YouTube Thumbnail

Goal: Create a bold Japanese YouTube/X thumbnail about subscription pricing being too expensive, using a dramatic comparison between a crossed-out high monthly fee and a cheaper monthly fee. Canvas: Vertical 3:4 thumbnail, 768×1024 style, optimized for mobile readability. Use a dark navy-to-deep-purple gradient background with a subtle spotlight glow behind the person. Keep all main text inside safe margins and make it extremely large, high-contrast, and legible. Layout: At the very top, place exactly 2 hanging price tags suspended by thin strings: left tag is red, tilted slightly, with the text 月15,000円 in bold white and a thick white diagonal strike-through line; right tag is neon green, tilted slightly, glowing, with the text 月3,000円 in bold white. Below the tags, center a huge white headline with black shadow: その課金、まだ早い. Under the headline, add one bright yellow rectangular banner spanning nearly the full width, with bold black text: 月3,000円で足りる21の使い方. Subject details: In the lower half, show a realistic studio-cutout portrait of a smiling young Japanese woman with long black hair and bangs, wearing a beige knit sweater. She faces the camera, raises her left hand open toward the viewer in a clear “stop/wait” gesture, and holds a gold credit card in her right hand. Use natural skin tones, clean beauty lighting, and a crisp cutout edge. Decorative elements: Add exactly 3 small floating gold yen coins with embossed yen symbols: one on the left upper-middle area, one near the lower-left edge, and one on the right-middle area. Add exactly 2 white speech/chat bubbles with three dark dots: one on the left side near the raised hand and one on the right side near the headline/shoulder area. Do not add extra coins, bubbles, icons, logos, or watermarks. Visual style: High-impact Japanese social media thumbnail, glossy 3D accents, strong drop shadows, neon glow on the green tag, clean compositing, sharp typography, saturated colors, professional viral-cover design. Make the text accurate and not garbled.

Goal: Create a high-impact Japanese YouTube thumbnail about automatically generating video captions/telops with AI, featuring a dramatic comparison from Vrew to Claude Code. Canvas: 16:9 horizontal thumbnail, 1200×675 style, optimized for YouTube. Use a dark blurred video-editing timeline interface as the full background, with purple and blue timeline tracks and small clip blocks visible but out of focus. Layout: Put a huge bold Japanese headline across the top reading AIでテロップを自動作成. The letters should be white with thick black outline and an additional thin white outer stroke, slightly tilted and tightly spaced for maximum impact. Place one large white speech-bubble complaint box on the left-middle with a black outline and a small pointer at the bottom right. Inside it, use bold black Japanese text for the complaint and a red emphasized final line with a yellow underline: 誤字脱字多すぎるし、テロップはズレまくってるし、変なところで改行するし、そのくせにそれ以外のことは何もできないって...\nVrewマジで使えんw. Place two app-style logo tiles in the center-right: exactly 2 logos total. Logo 1 is a cyan-blue rounded square Vrew-like icon with a white V mark, located near the center, partially overlapped by a small orange pixelated mascot/bug shape. Logo 2 is a larger orange-red rounded square Claude-like icon with a white radial starburst, located to the upper right, with a shiny gold crown tilted on its top-right corner. Add a small white label under the orange icon reading Claude Code in bold black text. Between the two logos, add exactly 1 curved red arrow with a white outline pointing from the blue logo toward the orange logo. Bottom text: Fill the bottom third with one enormous Japanese conclusion phrase reading これで全て解決. Make it thick rounded display lettering with a bright yellow gradient fill, heavy black outline, and glowing white outer stroke. The text should overlap the background and partly sit in front of the center graphics, creating a loud thumbnail composition. Visual style: Japanese viral tech thumbnail, extremely bold contrast, dense composition, exaggerated outlines, drop shadows, white glow effects, saturated colors, black background atmosphere, urgent and humorous tone. Make all Japanese text crisp, legible, and correctly spelled. Discrete elements to include: exactly 1 top headline, exactly 1 speech bubble, exactly 2 app logos, exactly 1 orange mascot/bug shape, exactly 1 red curved arrow, exactly 1 gold crown, exactly 1 Claude Code label, and exactly 1 huge bottom headline. Do not add extra logos, people, watermarks, or unrelated text.

Input an article, go through three rounds of Q&A, and it directly outputs cover prompts that can be used for image generation. No need to understand design, no need to write prompts yourself, the aspect ratio is fixed at 3:4, and facial consistency can be maintained.👇 👹 The entire workflow is as follows: 1. Skill installation and first-time configuration (save a photo of your own face + confirm the image generation model) 2. Give the article content to the agent, which automatically reads and refines it 3. Round 1: Recommend composition styles based on content (10 options to choose from) + automatically come up with candidate titles 4. Round 2: Face reference images + materials such as UI screenshots/product images 5. Round 3: Choose expressions, background tones, fonts, and font colors all at once, or leave it all to the model if you're lazy 6. Output complete prompts: 3:4 composition, safety zone, multi-reference image writing for Image 1 (face) + Image 2 (materials) are all included 7. Take it to Jimeng / Nano Banana / GPT-Image to generate images (if your agent has an image generation API configured, you can have it generate directly in the conversation) 8. Check if the titles have typos, and regenerate any parts you're unhappy with. 🧐 Tips: You must choose an image generation model that supports multiple reference images, otherwise facial consistency cannot be guaranteed. The skill has 8 built-in sets of example prompts reverse-engineered from real trending covers, and the model will automatically use them as references, pushing the image detail to the maximum.

Create a retro 2.5D anime thumbnail in a cinematic 16:9 frame, showing a close-up of a mischievous gothic anime girl leaning toward the camera in a cluttered analog electronics room. She has long straight black hair with blunt bangs, teal-green eyes, pale skin, small blush marks, pointed ears, and a wide unsettling grin with sharp triangular teeth. She wears a black top and a thin black choker, with her face centered and dominating the composition, shoulders cropped at the bottom, direct eye contact, playful but eerie expression. The background is a dim retro tech studio with exactly two visible CRT televisions: one large CRT on the left displaying bright cyan static and one darker CRT on the lower right with a small blue glow; include shelves, cables, ceiling pipes, hanging wires, old equipment, and a high window with washed-out daylight. Use a NORINORI CORE-inspired retro 2.5D aesthetic: cel-shaded anime character over a semi-realistic grungy room, thick ink outlines, muted olive-gray shadows, teal and magenta chromatic aberration along edges, VHS scanline noise, slight fisheye wide-angle distortion, low-light atmosphere, crisp face details, gritty analog texture, 1990s cyberpunk anime mood. Keep the image text-free, no logos, no watermark, no extra characters.

Goal: Create a bright vertical travel vlog thumbnail/collage featuring a smiling young woman traveler in a sunny outdoor alley, surrounded by cute scrapbook stickers and hand-drawn doodles. Canvas: Vertical 3:4 social media image, high-resolution, warm daylight, shallow depth of field. Background is a charming pedestrian street or café alley with plants, terracotta umbrellas, soft bokeh, and a small chalkboard sign in the distance. Main subject: A cheerful young East Asian woman with shoulder-length black hair and bangs stands slightly right of center, turned three-quarters toward the camera, smiling warmly. She wears a loose white T-shirt with a small nature print on the chest, light blue jeans, and a large beige backpack over one shoulder. Add a cute plush keychain hanging from the backpack. Put a thick white cutout outline around the subject, like a sticker. Layout and text stickers: Use exactly 6 main text stickers: 1) large top-left title reading Travel Vlog in oversized rounded pastel bubble letters with a thick white border; 2) top-right stacked sticker reading Good Vibes Only with a yellow heart and yellow smiley face; 3) small pink ribbon banner on the left reading let's go!; 4) dark cloud speech bubble on the right reading "explore more" with a small pink heart; 5) bottom-left sticker reading "on the way" in playful blue and pink bubble letters with a small white flower; 6) bottom-right sticky note reading Collect moments not things with a pink tape strip and a small heart. Decorative elements: Include exactly 3 illustrated travel icons: a cute line-art camera with a heart on the lens on the left, a folded map with a pink location pin on the lower right, and the backpack plush charm. Add multiple small white hand-drawn sparkles, arrows, hearts, squiggles, and doodle marks scattered around the subject, keeping them light and airy. Visual style: Photorealistic lifestyle portrait blended with kawaii sticker graphics, pastel colors, glossy scrapbook aesthetic, soft white outlines, playful vlog thumbnail design, warm golden sunlight, cheerful vacation mood. Constraints: Keep all text legible and in English, preserve the exact 6 main text stickers and 3 illustrated travel icons, avoid extra large words, avoid watermarks or logos, and make the subject the clear focal point.

Goal: Create a bright square Roblox-style promotional game thumbnail for 巨大アスレチック ブロックタワーを駆け上がれ！, an exciting block-tower obby where players climb a giant toy-brick tower and collect treasure chests to spin a gacha. Canvas: Square 1:1 thumbnail, 768x768 or larger, ultra-saturated colors, high-contrast mobile-game advertising composition, thick white and black sticker outlines around every character and text element. Layout: Put the red-and-white ROBLOX logo at the top left. Fill the background with a huge vertical tower made from colorful LEGO-like plastic studs and brick platforms, receding upward into a blue sky with clouds. Place the main Japanese headline across the upper-middle in giant layered text: a small black rounded label reading 「巨大アスレチック」 above enormous rainbow block letters reading 「ブロックタワー」, followed by bold white text with black outline reading 「を駆け上がれ！」 with yellow star icons on both sides. Under the title, add a blue banner with white text: 「宝箱を集めてガチャを回そう！」. Add two game HUD counters at the top right: exactly 2 rounded black panels, one showing a gold coin icon and 「1,234」, the other showing a treasure chest icon and 「宝箱 7/10」. Characters and objects: Include exactly 8 main visible characters: 1 cheerful orange-haired chibi girl in a yellow martial-arts outfit running in the foreground, 1 smiling panda companion at bottom left, 1 green-haired crowned chibi girl in a green outfit on the left, 1 red-kimono chibi girl near center, 1 black-haired ponytail chibi adventurer in green at center, 1 gray-helmet chibi girl with a small round helmet to the right of center, 1 purple wolf-eared chibi boy on the right, and 1 dark ninja boy flying at the upper right holding a small black cat. Include exactly 3 small pet/mascot creatures near the right group: a tiny black cat with the ninja, a yellow chick-like mascot, and a pink bunny-like mascot. Add exactly 1 golden treasure chest in the lower center foreground and exactly 1 red-and-gold capsule gacha machine at the lower right filled with multicolored balls and topped with a gold star. Scatter a few sparkling gold coins and star effects around the scene. Callouts and UI: Add a jagged red-yellow burst callout near the gacha machine reading 「宝箱の数だけ ガチャが回せる！」. Along the bottom edge, add exactly 4 black rounded instruction cards with orange outlines and icons: 1 chest icon card reading 「宝箱を集めて ガチャを回そう！」, 1 stopwatch icon card reading 「タイムアタックで ランキング上位を目指そう！」, 1 badge icon card reading 「バッジを集めて 図鑑をコンプリート！」, and 1 checkpoint flag icon card reading 「セーブポイントで どこでも復帰！」. Visual style: Roblox-inspired toy-block world, glossy 3D plastic bricks, chibi anime characters with oversized heads, big expressive eyes, joyful adventurous expressions, dynamic running poses, cartoon lighting, sparkle effects, strong drop shadows, thick outlines, vivid red yellow green blue purple palette, busy but readable YouTube thumbnail composition. Constraints: Keep all visible text in Japanese exactly as specified, make the headline the dominant focal point, use exactly 8 main characters, exactly 3 small pet mascots, exactly 2 top-right HUD counters, and exactly 4 bottom instruction cards. No photorealism, no watermark, no extra logos beyond ROBLOX.

office coffee machine as a sci-fi boss battle, cinematic sparks, exaggerated scale, punchy caption space, 16:9

Goal: Create a wide 21:9 Japanese article thumbnail / YouTube-style banner advertising a low-cost AI video creation strategy, with bold energetic typography and a futuristic creator-workstation theme. Canvas: Ultra-wide horizontal banner, 1200×514 style aspect ratio, bright blue-and-white tech background with slight vignette, glossy lighting, and high contrast for readability. Layout: Use a dynamic diagonal composition. The left two-thirds is dominated by oversized headline typography on layered white slanted panels with drop shadows. The right third shows a young male creator seen from behind at a laptop, looking at floating video-production screens. The bottom left contains a dark navy slanted caption bar with a secondary Japanese message. Add small icon circles along the lower right edge. Text content: Main headline must read exactly: 「Low Costで」 on the top white strip, 「AI動画」 in huge blue letters below it, 「をやるなら」 in smaller dark text beside it, and 「コレ!!」 in large hot pink letters with white outline on the right. Bottom caption bar must read exactly: 「12社のCPPに参加している筆者が、今ゼロから始めるならこの戦略で行く」 with 「12社」 and 「この戦略」 emphasized in yellow and the rest in white. Add a small handwritten note in the bottom right: 「はじめてでも安心！」 with a yellow underline. Subject details: Show a young Japanese male creator in a navy jacket, viewed from behind, hand on chin, facing a laptop. The laptop screen should show a video editing interface with timeline tracks and preview frames. Around the character, include exactly 4 floating media panels: 1 cinematic sci-fi hallway scene, 1 futuristic city skyline at sunset, 1 fantasy mountain landscape, and 1 software/dashboard screen. Add exactly 1 black-and-white movie clapperboard near the upper center, exactly 1 translucent play-button tile near the headline, and exactly 3 circular icons at the lower right: a pink piggy bank with yen symbol, a blue rising bar chart, and a checklist clipboard. Visual style: Polished Japanese marketing thumbnail, crisp vector typography mixed with semi-realistic digital illustration, electric blue gradients, white glow, subtle circuit-board lines in the background, dotted halftone accents, energetic shadows, yellow paint-stroke highlight behind the top headline, strong outlines around text, clean professional finish. Parameters: The main headline concept is Low Costで AI動画をやるならコレ!!; the bottom copy theme is 12社のCPPに参加している筆者が、今ゼロから始めるならこの戦略で行く; the accent color for the callout word is hot pink. Constraints: Keep all visible text in Japanese exactly as specified, avoid misspellings, avoid extra logos or watermarks, preserve the 21:9 thumbnail readability, and make the headline occupy most of the left side.

Create a cinematic portrait from the attached image. The scene has a pronounced cyan and turquoise color filter, with a soft haze effect and a bright blue light flare on the left. A blurred night background features bright yellow bokeh lights at the top. The style is analog photography, with subtle grain, a dreamy feel, soft lighting, and low saturation of warm tones.

Generate a high-end pop idol typography cover poster. Theme: music cover / idol visual / pop editorial / campaign concept Direction: Dynamic red typography cover / Red-background focused portrait cover / Dynamic idol stage poster / Headphone pop editorial cover Main Title: [Fill in main title] Subtitle: [Fill in short subtitle] Edition Small Text: [Fill in issue number / edition / minor info] Subject: [Adult young female idol / Adult young male idol / Pop artist / Performer from different countries] Country Setting: [China / Korea / Japan / Thailand / France / USA / Brazil / Argentina / UK, etc.] Atmosphere: [bold / stylish / emotional / kinetic / youthful / graphic / editorial] Color System: [Red / White / Black / Crimson / Soft White] The overall effect should resemble a high-end pop music visual cover or a fashion magazine poster. Use oversized typography as part of the visual structure, not just a simple title. Allow significant interaction between the subject and the text through: occlusion, interweaving, cropping, perspective, spatial layering, partial blurring, and foreground/background relationships. Layout should be clean and impactful, retaining only a small amount of auxiliary text. Choose one of the following four directions: 1. Dynamic Red Typography Cover Use a white or off-white background with oversized bold red text. Feature an adult young female or male idol in a dynamic pose, interacting strongly with the text. 2. Red Background Focused Portrait Cover Use a rich red background with a close-up or half-body portrait of an idol. Include elegant white serif text with a subtle focus box over the eyes; a dreamy atmosphere with clear eyes. 3. Dynamic Idol Stage Poster Use strong performance poses and exaggerated perspective (e.g., legs, boots, or arms closer to the lens). Large text is partially cut by the body, creating a stage visual or concert poster feel. 4. Headphone Pop Editorial Cover Feature an idol wearing headphones in a close-up or half-body shot. Incorporate tall vertical text interacting with the subject's silhouette, paired with 1-2 small label text boxes for a stylish, non-crowded look. Avoid: Cheap template feel, excessive small text, cluttered composition, weak fonts, fake brand logos, deformed limbs, incorrect fingers, plastic skin, or piled-up sticker elements. Requirements: Bold, clean, modern, and design-oriented. Generate only one high-quality standalone poster.

Create an international-quality cinematic movie poster for a film titled "Algorithm Fog City." Make it look like a masterfully designed festival-grade sci-fi thriller poster: a fog-drowned megacity, a lone figure in the lower foreground, a giant translucent human profile merged with glowing data streams and prediction-interface graphics, cold blue-gray atmosphere with subtle amber UI accents, dramatic vertical typography for the title, premium theatrical composition, realistic lighting, dense atmospheric depth, and polished high-end film poster design.

Ultra-realistic lifestyle photography of a confident young man standing outside a luxurious modern villa beside a premium sports car. He is wearing a perfectly tailored suit, an elegant wristwatch, polished shoes, and stylish sunglasses. The background features contemporary architecture, a beautifully landscaped garden, and warm golden-hour sunlight. His posture is confident and relaxed, creating an atmosphere of success and sophistication. Cinematic lighting, premium editorial photography, ultra-detailed, photorealistic, 8K, shallow depth of field, elegant composition, clean negative space for branding or text, portrait aspect ratio 4:5. Ultra-realistic lifestyle photography of a humble young man standing outside a simple brick house in a modest neighborhood. He is wearing clean, simple everyday clothes and comfortable shoes, with a calm, hopeful smile. The surroundings include a bicycle, small plants, and a peaceful residential street in soft morning sunlight. The atmosphere conveys dignity, hard work, resilience, and optimism. Cinematic natural lighting, premium editorial photography, ultra-detailed, photorealistic, 8K, authentic expressions, shallow depth of field, elegant composition, clean negative space for branding or text, portrait aspect ratio 4:5.

Create a vibrant anime-style YouTube thumbnail for a livestream gaming broadcast in a wide 16:9 layout. Set the scene inside a neon purple and pink streamer room. In the center, show a cute catgirl VTuber seated at a desk from the waist up, leaning forward with energetic body language, one hand on a computer mouse and the other hand reaching toward the viewer. Give her light orange-blonde bob-cut hair with soft bangs, fluffy brown-and-cream cat ears, and a visible cat tail. Cover the middle of her face with a solid rectangular censor block so her face is intentionally hidden. Dress her in a black-and-white maid-inspired outfit: a frilly white blouse, black dress bodice, puff sleeves, white ruffles, a black ribbon bow, and a gold bell choker. On the desk, include a mechanical keyboard with bright RGB lighting, a glowing gaming mouse, and a streamer microphone on the far left with pink-purple LED illumination. Add two cat-themed foreground props: a plush cat face at the bottom left and a black cat-shaped mug at the bottom right. Behind her, place a gaming chair decorated with paw-print details. On the left side of the thumbnail, add large bold Korean headline text in thick white block letters with black filled shadows and a glowing purple outline, stacked across two lines. The text should read: 방송중 대참사. Beneath it, add a smaller yellow comic-style burst caption with a black outline reading: > 크리퍼 실화냐. On the right side, place one large computer monitor angled inward. The screen should show a Minecraft-like scene with a bright blue sky, green trees, water, and a large green Creeper lunging outward toward the viewer. Outline the Creeper dramatically like a sticker cutout. Add starburst effects and neon accents around the monitor to make the moment feel chaotic and explosive. Use exaggerated clickworthy thumbnail aesthetics throughout: ultra-saturated colors, sharp cel shading, thick outlines, glossy highlights, high contrast, dynamic perspective, and a streamer-disaster mood designed to grab attention instantly.

A surreal giant woman sitting gracefully in the middle of Venice's Piazza San Marco, wearing an elegant black outfit and sunglasses, smiling softly while tourists gather around taking photos with their phones. Cinematic lighting, realistic architecture, dramatic scale contrast, ultra-detailed, photorealistic, travel photography, vibrant sky, natural shadows, high realism, 8K.

Create an ultra-wide cinematic mobile game cut-in banner in a dramatic fantasy anime-realism style. Canvas is a very wide horizontal rectangle, about 21:9, framed with thick black letterbox bars above and below the action area for a movie-like special attack screen. The subject is a heroic brown tabby cat, close-up from the shoulders up, positioned mostly on the left half and facing right with intense large green eyes, detailed fur, long white whiskers, and a determined expression. The cat wears a dark olive-green adventurer cloak with folds flowing backward and one visible round bronze clasp near the lower left. The background is a dark starry cosmic battle scene filled with glowing gold shards, sparks, triangular crystal fragments, streaking light trails, and bright white lightning bolts radiating across the right half. Place one large bold Japanese attack phrase across the lower-middle foreground, centered and spanning almost the full width: 星のかけらの力で　空へ！. The typography should be thick, heavy, game-like, pale cream to warm gold gradient with subtle beveling, dark shadow, and a thin horizontal golden line passing behind or through the text, making it feel like a special move title card. Keep the cat partially behind the text so the words dominate the cut-in. Use high contrast, sharp details, dynamic diagonal energy, glittering particles, and a premium fantasy RPG visual style. No extra logos, UI buttons, watermarks, or additional text.

Create a 16:9 editorial YouTube thumbnail about classical music, with a dignified photorealistic studio portrait of an elderly 19th-century French composer resembling Gabriel Fauré on the left half of the frame. He has wispy white hair, a high forehead, tired serious eyes, a large white handlebar mustache, and wears a formal black frock coat with satin lapels, a white high-collar shirt, and dark cravat. Use a muted warm brown textured studio backdrop with soft vignette lighting and empty negative space on the right for typography. Add exactly two text blocks: at the upper right, a large bold all-caps Spanish headline in bright golden yellow with dark drop shadow reading «EL ARRULLO DE LA MUERTE», arranged across three stacked lines; at the lower right, a smaller bold white caption with subtle black shadow reading Gabriel Fauré\nRéquiem, Op. 48, arranged across two lines. The composition should feel like a serious music essay cover: solemn, refined, slightly dramatic, high contrast between the black suit and brown background, clean typography, no extra logos, no watermark, no additional text.

do this for Argentina World Cup 2026, void main() { string player = "[PLAYER]"; string team = "[TEAM]"; // --- The series (infer the arc to dramatize) --- Arc a = infer_career_drama(player); // the prodigy years / the exile / the comeback - pick the prestige angle tone(restrained, moody, character_first); // NOT loud - quiet and heavy // --- Key art composition --- portrait(infer_player_persona(player), contemplative, half_shadow); environment(symbolic_setting(a), atmospheric, shallow_focus); // empty stadium / tunnel / rain on glass grade(infer_team_colors(team), desaturated_prestige, single_accent); // --- Streaming furniture (flat overlay) --- title(invent_series_title(player), elegant_serif_or_thin_sans, centered); tagline(invent_logline(player), small, below_title); platform_mark("LIMITED SERIES", "NOW STREAMING", micro_caps, corner); laurels(invent_critic_pullquotes(), thin); render(cinematic_still, film_grain: fine, premium_negative_space); }

Create a cinematic dark fantasy portrait of Luna and me: a young female warrior standing powerfully in the center of the frame with her legs apart, protecting a seated black panther directly in front of her. The warrior has long windswept golden-blonde hair, a calm confident expression, and wears ornate mirror-polished silver full plate armor with engraved filigree, layered pauldrons, gauntlets, greaves, and a dark flowing cape. The panther is a large sleek black leopard with glowing amber eyes, glossy fur, and an ornate gold chain collar, sitting alert between the warrior’s boots. Behind them, enormous torn crimson silk banners sweep diagonally across the sky like dramatic battle standards, embroidered with faint gold patterns. The background is an epic ruined ceremonial plaza or battlefield with dark spires, small fires, floating embers, wet reflective stone ground, and a turbulent blue-black storm sky with breaks of bright light. Use a low-angle heroic composition, centered symmetry, ultra-detailed realistic fantasy art, high contrast lighting, blue highlights on chrome armor, red backlight from the banners, rain-slick reflections, volumetric atmosphere, sharp focus on the woman and panther, and an intense movie-poster mood. No text, no watermark, no extra animals, no extra people.