warm pale color. 4. Body frame estimate: ストレート寄り; describe a simple, high-quality, just-size outfit impression. 5. Best hairstyle: suggest not too long bangs, center/side part, clean silhouette, ash/gray/dark ash tones, and avoid overly heavy or voluminous perms. 6. Clothing that suits: list clean tops such as black shirt and navy shirt, tailored jackets and leather jackets, slim to just-size silhouettes, and V-neck/open-collar tops. 7. Colors that suit / colors that do not suit: create two small comparison boxes. Suited colors: black, charcoal, navy, wine, blue-gray. Less-suited colors: yellowish beige, orange, mustard, bright yellow-brown, overly pale colors. 8. Subtle improvement points: suggest small grooming and styling adjustments such as eyebrow design, hair volume control, reducing under-eye shadows with concealer, not overdoing face-line changes, maintaining a clean silhouette, and natural skin tone refinement. Final summary: Add a full-width dark navy bottom summary bar with gold laurel/crown accents and the label 総評. Summarize that cool, mature charm is strong and black/navy/charcoal styling with sharp hair and high-quality simple clothing maximizes the impression. Constraints: Keep the reference portrait identity and expression unchanged, do not beautify it unrealistically, do not add extra people, do not use English labels in the report, and keep all Japanese text visually plausible and neatly typeset.

Goal: Create a cinematic Japanese supercar advertisement and technical blueprint poster for HAYABUSA 01, a fictional next-generation super sport hypercar. Canvas: Wide 16:9 landscape poster, dark navy/black background with subtle engineering grid lines, high contrast, sharp readable typography, glossy photorealistic render blended with wireframe CAD drawing. Main subject: A low, aggressive red hypercar in front three-quarter view facing right, occupying the lower center and right side. The front half is fully rendered in deep metallic crimson with black carbon fiber hood, sharp LED headlights, black mesh intakes, large splitter, black multi-spoke wheels, red brake calipers, reflections and rain-slick road highlights. The rear/left half transitions into a translucent white-blue wireframe cutaway showing chassis, wheel wells, cabin outline, engine/mechanical parts, and aerodynamic surfaces. Add blue and orange callout leader lines pointing to technical features. Layout: Top left contains the English title “HAYABUSA 01” and subtitle “NEXT GENERATION SUPER SPORT.” Beneath it is a specification box. Across the top left/center are two blueprint views: 1 top-down car view and 1 side profile view with measurement lines. The center-left and lower-left contain technical diagram panels. The right half has a large Japanese headline and performance metrics. Bottom right contains a limited-production price block and a faint manufacturer-style logo. Visible text content: Use crisp, legible text. Include these major Japanese headline lines exactly: “未来を、加速する。” and “頂点を超えるパフォーマンス。” Add smaller Japanese body copy beneath the headline. Include a stylized emblem/kanji mark at top right, “HAYABUSA 01” beneath it, and a red “01.” Include bottom tagline “DESIGNED FOR THOSE WHO DARE.” plus Japanese small copy. Include a large faint brand wordmark near the bottom right reading approximately “UN YAMAKI.” Technical content and counts: Show exactly 6 technical information areas: 1 specifications table, 1 V6 twin turbo engine diagram section, 1 suspension system section, 1 dimensions section, 1 aerodynamics callout, and 1 wheels & tires / carbon fiber body callout area. The specifications table should list 9 rows: overall size 4,750 × 2,020 × 1,180 mm, wheelbase 2,780 mm, vehicle weight 1,250 kg, engine V6 twin turbo, displacement 3,500 cc, max power 670 ps / 7,000 rpm, max torque 82.6 kgf·m / 4,500 rpm, transmission 8-speed DCT, drive system MR. The performance stack on the right should contain exactly 4 metric cards with icons: MAX POWER 670 ps, 0–100 km/h 2.8 sec, TOP SPEED 340 km/h, LATERAL G 1.85 g. The blueprint measurement drawings should show exactly 4 prominent dimension values: 4,750, 2,020, 2,780, and 1,180. The lower dimensions panel should show exactly 2 car views, front and rear, with width numbers around 1,730 and 1,710. Style: Premium automotive launch poster, cyberpunk Tokyo night mood, dark glossy street, red light trails on the far right, faint city lights and mist, precise white and cyan blueprint lines, orange accent callouts, subtle scanline/glow effects, luxury magazine advertising quality, ultra-detailed, realistic reflections, dramatic studio lighting. Constraints: Keep all text clean and readable, do not let Japanese characters deform, no people, no extra vehicles, no watermark, no messy duplicated text, maintain the half-wireframe half-photorealistic car effect.

Goal: Create a dark technical blueprint poster of a mechanical exploded assembly labeled PGU-05 Planetary Gear Unit, with the subtitle “Exploded View & Component Reference,” styled like a precision engineering CAD reference sheet. Canvas: Square 1:1 format on a black/charcoal background with a faint grid, thin border lines, corner crop marks, small registration crosshairs at the top and bottom center, and a small sheet number “01” in the upper-right corner. Use white and light gray monoline drafting lines, with selective red highlights. Main subject: Center a detailed isometric exploded view of a planetary gear unit, vertically arranged from top to bottom. Show exactly 10 labeled component groups with leader lines on the right: 01 Cap screw (x6), 02 Top cover, 03 Ring gear internal, 04 Planet gear (x3), 05 Sun gear, 06 Planet carrier, 07 Thrust washer, 08 Output shaft, 09 Bearing (x2), 10 Housing. Render the exploded parts as transparent wireframe/technical linework with hidden construction lines and dotted alignment axes. Make the sun gear the only emphasized component in red, positioned in the middle of the assembly, with a red leader line and red label. Left information panel: At the upper left, place the title “PGU-05 PLANETARY GEAR UNIT” and subtitle “EXPLODED VIEW & COMPONENT REFERENCE.” Below it, include a specifications block with exactly 5 rows: Gear ratio 27.31:1, Max input RPM 6000, Max output torque 320 N-m, Efficiency 94%, Weight 3.7 kg. Under that, add a function overview paragraph explaining that a planetary gear set uses multiple planet gears rotating around a central sun gear while meshing with an internal ring gear, distributing load and increasing torque capacity in a compact drive train. Inset diagrams: Add exactly 2 inset boxes on the lower-left side. The upper inset is labeled “SECTION A-A” and shows a white line cross-section of the assembled gear unit. The lower inset is labeled “05 SUN GEAR [DETAIL]” and uses red linework to show the isolated sun gear with dimension arrows and annotations such as Ø18.00, Ø32.00, and Ø12.00 (H7). Right reference panel: Use compact monospaced technical text for the component list and notes. Include material and tooth-count callouts such as ring gear Z=72 module 1.25, planet gear Z=24 module 1.25, and sun gear Z=18 module 1.25. Add a notes block with exactly 5 numbered notes: all gears 20° pressure angle, gear material 20CrMnTi, heat treatment carburized, all dimensions in millimeters, tolerances ISO 2768-mK. Add a bottom scale bar labeled 1:1 with ticks from 0 to 100 mm. Visual style: High-detail CAD drafting aesthetic, thin precise strokes, clean monospaced typography, subtle glow on white linework, red accent only for the sun gear detail and corresponding callouts, no photographic shading, no color except white/gray and red. Keep all text legible and aligned like a professional mechanical drawing.

Goal: Create a wide contact-sheet preview showing exactly 12 Korean classroom infographic worksheets generated from English exam passages, arranged as miniature pages for comparison and batch review. Canvas: Wide horizontal 16:9 image on a light gray background, with generous margins. Place 12 portrait-oriented A4-style page thumbnails in a clean grid: 6 pages across the top row and 6 pages across the bottom row. Each page has a white paper border, subtle drop shadow, and a small black number centered underneath from 1 to 12. Layout: Each thumbnail is a dense, colorful educational infographic page in Korean, designed for high school English reading comprehension. Use a consistent worksheet style: top title banner, small source label at the upper left, section blocks with numbered steps, cartoon students/teachers, simple icons, mini charts, diagrams, arrows, callout boxes, and a short summary box near the bottom. The pages should look readable as Korean educational posters when zoomed in but remain thumbnail-sized in the contact sheet. Pages: Include exactly 12 distinct infographic pages, numbered and titled as follows: 1. “사회사의 핵심 구성” about the core components of society; 2. “낯선 숲에서 커지는 불안” about anxiety growing in an unfamiliar forest; 3. “좋은 글은 많은 해석을 낳는다” about good writing producing many interpretations; 4. “진화와 생태계의 조화” about evolution and ecological balance; 5. “공정 중간 정보와 전략 변화” about mid-process information and changing strategies; 6. “빛의 만남: 그림 물자의 에너지 영향” about light interactions and energy effects; 7. “미디어 변화와 맞춤형 광고” about media change and personalized advertising; 8. “나라별 삶의 만족도 차이” about differences in life satisfaction by country; 9. “시련을 넘어 다시 도전한 선수” about an athlete overcoming trials and trying again; 10. “작은 돌이 행성으로 모이는 과정” about small rocks forming planets; 11. “서비스 가격은 왜 자주 바뀌는가” about why service prices change often; 12. “단순 노출 효과” about the mere exposure effect. Visual style: Bright Korean textbook infographic design, soft pastel backgrounds, navy and teal title headers, rounded content cards, friendly cartoon characters, small decorative academic icons, clean vector illustrations, and thin colored dividers. Use a polished classroom handout aesthetic, not photorealistic. Make the pages varied in color and diagram type while keeping them visually consistent as one batch. Text content: Use Korean text throughout the worksheet thumbnails. The main titles should be legible; smaller body text may be dense but should resemble authentic Korean educational material. Use the customizable overall topic set as Korean English exam passage infographic worksheets, and keep the page title style based on Korean. Constraints: Do not show people holding the pages. Do not create a single enlarged worksheet; the image must be a batch contact sheet with exactly 12 portrait thumbnails and exactly 12 numbers beneath them. Avoid watermarks, app UI, browser chrome, or extra captions outside the page numbers.

Create a clean, premium storyboard infographic for a product ASMR unboxing video. Background: White background with a modern minimalist layout. Title: STORYBOARD Product: HAN RIVER WET & DRY 2 IN 1 STEAM IRON Subtitle: ASMR UNBOXING (POV HAND) Create a 12-panel storyboard arranged in a 4×3 grid divided into: PART 1 (0–10s) PART 2 (10–20s) PART 3 (20–30s) Each panel should include: • Number & timestamp • Realistic cinematic image • Handwritten doodle text • Visual • Action • Doodle • Audio Use premium commercial photography with warm studio lighting, shallow depth of field and POV hands only. Finish the infographic with: • What's in the Box • Key Features • Warranty • Ideal For • Metadata section Typography should resemble a premium creative agency storyboard with clean spacing, dark blue accents and thin gray grid lines. (Then include the detailed shot list for all 12 scenes.)

Goal: Create a vertical Chinese social-media infographic poster teaching a cinematic Eastern xianxia portrait prompt for GPT Image-2, with a premium dark movie-poster aesthetic and a large rounded white content card. Canvas: 3:4 vertical poster, dark charcoal-black background with subtle warm bokeh and faint floral haze. Center a large off-white rounded rectangle panel with soft shadow and thin border, leaving a narrow dark margin around it. Header: At the top, outside or slightly above the white card, place a large pink-white Chinese headline: 电影级东方仙侠写真提示词. Under it, add a smaller white subtitle: 适配 GPT Image-2 完整版. Add a tiny centered tagline row beneath: “盛唐宫廷 / 梦幻云海 / 柔焦光影 / 超现实漂浮 / 电影质感”. Layout: Inside the white panel use a two-column layout. The left column is text-heavy, about 48% width. The right column is a vertical gallery, about 52% width, containing exactly 3 cinematic sample images stacked with rounded corners and thin borders. Each sample has a small pink Chinese label above it: 1) “版本一：云海软榻”, 2) “版本二：仙鹤宫殿”, 3) “版本三：花瓣云端”. Left column content: Use pink section headings with small circular icons. First section title: “核心提示词（复制使用）”. Under it, set dense black Chinese body text describing a cinematic realistic portrait of an adult ancient Chinese court woman in Tang-style xianxia fashion, including fair skin, delicate features, ornate updo, gold hairpins, pearl tassels, turquoise-blue gauze outer robe, crimson palace bodice, embroidered silk, jewelry, cloud sea, cranes, petals, gemstones, dreamy lighting, bloom, soft glow, 85mm lens, shallow depth of field, cinematic grading, ultra realistic, 8K, HDR, RAW photo, Kodak Portra 400, Unreal cinematic, volumetric light, masterpiece, best quality. Include some English technical phrases mixed into the Chinese text exactly like a prompt sheet. Negative prompt block: Below the main prompt, add a pink X icon and the heading “负面提示词（避免出现）”. Add a compact paragraph in English: “low quality, blurry, CGI, anime, cartoon, 3D render, doll face, wax skin, modern clothes, text, watermark, bad anatomy, extra fingers, deformed hands, oversaturated, bad proportions, ugly face, jpeg artifacts”. Keyword block: Add a divider line, then the heading “风格关键词”. Show exactly 10 rounded beige pill tags in two rows: 1) 盛唐宫廷, 2) 东方仙侠, 3) 梦幻云海, 4) 漂浮饰品, 5) 仙鹤, 6) 柔焦胶片, 7) 逆光体积光, 8) 华丽珠宝, 9) 青绿×暗红, 10) 超浅景深. Usage advice block: Add the heading “使用建议” and exactly 3 bullet points in Chinese: 1) “直接复制【核心提示词】到 GPT Image-2 使用”, 2) “根据需要选择版本一/二/三的描述进行微调”, 3) “可添加 ‘9:16 竖版’ 或 ‘3:4 竖版’ 来控制画面比例”. Right gallery image details: All 3 images feature the same young adult Chinese xianxia court beauty with ornate black updo, gold phoenix crown, pearl tassels, fair skin, crimson embroidered bodice, teal translucent silk robe, elaborate jewelry. Image 1 shows her reclining among pink clouds inside a dim palace, with floating flowers, warm window light, and surreal dreamy haze. Image 2 shows her seated by a palace window or terrace overlooking a lake with exactly 3 visible cranes, warm sunset mist, dark interior frame, and soft cinematic side light. Image 3 shows her standing or leaning on a balcony above a glowing sea of clouds, petals flying, cranes in the sky, golden backlight, teal and crimson flowing robes, epic romantic atmosphere. Visual style: Elegant Chinese editorial layout, pale blush-pink typography, clean sans-serif Chinese fonts, cinematic soft contrast, warm highlights, subtle grain, premium Xiaohongshu-style prompt card. Keep the poster information-dense but readable. Footer: At the bottom left on the dark margin, add a tiny gray copyright-style line: “© 提示词创作分享｜用 AI 复制电影级东方美学”. Constraints: Use exactly 3 gallery images and exactly 10 keyword tags. Keep all Chinese text crisp and legible. Avoid logos, watermarks, UI chrome, random extra sections, or additional sample images.

Goal: Create a square voxel-art Japanese infographic poster about building many AI websites with minimal tools, using a warm beige Minecraft-like block aesthetic. Canvas: 1:1 square composition, 768x768 style, soft studio lighting, tan paper-and-wood background, subtle voxel blocks in the corners, crisp isometric pixel/voxel edges, shallow shadows, no photorealism. Main headline area: At the top, place a large cream beveled signboard with blocky Japanese text reading 300超 AIサイト構築. Make “300超” bright orange-red and “AIサイト構築” black. Under the headline, attach a small centered beige tab label reading 実績. Use thick extruded voxel lettering. Central layout: Below the headline, create one large cream framed panel with a decorative stepped border. Inside it, divide the content into three vertical zones: left checklist, center workflow illustration, right checklist. Use dotted vertical divider lines between the zones. Left checklist: Title label reads 不要. Show exactly 4 rejected items, each with a large black voxel X icon on the left and a small cream label on the right. The 4 labels, top to bottom, are: 「フィグマ」, 「フレーマー」, 「ウェブフロー」, 「コード」. Center workflow illustration: Show exactly 3 main elements stacked vertically: 1) a black computer monitor with a simple code/editor window using orange and beige lines, 2) a cream document sheet with a few text lines and one orange square, 3) an orange right-pointing arrow along the bottom. Keep everything blocky and voxel-built. Right checklist: Title label reads 使うもの. Show exactly 3 approved items, each with a green voxel checkmark icon on a cream square and a small cream label to the right. The 3 labels, top to bottom, are: 「クロード」, 「動画生成」, 「プロンプトだけ」. Bottom row: Place exactly 3 separate cream beveled cards across the bottom of the main panel. Card 1 has an orange chat bubble icon and text 「相談風 デザイン」. Card 2 has an orange cube icon and text 「AIで 構築」. Card 3 has an orange pencil icon and text 「最小入力」. Characters and decorative objects: Add exactly 2 voxel characters/mascots: on the lower left, a small black-haired person in a black hoodie pointing upward toward the panel; on the lower right, an orange-and-white voxel cat sitting beside the panel. Add a small potted blocky plant on a shelf at upper left and a small shelf with upright books at upper right. Include scattered tiny beige and orange cubes for decoration, but keep the poster clean and readable. Visual style: High-quality 3D voxel diorama, blocky extruded Japanese typography, warm cream, tan, orange, black, and green palette, soft ambient occlusion, orthographic front view, friendly educational tech infographic, neatly aligned labels, crisp readable Japanese text. Constraints: Use exactly 4 X-mark rejected items, exactly 3 checkmark approved items, exactly 3 bottom feature cards, and exactly 2 mascot figures. Do not add extra sections, extra checklists, logos, watermarks, or English text.

Goal: Create a clean 16:9 Japanese business/technical infographic slide about how continuous reasoning context and explicit prompt caching improve long-running task efficiency. Use a polished PowerPoint-native infographic look with dense but readable explanatory text. Canvas: 16:9 landscape slide, warm off-white background, dark navy text, teal and olive green accent colors, thin rounded borders, subtle shadows, generous margins. Leave no photo-realistic elements; use flat vector icons and crisp typography. Top text area: Place a large bold Japanese headline at the top left: 継続推論と明示的キャッシュが長期タスクを効率化. Under it, add a smaller semibold lead sentence: 過去ターンの推論と再利用可能なプロンプトを選択的に保持することで一貫性と効率を高められるが、前提変更や利用回数を踏まえて保存範囲を設計する必要がある。 Main layout: Two large rounded rectangular panels sit side by side beneath the lead sentence. The left panel is teal and titled “reasoning.context”; the right panel is olive green and titled “明示的プロンプトキャッシュ”. Connect the panels with a thin line and a small circular chain-link icon centered between them near the bottom, suggesting coordination between reasoning context and cache. A small upward green arrow near the right panel points back toward it. Left panel details: Include exactly 3 vertically stacked turn markers on the far left, connected by a vertical line with a downward arrow. The markers are labeled “1ターン”, “2ターン”, and “3ターン”. Next to each marker, show a small person icon and speech bubble. To the right, include exactly 3 horizontal rounded cards with teal icon blocks and Japanese explanatory text: 1) gear icon, “auto｜モデルの既定動作を利用”; 2) checklist icon, “all_turns｜安定した目標、前提、優先順位を複数ターンで再利用”; 3) clock icon, “current_turn｜以前の推論が不要になった場面で現在ターンに限定”. Right panel details: Include exactly 3 horizontal rounded cards with olive icon blocks and Japanese explanatory text: 1) document icon, “再利用する共通プレフィックスを開発者が指定”; 2) database cylinder icon, “キャッシュ書き込みは通常入力単価の1.25倍”; 3) percent tag icon, “読み出しは割引されるため、反復利用の回数が効果を左右する”. Bottom conclusion band: Across the bottom, create one wide rounded rectangle callout with a thin yellow border. On the left of the band place a gold target icon with an arrow. To the right, place a bold Japanese conclusion: 長期タスクの一貫性と効率を高める一方、前提変更時には過去の推論や不要なキャッシュを切り離す設計が必要. Visual style: Japanese corporate slide design, crisp vector line icons, rounded rectangles, light cream background, teal left section, olive right section, yellow conclusion accent, strong hierarchy, highly legible Japanese sans-serif typography, no decorative clutter. Constraints: Preserve the exact count of elements: 2 main panels, 3 left turn markers, 3 left option cards, 3 right cache cards, 1 central chain-link connector, 1 bottom conclusion callout, and 1 target icon. Do not add extra panels, extra cards, watermarks, logos, or decorative characters. Keep all slide text inside the infographic sharp and readable.

Premium technical infographic of [product name ]. Use the reference image only to understand the shape and structure of the object, without copying the same photo, angle, composition, or background. Reinterpret the subject in a new professional and realistic photograph, clean and well-lit, with a suitable and more aesthetic background. Keep the object as a real photo, not an illustration. Add a technical blueprint-style overlay with white lines, arrows, dimensions, labels, and small diagrams of parts, materials, measurements, and functionality. Clear, elegant, and informative composition. Include a sketch box in the upper left corner with the title "[name] ".

Goal: Create a dark technical debug visualization of a pachinko machine playfield layout, showing ball lanes, collision rails, pegs, named gameplay regions, and simulated ball trajectories. Canvas: Square-ish 4:5 technical diagram on a nearly black burgundy background, with a transparent-engineering-overlay feel. Use a dark maroon grid of blocky rectangular obstacle silhouettes behind the layout. Main layout: Draw a large pachinko board occupying almost the full canvas. The board is formed by thick angular golden-brown rails: one large outer oval/octagonal loop around the perimeter, one large inner polygonal ring around an empty central dark void, and several short rail segments near the bottom and lower-right. Keep the rails chunky, beveled, and slightly translucent, like debug collision geometry. Trajectory paths: Add exactly 5 thin neon ball-path traces over the rails and lanes: 1 cyan path hugging the far-left launch lane, 1 hot pink path weaving near the left edge and bottom exit, 1 lime green path that curves from the upper-left across the mid-left and down to the bottom, 1 red path that crosses sharply through the left-middle and upper-left, and 1 yellow path following the outer left arc. The paths should overlap and look like simulated pachinko ball travel, with sharp turns and curved segments. Debug regions: Draw dashed cyan rectangular region boxes with small cyan labels. Include exactly 7 labeled regions: "region:JACKPOT_1" at left-middle, "region:STATIC" near the lower-left/middle, "region:START" centered lower-middle, "region:LUCKY" right-lower-middle, "region:LAUNCHER" bottom-right, "region:OUT" lower-left exit area, and one tall dashed launch/channel region along the left side. Pegs and labels: Add exactly 15 small green square peg markers with green debug labels. Place them around the central playfield: 2 near the upper-left labeled "peg-left-top-1" and "peg-left-top-2"; 3 near the top center labeled "peg-center-top-1", "peg-center-top-2", and "peg-1"; 3 on the upper-right labeled "peg-right-top-1", "peg-right-top-2", and "peg-right-path-2"; 3 on the lower-right/lower-middle labeled "peg-right-path-1", "peg-lucky-guide", and "peg-right-pocket-1"; 4 in the lower-left/lower-middle labeled "peg-left-path-1", "peg-left-pocket-1", "peg-start-left", and "peg-start-right". Make labels small, thin, and green, as if from a game-engine editor overlay. Additional details: Include one tiny cyan number box reading "19" near the left-middle jackpot area. Add a few small red guide triangles and line fragments near the top-left lane. The diagram should look like a GPT-generated game-layout review screenshot rather than polished UI art. Visual style: Low-light debug render, dark maroon and black palette, golden collision rails, cyan dashed UI overlays, green peg annotations, neon trajectory lines. No photorealism, no characters, no real pachinko machine cabinet, no decorative anime art. Customizable concept: Build the layout as a pachinko physics debug map titled by implication around ball trajectory and lane review. Use rail color muted golden brown, background color near-black burgundy, and trajectory colors cyan, hot pink, lime green, red, yellow.

Goal: Create a polished vertical Japanese trading-card-game strategy infographic explaining the pros and cons of adding a specific card to a deck. Canvas: Portrait 2:3 layout, dark navy-black fantasy UI background with thin gold ornamental borders, beveled panels, subtle glow, and a premium card-game analysis aesthetic. Use gold title typography and white Japanese body text. Main title area: At top right, place a large ornate gold headline reading 道化の一座 ハット. Beneath it, add the subtitle デッキに加えた際のメリット・デメリット. Under the subtitle, place a dark framed explanation box containing 3 short Japanese lines describing that the card can search/deploy Pendulum monsters, also enables non-theme monsters, supports interruption-resistant subroutes, and improves combo stability. Card display: At top left, show exactly 1 realistic Yu-Gi-Oh-style monster card mockup, named 道化の一座 ハット. The card should have an orange monster-card frame, star icons, a small LIGHT attribute icon, dense Japanese effect text, ATK/DEF line, and fantasy artwork of a jester-like rogue in blue clothing holding a staff amid swirling golden magic. Do not use official logos or exact copyrighted card layout details; make it a close fictional TCG-style homage. Middle comparison section: Add a centered gold label tab reading “Trigger resilience comparison”. Create exactly 2 horizontal comparison rows under it, each split into a left original-deck behavior column, a middle after-adoption result column, and a right small change-image column. Row 1 is draw-type trigger: blue icon, left box has a large blue circle meaning good resilience; arrow points right to a red X meaning resilience becomes worse; right mini diagram shows a blue person icon leading to a card/box and a prohibition symbol, implying the combo stops at the draw stage. Row 2 is interruption-type trigger: red/orange icon, left box has a large red X meaning poor resilience; arrow points right to a blue circle meaning resilience improves; right mini diagram shows a red person icon leading to a card/box and a blue shield check, implying interruption is avoided and deployment continues. Lower benefits and drawbacks: Create exactly 6 rectangular cards in two columns, 3 benefits on the left and 3 drawbacks on the right. Left column header: “メリット” in a blue panel. Right column header: “デメリット” in a red panel. Benefit card 1 uses a shield icon and says it becomes stronger against interruption-type triggers. Benefit card 2 uses a branching route icon and says the number of deployment subroutes increases. Benefit card 3 uses a checkmark icon and says combo stability improves. Drawback card 1 uses stacked card icons and says it becomes weaker against draw-type triggers. Drawback card 2 uses a weight/bag icon and says deck burden becomes larger. Drawback card 3 uses a warning triangle icon and says unnecessary cards may need to be adopted. Each of the 6 cards must include a bold colored heading plus two smaller Japanese explanatory lines. Bottom summary: Add a wide dark framed box with a small gold tab header reading “まとめ”. Inside, write a concise Japanese summary explaining the trade-off: resistance to interruption and flexible deployment improve, but weakness to draw-type triggers and deck-building constraints increase. End with a larger gold call-to-action line reading 環境や構築方針に応じて、採用を検討しよう！. Style constraints: Use crisp vector-like UI panels mixed with realistic card art, high contrast, clean alignment, thin gold borders, blue for positive elements, red for negative elements, arrows between comparison boxes, no watermark, no extra sections, and keep all text legible as an infographic.

Create a clean, premium storyboard infographic for a product ASMR unboxing video. Design specifications: White background with a modern, minimalist layout. Title at the top: STORYBOARD. Product name in bold green (replace with: [PRODUCT NAME]). Subtitle: ASMR UNBOXING. Include four information boxes below the title: Duration: 30 Seconds, Style: POV Hands, ASMR, Audience: 18–35 years old, Audio Suggestion: Soft ASMR • Crinkles • Tapping • Pouring. Create 12 storyboard panels arranged in a 3-column × 4-row grid. Each panel should contain: A numbered green badge (1–12), Timestamp (0–2.5s, 2.5–5s, etc.), A realistic cinematic image showing the scene, Handwritten white doodle text like: TA-DA!, POP!, WOW!, PICK!, CRINKLE~, TEAR!, POUR~, HOT WATER, STIR~, SMOOTH!, BEST!. Three text sections below every image: VISUAL:, ACTION:, DIALOGUE:. Use realistic product photography, warm wooden table, soft natural lighting, shallow depth of field, POV hands only (no face visible), premium commercial advertising style. Storyboard sequence: 1 (0–2.5s) Visual: Product box on wooden table. Action: Hands enter frame and point to the box. Dialogue: "Have you tried this before?"; 2 (2.5–5s) Visual: Opening the box. Action: Lift the top flap slowly. Dialogue: "Let's unbox it together."; 3 (5–7.5s) Visual: Multiple individual sachets neatly arranged. Action: Fully reveal the inside. Dialogue: "Wow, look how many!"; 4 (7.5–10s) Visual: Pick up one sachet. Action: Remove a single stick pack. Dialogue: "Let's start with one."; 5 (10–12.5s) Visual: Close-up of sachet. Action: Hold and gently crinkle it. Dialogue: "That crinkle sound is satisfying."; 6 (12.5–15s) Visual: Tear open the top. Action: Slow ASMR tearing. Dialogue: "Just a small tear."; 7 (15–17.5s) Visual: Powder visible inside. Action: Show the powder close-up. Dialogue: "Looks delicious."; 8 (17.5–20s) Visual: Pour powder into mug. Action: Slow pouring. Dialogue: "Pour everything in."; 9 (20–22.5s) Visual: Hot water being poured. Action: Steam visible. Dialogue: "Add hot water."; 10 (22.5–25s) Visual: Stir drink. Action: Slow circular stirring. Dialogue: "Mix it well."; 11 (25–27.5s) Visual: Finished drink. Action: Show creamy texture from above. Dialogue: "Looks smooth and creamy."; 12 (27.5–30s) Visual: Product box beside finished drink with thumbs up. Action: Hand gives thumbs up. Dialogue: "Easy, delicious, and ready!". Footer: Total Duration: 30 Seconds, Format: Vertical (9:16), Style: POV Hands, ASMR Unboxing. Typography should resemble a professional creative agency storyboard, with clean spacing, green accents, rounded panel borders, and high-end presentation suitable for client pitches.

Goal: Create a vertical Japanese educational infographic summarizing 切り花に炭酸飲料を入れる方法とメリット・デメリットまとめ, explaining how to add carbonated soft drinks to cut flower vase water, with benefits, drawbacks, recommended dilution, procedure, and better basic care methods. Canvas: Portrait 4:5 infographic, clean magazine-style layout on a warm off-white background, soft pastel borders, rounded information cards, subtle shadows, friendly household gardening aesthetic. Use a balanced mix of flat vector icons and small realistic photo panels. Main colors: coral pink, chocolate brown, mint green, pale yellow, sky blue, and light gray. Top header: Large bold Japanese headline in two colors, with the phrase about carbonated drinks emphasized in coral pink and the rest in dark brown. Under it, add a smaller green subtitle: 海外で話題の「花を長持ちさせる裏技」を正しく知って、きれいなお花を長く楽しみましょう。. On the upper right, place a realistic photo-style bouquet in a clear glass vase on a wooden table, with pink gerbera daisies, cream roses, small white filler flowers, and greenery. Beside it show exactly 2 drink bottles/cans: one red cola can labeled “COLA” and one blue cider bottle labeled “CIDER”. Below them show exactly 2 small vertical photo panels of vase water: one clear water close-up and one brown/tinted water close-up. Main upper content area: Use exactly 2 side-by-side rounded cards. Card 1, left, pale yellow title bar: title text なぜ炭酸飲料で花が長持ちする言われるの？. Include exactly 2 numbered benefit rows with pink circular number badges: 1) “糖分が栄養になる” with a simple icon of stacked sugar cubes, and explanatory small text saying sugar in soda may be used as flower energy; 2) “酸性成分が働く” with a blue water drop icon, and small text saying acidity may help water uptake. Card 2, right, pale pink title bar with a yellow warning triangle icon: title “知っておきたいデメリット・注意点”. Include exactly 4 warning rows, each with a red X icon: 1) sugar can encourage miscellaneous bacteria and make stems rot; 2) water becomes cloudy easily and looks bad; 3) dark-colored drinks such as cola can color the water and reduce visual beauty; 4) too much can have the opposite effect because excessive concentration may worsen water uptake and cause wilting. Keep text concise and Japanese. Middle blue instruction band: Create one wide rounded rectangle with a blue outline and pale blue fill. Divide into two columns. Left column title: “炭酸飲料の入れ方（おすすめの割合）”. Include a blue circular label “おすすめの割合” and a large formula: “炭酸飲料：水 = 1：10 ～ 1：20程度”, with small example text “例：水1リットルに炭酸飲料50〜100ml”. Add a “ポイント” subsection with exactly 2 checkmark bullet points: use clear cider/soda without artificial color when possible; dark drinks such as cola can color the water even in small amounts. Right column title: “手順”. Include exactly 4 numbered steps in blue circles: 1) put clean water in the vase; 2) add carbonated drink at the above ratio; 3) mix lightly; 4) arrange cut flowers. Add a pale yellow note box: “水はこまめに交換しましょう（できれば毎日）”. On the far right add a large simple equation illustration: water drop icon labeled “水” plus a glass with bubbly yellow liquid labeled “炭酸飲料”. Lower green care section: A wide rounded rectangle with a green header title: 切り花を長持ちさせる基本のお手入れ（炭酸飲料より効果的！）. Inside, show exactly 4 equal care cards in a row, each with a green numbered circle, a short Japanese title, a realistic photo thumbnail, explanatory text, and a green “ポイント” label. The 4 cards must be: 1) “茎を斜めに切り戻す”, photo of a hand cutting a green stem diagonally with a knife, explain better water absorption and freshness, point: cut underwater to prevent air entry; 2) “こまめに水替え”, photo of water being poured into a glass vase, explain changing water daily or every 1–2 days, point: recut stems when changing water; 3) “葉が水に浸からないようにする”, photo of stems and leaves inside a vase, explain submerged leaves rot and cause bacteria, point: remove leaves below the waterline and improve ventilation; 4) “市販の延命剤を使う”, photo of a blue flower food packet near a vase, explain it contains nutrients and antibacterial ingredients, point: follow product instructions. Bottom summary strip: Use two rounded boxes. Left larger pale pink box with label “まとめ”, a small flower icon, and text explaining that carbonated drinks may support flower longevity when used at the proper concentration, but thorough basic care is the most important secret. Right smaller pale pink advice box with label “一言アドバイス”, small vase-and-flower icon, and text advising to avoid direct sunlight and air-conditioner wind, and keep flowers in a cool place. Style constraints: Japanese typography must be legible, friendly, and bold for headings; use clean grid alignment and generous spacing. Do not add extra sections or extra repeated items beyond the specified counts. Avoid watermark, QR code, people, or brand logos other than the simple “COLA” and “CIDER” labels.

Create a polished square promotional cover image for Highlighted, showing a modern iPhone standing upright at a slight angle on a bright white desk, with a clean productivity-and-reading aesthetic. On the phone screen, display a minimalist gallery grid of exactly 12 saved highlight cards arranged in 3 columns by 4 rows, each with a small gray label line beneath it; the cards show varied bookish visuals such as a classical portrait, yellow notebook, framed photo, white note with cord, red-and-yellow abstract cover, pencil illustration, dark statue face, blue night cover, beige dotted page, pale sails, ocean water, and a balloon landscape. At the bottom of the phone UI, include a large rounded blue add button with a white plus sign. Surround the phone with translucent floating feature widgets: on the left, one pill-shaped toolbar with exactly 5 elements—a paper-plane/filter icon and 4 circular color swatches in white, light gray, black, and navy; on the upper right, one glassmorphism audio card with a play button and 5 horizontal transcript lines including 2 yellow highlight lines; in the middle right, one frosted audio waveform card with a glowing circular orb and blue waveform; on the lower right, one frosted action toolbar with exactly 5 icons—a document, chevron arrow, share, cloud upload, and envelope. Desk props include a white tray of folders with a green spreadsheet document icon on the left, a small stack of pastel sticky notes in the foreground, an open book with yellow highlighted text at bottom right, loose papers with highlighted passages, and a stack of hardcover books on the right. Use soft natural window light, shallow depth of field, realistic high-end product photography, creamy whites and warm neutrals, subtle shadows, glassy translucent UI overlays, crisp phone details, no visible brand logos except the app-like interface, no watermark, no extra text beyond simple UI marks. Use a premium launch-promo composition suitable for an in-app event cover, 1:1 square.

Goal: Create a dense Japanese infographic ranking AI image generation tools as a 2026 tier list, with a premium black, navy, and gold tech aesthetic, designed for social media sharing. Canvas: Square 1:1 poster, high resolution, dark black background with subtle blue grid lines and glowing cyan/gold accents. Use bold Japanese typography, sharp table borders, star ratings, crowns, badges, and app-logo style icons. Overall look should feel like a professional comparison chart made after extensive testing. Header: Large title at top: 「AI画像生成ツール Tier表」 with “AI” and Japanese text in white, “Tier表” in gold. Add a gold badge on the upper left reading 「2026年 最新版」. Above the title, add the small line 「保存必須！迷ったらこれを見ればOK」. Under the title, add a blue outlined subtitle bar: 「用途別に最強が一目でわかる 完全ガイド」. Add a small gold crown near the title. Top-right selection box: Add a bordered panel titled 「選び方のポイント」 with exactly 4 checkbox bullet items: 「何を作りたいかで選ぶ」, 「得意・不得意を理解する」, 「目的に合わせて使い分ける」, 「迷ったら上位から試す」. Main layout: A large comparison table fills most of the image. Left side has tier bands, middle has ranked tool rows, right side has star-rating columns and price notes. Use exact tier groups: SSS 「圧倒的最強」, SS 「非常に優秀」, S 「優秀」, A 「特化型で強力」, B 「用途次第で活躍」. Use large tier letters in gold, cyan, green, purple, and pale blue respectively. Main table rows: Include exactly 8 ranked tools, each with a circular rank medal, a square logo icon, a tool name, a short Japanese description, and several small colored feature tags. The rows are: 1. GPT Image 2 — description 「総合力No.1の最強モデル」, logo resembling the OpenAI knot mark, rank medal gold with “NEW” label. 2. Seedream 5.0 Pro — description 「広告・商用クリエイティブ最強」, blue spiral logo. 3. Nano Banana — description 「リアル写真・人物・商品に最強」, yellow banana logo. 4. Muse — description 「映画のような世界観・コンセプトアート」, purple M logo. 5. Ideogram — description 「文字デザイン・タイポグラフィ最強」, black abstract brain/typography logo. 6. Flux — description 「イラスト・アート・CG表現が得意」, blue triangular Flux logo. 7. Recraft — description 「ロゴ・アイコン・ベクターに最強」, black-and-white R-like logo. 8. Imagen 2 — description 「自然風景・写真の再現に強い」, multicolor Google G logo. Rating columns: Use exactly 8 comparison columns with Japanese labels: 「総合力」, 「リアル/人物」, 「イラスト/アート」, 「文字/デザイン」, 「編集/加工」, 「商用利用」, 「使いやすさ」, 「料金目安(月額)」. Fill each row with gold star ratings, including half/empty stars where appropriate, and compact monthly pricing notes in the final column. Keep the table legible but information-dense. Bottom section: Add a horizontal “best by use case” guide titled 「用途別 最強早見表」. Include exactly 7 crowned cards, each with a number, category, logo, tool name, and short verdict: 1. 「リアル人物」 — Nano Banana — 「圧倒的リアル」. 2. 「広告・商用」 — Seedream 5.0 Pro — 「商用品質No.1」. 3. 「総合力」 — GPT Image 2 — 「なんでも高水準」. 4. 「シネマ・世界観」 — Muse — 「映画レベル」. 5. 「文字・デザイン」 — Ideogram — 「文字が綺麗」. 6. 「イラスト・アート」 — Flux — 「アート表現が得意」. 7. 「ロゴ・アイコン」 — Recraft — 「ベクター最強」. Bottom-right recommendation box: Add a glowing panel titled 「迷ったらこれ！」 with a lightbulb icon and the message 「まずは上位から 3つ使えば ほぼ全てカバーできる！」. Footer: Add two dark bordered note boxes. Left box with target icon and two bullet notes: 「1つのツールにこだわらず、目的に合わせて使い分けるのが最強の戦略！」 and 「プロほど複数のツールを組み合わせて、クオリティを最大化しています。」 Right box with bookmark icon and text: 「保存して、いつでも見返せるようにしよう！」 and 「アップデートされたらまた最新版に更新します！」 Include a tiny disclaimer line about pricing and ratings being estimates as of 2026. Visual style: Sleek cyber dashboard, black glass panels, thin neon blue dividers, gold highlights, dense but organized layout, crisp Japanese text, app icons in white rounded squares, star ratings in metallic gold, no photographic background, no people. Constraints: Preserve the exact count of 8 ranked tools, 5 tier bands, 8 rating columns, 4 selection tips, and 7 bottom use-case cards. Make all text sharp and readable. Do not add extra tools, extra cards, watermarks, or random English labels.

Create a 1:1 square anime-style character sheet. The theme is a Japanese fantasy barrier master (Kekkai-shi) runner girl. Finish as a shared reference sheet for Seedance 2.0, with no background, an organized layout, and a numbered section configuration. If there is a reference image, it can be a live-action photo, anime, or illustration. Refer only to the facial features, facial impression, age, and hairstyle impression. Do not refer to clothing, background, pose, lighting, or art style. Naturally convert the reference face into a high-quality anime character. The background is a plain bright off-white or light gray. Do not include landscapes such as torii gates, shrines, forests, festivals, cityscapes, or magic circle backgrounds. Long descriptions, decorative text, logos, and watermarks are not needed. Include the following numbered sections with small, clear black labels. 01 FRONT 02 SIDE 03 BACK 04 FACE 05 DETAILS 06 COLORS 07 SILHOUETTE [Layout] 01 FRONT: A large front full-body view on the left. A standing posture visible down to the tips of the feet. The costume structure should be easy to read and give the impression of being able to run. 02 SIDE: A side full-body view in the center. Show sleeves, obi, back ribbon, legs, and feet. 03 BACK: A back full-body view in the center. Show the back of the haori, back ribbon, amulet holder, and back hair. 04 FACE: A large face close-up in the top right. A calm, concentrated expression. Eyes with kindness and inner strength. 05 DETAILS: Small panels on the right side showing hair ornaments, sleeve patterns, obi and back ribbons, amulets, barrier crests, accessories, and feet in an organized manner. 06 COLORS: A small color sample at the bottom. White, crimson, dark navy or black, dull gold, and pale bluish-white barrier light. 07 SILHOUETTE: A group of small running silhouettes or a full-body running silhouette at the bottom. Make it agile and elegant, like a barrier master runner. [Character Design] A Japanese fantasy girl barrier master. Short haori, form-fitting black or dark navy inner wear, short hakama-style or layered lower garment, waist belt, red back ribbon, modest gold decorations, waist amulet holder, paper amulets, runnable tabi boot style or Japanese fantasy shoes. Sleeves are wide but not too long, so they don't interfere when running. The character should not be too static, but rather have a light sense of dynamism and an atmosphere of being able to run. [Hair] Reflect the impression of the hairstyle from the reference image as much as possible and adjust it for a Japanese fantasy style. Add small red or gold hair ornaments if necessary. Do not make it too complex. [Magic Motif] A character who uses Japanese barrier magic. Put small barrier crest motifs on sleeves, amulets, and accessories. Do not include large magic circles or flashy background effects. [Art Style] High-quality 2D anime style. Clean line art, clear and elegant coloring, and an organized character sheet composition. Maintain a documentary feel while leaving character charm and glamor. [Negative] No background scenery, no torii background, no shrine background, no festival background, no magic circle background, no action scenes, no multiple characters, no live-action style, no 3D, no chibi style, no layout collapse, no long text, no large decorative characters, no logos, no watermarks, no broken limbs, no facial collapse, no costume inconsistency. Do not copy the clothing, background, or pose of the reference image.

Goal: Create a clean Japanese business infographic slide explaining the shift to assigning roles to AI, centered on the concept of an “AI employee.” Use AIに役割を持たせる時代へ。 as the large top headline. Canvas: Vertical portrait infographic, approximately 3:4 aspect ratio, white background, thin light-gray border, navy blue accent color, black body text, rounded rectangular content blocks, minimalist line icons. The design should look like a polished LinkedIn/X business slide or proposal handout. Layout: Use 6 stacked sections from top to bottom. Section 1 — Header and cycle diagram: At the top, place the large bold headline. On the left, include three short Japanese explanatory lines about spending one week developing a personal AI editor-in-chief, repeatedly writing roles, assigning work, checking output, and rewriting roles. On the right, show a circular 4-step workflow with navy arrows and simple icons. Count exactly 4 workflow steps: 1) pencil icon labeled 「役割を書き直す」, 2) document icon labeled 「役割を書く」, 3) person-at-desk icon labeled 「仕事を任せる」, 4) magnifying glass icon labeled 「アウトプットを確認」. Section 2 — Three company announcement cards: A rounded box with the heading そうしたら今週、3社が「仕事をするAI」を発表しました。. Inside it, create exactly 3 horizontal company cards. Card 1: OpenAI logo-like knot icon, title 「OpenAI」, product 「ChatGPT Work」, short Japanese description about announcing a new AI work structure that autonomously handles complex tasks. Card 2: Anthropic stylized AI logo, title 「Anthropic」, product 「Claude Cowork」, short Japanese description about expanding Claude Cowork, where AI works as a member of the team. Card 3: xAI logo, title 「xAI」, product Grok 4.5, short Japanese description about launching a new flagship strong in coding and agent tasks. Below the cards, place a dark navy banner with white text: 「3社とも、「答えるAI」ではなく「仕事をするAI」を出してきました。」. Section 3 — Key message block: Split into two columns. Left column has large bold text: 「AIを使う時代から、AIに役割を持たせる時代へ。」 Right column has a paragraph explaining that the whole industry is moving in this direction, and that ChatGPT Work, AI employees, and AI Company are no longer unusual concepts. End with a bold navy question: 皆さんはもう、AI社員導入していますか？. Section 4 — Definition of AI employee: Start with a navy pill heading: 「AI社員って何？」. Explain in Japanese that, simply put, it is an AI with a role. Include exactly 3 small role cards under 「例えば自分なら、」: 1) person icon labeled 「編集長（SNS・ブランド）」, 2) laptop/code icon labeled 「開発（コード）」, 3) document/search icon labeled 「秘書（調査・整理）」. Add a note that each is given a separate role. On the right, write that by giving AI roles like people have job roles, output becomes more stable. Section 5 — How to make it: Add a navy pill heading 「どうやって作るの？」 and explain that the method is surprisingly simple: create a Claude Code company prompt and operate it. Show exactly 4 numbered steps in a horizontal process. Step 1: 「Claude Codeで company/フォルダを作る」 with a dark terminal-style file tree showing exactly 7 files: company/, mission.md, vision.md, values.md, role_editor.md, role_developer.md, role_secretary.md, rules.md. Step 2: 「各役割のルールや基準を Markdownで書く」 with bullets: 「ミッション」, 「ビジョン」, 「判断基準」, 「話し方」, 「役割の詳細など」. Step 3: 「Claude Codeにプロンプトを渡す」 with a black speech bubble containing Japanese text asking it to read the company folder and act as the SNS editor-in-chief. Step 4: 「仕事を任せて、改善を繰り返す」 with a mini circular loop showing person-at-desk, magnifying glass, and pencil icons labeled work, check, fix. Section 6 — Bottom takeaway: A rounded footer strip with a navy lightbulb icon on the left and bold Japanese takeaway text: 大事なのはプロンプトの上手さではなく、「役割の設計」です。. On the right, add a small people/team icon and a sentence explaining that if you assume AI is something to train like a human, it becomes an employee you can rely on. Visual style: Japanese corporate infographic, crisp typography, generous spacing, subtle gray dividers, navy highlights, flat monochrome line icons, no photos, no gradients, no clutter. Keep all Japanese text legible and aligned. Do not add extra companies, extra steps, extra cards, or decorative elements beyond the specified counts.