Prompt Immagine per Group Couple

Create a vertical 4-panel manga comic strip in black and white, featuring chibi versions of Vocaloid characters. Panel 1: Hatsune Miku (twin tails) and KAITO (dark hair, scarf) are walking down a shopping street carrying grocery bags and bread. Panel 2: Kagamine Rin (short blonde hair with bow) and Len (ponytail) are decorating a room indoors with balloons and bunting flags. Panel 3: MEIKO (short brown hair) is whisking a bowl while Hatsune Miku (wearing an apron and headphones) arranges food on a plate in a kitchen. Panel 4: All six characters (KAITO, Miku, Rin, Len, MEIKO, Luka) are sitting around a dining table filled with a roast turkey, cake, and fruit, raising glasses for a toast.

Ultra-realistic candid photograph of a middle-class South Asian family having a peaceful Sunday morning in their small countryside home, father watering plants in the garden, mother preparing breakfast near an open window, two children playing barefoot nearby, simple clothing and authentic expressions, slightly imperfect old walls, hanging laundry, sunlight filtering through trees, realistic household objects everywhere, natural skin textures, genuine family interaction, warm morning atmosphere, documentary photography, 35mm lens, realistic depth, no staged posing, no artificial perfection.

脂香绮艳；秦淮烟月；顾盼生春；各具情态；CCD直闪；{argument name="人物组合" default="秦淮八艳：柳如是、陈圆圆、李香君、董小宛、顾横波、卞玉京、寇白门、马湘兰合照"}

Goal: Create a wide editorial sports diptych about Wimbledon tennis, with a realistic match scene on the left and a rough paper-cut illustration poster on the right. Canvas: Horizontal 16:9 composition, split exactly into 2 equal vertical panels. Left panel is a crowded outdoor grass tennis stadium in bright daylight; right panel is an off-white textured poster page with generous negative space. Left panel: Show a realistic, slightly painterly photograph-style Wimbledon grass-court rally. There are exactly 2 visible tennis players: 1 foreground player in all white sprinting and lunging left-to-right toward the net with racket extended, and 1 background opponent in white waiting near the far baseline. Include a black net across the lower middle, worn green grass with white court lines, dark green stadium walls, ball kids and officials in dark uniforms, and a dense crowd of spectators filling the upper stands. Add a central dark green scoreboard with Rolex branding and readable match details: “Marin CILIC” above “Roger FEDERER”, scores suggesting Cilic 2 0 and Federer 2 30, plus smaller match-stat lines. Keep the foreground player dynamic, low to the ground, with white headband, white shirt and shorts, white socks and shoes with small red accents. Right panel: Create a minimalist vintage tennis poster on textured cream paper. At the upper center-right, place large rough brush lettering reading {argument name="headline text" default="Still in Motion"} in dark forest green, tilted and hand-painted with distressed edges. Below it, draw a single faceted collage-style tennis player in white, mid-sprint to the right, stretched horizontally with one arm back and the racket arm extended toward a small yellow tennis ball. Use angular torn-paper shapes, visible paper grain, tan skin fragments, gray shadows, and dark green grass-stroke marks under the feet. Add exactly 2 small typography blocks: on the left of the illustrated player, stacked text reading {argument name="left small text" default="Same\nGame\nA Deeper\nYou"} with a short horizontal line beneath; on the right of the illustrated player, stacked text reading {argument name="right small text" default="TENNIS\nLIVES\nDIFFERENTLY\nHERE."} with a short horizontal line beneath. Visual style: Contrast a detailed, documentary tennis photograph on the left with a rough illustrated aesthetic on the right. Use Wimbledon colors: deep green, grass green, white, cream, muted yellow, tan, and black. Emphasize motion, athletic tension, textured grass, distressed paper, imperfect brush typography, and collage-like geometry. Constraints: Use exactly 2 main tennis players in the realistic left panel and exactly 1 illustrated tennis player in the right panel. Preserve the clean split-screen layout, no extra logos except the Rolex-style scoreboard on the left, no watermark, no modern UI elements.

Goal: Create a richly detailed “find the hidden creature” illustration of a lively Japanese summer shrine festival at night, where the viewer must search for one hidden {argument name="hidden creature" default="giant isopod"} among the crowd. Canvas: Wide horizontal 16:9 composition, panoramic and packed edge to edge with activity, viewed from a slightly elevated angle. The scene should feel like a high-quality anime background painting with crisp linework, warm lantern light, dense detail, and festive atmosphere. Setting: A crowded {argument name="festival location" default="Japanese shrine grounds"} during a summer matsuri. In the deep background, place a traditional shrine building centered at the top, with stone steps full of people. Add a red torii gate on the upper right. The sky is dark blue with visible stars and fireworks. Layout and counted elements: Include exactly 1 central red-and-white striped festival tower stage with taiko drummers on top, exactly 1 shrine building in the background, exactly 1 red torii gate on the right, exactly 5 large fireworks bursts in the sky, exactly 5 main food/game stalls, exactly 1 goldfish-scooping pool on the lower right, exactly 1 apple-candy stall on the left, exactly 1 takoyaki stall on the far left, exactly 1 target-shooting or prize game stall near the upper left, and exactly 1 colorful game stall at the far right. Add many strings of glowing red-and-white paper lanterns crossing the image horizontally and diagonally; make them numerous but orderly, with the brightest row spanning the upper third of the canvas. Crowd: Fill the foreground, middle ground, and background with a very dense crowd of festivalgoers. Include men, women, children, elders, couples, families, vendors, and performers. Most people should be Japanese, wearing a mix of colorful yukata, jinbei, casual summer clothes, hats, backpacks, and sandals. Show people eating festival food, carrying candied apples, taking photos, chatting, walking, watching games, and children playing. Make the crowd detailed enough that the hidden creature can blend in but still be discoverable. Hidden-object requirement: Hide exactly 1 {argument name="hidden creature" default="giant isopod"} somewhere in the scene, integrated naturally into the festival crowd or stall area. It should be visible if carefully inspected, not cropped off, not camouflaged into total invisibility, and not repeated anywhere else. Visual style: Vibrant Japanese anime festival illustration, highly detailed, warm orange lantern glow contrasted with cool night blues, hand-painted background feel, clean outlines, expressive faces, cinematic crowd composition, festive and joyful mood. Use realistic perspective and layered depth, with the foreground figures larger and more detailed than the background. Text and signage: Japanese festival banners may contain simple decorative symbols and minimal readable text, such as octopus, apple, target, shaved ice, or fish motifs. Avoid large English text, logos, watermarks, captions, or UI elements. Constraints: Make the image busy but coherent, with no empty areas. Keep the hidden-object puzzle fair and fun. Do not make the hidden creature the central focus. Preserve the feeling of a bustling summer night matsuri with fireworks, lanterns, shrine architecture, food stalls, games, and a joyful crowd.

Goal: Create a cinematic streaming-platform hero poster for {argument name="brand name" default="MUDONG film"}, presenting an AI-generated story universe as a “Now Showing” movie lineup. Canvas: Wide 16:9 landscape banner, dark luxury cinema atmosphere, black and deep brown background with soft golden bokeh, faint filmstrip textures, warm spotlight glow, subtle vignette, polished theatrical composition. Header: Top left place a red square film-logo icon with a white “M” and small perforated film holes, followed by the brand name “MUDONG film” in elegant white serif type and a small Chinese tagline beneath it. Center the giant headline {argument name="headline text" default="NOW SHOWING"} in large gold beveled serif letters with dramatic lighting. Under it add a thin divider line and the Chinese subtitle “六种世界观 · 开启你的第一部漫剧”. Top right add the Chinese phrase “用 AI 拍出属于你的故事宇宙” and a handwritten gold script line reading “Your Story Universe”. Main layout: Show exactly 6 tall movie-poster cards in one horizontal row, evenly spaced, each with a thin gold border, realistic cinematic key art, small “MUDONG film” at the top, Chinese quote text near the top, a large Chinese title near the bottom, a smaller English title/subtitle, “SEASON 01”, and a tiny descriptive Chinese sentence along the bottom edge of the card. Beneath each card repeat the title and genre label in clean white text, with a small red underline accent. Poster card 1: A cheerful fantasy journey scene in a travel vehicle or tuk-tuk on a European street, featuring three Journey-to-the-West-inspired characters: Monkey King with golden face paint, a red-robed monk, and a pig-like companion, lively and humorous. Chinese title “西游·人间一程”, English title “FANTASY ROAD”, genre label “FANTASY”. Poster card 2: A romantic sunset city scene with a young man and woman standing close, warm orange light, historic European architecture, emotional eye contact. Chinese title “时光告白”, English title “A Moment in Time”, genre label “ROMANCE”. Poster card 3: A lone astronaut standing on a rocky lunar surface facing Earth, starry black space, grand sci-fi mood. Chinese title “边界之外”, English title “BEYOND THE BOUNDARY”, genre label “SCI-FI”. Poster card 4: A dark rainy cyberpunk alley at night, neon signs, a serious young man in a black coat looking back, tense investigation mood. Chinese title “暗面追踪”, English title “THE SHADOW”, genre label “SUSPENSE”. Poster card 5: A Tang-dynasty-style historical mystery scene in ancient Chang’an at night, red lanterns, moonlit palace roofs, an elegant young woman in ornate red traditional clothing and hair ornaments looking over her shoulder. Chinese title “长安异闻”, English title “CHANG’AN MYSTERY”, genre label “HISTORY”. Poster card 6: A bright summer youth scene by the sea, blue sky, soft sunlight, smiling young man in a white shirt holding a cat, seaside town background. Chinese title “夏日回声”, English title “SUMMER ECHO”, genre label “YOUTH”. Footer: Center a tiny spaced-out line near the bottom reading “MUDONG FILM · AI CREATES A MORE POSSIBLE WORLD”. Keep all text crisp, premium, and cinematic. Visual style: High-end film festival poster design, realistic photographic key art, glossy gold typography, dramatic contrast, warm highlights, consistent branding, elegant Chinese and English typography. Constraints: Use exactly 6 poster cards and exactly the six genres listed. Do not add extra cards, extra logos, QR codes, watermarks, interface chrome, or unrelated text.

Create a delicate contemporary Japanese slice-of-life illustration showing a quiet, cozy everyday moment. STYLE Hand-drawn pen-and-ink artwork with fine expressive lines, naturally imperfect contours, subtle watercolor washes, visible paper texture, soft edges, and generous negative space. Blend Japanese minimalism with the charm of an independent sketchbook, café magazine, or modern lifestyle art book. Keep the artwork elegant, airy, tactile, and slightly unfinished. CHARACTERS Two young adults with simplified facial features, subtle expressions, relaxed body language, and natural interaction. Dress them in casual oversized contemporary clothing. Avoid realistic facial rendering; communicate personality through posture, gestures, and eye direction. ENVIRONMENT A warm, lived-in interior such as a café, apartment, studio, bookstore, kitchen corner, or creative workspace. Include selective details like wooden furniture, coffee cups, books, shelves, plants, windows, ceramics, stationery, and small everyday objects. Keep the setting uncluttered. COMPOSITION Full-body or three-quarter view at eye level. Seat the characters naturally facing one another. Use a balanced asymmetrical composition with generous clean space and an editorial framing. The relationship between the characters should be the main storytelling element. COLORS Use only muted, desaturated tones: warm cream, ivory, dusty blue, soft beige, light gray, sage green, natural brown, and off-white. Add one small red accent such as a mug, shoe, sock, notebook, or object. LIGHTING Soft natural daylight through a window with gentle ambient illumination and minimal shadows. Create a peaceful, warm, nostalgic atmosphere without dramatic lighting. RENDERING Sparse detail, delicate watercolor fills within fine ink outlines, subtle tonal variation, visible paper grain, and authentic hand-drawn imperfections. Avoid overly polished digital rendering. AVOID Anime, manga panels, cel shading, photorealism, hyperrealism, 3D rendering, glossy surfaces, vibrant colors, cinematic effects, heavy outlines, harsh shadows, and cluttered backgrounds. SCENE [Scene Description] The final image should feel like a premium contemporary Japanese lifestyle illustration-quiet, intimate, nostalgic, and beautifully ordinary, with the warmth of a carefully observed sketchbook moment.

Using the provided reference image as a style and setting guide, generate a character design sheet featuring {argument name="number of characters" default="9"} distinct individuals standing in a row against a plain background. The characters should represent the population of this specific environment (e.g., a cyberpunk Chinese street), showcasing "a thousand faces for a thousand people." Include a diverse mix of archetypes: elderly locals, laborers with cybernetic enhancements, merchants, scholars, and {argument name="special species" default="aliens or fantasy creatures"}. Ensure their clothing reflects the gritty, lived-in aesthetic of the reference scene—worn fabrics, earth tones mixed with subtle tech elements—and that each character has a unique face and expression.

Goal: Create a vertical four-panel manga page about a schoolboy climbing down one continuous ladder to meet a waiting girl, with the ladder drawn in front of the panel borders so it visibly connects from the very top to the very bottom across all panels. Canvas: Portrait manga page, roughly 4:5 aspect ratio, clean black outer border, four equal horizontal panels stacked vertically. Use crisp anime line art, soft cel shading, detailed sky backgrounds, and romantic school-life atmosphere. Layout: Exactly 4 horizontal comic panels. A single tall metallic ladder runs straight down the center of the entire page, overlapping and crossing every panel divider; the ladder must appear closer to the viewer than the black panel frames. Show the same teenage boy descending the ladder once in each panel, progressively lower each time, wearing a dark school blazer, white shirt, tie, black trousers, sneakers, and a black backpack. In the final panel, the boy reaches a rooftop-like school setting where a girl is waiting to his right. Panel details: Panel 1 has a bright blue sky with white clouds. The boy is high on the ladder near the top center, looking downward with a nervous, thoughtful expression. Include exactly 2 white rectangular narration boxes and 1 stylized climbing sound effect near the ladder. Text: 「どこまで降りればいいんだろう…」, 「きっとあの子が待ってる——」, and handwritten side text 「あの先に誰かが待っている」. Panel 2 continues the blue sky background. The boy is lower on the same central ladder, still descending carefully. Include exactly 2 white rectangular narration boxes and 1 stylized climbing sound effect. Text: 「もう少し…あと少しで会えるはず」, 「どんな顔で待ってるかな…」, and handwritten side text 「一段ずつ君に近づく」. Panel 3 shifts to a warm sunset sky with orange and pink clouds. The boy is even lower on the ladder, more anxious but hopeful. Include exactly 2 white rectangular narration boxes and 1 stylized climbing sound effect. Text: 「もうすぐだ…なんだかドキドキしてきた」, 「ちゃんと喜んでくれるかな…？」, and handwritten side text 「あと一段その先に」. Panel 4 is the largest emotional payoff at rooftop level during sunset, with a fence, low concrete wall, distant city buildings, trees, and warm golden light. The ladder continues down the center foreground. The boy stands on the left at the foot of the ladder, slightly embarrassed and smiling, still in school uniform with backpack. The girl stands on the right facing him, smiling brightly, wearing a navy school blazer, white shirt, red ribbon bow, plaid skirt, knee socks, and long brown hair. Add exactly 3 pink heart icons around the girl. Include exactly 2 speech bubbles, 1 white rectangular narration box, and 2 handwritten notes on rooftop surfaces. Speech bubble text: boy says 「待たせた…？」 and girl says 「うん！ずっと待ってたよ！」. Narration box text: 「やっとたどり着いたいちばん大切な場所」. Handwritten notes: 「ここでよかった♥」 on the left fence sign and 「きみとこれからも一緒に——♥」 on the right wall. Visual style: Japanese romantic shoujo manga mixed with modern anime illustration, clean panel borders, expressive faces, detailed uniforms, realistic clouds, soft sunset gradients, subtle motion lines, hand-drawn Japanese lettering, white caption boxes with black outlines, and a gentle emotional tone. Constraints: Use exactly 4 panels and exactly 4 depictions of the boy, one per panel. The ladder must be one continuous object centered vertically, visibly in front of all panel dividers. The girl appears only in the final panel. Keep the scene wholesome, romantic, and cinematic, with no extra characters or extra panels.

Goal: Create a cinematic widescreen historical poster about {argument name="headline year" default="1905"}, contrasting Albert Einstein's physics revolution with Claude Debussy's musical revolution in the same year. Canvas: 16:9 horizontal poster, dark midnight-blue and black palette with luminous gold typography, high-contrast dramatic lighting, photorealistic painterly collage style, elegant editorial design. Layout: Split the image vertically into two thematic halves with a large central black circular medallion overlapping both sides. Thin glowing gold orbital lines and a subtle vertical gold divider connect the two worlds. The central medallion contains the main typography, with the year huge at the top and supporting Spanish text below. Left half: A dramatic black-and-white portrait of Albert Einstein in profile facing upward to the left, wild gray hair, mustache, dark suit, contemplative expression. Behind him is deep space with stars, a curved Earth horizon at the bottom left, a warped spacetime grid funnel with a black hole-like depression, a small dark planet or eclipse near the grid, and handwritten equation text reading “E = mc²” near the upper left. Use cool blue highlights and fine scientific linework. Right half: A moody portrait of Claude Debussy in profile facing down to the right, dark curly hair and beard, formal black suit, hand resting against chin in a thoughtful pose. Behind him is an impressionist moonlit lake landscape inspired by Clair de lune: full moon in the upper right, blue night sky, distant dark trees and castle-like silhouettes, shimmering reflections on water, lily pads and exactly 3 visible pink-white water lilies near the lower center-right. Place a glossy black grand piano in the lower right corner with visible white and black keys. Add small elegant script text on the right reading “Suite bergamasque”. Central text content: In the black circular medallion, set large gold serif text: “{argument name="headline year" default="1905"}”. Beneath it, in stacked uppercase white/gold serif text: “DOS” and “REVOLUCIONES”. Below that, smaller white Spanish body text: “Mientras Einstein publicaba la relatividad, Debussy dudaba si publicar esta suite.” At the bottom, in warm gold serif text: “Dos revoluciones, un mismo año.” Typography and style: Use luxurious classical serif lettering for the title, with subtle beveling and gold glow. Body text should be centered and readable. Blend science and music visually: left side precise cosmic geometry, right side painterly impressionist water and moonlight. Add fine film grain, realistic lighting, soft bloom, and museum-quality poster polish. Constraints: Include exactly 2 main human figures: Einstein on the left and Debussy on the right. Include exactly 1 piano, exactly 1 central circular text medallion, exactly 1 equation “E = mc²”, exactly 1 phrase “Suite bergamasque”, and exactly 3 water lilies. Preserve all Spanish text exactly as specified. Do not add logos, watermarks, extra captions, or modern UI elements.

Create an ultra-realistic casual smartphone selfie of a young East Asian couple at a busy outdoor theme-park shopping street on a sunny winter day. The image should look like an unedited social media photo taken with a front-facing phone camera, close-up composition, square crop, natural lens distortion, soft haze from sunlight, and shallow but believable background blur. Two people are visible: 1) a very handsome young adult man on the left, tall and slim, with pale smooth skin, delicate facial features, large eyes, straight nose, soft lips, and slightly AI-idol-like perfection; he has {argument name="hair color" default="messy black medium-length hair with long bangs"}, wears a black coat over a black knit sweater and white undershirt, with a black backpack strap across his shoulder, and he leans his head gently toward the woman with a calm neutral expression; 2) a young adult East Asian woman on the right, shorter, realistic and natural-looking, with warm skin, brown eyes, shoulder-length brown hair with wispy bangs, a friendly small smile, subtle makeup, and faint natural skin texture; she wears a black coat and a thick {argument name="scarf color" default="cream white fleece scarf"}, leaning into the man while holding one white takeaway coffee cup with a cardboard sleeve near the bottom center of the frame. Background: crowded pedestrian street with many park visitors in winter clothing, European-style brick buildings, decorative street lamps, colorful hanging banners, and a burgundy storefront awning reading {argument name="awning text" default="VALENTINE'S"} on the upper right. Lighting is bright midday sun from above-left, creating realistic highlights on hair and faces, soft shadows, and slight overexposure in some areas. Keep the mood affectionate and casual, like a travel-date selfie. Do not add extra main subjects, do not make it a studio portrait, avoid cartoon or illustration style, avoid obvious filters, avoid text overlays or watermarks.

Goal: Create a vertical retro Teacher's Day tribute poster in a limited navy blue, warm orange-red, and cream palette, with a heroic educational illustration and bold typography. Canvas: Portrait poster, 2:3 aspect ratio, off-white paper background with subtle grain, aged print texture, risograph/screenprint look, slight ink misregistration and distressed halftone shading. Layout: Place a huge headline across the top reading {argument name="headline text" default="TEACHER’S DAY"} in tall condensed vintage serif capitals, navy blue with orange-red offset shadows and rough ink edges. Under it, center a large orange-red Chinese line reading {argument name="Chinese message" default="老师，辛苦了"}. Beneath that, add a small navy serif subtitle reading {argument name="subtitle text" default="Thanks for lighting the way"}. The lower two-thirds contains the illustration: a monumental female teacher rising behind oversized books, looking upward toward the right, while a tiny student stands at the bottom right for scale. Subject details: The main teacher is one adult woman with short wavy dark blue hair, round glasses, a calm proud upward gaze, pale cream skin, and a dark navy robe or cardigan over a light blouse. She holds exactly 2 books against her chest: one orange-red cover book in front and one cream/white book with navy outlines behind it. In the foreground, show exactly 3 oversized stacked books spanning the lower half: top book is mostly cream pages with navy and orange-red edges, middle book has an orange-red cover, bottom book has cream pages and a dark navy cover/edge. Add exactly 1 tiny student at the bottom right, wearing a navy school uniform and carrying an orange-red backpack, facing the teacher. Add stylized plant leaves behind the book stack, using navy and orange-red shapes, as decorative background elements. Visual style: Inspirational editorial poster illustration, simplified anatomy, elegant linework, high-contrast block colors, rough pencil-like crosshatching in the navy areas, warm nostalgic Chinese poster influence, clean centered composition, no photorealism. Constraints: Use exactly 3 visible text lines: the large English headline, the Chinese message, and the small English subtitle. Keep the typography centered and legible. Do not add logos, watermarks, extra people, classroom objects, or additional text.

A manga-style comic panel featuring a dynamic action scene. A young woman with brown hair and fox ears, wearing a blue denim jacket over a white top and a yellow skirt, is delivering a powerful kick to the face of a man. The man has messy dark hair, small bear-like ears, and wears a black hooded outfit; he is recoiling from the impact with a shocked expression. A golden crown with red jewels is flying off his head into the air. A speech bubble above the woman reads "Not anymore." Large yellow sound effect text reading "WHAM" appears in the lower left corner. Blue speed lines radiate from the center of the impact to emphasize the force.

Using the provided reference image, expand it into a square album-cover contact sheet made of exactly 9 separate panels in a 3×3 grid. Keep the same two musicians, blue monochrome night-film color grading, sunglasses, denim styling, rocky outdoor setting, and moody sky aesthetic from the reference. Generate alternate crops and camera angles as if from the same photo shoot: mostly low-angle close-ups and mid-close portraits looking upward, plus one top-down overhead panel in the upper-left. Separate every panel with clean white grid borders. Vary the framing across the 9 panels: 1 overhead two-person shot, 2 extreme close-up face crops, 4 low-angle two-person close-ups, and 2 looser mid-close shots showing more jacket/torso. Maintain gritty 1980s rock album photography, high contrast, visible film grain, deep cobalt blue tones, dramatic shadows, and no added typography or logos. Output as a square {argument name="album cover format" default="3×3 contact sheet collage"} with {argument name="color grade" default="deep monochrome cobalt blue"} and {argument name="border color" default="white"}.

一个女孩说着“{argument name="girl's dialogue" default="嘿，嘿，听我说！"}”，以及一个位于男孩上方的方形气泡，显示他的内心想法“{argument name="boy's inner thought" default="我就假装没听见吧"}”。以 {argument name="aspect ratio" default="竖向 (4:5)"} 的纵横比进行渲染。

Goal: Create a cinematic vertical manga page for episode 0 of a near-future domestic sci-fi story, blending photorealistic anime character rendering with clean manga panel borders. Canvas: Vertical 2:3 page, approximately 800 x 1200 px, black gutters and thin white panel borders, warm evening apartment lighting, shallow depth of field, highly detailed semi-realistic anime style. Layout: Use exactly 6 panels arranged as follows: Panel 1 top-left, wide kitchen cooking close-up; Panel 2 top-right, young man on sofa watching TV; Panel 3 middle-left, TV news broadcast screen; Panel 4 middle-right, close-up side profile of the young man; Panel 5 bottom-left, larger panel of the young man reclining with remote; Panel 6 bottom-right, android-like girl turning back toward camera in the kitchen. Characters: The main girl is {argument name="female character description" default="a delicate pale young woman with very long silver-white hair, soft doll-like features, blue glowing android eyes, cream knit sweater, dark apron straps"}. The main boy is {argument name="male character description" default="a slim young man with messy black hair, pale skin, dark hoodie, tired gentle expression"}. The girl appears in panels 1 and 6; the boy appears in panels 2, 4, and 5; the news anchor appears in panel 3. Panel details: Panel 1 shows the silver-haired girl cooking ginger pork in a frying pan in a cozy kitchen, using chopsticks or tongs, steam rising, warm backlight, bottles and plants blurred in the background. Add one speech bubble with Japanese text: {argument name="first speech bubble" default="今日の夕食は\n生姜焼きです"}. Add a small hand-drawn sound effect near the pan: 「ジュ〜」. Panel 2 shows the boy lying on a couch under a blanket, holding a TV remote, looking toward the television; the TV glows blue in the background. Add one speech bubble: 「おー」. Panel 3 is a TV news screen with a serious female news anchor on the left, a mountain forest search-and-rescue image on the right, blue broadcast graphics, and the channel logo “FNN NEWS.” Include a red breaking-news label 「速報」. Add exactly one large white news speech box: 「続いてのニュースです。\n〇〇山で行方不明になっている\n子どもは、現在も発見されておらず\n警察・消防による捜索が続いています。」 Add the lower headline: 「〇〇山で行方不明の子ども、いまだ発見されず」 and small subheadline: 「警察・消防が捜索続ける　悪天候で難航」. Panel 4 shows the boy in side profile, thoughtful, chin resting on hand, warm rim light, TV blur behind him. Add one speech bubble: 「まだ\n見つかって\nないのか……」. Panel 5 shows the boy reclined on the sofa holding the remote, seen from a lower angle with a mug and books softly blurred in the foreground. Add one speech bubble: {argument name="boy concerned line" default="早く見つかると\nいいよな〜"}. Panel 6 shows the silver-haired girl turning from the stove toward the viewer, glowing blue eyes clearly visible, calm expression, steam and kitchen highlights behind her. Add one speech bubble: {argument name="android reply" default="承知しました"}. Visual style: Premium cinematic manga, realistic anime faces, soft skin detail, filmic lighting, warm amber kitchen tones contrasted with cool blue TV-news light, detailed hair strands, glossy eyes, natural domestic setting, polished social-media comic page quality. Constraints: Use exactly 6 panels and exactly 6 speech bubbles plus the news graphics and one sound effect. Keep all Japanese text legible and placed inside rounded white manga speech bubbles or TV captions. Do not add extra characters, extra panels, watermarks, artist signatures, or unrelated text.

Use the uploaded image as the main restoration and identity reference. Convert this severely damaged {argument name="subject type" default="old portrait"} into a clean, fully restored modern-looking photo while preserving the original appearance, pose, and composition. Restore all missing and damaged areas of the photograph, including torn sections, faded parts, scratches, stains, cracks, peeling emulsion, discoloration, and burned or washed-out regions. Reconstruct the {argument name="subjects" default="man and woman"} completely so both subjects appear whole, natural, and clearly visible. Keep the same arrangement: the woman standing in front holding a {argument name="prop" default="large bouquet of flowers"}, and the man standing slightly behind her. Preserve their facial features, expressions, body proportions, posture, and elegant formal clothing, but refine everything to look polished, realistic, and complete. Transform the image from an antique sepia damaged print into a high-quality modern portrait with: clean natural skin tones, realistic facial details, sharp focus, balanced lighting, soft studio background, improved clarity and texture, realistic modern photo finishing. The final image should feel like a professionally restored contemporary portrait, as if the same couple was photographed clearly with a modern camera, while still keeping the classic formal elegance of the original scene. Style: photorealistic, high detail, restored portrait, modern studio photography, clean, elegant, natural colors, sharp and realistic.

Use the uploaded image as the only facial reference and preserve 100% facial identity, hairstyle, beard, skin tone, and natural skin texture. A medium shot of a young {argument name="subject" default="South Asian couple"} posing together, leaning against a silver metal railing at night. On the left, a man with a neatly groomed beard, dark hair, and a lean build wears a {argument name="clothing" default="dark maroon button-up shirt"} and a wristwatch, resting his chin on his right hand. Beside him, a young woman with a slender build, soft facial features, and long dark hair, wears a {argument name="outfit" default="beige floral-patterned traditional tunic"}, also resting her chin on her hands. Both are looking directly at the viewer with gentle smiles. They are centered in the frame against a blurred background of vibrant green foliage illuminated by colorful, bokeh-style neon lights in pink, blue, and yellow hues. The lighting is soft and warm, highlighting their faces and creating a romantic, inviting atmosphere. The composition is well-balanced, utilizing the railing as a foreground element to create depth. The style is that of a professional portrait, characterized by clear focus on the subjects and a creamy, out-of-focus background.

惊鸿破格 × 87版《红楼梦》 × 美能达胶片摄影 × 青春王国 · 大观园 × 宝黛共读西厢 × 原著人物形貌、体态与气韵还原

Create a single-panel modern manga illustration in a cinematic café interior. The scene shows exactly 2 characters in close-up, waist-up: on the left, a beautiful young woman with long light-brown hair tied half-up with loose strands, large glossy brown eyes, delicate earrings, natural makeup, and a sleeveless ribbed gray turtleneck top; she is smiling and speaking calmly while gesturing with one hand. On the right, a young man with short messy black hair, thick black rectangular glasses, expressive wide eyes, a drop of sweat on his cheek, an open shocked mouth, and a navy hoodie over a white shirt reacts in surprise. Between them, place one large vertical white manga speech bubble with a thick black outline, slightly oval, pointing toward the woman. The speech bubble contains vertical Japanese text in bold black, with the central acronym in bold blue Latin letters. Use the exact visible text arrangement: 「絵は描いてないけど、」 on the right column, blue vertical 「CMOA-I?」 in the middle, and 「漫画を作れるAIを使ったの。」 on the left column. Make the text look like printed manga lettering, sharp and readable, with the blue acronym standing out. Background: softly blurred cozy urban café with large windows, warm hanging lamps, dark walls, a chalkboard menu, plants, and evening light outside. Art style: polished seinen/shoujo manga hybrid, detailed linework, realistic anime faces, soft skin shading, glossy highlights, dramatic rim lighting, warm brown and amber color palette, shallow depth of field, high-resolution digital illustration. Composition: woman occupies the left third, man occupies the right third, speech bubble dominates the center upper area, characters cropped near the shoulders and chest, horizontal 3:2 aspect ratio. Avoid extra characters, extra speech bubbles, logos, watermarks, or unreadable random text.

“{argument name="セリフ" default="ケンカなんかしないよ？"}”という男の子と、その吹き出しに噛みつく凶暴そうな女の子。アスペクト比は縦長（4:5）で描画

Using the provided reference image as a rough stick-figure composition guide, transform the simple drawing into a warm, realistic family photograph. Preserve the arrangement of exactly 3 people: an adult on the left, a small child in the center, and an adult on the right, all holding hands and walking away from the viewer. Render them as a happy family seen from behind in a cinematic outdoor scene. Style: photorealistic, soft natural light, emotional and harmonious, shallow depth of field, high-detail DSLR look. Scene: place the family on a grassy hill or meadow at sunset, with golden backlighting, glowing sky, soft clouds, and a distant city skyline and water/river or bay in the background. Character interpretation: make the left adult a woman in a flowing light dress with long hair, the center figure a young child in casual light clothing, and the right adult a man in a light shirt and trousers. Mood: warm, peaceful, intimate, hopeful, family togetherness. Constraints: remove all phone UI, drawing toolbar, browser elements, text, and sketch marks; do not include any visible interface elements or captions; keep the final image as a polished square photographic composition.

Goal: Create a wide side-by-side comparison collage showing three input portrait photos on the left and a polished GPT-Image-style generated group photo on the right, demonstrating image-to-image character consistency for three young East Asian men. Canvas: Extra-wide horizontal image, approximately 2.6:1 aspect ratio, white background with two rounded-rectangle panels separated by a narrow vertical gap. Use realistic photography, crisp details, natural lighting, and a clean social-media demo aesthetic. Left panel: A rounded-corner collage labeled “Input” in small white text at the top left. It contains exactly 3 vertical portrait photos placed edge-to-edge: 1) a young East Asian man seated at a restaurant table in warm dim lighting, wearing a beige polo, with plates, salad, steak, sauce dishes, and glasses visible; 2) a young East Asian man outdoors by mountains and ocean under a bright cloudy sky, wearing a pale blue T-shirt and glasses, smiling; 3) a young East Asian man with curly hair and glasses standing at night near a waterfront city skyline, wearing a gray quarter-zip sweatshirt and light pants, smiling. Right panel: A single realistic generated office photo with rounded corners, showing exactly 3 young East Asian men matching the three input identities gathered around a laptop at a desk. The man from the restaurant photo stands on the left in a beige hoodie, leaning forward and pointing at the laptop screen. The man from the outdoor photo sits in the center wearing glasses and a light blue hoodie, smiling broadly. The curly-haired man from the night photo stands on the right wearing a dark hoodie, laughing and leaning in. The mood is collaborative, friendly, and energetic, like software developers working together. Office environment and objects: Modern developer workspace with computer monitors, plants, desk accessories, and warm daylight. Include exactly 1 laptop centered on the desk with an OpenAI knot logo sticker, 1 black square sticker reading “Change Build Ship Repeat,” and 1 small dinosaur sticker. Include exactly 5 stacked programming books to the left of the laptop labeled “Clean Code,” “Design Patterns,” “Spring Boot,” “Architecture,” and “System Design.” Include exactly 1 white mug labeled “GOOD DEVS BETTER TOMORROW.” Include exactly 1 black water bottle on the right labeled with code symbols and “Keep Building.” Include exactly 1 notebook on the right labeled “Ideas To Do Build Ship.” Wall text: Add exactly 3 visible motivational/code text areas in the background: left poster reading “Talk is cheap. Show me the code.”; center whiteboard reading “Good Code Better People A Brighter Future” with a small smiley face; right poster reading “Build Learn Iterate Ship.” Add a small watermark-like overlay near the top right reading “ChatGPT Images 2.5 by {argument name="creator name" default="小马哥"}”. Style: Photorealistic, high-resolution, convincing skin texture, natural smiles, accurate face consistency across the left input photos and right generated scene, shallow depth of field, soft office lighting, neutral modern colors. Customizable details: Use {argument name="character group" default="three young East Asian male software developers"} as the people being depicted, keep the main generated scene focused on {argument name="team activity" default="collaborating around a laptop"}, use {argument name="left label text" default="Input"} as the label on the source-photo panel, and keep the overall theme as {argument name="visual theme" default="developer collaboration demo"}. Constraints: Preserve the exact count of 3 input photos and 3 people in the generated office scene. Keep all visible English text legible. Do not add extra people, extra panels, or unrelated decorative elements. No surreal effects; the image should look like a clean before-and-after AI image generation showcase.

Create a cinematic YouTube thumbnail in a wide 16:9 aspect ratio, ultra-detailed photorealistic action-movie style. The scene is set at a luxury marina during a vivid orange-pink sunset, with sparkling water reflections, docked white yachts, palm trees, tall city high-rises in soft focus, and one small black helicopter flying in the sky near the upper left-center. On the right side, show two intense action characters cropped from waist/chest up: a young woman with messy blonde hair in a bun plus two braids, smoky eye makeup, hoop earrings, a black choker, black tactical tank top, visible floral and butterfly tattoos on her shoulder/upper arm, holding a black pistol close to her chest; beside her is a stern middle-aged man with short salt-and-pepper hair, wearing a plain black T-shirt and black tactical shoulder straps. Both stare directly at the viewer with serious expressions, lit by warm sunset rim light. On the left side, place a large graphic text stack and logo: at the top a black OpenAI knot logo inside a thick white sticker-like outline; below it exactly three stacked words reading “{argument name="top word" default="images"}” in huge white lowercase block letters, “{argument name="middle word" default="go"}” in white, and “{argument name="bottom word" default="hard"}” in bright neon yellow. Text must use a heavy rounded bold sans-serif font with thick black shadow/outline and white outer stroke, occupying the left half of the image. High contrast, saturated colors, dramatic thumbnail composition, sharp faces, shallow depth of field background, no extra text, no watermark.