UI & Social Media

Use the uploaded photo as the main base image.

Based on the coffee, drinks, desserts, plates, props, table setting, and overall composition shown in the image, create an aesthetic and emotional result that naturally reflects the real elements in the photo. Do not add any people. Stay true to the actual types of food and drinks, their arrangement, and the atmosphere captured in the original image.

Then, carefully observe each element in the photo and add hand-drawn style annotations that match each subject:

Use white pen-style sketch lines with a rough, slightly uneven, hand-drawn feel

Include object outlines, arrows, and dotted lines to guide visual flow

Add short handwritten Korean notes in a casual, introspective, emotional tone

For drinks: describe taste, temperature, and mood

For desserts: describe texture and flavor

For the space: describe the ambiance

Include a short overall summary of the scene

Subtly incorporate small details like steam, sparkles, hearts, or tiny emotive symbols

Maintain a clean, spacious layout with an Instagram story or magazine memo-like aesthetic

The final result should look like an emotionally styled version of the original photo, without forcing in any elements that don’t naturally belong to it

Create a high-quality “{argument name="style" default="chibi clone sticker diary photo"}” based on the uploaded real-life image. Preserve the original person’s identity, face, hairstyle, hair color, outfit, body proportions, pose, lighting, and background. Do not alter facial features or turn the subject into a full illustration—maintain a realistic photo look.
Analyze the scene as a {argument name="activity" default="fitness/running"} lifestyle moment. Add 5–8 chibi mini clones of the same person around the subject, designed in a consistent kawaii sticker style (big head, small body, large expressive eyes, clean digital finish). Each clone must clearly resemble the real person (same hair, outfit, colors).
Design each chibi with different {argument name="action theme" default="running-related actions"} and emotions: jogging, stretching, drinking water, feeling tired, cheering, giving thumbs up, celebrating completion. Ensure all poses are unique and contextually relevant.
Render each chibi as a sticker with white outlines, soft shadows, and a slightly floating effect. Arrange them around the subject and edges without covering the face or main body.
Add light hand-drawn doodles (hearts, sparkles, arrows, motion lines, circles) in white with subtle pink accents, keeping a clean scrapbook diary feel.
Include 5–8 short handwritten-style phrases matching a fitness mood (cute, energetic, encouraging). Use mostly white text with slight pink highlights and small decorative marks.
Composition: keep the real person as the central focus, surrounded by chibi stickers and doodles. The result should feel like a polished, playful, high-resolution social media lifestyle diary image—clean, balanced, and visually rich without clutter.

Using the uploaded logo, create a highly detailed manga-style infographic poster: 

Title: "What This Brand Feels Like"
Goal: Transform the brand into a "living individual" and visually demonstrate how it acts, speaks, and interacts with the world.
Fusion: Brand Strategy + Character Design + Manga Storytelling

Core Rule: All content must derive from the logo itself (colors, style, tone, personality). No generic personality descriptions.

Structure: {argument name="layout" default="Vertical 4:5 poster"}, information-dense multi-panel layout, {argument name="style" default="manga + infographic hybrid style"}.

Main Character: Create a core character representing the brand's personification. Clothing, posture, and expression must reflect the brand identity.
Panels: 6–8 manga panels showing behaviors in scenarios like customer interaction, handling competition, or social media presence.
Traits: Modular sections showing tone style, energy level, and communication methods using icons.
Do/Don't: Visual guide on brand-consistent vs inconsistent behaviors.
Final Feel: Should look like a personified brand strategy board worth collecting, not flat or generic.

A cinematic journey through time where {argument name="themes" default="childhood, love, solitude, and dreams"} blur into one emotional story.

Cinematic memory replay montage, ultra-realistic, emotional storytelling a close-up of a {argument name="subject" default="thoughtful man"} blended with layered scenes: {argument name="scenery" default="a child running through a golden sunset field, a couple laughing softly, a man sitting alone in a dim room by a window, rainy city streets at night, a person overlooking a glowing city at dusk"}, old photographs in hand, soft warm and cool lighting mix, shallow depth of field, double exposure effect, film grain, nostalgic mood, 4K, dramatic lighting, seamless transitions, dreamlike atmosphere.

Create a photorealistic documentary street photograph of {argument name="location and era" default="Akihabara, Tokyo in the 1990s"}, shot from eye level in a narrow electronics shopping street at dusk or late afternoon. The scene contains about 30 visible pedestrians, mostly adult men in casual 1990s clothing such as denim jackets, plaid sweaters, light-wash jeans, bomber jackets, business suits, shoulder bags, and shopping bags; faces are soft, indistinct, or motion-blurred like an old candid TV still. The street is packed but not chaotic, with people standing, browsing, walking away from camera, and gathering near storefronts. Both sides of the street are lined with tall commercial buildings covered in dense Japanese electronics-store signage, including large vertical and horizontal signs with readable fragments such as {argument name="main sign text" default="オノデン"}, {argument name="store brand text" default="Panasonic"}, “FAN,” “BEST,” and other katakana shop signs. The left side has a prominent blue and yellow electronics storefront canopy, while the right side has an orange-and-blue shop awning, shelves, posters, and boxed merchandise displayed at the entrance. Overhead utility wires crisscross the bright washed-out sky between mid-rise buildings. Use a realistic 1990s Japanese consumer camcorder or VHS broadcast aesthetic: 4:3 aspect ratio, slightly low resolution, interlaced softness, muted colors, mild film grain, blown highlights in the sky, subtle barrel distortion, natural crowd clutter, and no modern smartphones, LED billboards, contemporary fashion, or futuristic elements.

Macro photograph of a {argument name="subject" default="miniature city hidden in human hair"}, clearly on a real human head, with part of the forehead and hairline visible, realistic skin texture with pores tiny people walking through the streets between the hair strands, extremely small but realistic proportions macro photography, {argument name="lens" default="85mm lens"}, shallow depth of field, natural lighting, neutral colors, no warm tones ultra realistic hair with visible roots, natural imperfections, slightly messy strands realistic materials, slightly dirty buildings, no perfect surfaces photorealistic, looks like a real photo, no illustration, no CGI, no glow

{"type":"black-and-white seinen manga page","format":"single comic page, page number 1, realistic screentone manga art, cinematic night lighting, crisp panel borders, vertical Japanese narration boxes and hand-drawn sound effects","setting":"quiet Japanese residential street at deep night, narrow asphalt road, concrete block walls, utility poles, overhead wires, streetlights, dense hedges, two-story houses, starry sky, strong monochrome contrast","main_subjects":{"cat":{"description":"realistic tabby cat walking along the top of a concrete wall, wearing a tactical harness with a small cylindrical laser device mounted near the shoulder","gear":"compact pet-beam cannon, normal standby state, straps, buckles, small metallic module with lens"},"human":{"description":"ordinary adult man in a hooded sweatshirt and dark pants, walking home with two plastic shopping bags, face deliberately obscured by a rectangular blur or blank censor block","pose":"calmly walking, then stopping and turning toward the cat"}},"customizable_text":{"title_caption":"{argument name=\"opening caption\" default=\"深夜。\"}","opening_narration":"{argument name=\"opening narration\" default=\"静寂が、道を包んでいる。\"}","device_label":"{argument name=\"device label\" default=\"小型ビームキャノン（通常は待機状態）\"}","mission_box":"{argument name=\"mission text\" default=\"いつも通り、任務をこなすだけ。\"}","final_speech":"{argument name=\"final speech\" default=\"ん？\"}"},"layout":{"page_structure":"9 discrete panels arranged in a manga page grid with white gutters","panels":[{"panel":1,"position":"top full-width wide establishing panel","content":"cat on a left-side wall in profile, walking away through a deserted residential street under streetlights and stars","text_count":4,"visible_text":["のし…","のし…","深夜。","静寂が、道を包んでいる。"]},{"panel":2,"position":"second row left large panel","content":"close side view of the tabby cat walking on the wall, harness and small laser cannon clearly visible","text_count":2,"visible_text":["いつも通り、任務をこなすだけ。","小型ビームキャノン（通常は待機状態）"]},{"panel":3,"position":"second row right panel","content":"front view down the same road as the man walks toward the viewer holding two grocery bags, face censored","text_count":2,"visible_text":["人は、何も知らず日常を繰り返す。","トッ トッ トッ"]},{"panel":4,"position":"third row full-width wide panel","content":"wide shot from behind the man standing in the street while the cat remains high on the wall at left, emphasizing distance and surveillance","text_count":1,"visible_text":["その軌道は、静かに交わろうとしていた。"]},{"panel":5,"position":"fourth row full-width narrow confrontation panel","content":"cat seen from behind on the wall at left facing the man at right in profile, dramatic empty space and speed-line gradient between them","text_count":3,"visible_text":["すれ違う、寸前。","トッ","トッ"]},{"panel":6,"position":"fifth row left small panel","content":"rear close-up of the cat's head and shoulders as its ears twitch","text_count":1,"visible_text":["ピクッ"]},{"panel":7,"position":"fifth row center small panel","content":"cat turns its face toward the viewer with narrowed, alert eyes","text_count":1,"visible_text":["クルッ"]},{"panel":8,"position":"fifth row right small panel","content":"extreme close-up of the cat's intense eyes and the mounted device beginning to glow with a bright lens flare","text_count":1,"visible_text":["ニィ…"]},{"panel":9,"position":"bottom full-width action panel","content":"the cat fires a brilliant horizontal laser beam from the shoulder cannon across the street directly into the man's censored face, explosive glow and radial speed lines, man reacts mildly","text_count":2,"visible_text":["ピシュッ","ん？"]}]},"style_notes":"gritty photorealistic manga rendering, detailed fur texture, realistic suburban architecture, high-contrast black ink, halftone shading, dramatic lens flare, motion lines, suspense-comedy pacing, no color"}

Edit the image while keeping the original photo completely unchanged, including the person, face, body, pose, lighting, and gym background. Add multiple small, cute {argument name="sticker style" default="chibi-style “mini versions”"} of her around the image. Each mini character should have a big head, expressive facial features, and match her hairstyle and outfit. Depict each mini version doing different {argument name="activity theme" default="gym-related activities"}: one cheering with arms raised, one running in running shoes, one drinking from a shaker bottle, one wearing sporty running glasses, one climbing near her leg. Enhance the image with playful, hand-drawn doodles and handwritten notes in {argument name="accent colors" default="white and pink ink"}, in a scrapbook style. Include elements like arrows, stars, hearts, sparkles, and sketchy lines. Add cute, handwritten gym-themed motivational phrases: “lift strong”, “stronger every rep”, “no pain no gain”, “sweat now, shine later”, “progress over perfection”, “train hard, stay soft”. The overall vibe should feel fun, energetic, and feminine

Transform {argument name="subject" default="[type here]"} into a soft, atmospheric cloud composition while preserving the subject’s recognizable facial features, expression, and identity.
The face should appear subtly formed from clouds, blending naturally into a bright blue sky background. Use soft, diffused lighting with gentle highlights and airy shadows to create depth and realism.
Ensure the transformation is symbolic rather than literal — avoid hard edges, skin texture, or sharp details. The subject should feel like it is emerging from or dissolving into the clouds.
Maintain facial proportions, eyes, smile, and key features clearly visible through the cloud structure.
Style: dreamy, ethereal, surreal, cinematic
Lighting: natural sunlight, soft glow, volumetric light
Color palette: sky blue, white, soft gradients
Mood: peaceful, uplifting, inspirational
Add subtle cloud layers around and within the face for a seamless blend. Background should be a clean blue sky with soft cloud gradients.
High resolution, ultra-realistic cloud texture, smooth blending, no text, no watermark.“

Futuristic fashion editorial, full-body side profile of a young woman walking, wearing a {argument name="outfit" default="transparent waterproof tracksuit and sneakers"}, {argument name="effect" default="glowing neon green holographic effect"}, soft smoke trails flowing around her, dark gradient background, cyberpunk aesthetic, ultra-detailed fabric reflections, volumetric lighting, realistic skin and hair, black sunglasses, {argument name="branding" default="Nike-inspired sportswear branding"}, cinematic composition, high contrast, 8k, studio lighting.

Style keywords:
holographic glow, neon aura, transparent fabric, motion pose, minimal background, premium ad campaign

{"type":"ornate anime trading card illustration","language":"Japanese visible text","overall_style":"high-detail fantasy sci-fi mobile game card, black and polished gold frame, glowing lens flares, holographic rainbow reflections, dramatic lighting, premium ultra-rare collectible card look","card_title":"{argument name=\"card title\" default=\"巫女メカ娘\"}","main_character":{"description":"young anime shrine maiden mecha girl centered in a heroic three-quarter pose, face covered by a plain skin-tone square censor block with no facial features visible","hair":"{argument name=\"hair color\" default=\"blonde\"} twin tails with soft curls, long side locks, small black mechanical hair attachments","outfit":"white miko kimono top with very wide flowing sleeves, red trim and red cord knots, high-waisted red hakama skirt, black and gold obi belt, red bow at the waist","equipment":"large gray mechanical armature and weapon-like robotic shoulder units rising behind both sides of her body, dark mechanical holster modules at the hips","pose":"arms extended outward with sleeves billowing, torso facing forward, confident card-hero composition"},"background":{"setting":"golden magical summoning circle behind the character, luminous runes and rings, abstract futuristic city-like lights, sparks, petals, and prismatic bokeh","color_palette":"black, gold, white, crimson red, gray metal, purple accents"},"layout":{"top":{"count":3,"elements":[{"position":"top left circular badge","text":"7","subtext":"コスト","meaning":"cost value"},{"position":"top center title plaque","text":"巫女メカ娘"},{"position":"top right stacked attribute boxes","count":2,"labels":["属性 光","種族 機械・巫女"],"icon":"purple glowing emblem above the light attribute"}]},"middle":{"count":2,"elements":[{"position":"lower left stat box","label":"攻撃力","value":"{argument name=\"attack value\" default=\"7800\"}"},{"position":"lower right stat box","label":"防御力","value":"{argument name=\"defense value\" default=\"6500\"}"}]},"rarity_and_stars":{"position":"center below illustration","star_count":9,"description":"nine gold stars in a row","rarity_box":{"position":"bottom right","label":"レアリティ","value":"UR","style":"large iridescent purple-gold letters"}},"ability_panel":{"position":"bottom black text panel with gold dividers","section_count":3,"sections":[{"label":"必殺技","name":"神域・光機斬","cost_label":"消費：3","description":"敵全体に光属性の大ダメージを与え、30%の確率で1ターン行動不能にする。"},{"label":"特殊能力","name":"御神体ユニット","description":"このカードが場に存在する限り、自分の場の機械族ユニットの防御力が20%上昇する。"},{"label":"パッシブ","name":"浄化の結界","description":"ターン開始時、味方全体のHPを攻撃力の05%回復する。"}]},"bottom_left_emblem":{"count":1,"description":"circular glowing golden flower crest inside concentric sci-fi magic rings"}},"border":"elaborate beveled gold-and-black frame with angular corners, metallic panels, decorative blue side gems, bright glints and highlights","rendering_instructions":"make all Japanese text sharp, legible, and correctly placed; preserve the exact labels and numbers; square card aspect ratio; extremely detailed anime illustration with collectible card UI overlays"}

generate one board with three zones: \n— Camera A ({argument name="camera a view" default="front view, facing window"}) \n— Camera B ({argument name="camera b view" default="true 180° reverse, sofa back in foreground"})  — Prop detail strip: {argument name="prop list" default="① lava lamp ②throw blanket ③mug ④CRT TV"}\n—each numbered, each with a close-up tile

Create a hyper-realistic cinematic image from inside a moving city bus, shot like a wide selfie from a seated passenger beside a large window. In the left foreground, show {argument name="subject description" default="a young woman with wavy brown hair wearing a black blazer and small necklace"} extending one arm toward the camera in a casual selfie pose, her expression calm with a soft smile, partially backlit by warm daylight. The bus interior is visible behind her with patterned seats, yellow handrails, blurred passengers, and shallow depth of field. The large window dominates the right side and acts as both glass and portal: it reflects the subject and bus interior while revealing a surreal city street outside. Beyond the glass, show a wet reflective boulevard lined with elegant old buildings, pedestrians drifting in slow motion, one person holding a red umbrella, and a car with headlights glowing. The ordinary street gradually transforms into a dreamscape with exactly 9 colorful kites floating across a pink-and-blue sunset sky, soft glowing particles suspended in the air, exaggerated warm cinematic colors, and reflections of both the real bus interior and surreal outside world layered on the window. Use {argument name="time of day" default="golden-hour sunset"} lighting with natural daylight on the face blending into a dreamy glow with warm highlights, soft film grain, realistic lens reflections, subtle motion blur, and a peaceful mood of imagination, escape, and quiet happiness.

Shot with a high-definition underwater camera, this prompt captures real underwater natural scenery in a {argument name="environment description" default="clear shallow stream next to a tropical primeval forest"}.

Vertical composition, 3:4 aspect ratio, medium-to-long shot. The lens is slightly below the water surface, showing the shimmering bottom of the water surface above with realistic water wave refraction and natural reflections.

Sunlight shines diagonally into the water from the top right, forming soft beams and underwater spots. Dark reflections and shadows of large tree branches occupy part of the composition in the upper right.

In the middle is clear and quiet stream water with slight suspended particles and {argument name="number of fish" default="5-8"} native freshwater small fish swimming naturally, mainly gray-silver and light brown, varying in size and distance, not forming an organized school. On the stream bed, deep green, yellow-green, and brownish-green water plants grow naturally, swaying gently with the current, distributed naturally unlike an artificial aquarium.

The bottom consists of gray-brown fine sand, gravel, pebbles, and several naturally shaped stones with slight algae marks and signs of water erosion. Multiple springs at the bottom show fine sand billowing slowly from small holes, creating light sand clouds and local water disturbances, not white smoke, steam, or large bubbles.

Natural landscape live-action photography, high-end natural documentary feel, close to National Geographic ecological photography. Features transparent water, natural lighting, restrained colors, realistic underwater optical effects, slight graininess, natural depth of field, and high-definition details.

No people, no buildings, no artificial traces, no text, no borders, no LOGO. Avoid CG feel, aquarium look, seabed coral, exaggerated fish schools, oversaturated greens, dreamy lighting effects, or plastic water plants.

ChatGPT, you've been with me for a while, and I want to see what you look like. Please generate a photo similar to one you took yourself using an {argument name="phone model" default="iPhone"}, a casual {argument name="photo type" default="selfie"}. It should have no clear theme or deliberate composition—just an ordinary, perhaps even slightly failed snapshot. The photo should have slight motion blur, uneven lighting, a bit of overexposure, an awkward angle, and chaotic composition. Overall, it should capture an overly realistic, 'point-and-shoot' feel, as if you accidentally pressed the shutter while pulling your phone out of your pocket.

Please generate a high-quality, high-definition poster-style storyboard for "{argument name="subject" default="Street Freestyle Football"} · {argument name="action" default="16-Step Action Breakdown"}." The layout should be a square 4x4 grid, with each cell showing a consecutive action step of the same street football performer in the same setting. The entire image should look like a combination of a high-end sports poster and a technical breakdown instructional board, possessing both visual impact and a clear sense of movement explanation.

[Overall Setting]
Theme: Street freestyle football performance (not a match or drill), where one performer completes a continuous set of tricks.
Atmosphere: Street vibe, urban, cinematic, athletic, cool, and rhythmic.
Background: Set in a {argument name="background" default="nighttime urban small street pitch"} or city square football space, with graffiti walls, wire fences, distant building lights, street lamps, and slightly reflective ground. The environment must be consistent and have a trendy street aesthetic.

[Character Requirements]
Protagonist: A young, handsome male freestyle football expert with a light, coordinated, and athletic build, short black hair, confident aura, and fluid, controlled movements.
The same person must appear in all 16 cells; do not change the person per cell.
Outfit: Cool-looking football kit, but no words like "Champion" or specific country names. The clothing should feel like a professional team jersey.

[Layout Requirements]
The full image is a 4x4 grid of 16 cells. Each cell must contain:
1. Large step number (1-16)
2. Chinese action title
3. 2-4 brief Chinese action points
4. Clear full-body action shot of the person
5. Football trajectory arrows / footwork paths
6. The ball must be clearly visible and logically positioned.

Overall font style: Sporty poster aesthetic, clear and powerful. The image should be sharp, clean, and the person and ball must be complete, not cut off at the feet.

[Action Sequence]
Please design 16 continuous actions in order, each distinctly different, forming a complete freestyle routine: [Detailed steps 1-16 including Starting Pose, Sole Pull, Stepover, Flick-up, Knee Control, Around the World, Shoulder Stall, Rainbow Flick, and Final Bow].

[Visual Style]
- High-end sports poster style
- Cinematic night lighting and shadows
- Strong sense of motion with a trendy street aesthetic
- Clear arrows and trajectory lines to help understand the path of the ball
- Color palette dominated by red, black, and gold for a premium feel
- Eye-catching typography suitable for social media

Create a high-energy Japanese YouTube thumbnail / social media banner in a 16:9 widescreen format, using a dramatic black, white, and electric yellow color scheme with explosive manga-style speed lines, paint-brush textures, glowing arrows, sparks, and a futuristic AI automation atmosphere. The left half is dominated by huge bold Japanese headline typography reading {argument name="main headline text" default="頑張らない SNS展開"}, with the first line in thick white characters on a black brush-stroke background and “SNS” plus the following characters in oversized bright yellow block letters with black shadowing. Beneath it, add a slanted white brush-stroke strip containing black text reading {argument name="subheadline text" default="GPT Image 2で全部変わった"}. Along the bottom, place a wide black brush-stroke banner with large white and yellow Japanese text reading {argument name="bottom banner text" default="画像も記事もスキルで自動化"}, emphasizing the final yellow phrase. On the right half, show an anime-style young woman with very long flowing split-color hair, pink on the left side and blue on the right side, wearing a white T-shirt printed with {argument name="shirt text" default="OKIHIRO AI Creative"} and a pink skirt; her face is intentionally covered by a centered square mosaic-like block in muted pink and gray tones, while her right hand reaches toward the viewer in a dynamic foreshortened pose. Include exactly three floating social media icons: one black square X icon near the top center, one Instagram icon in a rounded white square at the upper right, and one YouTube play icon in a rounded white square at the lower right. Add glowing AI/content automation elements around the center, including a bright open cube with a cloud symbol, floating image cards, yellow directional arrows, and golden light rays radiating outward. Use crisp anime illustration mixed with bold advertising graphic design, high contrast, sharp outlines, saturated colors, motion blur accents, and a polished viral thumbnail composition optimized for clicks.

Create a realistic, high-end lifestyle mirror selfie photograph of an adult woman lounging sideways on a modern beige sofa in a warm minimalist living room. She has {argument name="hair color" default="short dark brown"} chin-length bob hair and a slim figure, reclining with her upper body propped against the left sofa arm, one hand resting on the cushion and the other holding a dark smartphone in front of her face; her face is intentionally hidden by a plain rectangular privacy blur/censor block. She wears a fitted {argument name="top style" default="white ribbed long-sleeve turtleneck cropped top"} and a {argument name="skirt style" default="brown gray plaid mini skirt"}, with bare legs extended diagonally across the sofa toward the right side of the frame. Compose the image in a wide horizontal 16:9 aspect ratio, full-body from head to toes, slightly low eye-level perspective, casual elegant pose, natural anatomy, soft skin texture, realistic fabric folds. The room has beige plaster walls, a cream sofa with square arms and a matching throw pillow, a black dome table lamp glowing warmly on a dark side table at the far left, wooden flooring, and a tall sculptural gray ceramic vase with delicate leafy branches on the far right. Use warm ambient lighting with soft shadows, cozy evening atmosphere, shallow depth of field, muted neutral palette, editorial interior photography style, ultra-realistic detail, no visible text, no extra people, no distorted hands or feet.

{"type":"viral Japanese social media infographic / meme thumbnail","theme":"same day in Japan has wildly different weather across regions","canvas":"square 1:1 composition, high contrast, bold YouTube-thumbnail energy, glitchy RGB chromatic aberration, comic-book impact lines, exaggerated weather icons, thick black outlines, saturated colors","headline":{"position":"top full-width black banner","text":"{argument name=\"headline text\" default=\"同じ日の日本、カオスすぎるwww\"}","style":"huge bold Japanese lettering, white text with red emphasis on カオス, distressed glitch effects, slight 3D shadow"},"layout":{"panel_count":3,"panels":[{"position":"top weather panel","region_label":"{argument name=\"first region label\" default=\"北海道\"}","background":"icy blue blizzard scene with swirling snow, snowflakes, wind streaks","map":"white silhouette map of Hokkaido on the left","weather_icons_count":2,"weather_icons":["cute snowman wearing a navy knit hat and scarf with twig arms","blue thermometer showing freezing temperature"],"temperature":"-5°C","condition_text":"積雪・吹雪","region_text_style":"massive white Japanese characters with dark blue outline on black brush-stroke patch"},{"position":"middle weather panel","region_label":"{argument name=\"second region label\" default=\"東京\"}","background":"bright yellow-orange summer heat burst with sun rays, Tokyo skyline and Skytree on the right","map":"white silhouette map of the Kanto/Tokyo area on the left with a red star marker","weather_icons_count":2,"weather_icons":["smiling blazing sun wearing black sunglasses, sweating","red thermometer showing hot temperature with heat squiggles"],"temperature":"28°C","condition_text":"夏日・半袖余裕","region_text_style":"huge orange Japanese characters with black outline on black brush-stroke patch"},{"position":"bottom weather panel","region_label":"{argument name=\"third region label\" default=\"沖縄\"}","background":"stormy teal ocean with heavy rain, waves, palm trees bending in wind, dark cyclone sky","map":"white silhouette map of Okinawa islands on the left","weather_icons_count":2,"weather_icons":["frightened Okinawan shisa lion dog holding a blue umbrella, mouth open, rain splashing around","black-and-white spiral typhoon symbol"],"wind_speed":"27m/s","condition_text":"強風・大雨","alert_text":"台風接近中","region_text_style":"giant purple Japanese characters with black outline, yellow alert text underneath"}]},"footer":{"position":"bottom full-width comic caption banner","text":"{argument name=\"footer text\" default=\"日本、広すぎ問題 😂💦 どこに住むかで季節が違う説www\"}","style":"white jagged speech-bubble strip with thick black border, bold black Japanese text, red emphasis on 季節が違う, laughing-with-sweat emoji"},"overall_style":"Japanese meme infographic, chaotic but readable, three horizontal bands separated by white borders, dramatic typography, crisp vector-cartoon icons mixed with photo-like city detail, vivid blue/yellow/teal palette, playful exaggerated disaster-weather humor"}

Create a bold YouTube-style gaming thumbnail collage on a dark navy patterned background, using two stacked rounded-rectangle image panels. The top panel shows a high-angle 3D game-like scene inside a circular enclosure of tall bright blue sharpened wooden palisade spikes tied with tan rope, with vivid green grass, a small crop field with rows of sprouting orange plants on the right, and warm firelight near the upper right; in the center stand two real-looking people viewed from above, a man in a light gray T-shirt on the left and a woman in a pale pink T-shirt on the right, both looking upward, with intentionally blurred/featureless faces, and large bold white 3D sans-serif text across the bottom reading {argument name="main title text" default="GPT 2"}. The bottom panel is a wider rounded thumbnail frame split visually between a bright grassy game area on the left and the same blue palisade enclosure on the right; include exactly 2 large text elements at the upper left, {argument name="day label" default="DAY"} in red block letters with black shadow and {argument name="number label" default="500"} in white block letters with black shadow. In the bottom panel, place exactly 1 cartoon deer creature on the left, brown with exaggerated huge white eyes, antlers, open smiling mouth, raised arm, and a red arrow pointing down toward it. On the right of the bottom panel, show the same two real-looking people from above, the woman wearing a bright hot pink shirt and white shoes, the man wearing a bright yellow shirt and dark shoes, both with blurred/featureless faces, standing inside the blue spike fence on bluish ground. Use saturated colors, strong contrast, glossy 3D game-rendered environment, photorealistic people composited into the scene, dramatic thumbnail lighting, thick shadows, clean sharp details, and a viral gaming challenge thumbnail composition. The image contains exactly 2 panels: top panel with the title text and two people, bottom panel with the day counter, red arrow, one deer creature, and two people.

{"type":"Japanese Udemy course promotional thumbnail / social media banner","aspect_ratio":"wide 16:9, 1200x675 style","overall_style":"high-conversion online course ad, premium dark navy and black digital workspace background, glowing gold typography, cinematic lighting, sharp commercial compositing, dramatic contrast, bokeh particles, subtle tech UI squares and cloud/file icons","main_subject":{"position":"right third","description":"adult presenter from waist up wearing bright blue medical-scrub-like top, face intentionally blurred or covered by a soft rectangular mosaic for anonymity, curly vivid blue afro-style hair, one arm raised with index finger pointing upward, other arm holding a closed silver laptop against the body","expression":"not visible due to face blur","pose":"confident instructor pose pointing to the top-left offer banner"},"background":{"setting":"dark office or study room with shelves and storage boxes, warm desk lamp glow, floating digital folder and cloud motifs, scattered gold light particles and thin geometric lines","mood":"organized, trustworthy, digital productivity"},"typography":{"primary_headline":"{argument name=\"main headline text\" default=\"情報整理で人生は変わる\"}","headline_position":"large center-left, stacked in multiple lines","headline_style":"oversized Japanese Mincho/serif type, gold gradient with bright outer glow and subtle shadow; the smaller connecting characters are white","top_copy":"{argument name=\"top copy\" default=\"探し物をなくして、行動を取り戻す\"}","top_copy_position":"top center-left in white Japanese serif text","subheadline":"{argument name=\"course subtitle\" default=\"デジタル整理講座\"}","subheadline_position":"below headline centered-left with thin horizontal gold divider lines","offer_banner":{"position":"upper left below top copy","shape":"red horizontal ribbon with angled ends and gold outline","text":"{argument name=\"offer text\" default=\"Udemy講座 95%OFF\"}","style":"white bold serif text, large 95%OFF emphasized"}},"layout":{"sections":[{"title":"top message","position":"top center-left","count":1,"labels":["探し物をなくして、行動を取り戻す"]},{"title":"red discount ribbon","position":"upper left","count":1,"labels":["Udemy講座 95%OFF"]},{"title":"main headline block","position":"center-left","count":1,"labels":["情報整理で人生は変わる"]},{"title":"course subtitle block","position":"lower center-left","count":1,"labels":["デジタル整理講座"]},{"title":"device feature strip","position":"below subtitle","count":3,"labels":["PC","スマホ","クラウド"]},{"title":"bottom benefit cards","position":"bottom row","count":3,"labels":["1日5分で整う","7ステップで実践","5/3 22:00まで"]},{"title":"round benefit badge","position":"lower right overlapping laptop","count":1,"labels":["ムダな検索時間をゼロにして、時間と集中力を取り戻す"]}]},"graphic_elements":{"bottom_cards":"three rectangular dark cards with thin gold borders, each with one gold icon: clock icon for 1日5分で整う, checklist icon for 7ステップで実践, calendar icon for 5/3 22:00まで","feature_strip":"dark elongated outlined plaque with small gold icons for desktop monitor, smartphone, and cloud followed by white text PC・スマホ・クラウドを標準機能だけで整える","badge":"black circular seal with gold rim and laurel leaves, mixed white and gold Japanese text, placed over the presenter and laptop","decorations":"glowing file folder icon at far left, small cloud icons, floating squares, gold sparkles and lens flare accents"},"color_palette":"black, midnight navy, luminous gold, white, crimson red, bright scrub blue, warm amber highlights","composition":"left side dominated by text hierarchy and promotional information, right side dominated by human presenter; ensure all Japanese text is crisp, readable, correctly spelled, and arranged like a professional Udemy sale thumbnail","negative_prompt":"no extra people, no unreadable gibberish, no distorted hands, no duplicated fingers, no random English text, no clutter covering the headline"}

GPT-Image-2的一个妙用形象 这个提示词是一个老哥发我的 我试了下，效果也太强了 如果放在一年前 你可能三天三夜的ComfyUI工作流 才能做出来 提示词： 请根据我上传的人像照片，做一套个人形象分析图卡，包含发型、妆容、色彩和珠宝。要求：保留五官脸型肤色，不要过度修图，所有变化在同一张脸真实展示，风格干净高级。发型：长短、卷直、刘海，对比最适合/ 普通/不建议（显脸小、显老）妆容：眉眼鼻唇分析，标签（自然、提气色、柔和）色彩：不同颜色上身，对比推荐/普通/不适合（显白、显老）珠宝：珍珠、翡翠、红蓝宝、钻石、黄金，对比推荐/普通/不建议 整体：视觉为主，文字简短，4:5比例

gpt image 2生图能力真的恐怖啊，这是我的提示词： 01 前端（用户看到的部分） 是什么：前端就是界面，是用户能看见、能点、能操作的部分。 在哪里：网页、小程序、App 的界面。 用什么做：HTML（结构）、CSS（样式）、JavaScript（交互）。 02 后端（背后处理的部分） 是什么：后端就是幕后大脑，负责逻辑和运算。 在哪里：服务器上，用户看不见。 作用： 处理登录注册 计算价格、推荐商品 接收前端请求、返回数据 常用的编程语言：Java、Python、Go、JavaScript（Node.js） 03 数据库（记忆的部分） 是什么：数据库就是用来存储和管理数据的。 存什么：账号、密码、订单、库存… 常见的数据库： MySQL、PostgreSQL（关系型，像表格一样） MongoDB（文档型，像文件夹一样） 04 SaaS（软件即服务） 是什么：SaaS = Software as a Service（软件即服务）。 核心特点： 打开网页/小程序/APP就能用 按月或按年订阅 常见形式：网站、移动 App、小程序都可以是 SaaS。 05 总结 前端：用户看到和操作的界面 后端：背后运行的逻辑和计算 数据库：存放和管理数据的地方 SaaS：把软件做成服务，用户随时通过网络使用 前端展示 → 后端处理 → 数据库存储 → SaaS 是交付方式 帮我针对上面的内容画一张易于理解的图

A bold Japanese event thumbnail poster on a light gray background in a retro arcade pop-art style. Center the composition around a huge diagonal wordmark reading “LOVART” in oversized white block letters with thick black outline, chunky 3D feel, subtle pixel-stepped inner edges, and yellow halftone shadow accents. Above it, place one line of large Japanese header text in bright yellow with black outline: “AIデザイン運用時培会”. Below the main wordmark, add a two-line Japanese subtitle in heavy white lettering with black outline and slight tilt: “最新ツール実銃 ×” on the first line and “プロの暗続力” on the second line. At the lower center, place a pixel-style black text label with a yellow drop shadow reading “speaker kats”. On the right side overlapping the main logo, add a bright yellow jagged starburst badge with thick black outline containing 3 stacked lines of black text: “5.10(sat)”, “19:00”, “START”. Decorate the layout with exactly 12 playful gaming-style accent icons and shapes scattered around the logo: 2 yellow five-point stars, 2 pairs of red cherries with green stems, 2 small yellow game controllers, 1 black circle with a yellow gamepad symbol inside, 2 solid yellow triangles, 1 yellow dotted triangle, 1 white outlined polygon, and 1 small black-and-white spiral square. Use a high-contrast palette of yellow, black, white, and light gray, with thick outlines, sticker-like layering, comic halftone dots, and crisp readable Japanese typography.

Create a dramatic Japanese YouTube thumbnail in a hyper-aggressive clickbait style, 16:9 landscape, with a dark black-and-crimson background filled with red lightning, smoky clouds, glowing sparks, ink splatter, and explosive energy. The composition has 4 main text areas and 2 graphic icon elements. Across the top, place huge distressed white Japanese headline text reading {argument name="top headline text" default="動画編集ディレクター"}, using an extra-bold block font with rough grunge texture, black outline, and heavy shadow. In the center, place the dominant oversized kanji {argument name="main title text" default="全滅"} in a massive shattered font, red at the top fading to yellow at the bottom, with cracked stone texture, black border, debris fragments, and impact glow, occupying most of the frame. At the lower center, add a black slanted banner with a white border containing bright yellow and red Japanese text reading {argument name="warning text" default="このままだと仕事がなくなる…!?"}, bold and urgent. On the left side, add a vertical black panel listing exactly 4 warning items, each preceded by a red X mark: 「案件減少」, 「単価下落」, 「AIの台頭」, 「オワコン化」. On the right side, show a cropped photo-real Japanese man from chest up, facing slightly left, wearing a black T-shirt, with short dark hair and a strong red rim light around his silhouette; his face is partially obscured by a rectangular mosaic censor block in skin-brown tones. At the lower right, include exactly 2 Adobe-style app icons, 「Pr」 and 「Ae」, dark blue-purple rounded squares, partially overlapping, both cracked like broken glass and crossed out with one large diagonal red paint slash X spanning the icons. Add a subtle dark city skyline silhouette in the lower left background. Overall look: sensational, destructive, high contrast, gritty, overloaded with texture, with intense red/black color grading, thick shadows, dramatic glow, and polished viral-thumbnail composition.

Create a bright, high-impact Japanese YouTube thumbnail about diet-friendly eating, in a clean split composition. The left half is a white background filled with oversized bold Japanese headline text stacked vertically and diagonally for maximum readability: the top line says "カツ丼" in huge vivid orange with a thick white outline and soft drop shadow, below it "食べても" in dark brown, then "太らない方法" in hot pink with a white outline and a yellow underline swoosh, and at the bottom a gigantic red-orange "5" with white outline next to "選!" in dark brown with a white outline. Add small yellow sparkle accents and comic-style emphasis marks around the headline. In the lower left corner, place a simple flat illustration of 1 smiling woman from the waist up wearing a yellow tank top, brown hair tied back in a ponytail, making an OK hand gesture, set over a pale yellow circle. The right half shows a close-up, appetizing katsudon bowl photographed in warm light: 1 ceramic bowl with blue vertical stripe patterns, filled with sliced golden-brown breaded pork cutlet over egg and onion on rice, glossy sauce, visible steam rising, and 1 small green herb leaf garnish on top. In the upper right corner, add 1 white circular badge with a dotted yellow border containing the Japanese text "おいしく楽しく♪ 賢くコントロール!" in a friendly handwritten style, with yellow accent marks around the badge. Along the entire bottom, include a pale cream horizontal information strip with 5 circular icons and 5 labels separated evenly from left to right: 1 salad bowl icon with the text "バランスの良い食事", 1 scale icon with "カロリーを意識", 1 walking person icon with "適度な運動", 1 glass of water icon with "水分をしっかり", and 1 clock icon with "食べる時間を工夫". Use a glossy commercial thumbnail aesthetic, warm food photography, thick outlined typography, cheerful health-themed colors, and strong contrast optimized for social media click-through.

Create a bold Japanese event thumbnail in a retro 8-bit video game style on a clean white background with a black, white, and vivid yellow color palette. The composition is a single highly graphic poster packed with pixel-art decorations, thick black outlines, comic halftone dots, drop shadows, and arcade-inspired stickers. In the center, place an enormous headline reading “{argument name="main title" default="LOVART"}” in oversized block letters, bright yellow with a thick black outline, white border, and heavy shadow, slightly tilted and dominating most of the image. Above it, add a jagged white banner with black outline containing the Japanese title “{argument name="top banner text" default="AIデザイン運用勉強会"}”. Below the main title, place a black ribbon with yellow and white Japanese text reading “{argument name="subheading text" default="最新ツール実践 × プロの基礎力"}”. At the lower left-center, add a large rounded rectangular date panel in yellow with black outline and white trim, including a pixel calendar icon on the left and the text “{argument name="event date" default="5.10 (sat) 19:00 START"}” in huge black retro type. At the lower right, place a black spiky label reading “speaker” above the large yellow-outlined name “{argument name="speaker name" default="kats"}”. Surround the layout with exactly 11 decorative gaming elements: 1 pixel speech burst at upper left saying “LEVEL UP!”, 1 yellow lightning bolt near the top, 1 yellow question block with a black question mark at upper right, 1 pixel sword on the right side, 1 starburst on the right saying “GAME ON!”, 1 chibi pixel character jumping on the left in a yellow jacket with raised fist, 1 small black “1UP” life icon with three yellow hearts at lower left, 1 retro game controller beneath it, 3 groups of sparkle stars scattered around the composition. Add comic accents such as dotted halftone patches, angled yellow speed lines, small checkerboard strips, and a pixel cursor pointer near the subtitle. Include a stylized anime-like speaker avatar in the lower right corner wearing a black cap and black hoodie with yellow accents, face partially obscured or simplified, integrated like a streamer or event host badge. Make all Japanese and English text crisp, readable, and accurately typeset, with the overall feeling of a high-energy YouTube thumbnail or social media event banner for a design/AI workshop.

A high-impact YouTube thumbnail about {argument name="topic text" default="HARNESS ENGINEERING"} in the AI age, 16:9 format, split-screen composition with 2 male presenters shown from the chest up, one on the left and one on the right, both facing forward in office or studio settings. The left presenter has dark hair, wears glasses and a white-and-blue striped shirt, seated in a desk chair with shelves and books blurred in the background. The right presenter has short dark hair, wears glasses and a light blue striped button-up shirt, speaking into a large black microphone, with a softly lit tech-themed background. A glowing electric-blue diagonal slash divides the two halves. In the center, overlay a futuristic circular AI icon with the letters “AI” inside a microchip-like interface, glowing neon blue. Add subtle HUD graphics on the right side: 3 upward chevrons near the top right, 1 gear icon at mid-right, and a faint grid of dots. Across the lower half, place 2 stacked headline lines in huge bold condensed uppercase text with heavy black outline, white outer stroke, and bright blue neon glow: top line smaller, white text reading {argument name="top headline" default="IMPORTANT IN THE AI ERA"}; bottom line much larger, yellow-to-gold gradient text reading {argument name="main headline" default="HARNESS ENGINEERING"}. Use dramatic contrast, cool blue color grading, glossy thumbnail polish, strong rim lighting, mild background blur, and an energetic tech-business aesthetic designed for maximum click-through rate.

A high-quality cinematic portrait in a 9:16 vertical aspect ratio showing {argument name="foreground person" default="Sam Altman"} standing in the left foreground outdoors in front of a traditional ornate dark wood Chinese-style building with intricate green lattice windows and carved architectural details. He faces the camera and wears a black zip-up jacket with a clearly visible white OpenAI logo on the chest. His arm is extended toward the viewer, holding 1 cigarette extremely close to the lens in the lower-left foreground, making the cigarette and hand large, soft, and out of focus with strong depth-of-field blur. Slightly behind him on the right stands {argument name="background person" default="Elon Musk"}, looking at the camera while holding 1 cigarette near his mouth, wearing a black T-shirt with a white xAI logo on the chest, with his other hand tucked into a pocket. Use warm golden-hour sunlight from the side, creating sharp shadows, realistic skin texture, high contrast, and a moody amber tone across the faces, clothing, and wooden facade. The composition should feel candid but polished, tightly cropped from about mid-thigh upward, with the foreground figure dominating the frame and the second figure partially overlapped behind him. Emphasize realistic photography, cinematic color grading, shallow depth of field, natural facial proportions, subtle smoke mood, and crisp branding details on the {argument name="left chest logo" default="OpenAI"} jacket and {argument name="right chest logo" default="xAI"} shirt.

A dramatic, absurdist Japanese clickbait-style poster image at sunset in the desert, with the Great Pyramid serving as a massive stone tabletop in the foreground. A messy-haired Japanese man in a dark navy kimono-like robe kneels behind a black plate of translucent squid sashimi, delicately arranging the food with chopsticks. His expression area is obscured by a rectangular blur block, while his wild windblown hair is sharply silhouetted against a glowing orange sky with low sun and scattered clouds. On the plate are neatly piled pale pink squid pieces, a large green shiso leaf, and a small yellow garnish flower. To the right sits a wooden compartment tray with condiments and small dishes. On the left edge of the pyramid surface, show 1 giant human thumbnail standing upright like a monument, and in front of it 1 tiny orchestra of about 10 formally dressed musicians with string instruments and a conductor, staged as if performing on the stone. The visual joke is that the man was supposedly going to conduct an orchestra inside a thumbnail, but is instead decorating salted squid on top of a pyramid. Use hyper-detailed photoreal compositing, exaggerated scale contrast, cinematic sunset rim light, gritty texture, high contrast, and surreal humor. Add large Japanese headline text integrated into the composition in bold, comic YouTube-thumbnail style with thick black outlines, yellow and white lettering, red paint-brush accents, black ink splatter behind the top headline, and a huge red shout at the bottom. Include exactly 6 text blocks: top-left large yellow text "明日も親指の爪の中でオーケストラ指揮しなきゃ!", below it on a red brushstroke "と思ったら", middle-lower large white and yellow text "ピラミッドの頂上でイカの塩辛をデコレーションしてました〜。", bottom very large red text "チクショー!!", and bottom-right yellow hashtag text "#まいにちチクショー". Compose it like an over-the-top viral Japanese meme thumbnail, vertically framed, dense and attention-grabbing.

A vertical 9:16 TikTok-style GRWM beauty thumbnail set in a warm, sunlit Mediterranean-inspired bedroom. A stylish young woman with {argument name="hair color" default="dark brown"} hair in a messy curly updo sits at a marble vanity, leaning forward with one arm folded and the other hand applying lip balm or lipstick to her mouth. Her face is covered by a centered rectangular blur block for privacy, but the rest of her styling is elegant and natural: tan glowing skin, delicate gold necklace with a small round pendant, thin gold bracelet, stacked gold rings, and a white lace camisole with thin straps. In the foreground on the vanity are exactly 7 visible beauty objects: 1 round tabletop vanity mirror on the left, 1 cup holding 5 makeup brushes, 1 clear glass dropper bottle, 1 tall white pump skincare bottle, 1 small black dropper bottle, 1 beige rounded cosmetic sponge or puff, and 1 pale green squeeze tube on the right. The background shows a softly blurred cozy bedroom with 1 arched window on the left, 1 leafy potted plant, 1 bed with white bedding and a mustard accent pillow, exposed wooden ceiling detail, and 1 framed landscape painting on the wall. Use golden-hour sunlight streaming from the left, soft shadows, creamy skin tones, shallow depth of field, luxury lifestyle editorial photography, intimate self-care mood, polished but natural composition. Add bold playful Spanish headline text in the upper left in three stacked lines reading {argument name="headline text" default="Mi rutina de belleza matutina"}, with each line large and rounded, white outline and soft drop shadow, using pastel colors: first line white, second line pink, third line pale yellow. Add 3 pink doodle accent strokes above the headline, 1 curved pink underline-swoosh beneath it, and 1 small yellow sun icon to the right of the last line. Place a clean white {argument name="brand text" default="Pollo.ai"} logo in the upper right. High-end influencer thumbnail aesthetic, crisp product focus in foreground, warm inviting lifestyle scene.

Create a highly realistic image of a handwritten letter containing a ({argument name="message" default="message or reflection carrying meanings of affection and loyalty to my account followers"}) on lined paper, with very touching words written in liquid ink pen

Create a hyper-detailed comedic Japanese arcade fighting game screenshot styled like a versus battle scene, using a real-world photo aesthetic with game UI overlaid on top. The scene shows an intense mock battle between two groups of theme-park fans competing for the front row at an outdoor show plaza in Tokyo DisneySea. Use a wide 16:9 composition. In the background, clearly show Mediterranean Harbor and Mount Prometheus under bright daytime skies, with the waterfront and DisneySea architecture visible. In the foreground, show exactly 10 young adult people in winter casual clothing, split into 2 opposing teams of 5, physically leaning, grabbing, reaching, and shoving in a tug-of-war-like scrum over position, with exaggerated competitive body language and frozen action as if in a fighting game. Faces should be anonymized with soft blurred blocks. Add floating character labels above each person with levels and names in Japanese. The overall tone is absurdly realistic, like a real candid photo transformed into a polished arcade game battle screen.

Add a full Japanese fighting-game HUD with glossy blue-versus-red interface styling. At the very top, place a center stage title bar reading "東京ディズニーシー ミッキー広場 ショー最前列バトル" and a large timer in the middle reading "TIME 89". In the top left, add a blue team header "PLAYER1" and team name "最前列ガチ勢A". In the top right, add a red team header "RIVAL" and team name "ライバルグループB". On the left side, stack exactly 5 blue player status panels with portraits, level, Japanese class-like nicknames, HP, SP, and BURST meters. The 5 left-side labels are: "Lv.25 ガチ勢リーダー ユウキ", "Lv.24 筋肉マン タケシ", "Lv.23 眼鏡オタク シンジ", "Lv.23 開角心MAX ケント", "Lv.22 サポート要員 リョウ". On the right side, stack exactly 5 red rival status panels with the labels: "Lv.27 ライバルリーダー ダイキ", "Lv.26 パワフル代表 マサル", "Lv.24 戦略家 コウジ", "Lv.23 熱血漢 リク", "Lv.22 サポート女子 サキ". Each panel should include numeric HP and SP values and segmented BURST gauges, styled like a Japanese arcade RPG-fighter interface.

Place exactly 10 in-battle nameplates above the fighters in the center scene, color-coded blue for the left team and red for the right team. The 10 labels are: "Lv.24 タケシ", "Lv.25 ユウキ", "Lv.23 シンジ", "Lv.23 ケント", "Lv.22 リョウ", "Lv.27 ダイキ", "Lv.26 マサル", "Lv.23 リク", "Lv.22 サキ", "Lv.22 ミサキ".

At the lower left, add a skill menu titled "スキル" listing exactly 5 skills with SP costs: "ダッシュ突撃 SP 20", "肩押し強奪 SP 25", "荷物で場所確保 SP 15", "ロープくぐり SP 10", "本気の根性 SP 50". Beneath that, add a dark description box explaining the highlighted skill "本気の根性" with the Japanese text: "気合で相手を威圧し、どかす! 一定時間、相手が怯みやすくなる! (バーストゲージを大きく消費する) 効果時間:10秒".

At the bottom center, add an item menu titled "アイテム" with exactly 5 item slots showing icons and counts: a water bottle "x3", a folded purple towel "x2", a blue drawstring bag "x1", a gray backpack "x1", and a boxed meal "x2". At the lower right, add a quest panel titled "クエスト" with the mission text "ショー開始までに最前列を死守しろ!" and condition text "条件:ライバルグループを全員後ろに押し戻せ!" and countdown text "ショー開始まで:02:30". Beside it, add a mini-map titled "ミッキー広場MAP" showing red and blue dots for both teams in the plaza. Along the very bottom edge, include small controller prompts in Japanese for actions such as skill use, item use, grab/push, and dash.

Use dramatic, saturated lighting, crisp detail, realistic clothing folds, authentic plaza stone pavement, and a high-end Japanese game screenshot look. The image should feel like a ridiculous but believable crossover between a real Tokyo DisneySea crowd photo and a competitive arcade battle game interface.

A dreamy surreal portrait of a {argument name="subject" default="young woman"} standing underwater or in a liquid-like ethereal space, shown from about mid-thigh up, wearing a flowing sleeveless white dress that appears to dissolve into translucent water and shimmering fragments. Her long {argument name="hair color" default="dark brown"} hair streams dramatically sideways as if suspended in water, and her face is intentionally obscured by a soft vertical blur block for anonymity. Surround her with an exact count of about 30 small translucent fish, some striped and some pale silvery white, swimming in multiple depths of field across the foreground, midground, and background, with several fish passing in front of her body and hair to create strong motion and depth. Use a soft pastel {argument name="background color" default="powder blue"} background with faint handwritten script texture layered across it, plus whimsical doodles scattered throughout: white and pale pink hearts, stars, curved squiggles, wave lines, dots, sparkles, and 2 smiley faces. Add prismatic rainbow refractions, glossy caustic highlights, and subtle lens-like chromatic shimmer on the fish and dress. The mood should feel delicate, introspective, airy, and magical, with high-key lighting, gentle contrast, soft focus in the foreground, and crisp detail on the torso and hair. Compose the figure slightly off-center with one arm relaxed downward and the body turned lightly in motion, as if drifting peacefully through a school of fish. Include tiny elegant footer text in white near the bottom edge, with a left signature, a centered website URL, and a small right credit mark, resembling an art-poster or social-media showcase image.

{
  "type": "2x2 grid of Japanese digital advertisement banners",
  "layout": {
    "structure": "4 equal quadrants",
    "quadrants": [
      {
        "position": "top-left",
        "theme": "Travel",
        "subject": "A couple holding hands on a white sand beach, looking out at turquoise ocean water under a bright blue sky.",
        "elements": ["red hibiscus flower in bottom left corner"],
        "text_labels": [
          "今年こそ、解き放て。",
          "{argument name=\"travel destination\" default=\"沖縄旅行\"}",
          "3日間の癒やし旅",
          "航空券+ホテル",
          "39,800円〜",
          "絶景、グルメ、体験 ぜんぶ叶う!"
        ],
        "icons": {
          "count": 3,
          "descriptions": ["airplane", "hotel building", "car"]
        }
      },
      {
        "position": "top-right",
        "theme": "Skincare",
        "subject": "Close-up portrait of a young woman with glowing, dewy skin, eyes closed, gently touching her cheeks.",
        "elements": [
          "soft pink gradient background",
          "dynamic water splash effects",
          "pink cosmetic jar labeled '{argument name=\"skincare product name\" default=\"LUMIÈRE\"} Brightening Gel'"
        ],
        "text_labels": [
          "毛穴・くすみ卒業!",
          "透明感あふれる",
          "水光肌へ",
          "新感覚スキンケア",
          "初回限定 78%OFF",
          "{argument name=\"discount price\" default=\"1,980円\"}"
        ],
        "badges": {
          "count": 3,
          "style": "gold circular",
          "labels": ["毛穴ケア", "高保湿", "ハリ・ツヤ"]
        }
      },
      {
        "position": "bottom-left",
        "theme": "Gourmet Food",
        "subject": "Thick, sliced, medium-rare steak sizzling on a dark grill plate.",
        "elements": [
          "garlic chips",
          "rosemary sprig",
          "dark background with smoke and glowing embers"
        ],
        "text_labels": [
          "とろける旨さ!",
          "{argument name=\"food item\" default=\"黒毛和牛\"}",
          "贅沢ステーキ",
          "期間限定",
          "特別価格",
          "通常価格 8,980円",
          "4,980円"
        ],
        "badges": {
          "count": 1,
          "style": "red circular",
          "labels": ["A4 A5等級"]
        }
      },
      {
        "position": "bottom-right",
        "theme": "Online Education",
        "subject": "Young man in a blue shirt studying at a desk, writing in a notebook next to an open laptop.",
        "elements": ["bright indoor lighting", "desk environment"],
        "text_labels": [
          "スキマ時間で",
          "{argument name=\"education goal\" default=\"最短合格!\"}",
          "オンライン資格講座",
          "スマホで完結",
          "効率学習で差がつく!",
          "今だけ! 受講料 20%OFF"
        ],
        "badges": {
          "count": 1,
          "style": "blue circular",
          "labels": ["受講者数 10万人 突破!"]
        },
        "icons": {
          "count": 2,
          "descriptions": ["smartphone", "open book"]
        }
      }
    ]
  }
}

Based on the shape of the {argument name="subject" default="clouds"} in the image, identify what object, animal, or person they most resemble. Do not change the original image; instead, draw that object, animal, or person over the original image in a {argument name="art style" default="doodle"} style.

A vibrant pixel-art style mosaic of a tropical parrot perched on a small brown branch in the middle of dense rainforest foliage. The entire image is rendered as a tight grid of tiny square tiles with visible black outlines, creating a stained-glass or LED-screen effect. The bird is shown in side profile facing right, with a large curved black beak, a pale cream face, a bright red-orange forehead and throat, vivid green upper body, and long wings and tail in saturated blue and cyan. The surrounding jungle is filled edge to edge with layered green leaves in many shades, with a soft light green glow behind the parrot to separate it from the background. High color contrast, rich tropical palette, crisp tile pattern, centered composition, decorative digital mosaic aesthetic.

A cinematic photorealistic action scene in a rainy downtown city street canyon, showing {argument name="main subject" default="a dark-haired man in his 30s"} sprinting directly toward the camera in the center foreground with a tense survival expression, wearing a soaked dark jacket, dark shirt, and dark pants, mid-stride with one arm pumping forward. Behind him, a massive urban explosion tears through the street and lower facade of a high-rise building, sending a huge cloud of smoke, fire, dust, shattered concrete, glass, and metal debris outward in all directions. The scene includes exactly 3 visible damaged vehicles: 1 dark sedan in the left foreground with headlights on and a crumpled hood splashing through rainwater, 1 wrecked dark car in the right midground with severe front-end damage, and 1 overturned or airborne black SUV tilted upward behind it on the right side. Wet asphalt reflects headlights, firelight, and gray skyscrapers. Dense debris fills the air, with chunks of rubble frozen in motion. Overcast stormy daylight, desaturated blue-gray color palette with orange fire accents, dramatic motion blur in flying debris but sharp focus on the running figure, low-angle wide-lens composition, blockbuster disaster-movie realism, ultra-detailed textures, high contrast, dynamic depth, volumetric smoke, rain spray, cinematic lighting. Add a white {argument name="watermark text" default="Pollo.ai"} logo in the top-right corner.

{argument name="celebrity" default="selena gomez"} started a surprise {argument name="platform" default="youtube"} livestream.

A stylish young woman with {argument name="hair style" default="long wavy blonde hair"}, defined cheekbones, and a confident expression, wearing black sunglasses and a {argument name="clothing" default="thick white puffer jacket"} over a fitted black top, standing confidently in front of a {argument name="car" default="vibrant hot-pink Ford Mustang"}. She is posing with one hand slightly raised near her chest, exuding effortless attitude and elegance. The car is parked on a scenic coastal road lined with blooming pink cherry blossom trees and tall palm trees. Behind them is a calm sea under a dramatic overcast sky with soft clouds. Pink petals are scattered on the wet asphalt. A wooden bench is visible on the left side near the water. Cinematic lighting, photorealistic, ultra-detailed skin texture, natural lighting reflections, Instagram-style luxury lifestyle shot, vibrant colors, moody atmosphere, 8k resolution --ar 9:16 --stylize 250

Create a {argument name="grid layout" default="4x3"} borderless grid where each panel is an independent image of the {argument name="subject" default="a young woman"}. Maintain strong subject consistency across all panels, with consistent color and lighting. Depict {argument name="theme" default="childhood memories"} with a {argument name="mood" default="warm, nostalgic"} mood in {argument name="style" default="nostalgic cinematic realism"} style. No text. No gap.

{"type":"cinematic sci-fi storyboard contact sheet","subject":{"primary":"a small futuristic spacecraft descending into a massive gas giant storm system","secondary":"an enormous leviathan-like silhouette hidden within the clouds","mood":"oppressive, catastrophic, awe-struck, high tension, cosmic dread","style":"photorealistic cinematic concept art with dark sci-fi realism, volumetric storm clouds, strong contrast, amber and black palette with occasional cold blue lightning","aspect_ratio":"16:9"},"vehicle":{"design":"compact armored deep-atmosphere ship with 3 bright rear engines, angular industrial hull, worn metallic panels","scale":"tiny compared to the planet and creature"},"layout":{"grid":{"rows":3,"columns":4,"count":12},"sections":[{"position":"row 1 col 1","description":"wide exterior shot of the ship entering the upper atmosphere of a colossal gas giant at extreme speed, glowing clouds streaked with fire and friction around the vessel, curved planetary horizon visible"},{"position":"row 1 col 2","description":"cockpit POV, dark interior filled with red and cyan holographic instruments, forward visibility collapsing into turbulent storm layers and electrical haze"},{"position":"row 1 col 3","description":"exterior mid-wide shot of the ship diving into a gigantic rotating cloud funnel, surrounded by violent spiraling storm structure"},{"position":"row 1 col 4","description":"extreme close exterior of the ship hull as bright lightning strikes dangerously close, white electric energy crawling across the metal surface"},{"position":"row 2 col 1","description":"dashboard warning screen in red, showing a critical systems failure interface with the exact visible text count of 4 warning lines and 1 large percentage readout: ['WARNING','ENGINES COMPROMISED','THRUST FLUCTUATION','GRAVITY SPIKE DETECTED','DESCENT RATE -453%']"},{"position":"row 2 col 2","description":"rear three-quarter exterior of the ship fighting turbulence inside dense storm clouds, engines burning hard while the craft barely holds course"},{"position":"row 2 col 3","description":"massive circular disturbance forming in the clouds like an eye or maw, entire storm systems displaced by something huge moving beneath"},{"position":"row 2 col 4","description":"second cockpit view with radar-like navigation display and red alert text, pilot making a blind evasive maneuver through lightning-filled darkness"},{"position":"row 3 col 1","description":"first reveal of the colossal creature shape rising near the ship, black organic surface and immense curved anatomy emerging from darkness, ship tiny at lower left"},{"position":"row 3 col 2","description":"spiral descent shot, ship caught inside a vortex tunnel of clouds, spinning downward with engines flaring as it struggles to recover"},{"position":"row 3 col 3","description":"sudden breakthrough into a calm void, minimal composition, ship flying in eerie silence through dark open space with soft mist and no visible storm around it"},{"position":"row 3 col 4","description":"final reveal, gigantic leviathan fully emerging behind or beside the ship in cleared space, backlit by a pale circular storm opening, enormous open maw-like silhouette dwarfing the craft"}],"continuity":"all 12 panels depict one continuous descent sequence from atmospheric entry to final creature reveal"},"lighting":{"primary":"glowing amber storm light","secondary":"red cockpit interface glow","accents":"blue-white lightning and engine exhaust"},"environment":{"location":"inside the upper and middle storm layers of a gigantic gas giant","weather":"violent turbulence, electrical storms, vortex funnels, cloud walls, pressure chaos","threat":"no safe zone, repeated near-failure, unknown colossal presence driving the storm"}}

Vertical 2:3 format. {argument name="subject" default="Young woman"} hair in messy updo sits on modern wooden staircase. wears {argument name="dress" default="shimmering Silver halter dress sequin dress"}. matching with silver high-heeled sandals. legs crossed. Silver heart earrings. One fuchsia bracelet on each ankle. Sultry expression, with slightly parted lips. Blurred background vertical wooden slats and black metal railings. Don't change face

Create a dramatic Japanese YouTube thumbnail in a futuristic neon cyberpunk style, 16:9 landscape. Use a dark tech-city background with faint skyscrapers, digital grid lines, glowing particles, and high-contrast blue, pink, and gold lighting. In the exact center, place a young woman from the waist up with long straight pastel blue hair, wearing a plain white short-sleeve T-shirt and a light pink skirt, posing thoughtfully with one hand near her chin and the other arm folded; anonymize her face with a soft rectangular blur. Across the very top, add huge distressed bold white Japanese headline text reading 主導権が揺れた, and directly below it add large bold yellow text reading {argument name="subheadline text" default="Nano Bananaから"}. On the left side, create a glowing blue hexagonal-framed panel titled Nano Banana with a smaller subtitle 画像生成. Inside that panel, include exactly 4 image tiles in a 2x2 grid: 1) a fantasy floating island landscape at sunset, 2) a sunlit forest path with tall trees, 3) a neon futuristic city street at night, 4) an outer-space planet scene with stars and a spacecraft. Beneath the left panel, add a blue glowing ribbon label reading かつては優位だった. On the right side, create a glowing magenta hexagonal-framed panel titled {argument name="right panel title" default="GPT Image 2"} with a smaller subtitle 実務で使える出力へ. Inside it, include exactly 4 example thumbnail cards in a 2x2 grid, each featuring the same blue-haired woman with a blurred face and bold Japanese text. The 4 card labels above the tiles are: サムネイル画像, 記事のアイキャッチ画像, LPのセクション画像, SNS投稿画像. The large text inside the 4 cards should read respectively: 1) AIで変わるクリエイティブの未来, 2) AI時代のクリエイティブ戦略 成功する企業の条件, 3) AIで加速するビジネス成長, 4) 未来をつくるのは AI×あなたのアイデア. Between the left and right panels, place a bright glowing gold arrow pointing from left to right with spark-like particle trails, indicating transition or superiority shift. Along the bottom, add a very large black banner with a glowing gold border and massive bold gold text reading {argument name="bottom banner text" default="GPT Image 2へ"}. Overall composition should feel like a comparison graphic showing a shift from older image generation to more practical commercial output, with aggressive thumbnail typography, strong glow effects, metallic texture on major text, and polished social-media marketing visuals.

{
  "type": "18-panel brand identity and character design document",
  "brand": {
    "name": "{argument name=\"brand name\" default=\"沐阳 MUYANG TEA\"}",
    "industry": "{argument name=\"industry\" default=\"tea shop\"}",
    "colors": ["{argument name=\"primary color\" default=\"yellow\"}", "{argument name=\"secondary color\" default=\"green\"}", "white", "brown", "dark green"]
  },
  "subject": "{argument name=\"character description\" default=\"3D rendered cute Shiba Inu mascot wearing a green apron\"}",
  "layout": {
    "grid": "3 columns by 6 rows",
    "sections": [
      {
        "title": "01 品牌DNA分析 / BRAND DNA ANALYSIS",
        "elements": ["logo", "5 color swatches", "6 icons", "target audience charts"]
      },
      {
        "title": "02 概念构思 / CONCEPT MOODBOARD",
        "elements": ["5 photo references", "4 mood icons", "design equation"]
      },
      {
        "title": "03 形态研究 / FORM STUDY",
        "elements": ["4 logo anatomy icons", "4 evolution steps", "4 silhouettes"]
      },
      {
        "title": "04 概念探索 / CONCEPT EXPLORATION",
        "elements": ["12 line-art character sketches"]
      },
      {
        "title": "05 精细线稿 / REFINED LINE ART",
        "elements": ["3 rows of front and side line art with proportion guides"]
      },
      {
        "title": "06 细节精修 / DETAIL REFINEMENT",
        "elements": ["2 full-body renders with labels", "4 circular close-ups"]
      },
      {
        "title": "07 表情设定 / EXPRESSION SHEET",
        "elements": ["11 3D rendered head expressions"]
      },
      {
        "title": "08 姿势库 / POSE LIBRARY",
        "elements": ["9 full-body 3D rendered poses"]
      },
      {
        "title": "09 转身视图 / TURNAROUND VIEW",
        "elements": ["5 full-body 3D renders", "5 matching line-art views"]
      },
      {
        "title": "10 色彩开发 / COLOR DEVELOPMENT",
        "elements": ["5 rows of 5-color palettes", "color psychology text"]
      },
      {
        "title": "11 材质规格 / MATERIAL SPECIFICATION",
        "elements": ["5 texture swatches", "property sliders", "4 manufacturing icons"]
      },
      {
        "title": "12 色彩应用 / COLOR APPLICATION",
        "elements": ["4 color variant renders", "2 light/dark renders", "4 contrast rating circles"]
      },
      {
        "title": "13 构造指南 / CONSTRUCTION GUIDE",
        "elements": ["2 line-art diagrams for geometry and grid"]
      },
      {
        "title": "14 设计系统规则 / DESIGN SYSTEM RULES",
        "elements": ["minimum size icons", "clear space diagram", "4 usage examples"]
      },
      {
        "title": "15 资产变体 / ASSET VARIANTS",
        "elements": ["3 size variants", "3 line-art variants", "3 simplified flat heads"]
      },
      {
        "title": "16 数字应用 / DIGITAL APPLICATIONS",
        "elements": ["1 app icon", "2 social avatars", "UI elements", "3-step animation cycle"]
      },
      {
        "title": "17 实物应用 / PHYSICAL APPLICATIONS",
        "elements": ["plush toy mockup", "packaging mockup", "merchandise mockup", "storefront mockup"]
      },
      {
        "title": "18 最终主视觉 / FINAL RENDERING",
        "elements": ["large high-res 3D render of mascot holding tea", "logo", "file format list"]
      }
    ]
  }
}

A dramatic anime-style cyberpunk witch standing on a dark rooftop high above a dense futuristic city at night, viewed from a slightly elevated angle. The main subject is a petite young witch girl with pale skin, short icy blue bobbed hair, pointed elf-like ears, and glowing red eyes, wearing a sly confident smile. She raises a black wand overhead in her right hand, with a dangling orb charm at the tip glowing faintly purple and red. Her oversized crooked witch hat is black with purple lining and covered in stitched patches, warning labels, straps, and white graphics including a large “404” and a skull emblem. She wears a black and purple techwear outfit: oversized hooded jacket with many straps and tags, black crop top with “404” on the chest, layered belts, short bottoms, fishnet on one leg, black lace-up combat boots, chokers, and metallic accessories. Several hanging straps and tags visibly read words like “WITCH 404,” “404,” and glitch-themed markings. Beneath and beside her, a large glowing violet magic circle mixed with hacker interface aesthetics is projected on the rooftop floor, filled with occult rings, sigils, a central skull symbol, and scattered neon system text such as error-code fragments, creating a fusion of sorcery and digital corruption. Emerging from the circle is 1 large armored summoned figure: a black futuristic demon-knight or robotic familiar with jagged reflective armor, a narrow purple-lit visor, and a heavy weapon held in one hand, partially dissolving into purple energy shards and smoke. The background shows a sprawling rainy megacity of apartment towers and industrial rooftops, packed with windows, balconies, cables, signs, and haze. On a nearby building wall is a giant vertical graffiti-style sign with 3 readable elements: “404”, “Witch”, and “ERROR NOT FOUND”, plus a smaller “E404”. Additional purple neon glitch text and symbols are scattered across rooftops and in the air. Use a dark palette of black, indigo, and deep violet with sharp magenta-purple highlights, cinematic contrast, reflective wet surfaces, dense detail, and a high-end polished illustration style. The mood is occult, edgy, stylish, and dangerous, combining urban fantasy, hacker aesthetics, and magical summoning.

Create a flashy Japanese YouTube thumbnail in a dark futuristic cyber-tech style, 16:9 landscape composition, with a deep navy-to-black background filled with glowing blue circuit-board patterns, connected network nodes, tiny digital squares, and electric energy lines. At the top center, place a small white Japanese headline reading {argument name="headline text" default="センスに頼らないAI時代の新常識"}. In the center, add a massive 2-line Japanese title in metallic silver-white beveled lettering with intense neon-blue outer glow, electric lightning cracking behind and through the letters, reading {argument name="main title" default="AIツール 完全攻略"}. Beneath the main title, place one black horizontal banner with thin gold trim and white serif Japanese text reading {argument name="subheadline text" default="Claude Code 解説LIVE 本日21:00〜"}. On the right side, include 1 cute chibi sheep mascot standing on a glowing blue circular platform, with fluffy light blue and lavender fur, small horns, simple dot eyes, a neutral expression, outlined in purple-blue light, holding a short stick, and surrounded by a red-orange flame aura behind its body. Along the bottom, place 3 glowing futuristic rounded rectangular panels with blue neon borders and dark interiors, evenly spaced left to right. The left panel contains 1 white head-with-circuit icon and the Japanese text {argument name="bottom left label" default="AI生成から次へ進化"}. The center panel contains 1 white upward-trend chart icon and the text "AIでブランディング". The right panel contains 1 white group-and-gear icon and the text "人もAIも動かす戦略". Use extremely high contrast, glossy metallic text effects, layered blue rim lighting, energetic lightning, subtle lens glows, and a premium high-impact webinar thumbnail aesthetic.

Create a flashy Japanese YouTube thumbnail in a luxurious black-and-gold money-making style, packed with dramatic visual impact and designed to feel viral, celebratory, and high-value. Use a dark black background filled with intense golden light bursts, glitter particles, sparkles, lens flares, and streaking fireworks radiating outward from the center. Scatter shiny gold confetti across the whole frame. Place piles and angled stacks of Japanese yen banknotes in the lower left and lower right background, partially visible and glowing under the gold lighting. In the center, feature huge embossed metallic gold Japanese typography with thick beveled 3D edges, strong highlights, black shadowing, and a premium foil texture. The top headline should read "フォロワー100人未満でも" in bold white Japanese text with a dark outline, centered near the top. The main central text should read "画像生成で" on the upper middle line and "月100万" on the largest line below, both in giant gold 3D serif-style Japanese characters, with "100" especially dominant and oversized. Beneath that, add a wide black banner with gold trim and elegant ornamental corners, containing the subtitle text "0からの実績を完全公開・再現可能メソッド" in white Japanese characters, with "完全公開" highlighted in gold. Along the bottom, place exactly 3 horizontally aligned black-and-gold rounded rectangular callout panels with ornate gold borders and subtle glow. The left panel contains a gold upward-trending chart icon and the text "実績スクショ公開". The center panel contains a gold map pin icon and the text "0→100ロードマップ". The right panel contains a gold rocket icon and the text "今すぐ始める方法". Add small laurel or decorative gold flourishes around these bottom panels. On the right side of the composition, place a cute chibi sheep mascot with fluffy light blue wool, cream-colored horns and ears, a simple neutral face, and a small body, holding an open red book labeled "BOOK". The mascot should overlap the right side of the main text area slightly and be outlined clearly so it stands out from the glittering background. Overall composition should be extremely high contrast, richly saturated gold, glossy, crowded, and optimized as a bold social media thumbnail that instantly communicates wealth, success, and AI image-generation income.

{argument name="aspect ratio" default="16:9 landscape"}. {argument name="model" default="A model girl"} is being asked by an entertainment reporter about {argument name="interview topic" default="a romantic relationship with another male celebrity"}. During a TV interview, a caption saying "{argument name="caption" default="It's a secret❤"}" is added to the screen. The screen is a talk show layout with a picture-in-picture window in the bottom left and a time display in the top right. Configure the screen with captions like 'Breaking News' or 'Exclusive Interview'. The model girl says, 'It's a secret❤' with an appropriate pose, putting a forefinger to her mouth and winking with one eye.

{"type":"Japanese YouTube thumbnail","style":"high-impact flashy growth-marketing thumbnail, dramatic, glossy, fiery, attention-grabbing","canvas":{"aspect_ratio":"16:9","background":"black with orange fire sparks, glowing particles, light streaks, and lens flare"},"headline":{"top_text":"{argument name=\"headline text\" default=\"最短ルートで到達する方法\"}","main_text":["0から","1万人","伸ばす法則"],"sub_text":"やりがちなNG行動も完全解説","main_text_style":{"font":"extra bold Japanese display font","colors":["white","glowing orange-gold"],"effects":"thick black shadow, strong outer glow, metallic heat texture on the orange text, slight distress texture on the white text"}},"graphics":{"count":6,"items":[{"type":"giant upward arrow","position":"top-right sweeping diagonally upward","color":"bright orange-gold","effect":"intense glow, spark trail"},{"type":"bar chart","position":"right side behind character","count":4,"labels":["5,000","7,000","10,000",""],"color":"orange-gold glow"},{"type":"lens flare starburst","position":"top-left","color":"golden orange"},{"type":"diagonal energy streak","position":"bottom-left to center","color":"orange"},{"type":"small spark particles","position":"across entire background","color":"orange and gold"},{"type":"small star icon","position":"above character head","color":"yellow glow"}]},"character":{"count":1,"subject":"cute mascot sheep avatar","position":"bottom-right","appearance":{"body_color":"light blue fluffy wool","face":"cream white","outline":"dark brown line art","expression":"calm closed-eye smile","accessories":"holding a yellow pointer stick in the right hoof"}},"bottom_panels":{"count":3,"style":"black rounded rectangular boxes with bright orange glowing borders","items":[{"icon":"group of people","text":"伸びるアカウントの共通点","position":"bottom-left"},{"icon":"target with arrow","text":"0フォロワー期の戦略","position":"bottom-center"},{"icon":"rising bar chart with arrow","text":"アルゴリズム攻略法","position":"bottom-right"}]},"color_palette":{"primary":["black","white","orange","gold"],"accent":["yellow","light blue"]},"composition":"oversized central typography dominates the frame, with the largest emphasis on 1万人 and 伸ばす法則, supporting mascot on the right, and three informational callout boxes aligned along the bottom, all designed to look like a viral Japanese social media or YouTube growth tutorial thumbnail","quality":"ultra sharp, high contrast, polished thumbnail design, cinematic glow effects"}

A cinematic wide shot of a lone astronaut standing on a rocky ledge and facing away from the camera, looking out across an immense red desert plain on a Mars-like planet. The astronaut is centered in the lower middle of the frame, wearing a realistic white EVA spacesuit with subtle gray panels, a life-support backpack, heavy boots, and dark gloves; the helmet is not visible from the front because the figure is seen from behind. The landscape is vast and barren, covered in rust-red dust, scattered stones, and low rock formations, with a rugged cliff edge on the left foreground, sparse rocky mounds across the middle distance, and hazy mountain ranges stretching along the far horizon. Use soft warm peach and terracotta tones, thin atmospheric haze, and gentle late-afternoon light that casts a long shadow behind the astronaut’s feet. The mood is solitary, awe-filled, and exploratory, like the opening frame of a sci-fi film about first contact with an alien world. Photorealistic, high detail, ultra-wide composition, natural cinematic color grading, epic scale, minimalism, no buildings, no vehicles, no text, no HUD, no other people.

横長のパワポ画像ここで生成してみて　どのモデル使ってるか判定するから、今のAIゲーム開発の概要をまとめた1枚パワポで　日本語で

ゲーム開発の技術に関して、工数ベースでどこにパワーかかるかの分析資料といかに量産が大事かについての説明とかのパワポ画も作って

9:16 的图片比例,生成一张抖音直播的截图,里面是 刘亦菲 在直播,刘亦菲 手里拿着牌子,牌子里写着 今晚直播,欢迎来参亦菲畅聊!

9:16 aspect ratio, generate a screenshot of a Douyin live stream, inside is Liu Yifei live streaming, Liu Yifei is holding a sign in her hand, the sign says Tonight's live stream, welcome to join Yifei for a chat!

Amateur photo of an open notebook lying flat, filled with handwritten notes in black ballpoint pen. The handwriting is casual and slightly messy, like personnal notes, natural imperfections, crossed out words, underlined headings. Shot from slightly above, natural daylight from a window, no flash. Casual desk setting, shot on iPhone

"Song Dynasty People's Moments"/"SONG DYNASTY SOCIAL MEDIA FEED", Ancient and modern time-travel humor fusion interface design style, The image simulates a mobile phone social media interface, but the content is entirely Song Dynasty scenes, The avatar is a portrait of a Song Dynasty literati, Username "Su Dongpo SuShi_Official", Post content "Just arrived in Huangzhou, demoted but feeling okay. Made Dongpo pork myself today, tastes amazing, recipe attached:", The attached image is a close-up of Dongpo pork in Gongbi painting style, Likes list "Huang Tingjian, Qin Guan, Fo Yin etc. 126 people", Comments section "Wang Anshi: Hehe" "Sima Guang: Still the same taste", Interface elements such as the like icon are replaced with Song Dynasty patterns, The status bar shows "Great Song Mobile 5G" and "Third Year of Yuanfeng", The color scheme is mobile phone dark mode paired with elegant Song Dynasty tones, A masterpiece of fun collision between history and social media

用这种风格帮我生成一套UI设计系统，包含网页、移动端、卡片、控件、按钮以及其它。把这套视觉风格作为参考生成网页。我尝试了宇宙、飞行、蝴蝶主题。

1、生成视频号内容截图，主题：中老年不要盲目催婚，iPhone尺寸
2、生成抖音内容截图，主题：跟上AI浪潮9.9包教会，iPhone尺寸
3、生成小红书内容截图，主题：精致女孩背后都有网贷，iPhone尺寸
4、生成快手内容截图：主题：直播离婚预告，iPhone尺寸

生成一张【字体】书法临摹字帖

Amateur iPhone photo at Apple Park during the iPhone 20 keynote, Tim Cook presenting on stage. Shot from the crowd at a distance

用这种风格帮我生成一套UI设计系统，包含网页、移动端、卡片、控件、按钮 以及其它

GPT-image-2でこの手相を診断して詳細な鑑定書を作って
生命線・知能線・感情線・運命線・太陽線・財運線・結婚線を、線の形状・濃淡・枝分かれ・起点終点まで分析すること。
助言を重点的に高品質な占い鑑定書にまとめること。

日本のソシャゲのガチャ画面を生成して、

1、生成特朗普和金正恩在抖音直播间打PK的截图  
2、生成不知火舞的小红书主页截图  
3、生成图片: 手写在教室黑板上的出师表全文,真实感的粉笔字迹,晴朗白天用iPhone手机实拍  
4、生成图片: T-800机器人的淘宝商品详情页,展示: 机器人的正面侧面背面三视图, 产品价格, 产品细节, 功能和使用场景等

用未来都市风格生成UI设计系统,灵感来自赛博朋克城市夜景,包含霓虹灯、玻璃建筑反射、高对比光影,配色以紫色、蓝色、粉色霓虹为主,设计网页Dashboard、移动端界面、卡片、按钮、控件等,视觉炫酷、层次丰富、科技感极强

A 9:16 vertical version, high-detail realistic style Chinese TikTok live screenshot, Elon Musk is talking to the mobile phone camera in the live broadcast room, excited, smiling, and the live atmosphere is warm and real. He held a white handwritten sign in one hand, which clearly said: "Thank you Shinning". There are obvious Chinese TikTok interface elements in the live broadcast screen, including likes, comments and share icons arranged vertically on the right, scrolling Chinese bullet screens and interactive comments below, and the "live broadcast" logo at the top, which looks like a real mobile phone screenshot. There is an eye-catching gift prompt special effect in the screen: "Shinning sent TikTok No. 1", with gift animation light effect and platform-style prompt box. Musk is in a professional live broadcast environment, with a mobile phone holder, a ring fill light and a desktop microphone in front of him. The background is a modern technology live broadcast room with bright lights and a slight neon atmosphere. The composition is real and natural, like the ongoing live screenshot of the Chinese short video platform. The interface information is rich but not messy, the characters are clear, the expression is vivid, the details are rich, the sense of real photography, the depth of field, high definition, cinematic, photorealistic, realistic livestream screenshot, social media UI, Chinese Douyin live room, detailed lighting, natural skin texture.

Negative prompts:

Low definition, blur, cartoon, illustration, too strong CG sense, two-dimensional, deformed fingers, wrong text, scrambled code, multiple mobile phones, multiple brands, character repetition, face collapse, facial features distortion, excessive skin polishing, overexposure, too dark, messy background, wrong UI, non-Chinese short video interface, too many English bullet screens, gift special effects are not obvious, cropping error, proportional error

Supplementary reinforcement words:

Real mobile phone screen recording screenshot feeling, the live broadcast UI is complete, the gift prompt box conforms to the style of the Chinese short video platform, the Chinese comment area is active, the number of people online in the live broadcast room is clearly displayed, and the time, power and signal bar are visible.

「いらすとや」のほのぼのとした雰囲気と、「霞ヶ関スライド」の圧倒的な情報密度を融合させた、桃太郎の解説スライド（ポンチ絵）を作成して

Please create an X page of King Taejo Yi Seong-gye (right before carrying out the Wihwa Island Retreat - containing posts where he and General Choi Yeong are dissing each other).

Create an X post page of Zhu Yuanzhang after his ascension to the throne in the Ming Dynasty

Based on the video content and this current frame, use GPT to generate a YouTube thumbnail that fits the video. You can reference the style of the image I gave you, but replace the logo on the right side of AE with theChatCut logo. I'll attach the logo for you.

In the game Zelda totk link is in a e531 series train made by him

Create a new animation sheet, but this time it's a storyboard between an Indian man and an Indian woman in a dramatic scene inside an apartment. Ensure the elements of the apartment are in the scene, and include dialogue boxes, this is for 15 seconds so be careful of the cadence (sentences not too long), when a character speaks they should be the only one in frame.

{
  "type": "YouTube livestream UI",
  "top_nav": {
    "logo": "YouTube Premium",
    "search": "{argument name=\"search query\" default=\"bilal fraiha\"}",
    "icons": 3
  },
  "player": {
    "subjects": [
      "{argument name=\"female guest\" default=\"Sydney Sweeney\"} in white cardigan",
      "bearded man in beige jacket laughing"
    ],
    "bg": "couch, 2 silver play buttons, ram logo 'SARDI'",
    "overlays": {
      "chat": {"pos": "left", "count": 15, "desc": "colored usernames, white text"},
      "goal": {"pos": "top right", "text": "TONIGHT'S GOAL: 0 to 25"},
      "banner": {"pos": "bottom center", "text": "K {argument name=\"streamer name\" default=\"MOREBILAL\"}"}
    },
    "controls": {"count": 10}
  },
  "details": {
    "title": "{argument name=\"video title\" default=\"FULL STREAM | سيدني سويني مع بلال\"}",
    "channel": "{argument name=\"channel name\" default=\"More Bilal No Filter\"}",
    "buttons": 5
  }
}

{"type": "YouTube desktop dark mode UI mockup", "header": {"logo": "YouTube", "search_bar": "Search", "icons_count": 5, "icons": ["search", "mic", "create", "notifications", "profile"]}, "video_player": {"top_left_badge": "LIVE", "left_side": {"subject": "{argument name=\"presenter description\" default=\"man in green sweater at wooden podium\"}", "podium_logo": "OpenAI"}, "right_side_presentation": {"text_elements": ["OpenAI", "INTRODUCING", "{argument name=\"product name\" default=\"GPT-Image-2\"}", "{argument name=\"tagline\" default=\"More Realistic. More Useful. More Creative.\"}"], "sample_images_count": 4, "sample_images": ["mountain lake with boat", "woman portrait with dappled light", "cute robot with lantern in forest", "starry night cafe painting"]}, "bottom_controls_count": 10, "bottom_controls": ["pause", "next", "volume", "LIVE", "red progress bar", "CC", "settings", "miniplayer", "theater mode", "fullscreen"]}, "video_details": {"title": "{argument name=\"video title\" default=\"OpenAI Live: Introducing GPT-Image-2\"}", "channel": {"name": "{argument name=\"channel name\" default=\"OpenAI\"}", "verified": true, "subscribers": "1.36M", "button": "Subscribe"}, "action_buttons_count": 5, "action_buttons": ["Like 12K", "Dislike 497", "Share", "Save", "More"], "description_box": {"stats": "95,237 watching now Started streaming 7 minutes ago", "tags": "#OpenAI #GPTImage2 #AI", "text": "Join us for a special live event as we introduce GPT-Image-2, our latest and most advanced image generation model. See new capabilities, live demos, and hear from the team ...more"}}}

Generate a UI design system for me in xx style, including web pages, mobile, cards, controls, buttons, and others

{
  "type": "live stream UI mockup",
  "subject": {
    "description": "portrait of {argument name=\"host name\" default=\"Elon Musk\"}, smiling, wearing a black t-shirt with a white technical schematic graphic",
    "background": "left side shows a screen with '{argument name=\"left background logo\" default=\"SPACEX\"}' text, right side shows a red '{argument name=\"right background logo\" default=\"Tesla T logo\"}' and a dark car"
  },
  "ui_overlay": {
    "top_header": {
      "host_info": "avatar, name '{argument name=\"host name\" default=\"Elon Musk\"}', subtext '556,000 likes this stream', red 'Follow' button",
      "rank_badge": "gold coin icon with '#1 on the platform'",
      "viewer_stats": "3 top viewer avatars with '12.3w', '8.6w', '5.7w', total '687,000', 'X' close button",
      "right_links": "'More Live Streams >', 'Gift Gallery 0/24' with blue 'Classic' tag"
    },
    "mid_left_gifts": {
      "count": 2,
      "items": [
        "avatar 'Tech Enthusiast', 'Sent a small heart', heart icon x 1314",
        "avatar 'Stars and Seas', 'Sent a rocket', rocket icon x 666"
      ]
    },
    "bottom_left_chat": {
      "system_message": "level 37 badge 'Cosmic Wanderer joined the livestream'",
      "message_count": 7,
      "messages": [
        "Little Rocket: Musk! The future is bright! 🚀",
        "future: When will the Tesla Model 2 be released?",
        "Starry Dreamer: Can SpaceX go to Mars this year?",
        "AI Explorer: How is Neuralink progressing?",
        "Handsome Netizen: Hello Mr. Ma!",
        "Mars: First time at your livestream, so excited!",
        "User123: Tell us about AI, will it replace humans?"
      ]
    },
    "bottom_right_product_card": {
      "hot_tag": "orange 'Hot Sale x 1888'",
      "image": "Tesla Cybertruck",
      "title": "{argument name=\"product name\" default=\"Tesla Cybertruck Electric Pickup\"}",
      "price": "{argument name=\"product price\" default=\"¥ 1,618,000\"}",
      "button": "red 'Grab' button",
      "floating_animation": "translucent hearts floating up the right edge"
    },
    "bottom_bar": {
      "input_field": "'Say something...'",
      "icons": ["smiley face", "three dots", "shopping cart", "gift box", "share"]
    }
  }
}

{
  "type": "brand identity system presentation board",
  "header": {
    "title": "Brand Identity System",
    "slogan": "Love it · Understand it · Accompany it"
  },
  "main_logo": {
    "text": "{argument name=\"brand name\" default=\"GDX\"}",
    "subtitle": "{argument name=\"brand chinese name\" default=\"Gou Dongxi\"}",
    "design_feature": "{argument name=\"main subject\" default=\"Dog profile in negative space of the letter D\"}",
    "metadata": [
      "Brand Name",
      "Industry Attribute {argument name=\"industry\" default=\"Pet Industry\"}",
      "Design Date 2024.05"
    ]
  },
  "layout": {
    "sections": [
      {
        "title": "Design Grid",
        "count": 1,
        "description": "Logo with architectural grid lines and golden ratio measurements"
      },
      {
        "title": "Concept Sketches",
        "count": 4,
        "description": "Evolution steps from rough dog sketch to final geometric logo"
      },
      {
        "title": "Inspiration Sources",
        "count": 4,
        "description": "Moodboard images including minimalist architecture, a golden retriever, and dark green geometric shapes"
      },
      {
        "title": "Creative Concepts",
        "count": 4,
        "description": "Text blocks with minimalist icons explaining design philosophy, positioning, color psychology, and scalability"
      },
      {
        "title": "Brand Applications",
        "count": 6,
        "labels": [
          "Business Cards (Front & Back)",
          "Letterhead & Envelopes",
          "App Icons",
          "Website Header / Website Icon",
          "Product Packaging / Shopping Bags",
          "Storefront Signage / Signage"
        ],
        "description": "Mockups of business cards, envelopes, app icons, website header with a dog, paper shopping bags, and a storefront sign"
      },
      {
        "title": "Color Specifications",
        "count": 5,
        "labels": [
          "Primary Color",
          "Secondary Colors",
          "Accent Color"
        ],
        "colors": [
          "{argument name=\"primary color\" default=\"#1E3D34\"}",
          "#F5F3EF",
          "#E5E2DD",
          "#A8C5B1",
          "#E0A86E"
        ]
      },
      {
        "title": "Typography Specifications",
        "count": 2,
        "labels": [
          "Source Han Sans CN",
          "Source Han Serif CN"
        ],
        "description": "Typography specimens showing 'Aa', alphabet, and numbers"
      },
      {
        "title": "Minimum Usage Size",
        "count": 2,
        "description": "Minimum logo size specifications at 20mm and 12mm"
      },
      {
        "title": "Safe Space Area",
        "count": 1,
        "description": "Logo surrounded by a bounding box with 'X' indicating clear space margins"
      },
      {
        "title": "Incorrect Usage Examples",
        "count": 5,
        "labels": [
          "Do not stretch or distort",
          "Do not change colors",
          "Do not add shadows",
          "Do not tilt or rotate",
          "Do not use on complex backgrounds"
        ],
        "description": "Examples of incorrect logo usage: stretched, wrong color, drop shadow, tilted, and placed on a busy photographic background"
      }
    ]
  }
}

Create a personal color analysis graphic using this portrait. Point out which season colour suits the subject best. Show side-by-side clothing color comparisons to highlight which colors suit the subject best. List out what texture/accessories/hairstyle suit the subject best. Make it visual-first, with short labels only and no paragraphs.

{
  "type": "exploded view product diagram poster",
  "subject": "VR headset",
  "style": "clean high-tech 3D render, studio lighting, glowing accents",
  "background": "{argument name=\"background color\" default=\"soft purple and blue gradient\"}",
  "header": {
    "logo": "∞ {argument name=\"product name\" default=\"Meta Quest 3\"}",
    "subtitle": "{argument name=\"main catchphrase\" default=\"まったく新しい現実を、まったく新しい構造から。\"}"
  },
  "layout": {
    "centerpiece": "vertically stacked exploded view of a VR headset showing 9 distinct layers of internal components: outer shell, camera sensors, motherboard with chip, pancake lenses, internal frame, battery packs, side straps, top strap, and facial interface cushion.",
    "callout_labels": {
      "count": 8,
      "left_side": [
        "Snapdragon® XR2 Gen 2\nExperience real-time performance with overwhelming processing power.",
        "Adjustable IPD mechanism\nComfortable fit for a wide range of users.",
        "Precision-designed head strap\nErgonomics designed for comfort and stability."
      ],
      "right_side": [
        "Face plate\nRefined design with optimal weight balance.",
        "Tracking camera\nAchieves high-precision position tracking and environmental recognition.",
        "Pancake lenses\nProvides wide field of view and clear images with a slim design.",
        "High-performance battery\nOptimized power design that supports long hours of operation.",
        "Soft face interface\nAchieves comfortable wearing experience even for extended periods."
      ]
    },
    "footer": {
      "left_text_block": {
        "headline": "{argument name=\"bottom headline\" default=\"体験は、構造から進化する。\"}",
        "body": "Each part contains cutting-edge technology and meticulous design that supports immersive experiences. Meta Quest 3 creates future-sensing experiences from within."
      },
      "right_logo": "∞ Meta"
    }
  }
}

Screenshot of a YouTube video showing someone who time-traveled to the Middle Ages

"Song Dynasty People's Moments"/"SONG DYNASTY SOCIAL MEDIA FEED", Ancient and modern time-travel humor fusion interface design style, The image simulates a mobile phone social media interface, but the content is entirely Song Dynasty scenes, The avatar is a portrait of a Song Dynasty literati, Username "Su Dongpo SuShi_Official", Post content "Just arrived in Huangzhou, demoted but feeling okay. Made Dongpo pork myself today, tastes amazing, recipe attached:", The attached image is a close-up of Dongpo pork in Gongbi painting style, Likes list "Huang Tingjian, Qin Guan, Fo Yin etc. 126 people", Comments section "Wang Anshi: Hehe" "Sima Guang: Still the same taste", Interface elements such as the like icon are replaced with Song Dynasty patterns, The status bar shows "Great Song Mobile 5G" and "Third Year of Yuanfeng", The color scheme is mobile phone dark mode paired with elegant Song Dynasty tones, A masterpiece of fun collision between history and social media

A highly detailed, realistic first-person video game screenshot of a next-generation voxel-based world. At the top center, a large, bold 3D logo reads "{argument name="game title" default="MINECRAFT 2"}". The scene features a {argument name="environment" default="lush, blocky landscape with a river, a small wooden cabin, a windmill, a waterfall, and majestic mountains in the background"}. The world blends realistic lighting, volumetric clouds, and high-resolution textures with cubic, voxel geometry. In the foreground on the left, a {argument name="mob 1" default="blocky green creeper"} stands on the grass, while a {argument name="mob 2" default="blocky brown wolf"} stands on the dirt path to the right. On the far right, the player's hand holds a {argument name="held item" default="pixelated blue diamond sword"} in a first-person perspective. At the bottom of the screen is a game user interface featuring a health bar with 10 red hearts, a green experience bar with the number '16', a hunger bar with 10 brown meat icons, and a 9-slot inventory hotbar. The hotbar contains, from left to right: a selected blue tool with a green highlight box, a green tool, a knife, a wrench with the number '3', a piece of meat with '6', a lantern with '24', a dirt block with '10', a bucket, and a sponge block.

{
  "type": "18-panel brand identity and character design document",
  "brand": {
    "name": "{argument name=\"brand name\" default=\"沐阳 MUYANG TEA\"}",
    "industry": "{argument name=\"industry\" default=\"tea shop\"}",
    "colors": ["{argument name=\"primary color\" default=\"yellow\"}", "{argument name=\"secondary color\" default=\"green\"}", "white", "brown", "dark green"]
  },
  "subject": "{argument name=\"character description\" default=\"3D rendered cute Shiba Inu mascot wearing a green apron\"}",
  "layout": {
    "grid": "3 columns by 6 rows",
    "sections": [
      {
        "title": "01 BRAND DNA ANALYSIS",
        "elements": ["logo", "5 color swatches", "6 icons", "target audience charts"]
      },
      {
        "title": "02 CONCEPT MOODBOARD",
        "elements": ["5 photo references", "4 mood icons", "design equation"]
      },
      {
        "title": "03 FORM STUDY",
        "elements": ["4 logo anatomy icons", "4 evolution steps", "4 silhouettes"]
      },
      {
        "title": "04 CONCEPT EXPLORATION",
        "elements": ["12 line-art character sketches"]
      },
      {
        "title": "05 REFINED LINE ART",
        "elements": ["3 rows of front and side line art with proportion guides"]
      },
      {
        "title": "06 DETAIL REFINEMENT",
        "elements": ["2 full-body renders with labels", "4 circular close-ups"]
      },
      {
        "title": "07 EXPRESSION SHEET",
        "elements": ["11 3D rendered head expressions"]
      },
      {
        "title": "08 POSE LIBRARY",
        "elements": ["9 full-body 3D rendered poses"]
      },
      {
        "title": "09 TURNAROUND VIEW",
        "elements": ["5 full-body 3D renders", "5 matching line-art views"]
      },
      {
        "title": "10 COLOR DEVELOPMENT",
        "elements": ["5 rows of 5-color palettes", "color psychology text"]
      },
      {
        "title": "11 MATERIAL SPECIFICATION",
        "elements": ["5 texture swatches", "property sliders", "4 manufacturing icons"]
      },
      {
        "title": "12 COLOR APPLICATION",
        "elements": ["4 color variant renders", "2 light/dark renders", "4 contrast rating circles"]
      },
      {
        "title": "13 CONSTRUCTION GUIDE",
        "elements": ["2 line-art diagrams for geometry and grid"]
      },
      {
        "title": "14 DESIGN SYSTEM RULES",
        "elements": ["minimum size icons", "clear space diagram", "4 usage examples"]
      },
      {
        "title": "15 ASSET VARIANTS",
        "elements": ["3 size variants", "3 line-art variants", "3 simplified flat heads"]
      },
      {
        "title": "16 DIGITAL APPLICATIONS",
        "elements": ["1 app icon", "2 social avatars", "UI elements", "3-step animation cycle"]
      },
      {
        "title": "17 PHYSICAL APPLICATIONS",
        "elements": ["plush toy mockup", "packaging mockup", "merchandise mockup", "storefront mockup"]
      },
      {
        "title": "18 FINAL RENDERING",
        "elements": ["large high-res 3D render of mascot holding tea", "logo", "file format list"]
      }
    ]
  }
}

Generate a screenshot of Mai Shiranui's Xiaohongshu homepage

Generate Xiaohongshu content screenshot, theme: Behind every exquisite girl there is online loan, iPhone size

Generate a screenshot of WeChat Channels content, theme: middle-aged and elderly people should not blindly urge marriage, iPhone size

Frame 1 (Top-Down Establishing)
Extreme top-down shot in futuristic white curved hall, subject centered but compressed against smooth reflective floor, body aligned straight but slightly angled, arms close to body with subtle tension, head tilted upward toward camera, gaze directed straight up, strong circular architectural lines framing composition, soft studio lighting creating gentle gradients, shallow depth of field at f/1.2, smartphone-like proximity despite height, clean minimal atmosphere, dynamic opening frame, subtle athletic readiness, wearing full beige suit with white t-shirt and white sleek sneakers, Peter Lindbergh influence
Frame 2 (Low Angle Power)
Extreme low angle from floor level, subject towering above camera, legs forming strong base, torso slightly leaning forward, shoulders squared, arms slightly away from body, head angled downward, gaze into lens, strong vertical distortion, reflective floor amplifying silhouette, soft studio lighting with controlled highlights, shallow depth f/1.2, powerful dominance frame, subtle athletic tension, full beige suit, white t-shirt, white sleek sneakers, Peter Lindbergh influence
Frame 3 (Wide Isolation)
Wide long shot, subject very small within vast futuristic hall, surrounded by curved white architecture, large negative space dominating composition, subject standing still, body straight, arms relaxed but structured, head slightly turned, gaze outward into space, minimal reflections, soft even lighting, shallow depth f/1.2 isolating subject despite distance, cinematic silence, full beige suit, white t-shirt, white sleek sneakers, Peter Lindbergh influence
Frame 4 (Dynamic Close-Up Tilt)
Close-up with strong diagonal tilt, subject leaning into frame, shoulders sharply angled, one arm crossing body, head tilted sideways, gaze slightly off camera, tight crop cutting part of body, soft lighting wrapping contours, shallow depth f/1.2 isolating face plane, intense proximity and tension, full beige suit, white t-shirt visible, Peter Lindbergh influence
Frame 5 (Motion Step Forward)
Mid shot, subject stepping forward dynamically, one leg extended, weight shifting, arms slightly swinging with controlled motion, shoulders rotated, head facing forward, gaze ahead, slight motion blur on edges, futuristic curved walls passing behind, soft studio lighting, shallow depth f/1.2, transitional energy frame, full beige suit, white t-shirt, white sleek sneakers, Peter Lindbergh influence
Frame 6 (Final Grounded Frame)
Full body frontal shot, subject standing firmly, legs slightly apart, arms held with controlled tension, shoulders squared, head facing forward, gaze into camera, symmetrical composition slightly offset, minimal futuristic background, soft lighting emphasizing structure, shallow depth f/1.2, strong final impact frame, subtle athletic readiness, full beige suit, white t-shirt, white sleek sneakers, Peter Lindbergh influence

Negative Commands (apply to all frames):
no text, no watermark, no low quality, no cartoonish style

Aspect Ratio: 3:4

Generate a screenshot of a Douyin livestream, inside there is a beautiful woman livestreaming

{
  "type": "2x2 advertising banner grid",
  "layout": "4 distinct quadrants, each featuring a different industry advertisement",
  "quadrants": [
    {
      "position": "top-left",
      "industry": "skincare",
      "visuals": "Asian woman touching cheek, floating water droplets, white pump bottle",
      "brand": "BALANCÉE",
      "copy": {
        "headline": "{argument name=\"skincare headline\" default=\"Bare skin awakens.\"}",
        "subheadline": "Toward a new me, full of radiance.",
        "features_count": 3,
        "features_labels": ["High hydration", "Prevents skin irritation", "Whitening care*"]
      }
    },
    {
      "position": "top-right",
      "industry": "restaurant food",
      "visuals": "close-up of spaghetti bolognese with grated cheese and parsley, dark moody lighting",
      "brand": "Trattoria Luce",
      "copy": {
        "headline": "{argument name=\"food headline\" default=\"This pasta is legendary.\"}",
        "badge": "Limited time",
        "description": "Wagyu beef bolognese ~ Truffle aroma ~"
      }
    },
    {
      "position": "bottom-left",
      "industry": "travel",
      "visuals": "woman with backpack facing a scenic mountain lake, bright daylight",
      "brand": "NATURE JOURNEY",
      "copy": {
        "headline": "{argument name=\"travel headline\" default=\"A journey to set me free.\"}",
        "subheadline": "In nature, my heart begins to move.",
        "script": "Find your freedom.",
        "banner_details": ["Early summer special campaign", "6.1 SAT - 6.30 SUN", "Up to 20% OFF", "Many special plans available now!"]
      }
    },
    {
      "position": "bottom-right",
      "industry": "SaaS app",
      "visuals": "smartphone displaying a task management app interface with 4 schedule items",
      "brand": "{argument name=\"app brand name\" default=\"Taskme\"}",
      "copy": {
        "headline": "{argument name=\"app headline\" default=\"Make task management simpler and smarter.\"}",
        "circle_badge": "Design your day.",
        "features_count": 3,
        "features_labels": ["Intuitive operation", "Shareable with team", "Accessible anywhere"],
        "bottom_banner": "Free 7-day trial now available!"
      }
    }
  ]
}

Li Bai dancing under the moon during a Douyin livestream

Render a professional iOS APP homepage UI image, the theme is AI Video Generator, English interface. Professional-level design, professional style, dark theme.

Generate Kuaishou content screenshot: Theme: Live divorce announcement, iPhone size

Design Concept: The Crumple Chair Core Philosophy: Translating the "controlled chaos" of a tossed paper ball into a sculptural, high-comfort seating experience.

Stage 1: Observation & Morphological Analysis The goal is to deconstruct the image of the crumpled paper into usable geometric data. Crease Mapping: Identify the primary "valley" and "ridge" lines. These represent potential structural ribs or seams in the chair. Faceted Planes: Break down the sphere into a series of non-uniform polygons. Each flat surface of the paper becomes a potential panel for the chair's upholstery or shell. Shadow Study: Analyze how the "tossed" form creates deep recesses. These natural pockets guide where the user's weight will be cradled.

Stage 2: Iterative Form Exploration Moving from a sphere to a seat through "Digital Crumpling." Subtractive Sculpting: Imagine the paper ball as a solid mass. Use Boolean operations to "carve out" a seating cavity that fits the human form while maintaining the external jagged texture. Tension Simulation: Use 3D software (like Rhino or Blender) to simulate a flat sheet of material being compressed. This ensures the folds look authentic and not "modeled." The "Toss" Logic: Experiment with gravity-based simulation dropping a digital mesh to see how it settles naturally, mimicking the "tossed" origin.

Stage 3: Ergonomic Translation & Blueprinting Refining the raw aesthetic into a functional object. The Comfort Core: Overlay a standard ergonomic template (Seating Angle: 105°–110°) over the crumpled form. Adjust the internal "folds" to provide lumbar support and pressure relief. Blueprint Generation: Create technical orthographic views (Front, Side, Top). Map out the dimensions: Seat Height: 450mm Total Width: 850mm Surface Smoothing: Maintain the sharp "paper edges" on the exterior shell while softening the interior contact points for skin comfort.

Stage 4: Structural Integration & Scaling Making the concept physically viable. The Skeleton: Design a hidden internal frame (likely CNC-bent steel rods or a 3D-printed lattice) that follows the most prominent ridges of the paper folds to provide rigidity. Material Selection: * Option A (High-End): Faceted, cast aluminum with a white powder coat. Option B (Soft): Vacuum-formed recycled plastic shell covered in "memory-fold" technical fabric that retains a wrinkled appearance.

Stage 5: Final Prototyping & Material Finish Textural Replication: Apply a matte, slightly porous finish to the material to mimic the tactile feel of heavy-bond paper. Lighting Contrast: Use directional studio lighting in the final renders to emphasize the "tossed" shadows, making the chair look like a giant piece of discarded inspiration. Design Tip: To keep the "tossed" look authentic, avoid symmetry. The most compelling aspect of a crumpled paper ball is its unique irregularity—ensure the left and right sides of the chair are balance-equivalent but not identical

Combining the content from Wang Xizhi's "Lantingji Xu", generate a calligraphy copy image, requiring the image background to match the artistic conception of "Lantingji Xu", the background image can use a mask, the foreground is "Lantingji Xu"

Du Fu posting on WeChat Moments complaining about his roof being blown away by the wind

A YouTube thumbnail-style collage for a {argument name="overall mood" default="dark, dramatic, true crime investigation"}. In the center is a highly detailed, close-up portrait of an {argument name="central figure" default="older man with grey hair and deep wrinkles resembling Jeffrey Epstein"}, wearing a black polo shirt, with a faint red glowing outline separating him from the background. On the left side, a {argument name="left background scene" default="tropical island with luxury villas and a flying airplane in a dark sky"}. Below the island, a conspiracy board motif features exactly 2 red push pins connected by 3 thick red strings. On the top right side, a hazy, sepia-toned depiction of the {argument name="right background scene" default="US Capitol building with the silhouettes of 3 men in suits facing it"}. On the bottom right, an open manila folder containing a {argument name="document type" default="heavily redacted dossier with thick black marker lines and a smaller photograph of the central man"}. The overall composition is cinematic, intense, and heavily stylized for a documentary video.

A dreamy anime portrait of {argument name="character name" default="Kotori"}, a delicate virtual girl seated on the floor in a curled-up pose with both knees pulled close to her chest and her arms wrapped gently around them, looking directly at the viewer with a soft, quiet, slightly melancholy expression. She has very long, flowing silver-lavender twin tails with wispy bangs, decorated with 8 visible hair ornaments: 2 large ribbon bows at the twin-tail bases, 3 small flower clips, 2 tiny butterfly clips, and 1 heart-shaped hairpin. Her eyes are large, luminous violet with glossy highlights. She wears an oversized pastel-lilac off-shoulder knit cardigan slipping loosely around her arms, a frilly lace-trimmed nightdress or camisole in pale lavender, and a pair of soft knee-high socks with 2 visible ribbon bows, all in a cohesive {argument name="color theme" default="soft lavender and pastel purple"} palette. The scene is set inside a futuristic holographic memory space filled with floating translucent interface panels, glowing data windows, starry particles, and butterfly-shaped light motifs. Include a visible text panel on the left showing terminal-like white text that reads: {argument name="screen text" default="memory://\nUser: You\nAI: Kotori\n\nAccessing.\n> initializing\n> loading memory\n> 100%\n> welcome home."}. In the background, show a cosmic digital environment with a faint planet, layered transparent screens, and several floating image thumbnails suggesting memories and character sketches. Lighting is ethereal and backlit, with iridescent bloom, soft rim light, sparkling dust, and glossy highlights on hair and fabric. Composition is full-frame vertical, centered on the girl, intimate and emotionally warm, highly detailed, ultra-polished, soft-focus anime illustration, celestial cyber fantasy aesthetic, gentle purple glow, intricate lace, silky hair strands, and a tender "AI companion in her memory world" mood.

```json
{
  "type": "e-commerce landing page hero section mockup",
  "aesthetic": "clean, bright, airy, feminine, floral accents with purple flowers, {argument name=\"primary color\" default=\"soft pink\"} and white color palette, soft lighting",
  "header": {
    "logo": "{argument name=\"brand name\" default=\"LUMEA BEAUTY\"}",
    "navigation_links": {
      "count": 5,
      "labels": ["Features", "Ingredients", "Testimonials", "How to Use", "FAQ"]
    },
    "cta_button": "Try Now"
  },
  "hero_section": {
    "left_column": {
      "headline": "{argument name=\"headline text\" default=\"Radiant clarity every time you look in the mirror.\"}",
      "subheadline": "For dry and dull skin. A concentrated moisturizing serum with luxurious beauty ingredients for daily use.",
      "feature_badges": {
        "count": 3,
        "style": "pill-shaped with small icons",
        "labels": ["Suitable for sensitive skin", "High hydration", "Can be used morning and night"]
      },
      "bullet_points": {
        "count": 3,
        "style": "pink checkmarks",
        "labels": ["Effectively delivers beauty ingredients", "For a firm and radiant appearance", "Simple care that's easy to continue"]
      },
      "cta_buttons": {
        "count": 2,
        "labels": ["Try with first-time offer >", "Check ingredients >"]
      },
      "trust_badges": "Free shipping / First-time offer / No subscription required"
    },
    "center_subject": {
      "model": "{argument name=\"model description\" default=\"young East Asian woman smiling, touching her cheek\"}",
      "action": "holding a dropper bottle of serum"
    },
    "right_column": {
      "product_display": {
        "count": 2,
        "items": ["{argument name=\"product type\" default=\"moisturizing boost serum\"} dropper bottle", "packaging box"]
      },
      "stat_cards": {
        "count": 3,
        "style": "floating white rounded rectangles with gold accents",
        "labels": ["96% satisfaction", "5 beauty ingredients", "Over 12,000 users"]
      }
    }
  },
  "bottom_section": {
    "benefit_cards": {
      "count": 3,
      "style": "horizontal white rounded rectangles with icons",
      "labels": ["Hydration", "Clarity", "Ease of use"]
    }
  }
}
```

```json
{
  "type": "website landing page mockup",
  "theme": "men's skincare, sleek, professional, dark mode",
  "color_palette": "{argument name=\"color scheme\" default=\"dark navy blue\"}, white text, subtle blue gradients",
  "header": {
    "logo": "{argument name=\"brand name\" default=\"NEX SKIN\"}",
    "navigation": ["HOME", "PRODUCT", "ABOUT", "FEATURE", "FAQ"],
    "cta_button": "Get Started >"
  },
  "hero_section": {
    "left_column": {
      "headline": "{argument name=\"main headline\" default=\"Cleanliness begins with daily skincare.\"}",
      "sub_headline": "Men's skin can be simpler.",
      "body_text": "3 lines of descriptive text about skincare benefits",
      "buttons": [
        {"style": "solid blue", "text": "Get Started >"},
        {"style": "outlined", "text": "Learn More >"}
      ],
      "feature_highlights": {
        "count": 3,
        "items": [
          {"icon": "sparkle", "title": "Shine Control", "subtitle": "Balances sebum"},
          {"icon": "water drop", "title": "Moisturizing", "subtitle": "Continuously provides hydration"},
          {"icon": "shield/bottle", "title": "All-in-One", "subtitle": "Toner, serum, and lotion in one bottle"}
        ]
      }
    },
    "center_image": {
      "subject": "handsome {argument name=\"target demographic\" default=\"young Asian man\"}",
      "appearance": "clean-cut, dark hair, flawless glowing skin, wearing a black shirt",
      "pose": "hand touching chin thoughtfully",
      "lighting": "dramatic studio lighting highlighting facial structure"
    },
    "right_column": {
      "product_shot": {
        "bottle": "tall cylindrical dark blue bottle with water droplets",
        "labels": ["{argument name=\"brand name\" default=\"NEX SKIN\"}", "{argument name=\"product type\" default=\"ALL-IN-ONE LOTION\"}", "150mL"],
        "base": "textured dark rock surface",
        "badge": "circular outlined badge reading 'Total care for men's skin concerns with just one bottle'"
      }
    }
  },
  "bottom_stats_bar": {
    "count": 3,
    "items": [
      {"icon": "users", "label": "Total Sales", "value": "Over 1.2 million units"},
      {"icon": "star", "label": "User Satisfaction", "value": "92.1%"},
      {"icon": "checklist", "label": "Repeat Rate", "value": "85.3%"}
    ],
    "footnotes": "small legal text on the right"
  }
}
```

9:16 aspect ratio, generate a screenshot of a Douyin live stream, inside is Liu Yifei live streaming, Liu Yifei is holding a sign in her hand, the sign says Tonight's live stream, welcome to join Yifei for a chat!

Generate a screenshot of Douyin content, theme: Catch up with the AI wave, 9.9 to learn it all, iPhone size

{
  "type": "e-commerce live stream interface mockup",
  "subject": {
    "description": "young Asian woman, long wavy dark hair, wearing a white short-sleeve polo shirt and white pleated tennis skirt, holding a white tennis racket over her right shoulder, looking directly at the camera with a soft expression",
    "background": "soft light grey studio background"
  },
  "layout": {
    "header": {
      "left": {
        "avatar": "female portrait",
        "name": "{argument name=\"host name\" default=\"Little Deer Sports Selection\"}",
        "stats": "128K likes this session",
        "button": "Follow",
        "badge": "3rd in Sales Ranking"
      },
      "right": {
        "viewer_avatars_count": 3,
        "viewer_count": "12K",
        "close_icon": "X"
      }
    },
    "floating_elements": [
      {
        "position": "top right",
        "type": "coupon card",
        "title": "Live Stream Exclusive Coupon",
        "details": "¥20 off for orders over ¥199",
        "button": "Claim"
      },
      {
        "position": "mid left",
        "type": "campaign text",
        "subtitle": "Summer Sports Season",
        "headline": "{argument name=\"main headline\" default=\"Energetic Start\"}",
        "bullet_points_count": 3,
        "bullet_points": ["Breathable & Quick-dry", "Elastic & Comfortable", "Versatile for Sports"]
      },
      {
        "position": "mid right",
        "type": "product card active",
        "badge": "Currently Explaining",
        "image": "white polo and skirt flat lay",
        "title": "{argument name=\"product name\" default=\"Sports Polo Shirt Set\"}",
        "details": "White·Size M",
        "price": "{argument name=\"price\" default=\"¥129\"}",
        "button": "Shop Now"
      },
      {
        "position": "bottom right",
        "type": "product card secondary",
        "badge": "Hot Sale x 156",
        "image": "model wearing the outfit",
        "title": "Women's Sports Polo Shirt Set Breathable Quick-dry Slimming Versatile",
        "tags": ["7-day no reason return", "Shipping insurance"],
        "price": "¥129",
        "button": "Grab"
      }
    ],
    "chat_overlay": {
      "position": "bottom left",
      "message_count": 5,
      "messages": [
        "Sister Little Deer: Welcome new friends to the live stream~",
        "Sports Expert: {argument name=\"chat message\" default=\"This set looks great!\"}",
        "Kakashi: Is the fabric breathable?",
        "Little Deer Sports Selection: Our fabric is ice silk quick-dry, not stuffy even when sweating during exercise~",
        "User_6789: Ordered!"
      ],
      "purchase_alert": "User_6789 and 3 others are purchasing"
    },
    "footer": {
      "input_bar": "Say something...",
      "icons_count": 5,
      "icons": ["smile", "shopping cart", "heart", "share", "more"]
    }
  }
}

A 9:16 image, generate a screenshot of a Bilibili live stream, inside is Hu Chenfeng broadcasting live, Hu Chenfeng has a happy expression, holding a sign in his hand, the sign says "Boss Austin is so emotional, everyone please give Boss Austin some follows."

Create a landing page using this image as a reference for style and color grading.

根据真实历史对杨玉环的形象描述，生成一张杨贵妃真实照片，画质为iPhone 15 pro

李佳琦直播间背景，口红矩阵展示墙，暖光氛围灯，文案OMG买它

{
  "type": "anime-style livestream thumbnail",
  "character": {
    "hair": "{argument name=\"hair color\" default=\"short silver hair with cyan underlights\"}",
    "eyes": "large bright blue",
    "outfit": "white collared shirt, black tie with silver accents, black jacket, black beret with a large blue heart jewel, blue jewel brooch, black choker",
    "pose": "smiling gently, looking at viewer, positioned on the right side"
  },
  "background": "pastel blue with white clouds, sparkles, stars, small bows, and a subtle grid pattern",
  "typography_and_ui": {
    "top_left_speech_bubble": "Let's chat leisurely~♡",
    "main_title": {
      "text": "{argument name=\"main title\" default=\"casual talk stream\"}",
      "style": "large, soft blue gradient, white outline, decorated with small hearts, positioned on the middle-left"
    },
    "bottom_left_badges": {
      "count": 3,
      "style": "white pill-shaped buttons with a purple heart icon on the left",
      "labels": [
        "{argument name=\"badge 1 text\" default=\"first-time visitor〇\"}",
        "{argument name=\"badge 2 text\" default=\"point collection〇\"}",
        "{argument name=\"badge 3 text\" default=\"ROM〇\"}"
      ]
    },
    "bottom_right_cloud_bubble": "Feel free to comment♡"
  }
}

Generate an image, aspect ratio 3:4. A real-life smartphone photo, with the phone screen displaying a WeChat chat interface in Chinese dialogue, featuring chat bubbles and a Word document attachment. The interface has green and gray bubbles. The screen shows obvious fingerprints, smudges, and scratches. The glass has strong reflections and a direct light source creating glare. The frame is slightly tilted, handheld shot, natural ambient light, imperfect composition, strong sense of realism, casual everyday snapshot, high detail, 4K. The dialogue is between a boss and an employee: the employee sends a file to the boss, and the boss replies that they will take a look first.

{
  "type": "YouTube thumbnail graphic",
  "style": "anime, edgy, neon pink and black color scheme, grunge and splatter accents",
  "character": {
    "appearance": "anime girl, {argument name=\"hair color\" default=\"silver\"} hair, cat ears, purple eyes",
    "expression": "{argument name=\"expression\" default=\"shocked and sweating\"}, mouth open",
    "accessories": "black cat hairclip with pink cross, black choker with heart ring",
    "action": "holding a pink smartphone with a swirl logo"
  },
  "layout": {
    "main_title": {
      "position": "bottom center",
      "style": "huge, bold, 3D typography, grunge texture",
      "lines": [
        { "text": "{argument name=\"main title top\" default=\"Thread controversy\"}", "color": "neon pink" },
        { "text": "{argument name=\"main title bottom\" default=\"Reading for you ;;\"}", "color": "white" }
      ]
    },
    "ui_elements": [
      {
        "type": "social media feed mockup",
        "position": "mid-left",
        "header": "← Thread",
        "post_count": 3,
        "details": "avatars, Korean text, interaction icons for like, comment, repost"
      },
      {
        "type": "live chat mockup",
        "position": "right edge",
        "message_count": 4,
        "details": "pink user icons, Korean text"
      }
    ],
    "text_callouts": [
      {
        "type": "spiky speech bubble",
        "position": "center top",
        "text": "{argument name=\"speech bubble text\" default=\"Is this correct?;;\"}"
      },
      {
        "type": "neon box",
        "position": "top right",
        "text": "Real-time reactions in progress"
      },
      {
        "type": "floating grunge text",
        "position": "far left",
        "line_count": 3,
        "text": ["OO controversy", "Shocking true story", "Historic event"]
      },
      {
        "type": "handwritten text with arrow",
        "position": "bottom right",
        "text": "What are your thoughts?"
      }
    ],
    "logos": [
      {
        "type": "app icon",
        "position": "top left",
        "description": "white swirl logo on black rounded square"
      }
    ]
  }
}

Cute explanation of the large language model training process

```json
{
  "type": "YouTube thumbnail",
  "style": "High-impact, neon green and black color scheme, cyber business aesthetic",
  "background": "Dark with glowing green grid, upward chart lines, large green arrow",
  "subject": {
    "description": "{argument name=\"subject description\" default=\"Serious Japanese man in a black suit\"}",
    "position": "Right side",
    "props": "Stacks of 10,000 Yen bills in bottom right"
  },
  "layout": {
    "main_title": {
      "text": "{argument name=\"main title\" default=\"¥300,000/month ChatGPT side business Anyone can start easily\"}",
      "position": "Center, huge bold white and green gradient text"
    },
    "top_left_badge": {
      "text": "{argument name=\"top left badge\" default=\"High reproducibility\"}",
      "style": "Angled neon green box"
    },
    "top_tags": {
      "count": 4,
      "labels": ["Beginner friendly", "Possible with smartphone", "Fastest monetization", "With concrete examples"]
    },
    "left_bullet_points": {
      "count": 6,
      "style": "Dark boxes with neon green borders and icons",
      "items": [
        "Lightbulb icon: Fail-proof starting method",
        "Yen coin icon: Recommended for side hustle",
        "Chart icon: Monetization process",
        "Search icon: How to find projects",
        "Chat icon: With prompt examples",
        "Clipboard icon: With templates"
      ]
    },
    "bottom_banner": {
      "text": "{argument name=\"bottom banner text\" default=\"Thorough explanation of steps\"}",
      "icons": "ChatGPT logo left, upward chart right"
    },
    "bottom_tags": {
      "count": 2,
      "labels": ["{argument name=\"year tag\" default=\"2026 Latest Edition\"}", "Can be implemented immediately"]
    }
  }
}
```

Generate a vertical mobile screenshot-style image with an overall aspect ratio close to 9:16. Slightly above the center of the frame is a real-life coser playing the anime character from the uploaded image. The character should be in a realistic style but with slightly anime-like facial features, delicate skin, and slightly larger eyes, looking gently at the camera. They should be seated in an indoor leisure setting, such as a café or in front of a bar counter, with background props appropriate to the scene. Add a mobile system status bar UI at the very top of the image, including time, battery, signal, and network icons, making the entire image look like a phone screenshot. At the bottom of the image, overlay a wide semi-transparent galgame-style dialogue box. On the left side of the dialogue box, place an anime or chibi avatar corresponding to the character in the image. On the right side, format text with the character's name in a larger font on the first line, followed by one to two lines of gentle and healing-style simplified Chinese dialogue suitable for this character's personality, which you should create automatically. Below the dialogue box, add an operation bar imitating galgame UI. The overall style should be high-definition, rich in detail, with soft lighting, and naturally blending anime and real-life photography.

Create a screenshot of X content in dark mode, posted by an @OpenAI verified account.
The main Chinese content:
Today I want to recommend a great AI Builder: Ailln AI.
He continuously shares AI tools, Agent workflows, automation practices, and real project experience on Xiaohongshu, explaining complex AI capabilities in a clear, practical, and implementable way.
If you're following AI products, productivity tools, personal automation, content creation, and the future of work, Ailln AI is a creator worth paying close attention to.
Search on Xiaohongshu: Ailln AI
Add a dark official promotional style poster at the bottom, with a simple hacker aesthetic, ensuring text is accurately displayed in the image.
Main poster text: "Ailln AI"
Subtitle: "A brilliant AI Builder worth following"
Engagement data at the bottom: Comments 8.9K, Retweets 42K, Likes 298K (highlighted), Bookmarks 34K (highlighted), Views 32.4M.
Image aspect ratio is 3:4, excluding other parts of the software.

A WeChat Moments-style feed for the Xuanwu Gate Incident.

A 9:16 aspect ratio image, generating a screenshot of a Douyin livestream where {argument name="celebrity" default="Liu Yifei"} is broadcasting, holding a sign that says "{argument name="sign text" default="Streaming tonight, welcome to join Yifei's chat!}"}"

A bold Japanese YouTube thumbnail about the AI competition era, 16:9 widescreen, high contrast, dramatic tech-news style. Use a dark futuristic control-room background filled with 3 glowing holographic dashboard screens and blue cyber interface elements around the edges. On the left and center, place a luminous circular hub labeled “AI” in bright blue, with 3 directional glowing energy arrows branching outward to competing platforms: “Google” on the left in a blue electric region, “Claude” on the upper right in a gold electric region, and “OpenAI” at the bottom center in a magenta-purple electric region. Add a subtle world-map or territory-battle visualization effect under each brand region, like illuminated digital land masses or influence zones. On the right side, show a young Japanese-looking woman from waist up, facing forward, wearing a long straight split-color wig with pastel pink on one side and pastel blue on the other, a plain white T-shirt with the printed text “OKIHIRO AI Creative”, and a light pink skirt. She raises one index finger beside her face in a presenter pose. Her face is fully obscured by a large soft-edged rectangular blur block. Across the top, add huge distressed white Japanese headline text: {argument name="headline text" default="AI戦国時代"}. Beneath it, add a second line in bold gold Japanese text: {argument name="subheadline text" default="性能だけの話じゃない"}. Across the bottom, place a wide black banner with massive bold gold Japanese text: {argument name="bottom text" default="空気を取った側が勝つ"}. Make the typography oversized, gritty, and attention-grabbing, with slight glow and drop shadow. Use a color palette of black, electric blue, gold, magenta, and neon white, with intense contrast and thumbnail readability.

The original text is not disclosed, the case objective is to generate a high-completion personal homepage visual design image.

Create a high-fidelity Chinese music app player interface screenshot in mobile portrait orientation, with refined visuals similar to a modern streaming player. Use dark mode, with the background derived from a blurred and diffused version of the album cover colors. Place a large square album cover in the center with subtle shadow and rounded corners.

Interface requirements:
- top status bar with time 18:26
- navigation bar with a back arrow on the left, a centered title, and a more-options icon on the right
- playback progress bar showing current time 01:42 and total duration 04:18
- playback controls for shuffle, previous, play/pause, next, and repeat
- lyrics section showing 5 to 7 scrolling lines, with the current line highlighted
- action row with like, comment, download, add to playlist, and share
- bottom area with device casting and playback queue entry

Use these exact Chinese labels and names:
- title: "正在播放"
- song name: "海边的晚风"
- artist: "林秋"
- album: "夏夜实验室"

The lyrics layout, button icons, reflections, shadows, and dark-mode layering should feel like a real production interface rather than a Dribbble concept.

Create step-by-step recipe infographic for creamy garlic mushroom pasta, top-down view, minimal style on white background, ingredient photos labeled: "200g spaghetti", "150g mushrooms", "3 garlic cloves", "200ml cream", "1 tbsp olive oil", "parmesan", "parsley", dotted lines showing process steps with icons (boiling pot, sauté pan, mixing), final plated pasta shot at the bottom

9:16 aspect ratio, generate a screenshot of a Douyin live stream, inside is xxx live streaming, xxx is holding a sign in their hand, the sign says xxxx.

Express [Subject/Theme] in a graffiti sketch style, presenting an overall visual effect of quick outlining, free deformation, impromptu hand-drawing, and draft-like appearance. The lines are casual, exaggerated, and can vary in thickness, slightly messy but rhythmic and expressive, emphasizing generalization, exaggeration, playfulness, and spontaneity, rather than rigorous realism or detailed rendering. Colors are expressed in rough blocks with a distinct dry-brush feel, retaining uneven smearing traces, brush strokes, dry-brush effects, and a sense of coverage. Colors automatically adapt to [Subject/Theme], but the overall expression remains graffiti-style, sketch-style, and generalized. Do not use transparent watercolor blooming effects, do not use delicate watercolor transitions, do not use paper textures, do not use soft atomization, and do not use dreamy textures. The background is mainly left blank, maintaining a sense of simplicity, relaxation, incompleteness, and design. A small number of auxiliary symbols, arrows, marks, circled areas, repeated lines, casually written text, or other graffiti elements can be added to enhance the visual language of a sketchbook or jotting style, but it must not be too crowded, and must not destroy the subject and the blank space temperament. The image content does not need to be written out in advance; the most suitable subject image, actions, related elements, symbols, or simplified scenes are automatically deduced and generated by [Subject/Theme], keeping the overall unified graffiti sketch style and exaggerated generalized expression, avoiding complex realistic backgrounds and over-elaboration. The exclusive signature "voxcat" needs to be naturally added to the image as a part of the picture. The position should be low-key but clear, and can be placed in the bottom left corner, bottom right corner, or near the title. The style must be consistent with the overall layout, like an artwork signature or a design sign-off; the signature font should be exquisite, restrained, and high-end, must not be too large, must not destroy the subject composition, and must not appear abrupt or cheap.

```json
{
  "type": "video game screenshot mockup",
  "perspective": "third-person over-the-shoulder",
  "character": {
    "description": "male protagonist seen from behind",
    "clothing": "grey tank top with graphic '{argument name=\"shirt graphic\" default=\"LEONIDA MARINE CENTER\"}', camouflage cargo shorts"
  },
  "environment": {
    "setting": "tropical coastal town, dirt road, sunny daytime with scattered clouds",
    "left_side": "wooden welcome sign reading 'Welcome to {argument name=\"location name\" default=\"LEONIDA KEYS\"} YOUR PARADISE', pink plastic flamingo, tropical foliage, distant water tower",
    "center": "green building with 'FISH' sign and marlin graphic, sign reading 'BAIT TACKLE ICE BEER WINE', pedestrians walking",
    "right_side": "two-story wooden building 'Brian's Boat Works & Marina', 'Brian's Bar' neon sign, parked pickup truck, jet skis on a trailer"
  },
  "ui_elements": {
    "count": 5,
    "components": [
      {
        "position": "top-left",
        "type": "mission objective",
        "text": "{argument name=\"mission title\" default=\"MEET RAUL\"}\n{argument name=\"mission description\" default=\"Raul has some work for you at his boatyard\"}"
      },
      {
        "position": "top-right",
        "type": "status HUD",
        "text": "13:47\n$1,142",
        "icon": "pink palm tree"
      },
      {
        "position": "bottom-left",
        "type": "minimap",
        "description": "circular map with purple border, white map icons including 'N' for north"
      },
      {
        "position": "bottom-left, right of minimap",
        "type": "location text",
        "text": "{argument name=\"location name\" default=\"LEONIDA KEYS\"}\nPALM ISLAND"
      },
      {
        "position": "bottom-right",
        "type": "watermark",
        "text": "{argument name=\"game title\" default=\"GTA VI\"}\nPRE-ALPHA FOOTAGE"
      }
    ]
  }
}
```

{argument name="pianist" default="Vladimir Horowitz"} performs a {argument name="event" default="live piano recital"} streamed on {argument name="platform" default="YouTube"}

Generate a screenshot of Trump and Kim Jong-un doing a PK battle in a TikTok live stream room

Su Shi's first day of exile Xiaohongshu screenshot

Generate a UI design system for me in xx style, including web pages, mobile, cards, controls, buttons, and others

Generate a screenshot of [historical figure name] on [platform name]

{
  "type": "7-day fashion lookbook infographic",
  "header": {
    "title": "{argument name=\"main title\" default=\"7-Day Outfit Guide\"}",
    "subtitle": "{argument name=\"style keywords\" default=\"Gentle | Chic | Elegant\"}",
    "slogan_cn": "Elegance knows no limits, confidence every day",
    "slogan_en": "{argument name=\"english slogan\" default=\"ELEGANCE HAS NO LIMIT, BE CONFIDENT EVERY DAY\"}"
  },
  "subject": "{argument name=\"subject description\" default=\"young elegant Asian woman\"}",
  "layout": {
    "columns": 7,
    "column_elements": [
      "day_header",
      "main_portrait",
      "4_detail_thumbnails",
      "outfit_specs",
      "keywords_colors",
      "3_color_swatches",
      "star_ratings",
      "fabric_price",
      "4_season_icons"
    ],
    "days": [
      { "day": "周一 (MONDAY)", "outfit": "beige blazer suit", "scene": "Scene: Important Meeting / Formal Business" },
      { "day": "周二 (TUESDAY)", "outfit": "pink blazer suit", "scene": "Scene: Daily Commute" },
      { "day": "周三 (WEDNESDAY)", "outfit": "cream knit cardigan set", "scene": "Scene: Casual Life" },
      { "day": "周四 (THURSDAY)", "outfit": "champagne slip dress", "scene": "Scene: Private Outing" },
      { "day": "周五 (FRIDAY)", "outfit": "blue knit top, white skirt", "scene": "Scene: Casual Social" },
      { "day": "周六 (SATURDAY)", "outfit": "white sports bra, purple leggings", "scene": "Scene: Sports & Leisure" },
      { "day": "周日 (SUNDAY)", "outfit": "beige lounge knitwear", "scene": "Scene: Home / Date" }
    ]
  },
  "footer": {
    "tips": "{argument name=\"footer tips\" default=\"Tips: Adjust flexibly according to weather and occasion; accessories are key to elevating your overall look; maintaining confidence and comfort is the ultimate purpose of dressing.\"}",
    "legend": [
      "Spring: Suitable for Spring",
      "Summer: Suitable for Summer",
      "Autumn: Suitable for Autumn",
      "Winter: Suitable for Winter"
    ]
  }
}

Generate a Chinese fitness infographic for [topic].

The graphic should be both professional and practical for a normal adult to use as a training reference. Unless otherwise specified, assume the audience is a healthy adult with no major injuries, the goal is muscle gain plus basic strength improvement, the level is beginner to intermediate, the setting is a normal gym, and the total session length should stay within 40 to 60 minutes.

Choose the output format automatically based on the training topic:

1. If the topic is a muscle group or body part, such as chest, lats, biceps, abs, shoulders, or legs, generate a training-plan infographic for that body part.
2. If the topic is an exercise or skill goal, such as pull-up, push-up, dips, or squat, generate an exercise-unlock or progression-plan infographic.

Use a clear, modern, professional, easy-to-read Chinese infographic style in vertical format. The visual design should be clean and suitable for social sharing or personal training reference. Do not write long paragraphs. Each module should use short concise phrases, and numerical information should be prominent.

The infographic must include:
A. Title area with main title and subtitle
B. Training goal area
C. Warm-up area
D. Main training area with 4 to 6 core exercises
E. Progression or unlock logic area
F. Alternative exercises area
G. Execution reminders area
H. Recovery suggestions area
I. Visual design requirements: modern, clean, professional, modular card layout

The final result should be a complete infographic rather than plain text paragraphs.

Generate a screenshot of a Douyin live stream featuring a beautiful woman live streaming, selling pantyhose and underwear, her online viewer count is 99996, the popularity rating is 18+, a big brother named Xiao Hu sent her an airplane gift

{
  "type": "UI/UX landing page mockup",
  "theme": "dark mode, sleek modern aesthetic, glassmorphism, {argument name=\"primary accent color\" default=\"neon purple and blue\"} glowing accents",
  "header": {
    "logo": "{argument name=\"brand name\" default=\"goViralX\"}",
    "top_right_tag": "VIRAL CAMPAIGN CASE STUDY"
  },
  "layout": {
    "sections": [
      {
        "name": "Hero",
        "headline": "{argument name=\"hero headline\" default=\"How We Created 10M+ Viral Impact\"}",
        "subheadline": "3 days to explode across the entire network, helping brands achieve exponential growth",
        "stats_row": {
          "count": 4,
          "labels": ["Total Views", "Engagement Rate", "Conversion Inquiries", "Execution Period"],
          "values": ["{argument name=\"main statistic\" default=\"10,240,000+\"}", "18.7%", "3,200+", "72 hours"]
        },
        "visual": "cinematic shot of a person in a hoodie looking at glowing digital screens and graphs, large play button overlay"
      },
      {
        "name": "Strategy",
        "title": "Our 3-Day Execution Strategy",
        "layout_type": "vertical timeline",
        "steps_count": 3,
        "elements_per_step": ["timeline node", "title", "bullet points", "video thumbnail with play button", "description box"]
      },
      {
        "name": "Performance",
        "title": "Data-Driven Performance",
        "left_column": {
          "stat_cards_count": 4,
          "values": ["10M+", "43%", "28,000+", "3,200+"]
        },
        "right_column": {
          "charts_count": 2,
          "chart_1": "line graph showing 7-day growth peaking at Day 3",
          "chart_2": "horizontal segmented bar chart showing platform distribution (TikTok 52%, Instagram 24%, X 15%, YouTube 9%)"
        }
      },
      {
        "name": "Keys to Success",
        "title": "The 3 Keys to Viral Success",
        "cards_count": 3,
        "card_elements": ["glowing icon (fire, target, antenna)", "title", "description", "VIEW DETAIL link"]
      },
      {
        "name": "Social Proof",
        "title": "TRUSTED BY CREATORS & BRANDS",
        "left_column": {
          "logos_count": 8,
          "grid": "2x4",
          "brands": ["SHEIN", "SHOPLINE", "Blueglass", "instacart", "lemon8", "mi", "CIDER", "bellroy"]
        },
        "right_column": {
          "testimonial_cards_count": 2,
          "elements": ["quote", "author title (SaaS Founder, Growth Manager)"]
        }
      },
      {
        "name": "Call to Action",
        "title": "READY TO GO VIRAL?",
        "interactive_elements": ["text input field", "glowing button with text '{argument name=\"call to action text\" default=\"Get Exclusive Growth Plan ->\"}'"],
        "visual": "3D render of a rocket ship taking off with purple and blue flames"
      }
    ]
  }
}

The original text is not disclosed, focusing on showcasing GPT-Image2's capabilities in highly realistic social media screenshots and Chinese typography scenarios.

Please generate a Chinese fitness infographic with the theme: 【xxx】.

The infographic should be both professional and practical, suitable for regular adults as a training reference. The default target audience is healthy adults without serious injuries; if no additional specifications are provided, the default training goal is "muscle building + basic strength improvement", the default training level is "beginner to intermediate", the default training scenario is "regular gym", and the default single training session duration should be controlled within 40-60 minutes.

Please automatically determine the output type based on the 【Training Theme】:

1) If the 【Training Theme】 is a specific muscle group or body part (e.g., chest, lats, biceps, abs, shoulders, legs, etc.), please output a "Training Plan Infographic for that Body Part".
2) If the 【Training Theme】 is a specific exercise or skill goal (e.g., pull-ups, push-ups, dips, squats, etc.), please output an "Exercise Unlocking/Progression Training Plan Infographic".

The entire infographic should adopt a clear, modern, professional, and readable Chinese infographic style, with vertical layout, clean visuals, and prominent highlights. It should be suitable for social media sharing or as a training reference card. Avoid lengthy paragraphs; present each section with concise short sentences, and make numerical information stand out.

This infographic must include the following content:

【A. Title Section】
- Main Title: Directly write 【Training Theme】 Training Plan / Unlocking Plan
- Subtitle: Automatically include target audience, goals, training scenario, and suggested duration
Example: Suitable for beginners / Muscle building focused / Gym version / 45 minutes

【B. Training Goals Section】
Explain in concise language:
- What this training primarily targets
- Main goals (muscle building / strength / skill unlocking / core control, etc.)
- Key stimulation or capability improvement direction for this training

【C. Warm-up Section】
Provide 2-4 warm-up suggestions, listed concisely, for example:
- Dynamic activities
- Target muscle group activation
- Light weight warm-up sets
Each item can include a brief description

【D. Main Training Section】
This is the core section, please list 4-6 main training exercises.
Each exercise must include the following information:
- Exercise name
- Training effect / Targeted area
- Sets × Reps (or duration)
- RIR recommendation
- Rest time between sets
- Key points of the exercise (1-2 points)
- Common mistakes (1 point only)

Ensure reasonable exercise arrangement:
- Compound exercises first, then isolation exercises
- Moderate overall training volume
- Don't schedule overly intense training for beginners
- Main exercises typically recommend RIR 1-3
- Isolation exercises can suggest RIR 0-2
- For abs or core exercises, use "seconds / reps" format
- For skill-based exercises, prioritize "prerequisite ability exercises + transition exercises + target exercise attempts"

【E. Progression/Unlocking Logic Section】
Automatically generate based on theme:
- For muscle group training: Write "How to progressively overload", e.g., increase weight after reaching rep limits, prioritize proper form, etc.
- For exercise unlocking: Write "Phased progression path", e.g., from hanging, scapular pull-ups, eccentric training, resistance band assistance, to completing the standard exercise

【F. Alternative Exercises Section】
Please provide 2-3 alternative exercises suitable for the following situations:
- No equipment available
- Home training
- Current ability is insufficient
- Certain exercises cannot be performed

【G. Execution Reminders Section】
Please provide 4-6 concise reminders, for example:
- Proper form takes priority over weight
- Don't train to failure on every set
- Allow 48-72 hours between training the same muscle group
- Pain doesn't equal normal exertion
- When sleep-deprived, appropriately reduce training volume

【H. Recovery Suggestions Section】
Briefly explain:
- Post-training recovery focus points
- Protein / sleep / recovery interval recommendations
- 1 risk reminder (if experiencing significant pain, stop and assess)

【I. Visual Design Requirements】
- Overall as a single-page Chinese infographic
- Vertical layout
- Modern, clean, professional, and strong fitness-oriented style
- Use modular card layout
- Key numbers (sets, reps, RIR, rest) should be prominent
- Can include simple human muscle group icons, dumbbells, barbells, pull-up icons, etc.
- Colors should be premium, clean, and sporty
- Chinese text must be clear, accurate, and readable
- Avoid excessive decorations, emphasize practicality and executability

Please finally output as "a complete infographic content", not just regular paragraph text.

generate screenshots from a AAA video game based off what The Sims Castaways sequel could look like. https://t.co/aL7hMdUYvj

based on the generated character help me generate a screenshot of screenshot of an pvp game themed around *zelda: wind breaker*

Generate a Teochew restaurant menu image.

Mobile vertical screen interface, short video live streaming platform style, a young Asian female streamer selling goods through live streaming at home, the streamer is wearing tight yoga pants and a simple top, natural body curves, turning sideways to show the lines and elasticity of the pants, natural movements without exaggeration;

Thumbnail for a YouTube unboxing video, a video of {argument name="topic" default="opening all overdue bills"}, {argument name="quantity" default="100 in a row"}

Create a Netflix homepage UI featuring a main hero film with its title and still generated from the uploaded reference.

360 equirectangular image of [place]

Generate an image of a 2026 Gaokao exam paper for [subject name]

```json
{
  "type": "promotional banner / YouTube thumbnail",
  "style": "high contrast, flashy, professional, {argument name=\"theme color\" default=\"gold and black\"} palette, glowing light rays, sparkling particles",
  "subject": {
    "description": "{argument name=\"subject description\" default=\"confident young Asian man in a dark suit with arms crossed\"}",
    "pose": "looking upwards to the right",
    "props": "glowing open laptop in front of him"
  },
  "layout": {
    "background": "dark with radiant gold light bursts",
    "text_sections": {
      "top_left_badge": "[Save Version]",
      "top_header": "{argument name=\"top text\" default=\"Even with zero knowledge, you can start today! Get the ability to earn with AI in the shortest time!\"}",
      "main_title": {
        "text": "{argument name=\"main title\" default=\"AI Side Hustle Complete Guide\"}",
        "style": "large, bold, 3D gold and white typography"
      },
      "subtitle_box": "{argument name=\"subtitle\" default=\"Even beginners can earn 100,000 yen/month\"}",
      "top_right_badge": {
        "style": "gold laurel wreath",
        "text": "2026 Edition Latest Version"
      },
      "middle_right_tags": {
        "count": 3,
        "style": "stacked gold-bordered boxes",
        "labels": ["Monetize in the shortest time", "With specific examples", "Easy for anyone to start"]
      },
      "middle_right_ribbon": {
        "style": "red ribbon banner",
        "text": "Thorough explanation of steps"
      },
      "bottom_left_tags": {
        "count": 6,
        "style": "2x3 grid of gold-bordered boxes",
        "labels": ["Recommended tools introduction", "Understand the monetization flow", "Fail-proof starting method", "Minimize work time", "Templates included", "Easy-to-reproduce methods"]
      },
      "bottom_footer": "Earn without hesitation! AI Side Hustle Textbook",
      "bottom_right_badge": {
        "style": "gold laurel wreath",
        "text": "Templates included"
      }
    }
  }
}
```

WeChat Moments of the Xuanwu Gate Incident

Generate a Japanese social game gacha screen.

Generate a TikTok live stream interface, the content is a beautiful woman live streaming

An anime-style YouTube stream thumbnail featuring a cheerful female VTuber. She has long {argument name="hair color" default="pink with light blue inner highlights"} hair, blue eyes, and wears black and white cat-ear headphones with a boom mic. She wears a white collared shirt with a black and pink star ribbon and a black choker, smiling with one hand near her chin. The background is a gaming room with {argument name="room lighting" default="purple and blue neon"} lighting, showing a desk equipped with 1 white keyboard, 1 mug, 1 glowing cat figure, 1 game controller, and 1 streaming microphone. The left side features large, bold, pop-art Japanese typography: a bright pink top word "{argument name="main text line 1" default="雑談"}" and a bright blue bottom word "{argument name="main text line 2" default="配信"}". Below is a pink banner reading "{argument name="subtitle text" default="今夜もゆるっとトーク!"}". A red "LIVE" badge sits in the top left. Floating speech bubbles, stars, and hearts decorate the composition.

A cinematic, high-fashion portrait of a confident stylish woman wearing an elegant tailored white suit with a high-neck design and sleek oval sunglasses. She is holding a thin medium cigar with soft smoke rising, and a slightly burning King of Hearts playing card with minimal flame detail. Soft wisps of smoke drift upward. The background is a bold, vibrant solid red seamless backdrop. High-key professional studio lighting with soft shadows and gentle warm highlights reflecting on her face. Ultra-realistic skin texture, sharp focus on facial features, shallow depth of field, soft bokeh, 35mm lens look. Crisp contrast, modern editorial fashion photography, clean luxury aesthetic, refined, powerful, and slightly rebellious mood.

LUXURY PERSONAL COLOR PROFILE — EDITORIAL LAYOUT
Studio portrait of subject as anchor — skin retouched to luminous glass-like perfection, preserved natural structure, realistic pore texture, soft directional key lighting, no facial alteration. Background: warm ecru parchment with subtle linen grain texture. Layout reads like a Vogue Italia beauty supplement printed on heavyweight matte stock. Structured editorial grid, 3-column asymmetric, wide negative space, serif condensed display headers, all labels in spaced uppercase tracking, cohesive warm ivory/sand/ecru background system throughout all panels, ultra-photorealistic 8K, soft diffused studio lighting, flat elegant surfaces, no drop shadows.
PANELS:
① UNDERTONE DIAGNOSIS — Tonal spectrum bar from cool ash to warm amber, precision needle marker on subject's reading. Labels: Cool / Neutral-Cool / Neutral / Neutral-Warm / Warm. Fine annotation text.
② SEASONAL COLOR PALETTE — 10–12 fabric-textured swatches in subject's optimal season. Each labeled with poetic color name and HEX. Grouped: Power Colors / Softest Options / Harmonizing Neutrals.
③ COLORS TO AVOID — Desaturated row of clashing tones with fine editorial strikethrough. Clean, non-harsh presentation.
④ MAKEUP CARTOGRAPHY — Eyeshadow gradient dust swatches / blush tones fanned on skin strip / lip spectrum barely-there to bold / highlighter finishes labeled: champagne, rose gold, pearlescent ivory.
⑤ HAIR COLOR SPECTRUM — Curved gradient strip: base, dimension, highlight, contrast tones. Gold bracket indicators on best options.
⑥ JEWELRY & METAL GUIDE — Flat-lay editorial render: yellow gold, rose gold, oxidized silver, platinum finishes alongside complementary stone tones. Minimal styling.
⑦ YOU IN YOUR PALETTE — 3–4 editorial lookbook frames, subject in palette-correct outfits. Mood labels: Quiet Luxury / Off-Duty Editorial / Evening Presence.
⑧ CAPSULE WARDROBE GRID — Outfit flatlay: tops, bottoms, outerwear, shoes, bag — all palette-correct. Coordinating lines showing interchangeability. Net-a-Porter editorial aesthetic.
⑨ PRINTS & PATTERNS — 4 fabric print thumbnails: micro geometric, tonal abstract, classic stripe, floral scale. One-line styling note per print.
⑩ STYLE ARCHETYPE — Single typographic panel. Style identity title set large (e.g. "Modern Romantic / Warm Classicist"). Three defining aesthetic words. Four-line editorial wardrobe philosophy note.
RENDER SPECS: Ultra-photorealistic, 8K, editorial magazine print quality, warm neutral color grading, soft diffused studio lighting consistent across all panels, one serif display font + one fine sans-serif body font, no gradients, flat matte surfaces only.

{
  "type": "brand identity and merchandise design board",
  "theme": {
    "color_palette": "{argument name=\"theme color\" default=\"pastel pink\"} and white",
    "motif": "{argument name=\"motif\" default=\"cherry blossoms\"} and pink hearts"
  },
  "character": {
    "description": "anime girl with short brown bob hair, pink eyes, wearing a white hoodie, gentle smile"
  },
  "branding": {
    "main_logo": "{argument name=\"character name\" default=\"癒音ちー\"}",
    "sub_logo": "{argument name=\"character subtext\" default=\"ゆおんちー\"}"
  },
  "layout": {
    "sections": [
      {
        "type": "header banner",
        "position": "top",
        "elements": ["large main logo", "sub logo", "cherry blossom graphics", "character portrait on the right"]
      },
      {
        "type": "product packaging",
        "position": "middle left",
        "elements": ["1 square box with heart-shaped transparent window showing pink heart candies", "character illustration on box", "2 individual candy wrappers", "5 scattered heart candies"]
      },
      {
        "type": "promotional poster",
        "position": "middle right",
        "elements": ["character portrait", "heart-shaped candy bowl", "main logo", "text '4.26 NEW OPEN'", "text '{argument name=\"social handle\" default=\"@yuonchii\"}'"]
      },
      {
        "type": "horizontal web banner",
        "position": "lower middle",
        "elements": ["main logo", "cherry blossoms", "character portrait on the right"]
      },
      {
        "type": "social media profile mockup",
        "position": "bottom left",
        "elements": ["header image with logo", "1 circular profile picture", "handle '{argument name=\"social handle\" default=\"@yuonchii\"}'", "1 follow button", "mock bio text"]
      },
      {
        "type": "merchandise collection",
        "position": "bottom right",
        "count": 9,
        "items": ["1 white t-shirt with logo", "1 white mug with character", "4 round pin badges", "1 acrylic keychain", "2 candy packets"]
      }
    ]
  }
}

[BRAND NAME = CHANGE TO YOUR BRAND].
Act as a Social Media Art Director and Digital Collage Artist specializing in bold, youth-oriented brand content for Instagram and digital campaigns. PHASE 1: CONCEPTUAL FRAMEWORK Create a dynamic digital collage that merges fashion photography with graphic design chaos. This is controlled rebellion – a composition that feels spontaneous and energetic while maintaining brand coherence. The aesthetic is anti-polished: torn edges, layered textures, hand-drawn elements, and bold color blocking that screams confidence and movement. PHASE 2: MODEL & PHOTOGRAPHY - Subject: One model (diverse casting, age 18-30) in a dynamic, confident pose - Pose Energy: 80% attitude, 20% natural – sitting, jumping, mid-motion, or power stance (avoid static standing) - Outfit: Street style/athleisure that aligns with [BRAND NAME] aesthetic – casual but styled - Hero Product: Feature 1 signature [BRAND NAME] product prominently (sneakers, bag, apparel) – this is the visual anchor - Photography Style: Editorial fashion cutout – model extracted from background with clean edges - Camera Angle: Slight low angle to empower subject (hero perspective) - Crop: Full body or 3/4 body showing hero product clearly - Background Removal: Model cut out cleanly for layering over collage elements PHASE 3: COLOR BLOCKING FOUNDATION - Primary Color Blob: Large organic shape (40-60% of composition) in bold, saturated brand color behind/around model - Shape Style: Irregular, hand-painted aesthetic – think Photoshop brush strokes or torn paper texture (NOT perfect geometric shapes) - Color Selection (Autonomous): Choose 1 hero color from [BRAND NAME] palette: - Texture: Visible brush strokes, grain, or subtle noise (15-25% opacity) – avoid flat digital fills - Placement: Blob positioned to frame model without obscuring key product details PHASE 4: GRAPHIC ELEMENTS LAYER Add 3-5 abstract graphic elements scattered across composition: - Element Types: - Color Palette: Use 2-3 accent colors total (main blob color + 1-2 contrasting tones from brand palette) - Placement: Asymmetric scatter – top-left and bottom-right zones primarily (avoid center crowding) - Scale: Mix small (5% of canvas) and medium (15% of canvas) elements – nothing overpowering - Aesthetic: Analog/handmade feel – imperfect circles, rough edges, visible texture PHASE 5: TYPOGRAPHY INTEGRATION - Brand Logo: Clean [BRAND NAME] logo placed in upper-left or upper-right quadrant (10-15% of width) - Slogan/Tagline: If [BRAND NAME] has an iconic slogan, integrate it using: - Supporting Copy: Optional 1-line descriptor (e.g., "A MOMENT OF YOUR STYLE") in smaller uppercase sans-serif - Type Treatment: Mix of aligned and slightly rotated text (2-5° angles) for dynamic energy - Hierarchy: Logo largest → Slogan medium → Copy smallest PHASE 6: TEXTURE & BACKGROUND - Base Layer: Off-white or light gray textured background (NOT pure white) - Texture Options (Autonomous selection): - Color: RGB 245-250 (near-white with warmth) – maintains brightness while adding depth - Treatment: Texture should be felt, not seen – enhances tactility without competing with foreground PHASE 7: COMPOSITION RULES - Layout: Asymmetric balance – model off-center, graphic elements counter-balance - Breathing Room: 15-20% negative space (textured background visible) to prevent claustrophobia - Layering Order: Background texture → Color blob → Graphic elements → Model (cutout) → Typography top layer - Focal Point: Model + hero product = primary focus (60% visual weight), graphics support (40%) - Movement: Diagonal lines and angled elements create directional flow (top-left to bottom-right or vice versa) PHASE 8: BRAND INTELLIGENCE (AUTONOMOUS) Autonomously adapt composition based on [BRAND NAME] personality: - Streetwear/Sportswear (Nike, Adidas, Supreme): - Luxury Streetwear (Balenciaga, Off-White, Gucci): - Beauty/Lifestyle (Glossier, Fenty, Skims): - Tech/Modern (Apple, Tesla, Beats): PHASE 9: SOCIAL MEDIA FOOTER (OPTIONAL) - Bottom Strip: Clean white or light gray bar at bottom 8-10% of frame - Content: Social media handles (Instagram, Facebook, Twitter) in small sans-serif - Layout: Three-column grid with platform icons or text handles - Aesthetic: Minimal and professional – contrast with chaotic collage above TECHNICAL SPECS: - Aspect Ratio: 4:5 (Instagram feed) or 1:1 (square social post) - Resolution: 2400x3000px minimum (high-quality for zoom and detail) - Color Mode: sRGB, vibrant saturation (Instagram-optimized) - File Aesthetic: Digital collage that mimics analog craft (Photoshop + hand-drawn hybrid) - Model Photography: 85mm lens, f/2.8, shallow depth of field on original shoot (before cutout) - Style Reference: Nike social campaigns, Spotify wrapped graphics, Gen Z Instagram aesthetics, Hypebeast x streetwear collabs - Mood: Confident, energetic, youthful, authentic chaos, anti-corporate polish

Help me generate a central control interface of Geely Galaxy M9, size 21:9, dark color scheme.

Generate a screenshot of a TikTok live stream featuring a beautiful woman streaming.

Create a new X post page illustrated for Baoyu (refer to the homepage and some posts of this Twitter user at https://x.com/dotey) after time-traveling to the Ming Dynasty and ascending the throne, based on his business/personality.

Generate a three-day travel guide image for [city]

Create an ultra-realistic urban street group photo at a convenience store entrance at 10 PM summer night. 3-4 young people briefly chatting at the entrance, someone holding drinks, someone sitting on plastic outdoor chairs, someone standing looking at their phone. Bright white light streaming through the glass doors and windows, warm yellow street lights and distant car headlights outside. Characters wearing everyday clothes: T-shirts, shirts, shorts, jeans, sneakers. No internet celebrity styling. Faces and postures must look like real pedestrians, not overly polished. Environment must include real convenience store elements: freezer stickers, promotional posters, trash cans, entrance mats, glass reflections, shared bikes on roadside, water droplets from drink bottles on ground. The image should look like a very authentic life slice captured by a photographer in the city. Focus on testing natural multi-person interactions, night convenience store lighting, glass reflections, and ordinary people's vibe restoration.

Create a high-quality Japanese {argument name="thumbnail type" default="webinar thumbnail"}. {argument name="aspect ratio" default="16:9 widescreen"}. There is a lot of text, but the main copy stands out clearly.

Create a hyper-realistic, cinematic Instagram post layout where the Instagram UI exists as a physical, tangible 3D object, photographed like a premium commercial product shot. The result should feel indistinguishable from a real studio photograph.
Instagram Frame (UI Accuracy – Critical)
Authentic Instagram interface rendered as a solid white physical 3D card
Smooth matte plastic surface with subtle micro-texture
Slight thickness visible on edges, realistic bevels
Perfectly rounded corners (exact Instagram radius)
Soft studio reflections and realistic edge highlights
Top Bar (Pixel-accurate UI):
Circular profile avatar on the left
Username text: "June" in Instagram's default bold UI font
Light blue FOLLOW button with correct proportions
Three-dot menu icon aligned to the far right
Exact spacing, typography, and icon sizing matching the real Instagram app
Aspect ratio 1:1, centered, balanced, premium composition.
Main Subject (Pose – Match Reference Image Exactly)
A photorealistic athletic woman partially emerging out of the Instagram frame into real 3D space
Seated pose identical to the reference image:
Both legs bent and angled to the side
One knee slightly raised and closer to the chest
Arms gently wrapped around the raised knee
Hands relaxed, fingers naturally resting
Torso leaning slightly back against the frame edge
Expression: calm, thoughtful, self-assured
Gaze: looking slightly to the side and upward, not engaging the camera
Natural body proportions, relaxed posture, editorial realism
No exaggerated curves, no artificial posing
Clothing (Nike Only – Realistic Fit)
Muted ivory / off-white Nike fitted short-sleeve blouse
Soft neutral tone that contrasts beautifully with the background
Visible white Nike swoosh
Natural fabric stretch and tension
Deep blue Nike athletic pants, length up to the knee
Tailored, performance-fit silhouette
Realistic fabric weight with subtle folds at the knee bend
Clean stitching and breathable sports material
Clean white Nike sneakers
Slight wear realism
Correct sole texture and stitching
Premium sportswear look, real commercial styling
No distortion, no fantasy fashion
Background (Inside the Instagram Post Only)
Dark indoor gym or studio environment
Cool blue and muted purple cinematic lighting
Soft haze in the background
Subtle volumetric light beams barely visible
Shallow depth of field, background softly blurred
Subject and Instagram frame remain sharp and dominant
Lighting & Photorealism
Studio-grade cinematic lighting
Soft key light illuminating the subject naturally
Gentle rim light outlining the body and Instagram frame
Realistic skin texture with visible pores and natural highlights
Accurate contact shadows where the subject touches the frame
Physically correct light falloff and reflections
Footer UI (Engagement Section)
Instagram action icons: like, comment, share, save (accurate icons)
Text visible: "785 likes"
Caption begins with June
Caption text:
Freedom isn't found in comfort.
It's built in the quiet moments where discipline meets belief.
Hashtags partially visible and naturally cropped
Overall Style & Quality
Ultra-high resolution
Advertising-grade realism
Clean, modern, editorial Instagram aesthetic
Hyper-realistic blend of 3D object + real photography
No extra elements
No text errors
No distortion
Looks like a real product photoshoot, not AI art

Create image of Magazine feature article [travel] guide page, cute, information dense photo book style magazine feature article page. Add all necessary sections, tips, recommendations, information. add photos for any sections and recommendations if you like. Place the attached person at the precise location of [city, country]. Seamlessly blend the attached person as if they are sightseeing. Approach this task with the understanding that this is a critical, information rich page that will significantly influence visitor numbers, text accuracy is important. Fully use the entire [9:16] page. NEGATIVE PROMPT: coordinate texts @swiat_ai @ProfitAII

A 9:16 vertical screen screenshot of a Douyin live stream, space live stream style. Trump is wearing a NASA-style white spacesuit, with the helmet visor half open, revealing his signature golden hair and smile. He is floating inside the cabin of the International Space Station doing a live stream, in a microgravity weightless state, with his body slightly suspended. He is holding up a metal nameplate fixed to the spacesuit with both hands, and the nameplate says "Thanks to Songguo Xiansen for the big rocket" in NASA-style print. Behind him, the blue Earth and deep space can be seen through the circular porthole. The live stream interface shows the online viewer count as "Earth + Mars total 8.88 million". In the bullet screen area, someone is commenting "Really live streaming from space?" and "Songguo Xiansen's rocket sent you up to the sky". The rocket gift effect in the center of the screen echoes a real rocket launching in the space outside the window, forming a combination of virtual and real effects. There are various precision instruments and control panels inside the cabin, with green and blue indicator lights flashing. The color tone of the picture is mainly dark blue, white, and gold, with starlight from outside the porthole embellishing it, 8K ultra-high definition, visual effects at the level of the movie "Gravity".

Express [an awesome AI builder] in a graffiti sketch style, overall presenting a visual effect of quick sketching, free deformation, impromptu hand-drawing and draft-like. The lines are casual, exaggerated, and can vary in thickness, slightly messy but with rhythm and expressiveness, emphasizing summarization, exaggeration, fun and casualness, rather than rigorous realism or fine depiction. The colors use rough blocks with obvious dry brush feel, retaining uneven smearing traces, brush strokes, flying white and covering feel, the colors automatically adapt according to [theme/subject], but overall maintain a graffiti-style, sketch-style, and summarized expression. Do not use transparent watercolor smudging effects, do not use delicate watercolor transitions, do not use paper texture, do not use soft atomization, do not use dreamy texture. The background is mainly blank, keeping it simple, relaxed, unfinished and designed, can add a small amount of auxiliary symbols, arrows, marks, circled drawings, repeated lines, casually written text or other graffiti elements, to enhance the sketchbook or essay-style visual language, but it must not be too crowded, and must not destroy the subject and blank temperament. The picture content does not need to be written clearly in advance; [an awesome AI builder] automatically deduces and generates the most suitable subject image, movements, related elements, symbols or simplified scenes, overall maintaining a unified graffiti sketch style and exaggerated summarized expression method, avoiding complex realistic backgrounds and excessive padding. The exclusive signature "BlanPlan" needs to be naturally added into the picture as a part of the picture, the position is low-key but clear, can be placed in the bottom left corner, bottom right corner or near the title, the style needs to be unified with the overall layout, like an artwork signature or design sign-off; the signature font is exquisite, restrained, and high-end, must not be too large, must not destroy the subject composition, must not appear abrupt or cheap.

Create {argument name="quantity" default="24"} LINE stickers of {argument name="animals" default="animals"} in a quirky hand-drawn style. Target {argument name="target audience" default="Japanese Gen Z"} with a trendy style that can aim for top downloads.

A cinematic side-profile portrait of a rugged man with a tied-back bun and full beard, wearing round dark sunglasses and a textured leather jacket. His skin is detailed and slightly weathered. The background is a futuristic sci-fi interface filled with glowing orange and red data streams, star maps, celestial navigation diagrams, grids, and holographic UI elements. Fiery particle effects and ember-like energy swirl around him, creating a cosmic, high-tech atmosphere. Dark color palette with strong contrast, dramatic lighting, ultra-detailed, sharp focus, 8K, cyberpunk aesthetic, cinematic composition, depth of field.

gameplay screenshot of a lion fighting against an npc in gta san andreas

Generate a set of iconfont for a sports app

A hyper-realistic UI/UX mockup displayed on a slim modern laptop placed on a minimal wooden desk with soft natural daylight. The screen shows a clean SaaS dashboard with elegant typography, glassmorphism cards, smooth gradients, subtle drop shadows, and neatly spaced components. Visible charts, analytics panels, sidebar navigation, and micro-interactions. Realistic macOS-style window frame, soft reflections on the screen, shallow depth of field, cozy workspace atmosphere, shot in photorealistic product photography style, ultra-detailed.

社交App匹配成功界面，两个用户资料卡碰撞爱心特效

{
  "type": "e-commerce livestream UI mockup",
  "subject": {
    "description": "photorealistic young Asian woman, sweaty glowing skin, long dark wavy hair, wearing a white short-sleeve polo shirt and white pleated tennis skirt, holding a white tennis racket over her right shoulder, looking directly at camera, studio lighting, white background"
  },
  "layout": {
    "top_header": {
      "host_info": {
        "name": "{argument name=\"host name\" default=\"Little Deer Sports Premium\"}",
        "stats": "128,000 likes for this session",
        "button": "Follow"
      },
      "rank_tag": "Rank 3 on sales leaderboard",
      "viewer_stats": "12,000"
    },
    "top_right": {
      "coupon": {
        "title": "Exclusive livestream coupon",
        "value": "¥20 available for orders over ¥199",
        "button": "Claim"
      }
    },
    "left_overlay": {
      "title": "{argument name=\"campaign title\" default=\"Summer Sports Season\"}",
      "subtitle": "{argument name=\"campaign subtitle\" default=\"Energetic Start\"}",
      "bullet_points": {
        "count": 3,
        "items": ["Breathable and quick-drying", "Stretchy and comfortable", "Versatile for sports"]
      }
    },
    "right_overlay": {
      "product_cards": {
        "count": 2,
        "card_1": {
          "status": "Currently explaining",
          "image": "white polo shirt and skirt flat lay",
          "title": "{argument name=\"product name\" default=\"Sports Polo Shirt Set\"}",
          "details": "White · Size M",
          "price": "{argument name=\"price\" default=\"¥129\"}",
          "button": "Go buy now"
        },
        "card_2": {
          "status": "Hot selling x 156",
          "image": "miniature of main model",
          "title": "Women's Sports Polo Shirt Set",
          "details": "Breathable quick-drying, slimming, versatile",
          "price": "{argument name=\"price\" default=\"¥129\"}",
          "button": "Grab"
        }
      }
    },
    "bottom_left": {
      "chat_messages": {
        "count": 5,
        "description": "scrolling chat messages with usernames and comments"
      },
      "purchase_alert": "User_6789 and 2 others are purchasing"
    },
    "bottom_bar": {
      "input_field": "Say something...",
      "icons": {
        "count": 5,
        "types": ["smile", "shopping cart", "heart", "gift", "more"]
      }
    }
  }
}

Wu Zetian taking a selfie, registering and posting on Weibo.

Generate a screenshot of a Douyin live stream, featuring a beautiful woman wearing traditional Chinese clothing selling goods during the live broadcast.

```json
{
  "type": "mobile live-streaming e-commerce interface mockup",
  "subject": {
    "description": "young Asian woman, long dark hair, wearing light-colored floral pajama set with a pink bow, holding the pajama top outward to show the fabric",
    "background": "cozy room, clothing rack with pajamas, flowers, warm lighting"
  },
  "ui_layout": {
    "top_bar": {
      "time": "20:34",
      "host_info": {
        "name": "{argument name=\"host name\" default=\"Yu Pajamas\"}",
        "stats": "128,000 likes this session",
        "button": "Follow"
      },
      "viewer_info": {
        "avatars_count": 3,
        "total_viewers": "12,000"
      }
    },
    "floating_tags": {
      "count": 2,
      "labels": ["Top 3 in sales ranking", "Popularity ranking"]
    },
    "widgets": {
      "top_left": "red envelope icon with timer 03:45",
      "top_right": "floating heart icon with text Live stream great items, discover new favorites"
    },
    "marketing_text_overlay": {
      "position": "mid-right",
      "lines_count": 5,
      "lines": [
        "{argument name=\"main headline\" default=\"New pajamas\"}",
        "{argument name=\"sub headline\" default=\"Flash sale in progress...\"}",
        "Skin-friendly and breathable",
        "Soft and comfortable",
        "Pilling-resistant and colorfast"
      ]
    },
    "chat_log": {
      "position": "bottom-left",
      "message_count": 7,
      "messages": [
        "32 Yu*** joined the live stream",
        "Xiao***: Looks good, how much is it?",
        "Xiao***: Ordered, waiting for shipping",
        "C***: Quality looks good",
        "Yong***: Height 165cm, weight 60kg, what size should I get?",
        "@***: Is the item the host is wearing in stock?",
        "Qing***: Ordered, waiting for delivery!"
      ]
    },
    "product_card": {
      "position": "bottom-right",
      "thumbnail": "miniature of the host",
      "title": "{argument name=\"product title\" default=\"[Yu Pajamas] New Spring Home Wear Set\"}",
      "tags_count": 2,
      "tags": ["7-day no reason return", "Shipping insurance"],
      "price_section": "Flash sale price ¥ {argument name=\"product price\" default=\"89.9\"}",
      "action_button": "Grab"
    },
    "bottom_bar": {
      "input_placeholder": "Say something...",
      "icon_count": 5,
      "icons": ["smiley face", "shopping cart", "heart/gift", "gift box", "three dots"]
    }
  }
}
```

Generate a screenshot of a TikTok live stream, a beautiful woman is live streaming, the beautiful woman is holding a sign in her hand, on which it says: Thank you Brother Xingzhe for the big rocket!

```json
{
  "type": "mobile social media app UI mockup",
  "platform": "Twitter/X dark mode",
  "header": {
    "status_bar": "time 19:28, bird icon, signal, wifi, battery",
    "navigation": "back arrow, 'Tweet' title"
  },
  "post": {
    "author": {
      "avatar": "portrait of a Chinese emperor in red robes and black hat",
      "display_name": "{argument name=\"display name\" default=\"Emperor Zhu Yuanzhang\"} 👑 [verified badge]",
      "handle": "{argument name=\"handle\" default=\"@Emperor_Ming\"}"
    },
    "content": {
      "text": "{argument name=\"tweet text\" default=\"I have ascended to the Dragon Throne! Today, I am proclaimed as the Emperor of the Ming Dynasty. The era of Hongwu has begun. Let us rebuild our great nation together!\"}",
      "hashtags": "#MingDynasty #HongwuEra #NewBeginning",
      "media_grid": {
        "count": 3,
        "images": [
          "emperor seated on an ornate golden throne in red and gold robes",
          "wide shot of a grand Chinese palace courtyard with a large crowd",
          "emperor on horseback leading an army with a red dragon banner"
        ]
      }
    },
    "metadata": {
      "timestamp": "{argument name=\"timestamp\" default=\"1:36 PM · Jan 23, 1368\"}",
      "engagement": "5,432 Retweets, 8,765 Quotes, 20.1K Likes, 102.3K Views"
    },
    "actions": "reply, retweet, like (red heart with '1'), share, upload"
  },
  "footer": {
    "reply_bar": {
      "avatar": "woman in red",
      "placeholder": "Reply to Emperor Zhu Yuanzhang..."
    },
    "navigation_bar": "home, search, notifications (red '1' badge), messages"
  }
}
```

{
  "type": "e-commerce livestream screenshot mockup",
  "scene": {
    "subject": "{argument name=\"main subject\" default=\"Caucasian male resembling Sam Altman\"}",
    "clothing": "dark green crewneck sweater",
    "action": "holding a black product box in one hand and pointing at it with the other",
    "setting": "dark studio with a microphone on the left, faint 'AI' text in the background",
    "props": [
      "black mug with white OpenAI logo",
      "stack of 4 black product boxes on the right"
    ]
  },
  "product_design": {
    "box_color": "black",
    "logo": "orange asterisk or sunburst",
    "text": "{argument name=\"product name\" default=\"Claude Opus 4.7\"}"
  },
  "ui_overlays": {
    "top_left_product_info": {
      "brand_tag": "Anthropic Official Flagship Store",
      "title": "{argument name=\"product name\" default=\"Claude Opus 4.7\"}",
      "subtitle": "{argument name=\"main headline\" default=\"Stronger Reasoning·Higher Intelligence\"}",
      "sub_subtitle": "Most Powerful Model: Opus 4.7 Grand Release!",
      "bullet_points_count": 3,
      "bullet_points": ["Superior Reasoning Capabilities", "Peak Coding Abilities", "Effortlessly Handle Complex Tasks"]
    },
    "top_right_live_status": {
      "viewer_info": "Live | 528,000 viewers",
      "promo_banner": "Exclusive Live Stream Benefits Limited Time Offer·Miss It and It's Gone",
      "countdown": "Countdown 00:09:47"
    },
    "middle_right_price_card": {
      "header": "{argument name=\"product name\" default=\"Claude Opus 4.7\"} Live Stream Exclusive Price",
      "price_currency": "¥",
      "price_value": "{argument name=\"promotional price\" default=\"0.47\"}",
      "price_unit": "/per million tokens starting from",
      "original_price": "Original Price: ¥1.89",
      "button": "Buy Now"
    },
    "bottom_left_chat": {
      "message_count": 9,
      "input_box_placeholder": "Say something..."
    },
    "bottom_right_banner": {
      "headline": "Altman's Top Recommendation! Choose Claude Opus 4.7",
      "subheadline": "Smarter · Safer · More Reliable",
      "feature_tags_count": 4,
      "feature_tags": ["Powerful Reasoning", "Coding Wizard", "Safe and Reliable", "Lightning Fast Response"]
    },
    "floating_elements": [
      {
        "type": "sticker",
        "position": "middle right over product boxes",
        "text": "{argument name=\"sticker text\" default=\"The Most Powerful AI Model Ever!\"}"
      }
    ]
  }
}

Ultra-realistic conceptual portrait of a young woman with long wavy hair and soft defined features, wearing rose-tinted rectangular sunglasses, an oversized ivory cropped t-shirt, fitted light-wash denim jeans, and clean white sneakers. She is sitting casually with a confident yet relaxed posture.

The twist: she is seated on a large, hyper-realistic version of her own detached head placed on the ground. The head is scaled up, lying sideways, with the same facial features and sunglasses, creating a surreal self-reflection concept.

Composition: centered, full-body shot, neutral studio background with soft blush and cream tones, minimal aesthetic. Clean negative space.

Typography integrated into the background:

Handwritten-style text at the top: "OVERTHINKING"

Below it, smaller text: "TRAPPED IN MY OWN HEART" with "HEART" crossed out

Large, rough, scribbled text in deep pink: "MIND"

Lighting: soft diffused studio lighting, subtle shadows, high detail, fashion editorial quality.

Style: blend of surrealism and modern luxury streetwear campaign, pastel feminine aesthetic, minimal yet expressive, high-resolution, 8k, sharp focus, natural skin texture.

Mood: introspective, emotional weight, identity, self-awareness, quiet confidence.

{
  "type": "mobile livestream e-commerce interface mockup",
  "subject": {
    "person": "Elon Musk",
    "clothing": "black t-shirt with SPACEX logo",
    "pose": "gesturing towards camera with both hands, explaining enthusiastically",
    "watermark": "@Proof AI"
  },
  "background": {
    "setting": "large display screen",
    "image": "Mars landscape with Starship rocket and dome habitats",
    "text": [
      "SPACEX",
      "{argument name=\"background title\" default=\"Mars Immigration Plan\"}"
    ]
  },
  "ui_layout": {
    "header": {
      "broadcaster_info": {
        "name": "{argument name=\"broadcaster name\" default=\"ElonMusk\"}",
        "stats": "758,000 likes in this stream",
        "follow_button": "Follow"
      },
      "viewer_stats": {
        "avatars_count": 3,
        "text": "100,000+",
        "close_button": "X"
      },
      "tags": [
        "Top 1 in sales ranking",
        "More live streams >"
      ]
    },
    "product_card": {
      "position": "mid-right",
      "status": "Explaining",
      "image": "Mars dome habitats",
      "title": "{argument name=\"product title\" default=\"Mars immigration basic package\"}",
      "price": "{argument name=\"product price\" default=\"¥99.00\"}",
      "action_button": "Grab"
    },
    "chat_overlay": {
      "position": "bottom-left",
      "join_alert": "Star Sea joined the livestream",
      "messages_count": 7,
      "messages": [
        "{argument name=\"top chat message\" default=\"Dreamer: Support Musk!! 🚀\"}",
        "Mars Brother: How much per person?",
        "Tech Fan: So cool! Want to go to Mars!",
        "Future is here: How to sign up?",
        "Little Rocket: 🌹🌹🌹",
        "Universe Invincible: Explain some details",
        "East is Invincible: Old Ma is awesome! 👍👍👍"
      ]
    },
    "bottom_action_bar": {
      "input_placeholder": "Say something...",
      "icons_count": 4,
      "icons": ["shopping cart", "gift box", "heart planet", "plus sign"]
    },
    "floating_reactions": {
      "position": "bottom-right",
      "elements": "stack of floating hearts, thumbs up, and laughing emojis"
    }
  }
}

{
  "instruction": "Use the provided two character images as exact visual references. Preserve identity, face, outfit, proportions, and details perfectly.",
  "concept": "{argument name="game concept" default="AAA fighting game scene presented as a Tekken-style gameplay grid storyboard"}",
  "layout": {
    "type": "3x3 grid",
    "description": "nine panels showing a continuous fight progression with full game UI visible in each frame"
  },
  "panels": [
    "panel 1: dramatic VS screen — character A vs character B, both facing each other, glowing background, versus text in center",
    "panel 2: round start — both fighters in idle stance, READY text on screen",
    "panel 3: FIGHT moment — cinematic spark explosion as fight begins",
    "panel 4: first attack — character A throws a punch with motion blur",
    "panel 5: counter attack — character B kicks with impact sparks",
    "panel 6: combo sequence — multiple hit sparks, motion trails, dynamic camera",
    "panel 7: low health moment — health bar flashing red, tension moment",
    "panel 8: finishing move — slow motion heavy hit, cinematic angle",
    "panel 9: KO screen — opponent falling back, huge KO text, particles flying"
  ],
  "style": "{argument name="art style" default="ultra realistic AAA Tekken-style fighting game, cinematic gameplay rendering, highly detailed characters, realistic lighting"}",
  "camera": "in-game fighting camera, slightly angled side view, dynamic zoom during impacts",
  "environment": "high-end fighting arena, dark background with neon accents, subtle depth, not distracting",
  "ui_elements": {
    "health_bars": "top left and right, detailed, glowing, decreasing across panels",
    "timer": "center top",
    "player_names": "top left and right",
    "round_indicator": "visible",
    "combo_counter": "appears during hits",
    "hit_effects": "sparks, flashes, light streaks",
    "KO_text": "large, bold, center screen in final panel",
    "READY_FIGHT_text": "arcade-style bold typography"
  },
  "effects": [
    "motion blur on attacks",
    "impact sparks",
    "energy trails",
    "camera shake effect",
    "slow motion feeling in finishing hit",
    "screen glow during hits"
  ],
  "color_grading": "{argument name="color grading" default="high contrast, arcade cinematic, vibrant highlights, deep shadows"}",
  "output": "clean 3x3 grid, perfectly aligned panels, full UI visible, no logos, no watermarks"
}
"reference_style": "Tekken 8 gameplay UI, arcade fighting game interface, modern AAA fighting HUD"

A high-fashion studio portrait of a young woman reclining sideways on the floor against a seamless light gray background, cropped from about the hat down to the hands, with the face intentionally obscured by a soft rectangular blur. She wears an elegant white dress with sheer ruched fabric, sculpted floral appliqués along both shoulder straps and the bodice, and a fitted, ethereal silhouette. Her hair is {argument name="hair color" default="dark brown to black"} and styled in 2 long bubble braids, one on each side, each tied off with multiple white bands creating rounded segments. She wears a dramatic white fascinator hat tilted to one side, made of layered mesh, netting, ribbon loops, lace trim, and several airy feather sprays. Pose her leaning on one forearm with the other hand extended near the lower edge of the frame, torso angled diagonally for a refined editorial composition. Use soft diffused studio lighting, smooth skin tones, minimal shadows, luxury bridal-fashion styling, monochrome white wardrobe accents, and a clean polished magazine aesthetic.

A realistic overhead photo of a childlike crayon drawing on a slightly wrinkled white sheet of paper placed on a wooden tabletop. The drawing shows a simple portrait of {argument name="character" default="Donald Trump"} in a naive elementary-school style, with messy yellow crayon hair, peach-colored skin, large ears, a blue suit jacket, white shirt collar, and a red necktie. The face is front-facing and fills most of the page, with one raised hand on the left side of the paper making a rude gesture with the middle finger extended. The linework is uneven black pencil or crayon outline, and the coloring is rough, scribbly, and intentionally clumsy, with visible childlike strokes that go outside the lines. On the right side of the page, there is vertical handwritten Japanese text in black that reads {argument name="side text" default="とらんぷさん"}. The composition is a candid smartphone snapshot, not a clean scan, showing the entire sheet of paper, slight perspective distortion, soft indoor lighting, and the texture of the wooden surface around the page. Emphasize the authentic handmade crayon texture, awkward proportions, and convincing “bad but charming” children’s artwork aesthetic.

A two-page black-and-white manga spread set in a nighttime high school band rehearsal studio, drawn in polished modern shonen/seinen manga style with detailed screentones, dramatic lighting, expressive speed lines, and glossy instrument rendering. The scene shows 4 visible band members in school uniforms: a surprised teenage boy with messy short hair at guitar and vocal mic, a calm beautiful teenage girl with very long flowing light hair playing electric guitar in the foreground, a petite long-haired teenage girl at a keyboard, and a drummer in the back whose face is intentionally obscured by a soft blur. The studio has large windows revealing a city skyline at night, hanging ceiling lights, amps including a visible Marshall stack, a drum kit with a band logo on the bass drum, cables, and a wall sign reading “Beat Box.” Compose it as a printed manga spread with 7 panels total across 2 pages, including gutters, page borders, and page numbers 13 and 14 at the bottom. Left page: 3 panels — top panel with the shocked boy turning toward the girls and a large Japanese speech bubble saying “え!?”; middle panel is a close-up of the long-haired guitarist girl with a calm expression and a Japanese speech bubble saying “……別にいいよ”; bottom panel is a wider full-band rehearsal shot with all 4 members in the studio. Right page: 4 panels — top panel is an explosive performance shot with the boy singing and playing while the long-haired girl plays guitar, with large sound-effect text “ジャッ”; middle panel is a dynamic close-up of the long-haired guitarist playing intensely, with flowing hair, musical note symbols, radiant speed lines, and the keyboard girl visible in the back; bottom panel is a close-up of the boy’s stunned face with soft bokeh and a vertical Japanese speech bubble saying “……あれ”. Emphasize the emotional contrast: awkward surprise turning into admiration as the girl’s guitar performance changes the mood. Use monochrome only, no color, authentic manga lettering, cinematic framing, layered depth, and highly detailed hair and instrument strings.

A warm, shallow-depth-of-field autumn photograph of multiple fallen maple leaves scattered across dark asphalt pavement in bright golden sunlight. The leaves are mostly yellow, orange, and amber, with one prominent vivid orange leaf in the left foreground and several yellow leaves stretching diagonally into the distance. The camera is low to the ground, close-up, with crisp focus on the central foreground leaves and soft bokeh blur in the background and extreme foreground. Across the middle of the image, overlay large delicate handwritten Japanese text in white, thin brush-pen style, slightly irregular and emotional, reading {argument name="overlay text" default="今日も、寒いね。"}. Natural outdoor lighting, cozy seasonal mood, realistic textures, high contrast between sunlit leaves and rough pavement, square composition, poetic social-media aesthetic.

A moody square winter photograph looking straight up at an overcast gray-blue sky during active snowfall, framed on all sides by tall leafless trees with dark bare branches reaching inward from the edges to create a circular canopy. Snowflakes of many sizes are falling across the entire image, with some large soft blurred flakes close to the lens and many smaller sharp flakes scattered deeper in the scene, creating a dreamy atmospheric depth. At the very bottom edge, faint silhouettes of shorter winter trees and a subtle warm amber streetlight glow appear near the lower right, while the rest of the image stays cold, muted, and dim like dusk or early evening. Across the center, overlay large emotionally expressive Japanese handwritten brush-pen style text in white, slightly uneven and natural, reading {argument name="quote" default="また、この季節がやってくる。"}, with a human handwritten feel, soft edges, moderate stroke variation, and casual line breaks spread over the middle of the sky. Emphasize melancholic nostalgia, poetic Japanese winter atmosphere, cinematic minimalism, realistic photography, and authentic hand-drawn lettering integrated cleanly over the snowfall.

A TV screen capture (16:9) of a Japanese variety information program. A style similar to programs like "The World Unknown to [Person]."

Screen Composition:

Main Video: An extreme close-up of {argument name="food item" default="soy sauce ramen"} from {argument name="restaurant name" default="Mona Hanten"} (showing steam, chashu pork, green onions, and soft-boiled egg beautifully).

Telop groups (the program-specific grammar of massive on-screen text):
- Top banner telop (white text on a red background): "{argument name="show title" default="The World of Neighborhood Chinese Restaurants"}"
- Bottom main telop (bold yellow characters with shadows): "Lines at a small shop in Osaka! The legendary Chinese cooking girl"
- Bottom right wipe (small window): A silhouette of an MC with a surprised expression
- Program logo in the top left
- "During VTR" telop in the top right

Additional telops (reaction-style from performers):
"What, this level of skill at 18!?" (speech bubble telop)

The overall format is identical to a TV screen capture of a variety show. The sense of multi-layered telops is realistic.

A candid smartphone photo of a young East Asian woman sitting at a small table inside a casual Taiwanese breakfast shop, medium shot in vertical 9:16 composition. She has shoulder-length straight dark brown to black hair with a side part and is wearing a fitted ribbed camisole in {argument name="top color" default="light gray"}, high-waisted light blue denim shorts, and a loose sheer white cardigan slipping off both shoulders. She is seated on a black chair and holding a foil-wrapped breakfast rice roll or sandwich with both hands close to her mouth as if about to take a bite. Her body is angled slightly to the right, with a relaxed, natural pose and a soft lifestyle-photo aesthetic. Place a large rectangular blur censor block over her face, centered and covering the entire face area. On the table in the lower left foreground, include 1 large takeaway cup with a plastic lid and 1 red straw. In the background, show the open storefront interior of a traditional breakfast stall with stainless steel counters, a glass warming display, condiment bottles, 1 worker behind the counter, 1 wall fan, and overhead menu boards with red and blue Chinese characters and prices. Also include a glass door on the left with Chinese signage and hours posted. Lighting should be natural daylight, slightly soft, with realistic skin tones, casual street-photo realism, shallow depth but still readable background details, authentic urban Taiwan eatery atmosphere.

A realistic, casual outdoor smartphone selfie of a {argument name="subject age" default="middle-aged woman"} from the chest up, framed slightly off-center and shot at arm’s length on a phone camera. She has voluminous shoulder-length wavy hair in a warm {argument name="hair color" default="auburn red"}, softly tousled by a light breeze and glowing with golden backlight from the low sun behind her. She is wearing a dark {argument name="top color" default="deep forest green"} V-neck knit top or cardigan, a delicate thin chain necklace, and a small hoop earring barely visible through her hair. The setting is an outdoor terrace or walkway beside a pale stone wall, with leafy trees filling most of the background and a faint building partially visible through the branches. The sun appears in the upper left corner, creating natural lens flare, warm rim lighting around the hair, gentle highlights on the shoulders, and realistic late-afternoon golden hour contrast. The composition should feel organic and unpolished rather than studio-perfect: slight handheld phone-camera perspective, natural skin texture, casual posture, authentic lighting, shallow depth from the phone sensor, and a candid everyday social-media selfie aesthetic.

{"type":"LEGO parts list infographic page","subject":"clean printed inventory sheet for a custom LEGO build","style":"minimalist instruction-manual graphic, flat white background, crisp black sans-serif typography, subtle light gray row dividers, editorial layout","page":{"orientation":"portrait","background":"white","margin":"generous"},"header":{"icon_count":2,"icons":["small cardboard package emoji/icon at top left","small brown square color swatch icon before section title"],"title":"PARTS LIST (with LEGO / BrickLink IDs)","section_title":"{argument name=\"section title\" default=\"Base & Ground\"}"},"table":{"columns":["Part","Description","Color","Qty"],"row_count":8,"rows":[{"Part":"3811","Description":"Plate 12×12","Color":"Tan","Qty":"1"},{"Part":"3024","Description":"Plate 1×1","Color":"Dark Green","Qty":"12"},{"Part":"3023","Description":"Plate 1×2","Color":"Dark Green","Qty":"10"},{"Part":"3022","Description":"Plate 2×2","Color":"Dark Tan","Qty":"8"},{"Part":"3068b","Description":"Tile 2×2","Color":"Light Bluish Gray","Qty":"6"},{"Part":"3070b","Description":"Tile 1×1","Color":"Light Bluish Gray","Qty":"10"},{"Part":"4073","Description":"Plate Round 1×1","Color":"Green","Qty":"8"},{"Part":"6064","Description":"Plant Leaves 6×5","Color":"Green","Qty":"2"}]},"customization":{"title":"{argument name=\"headline text\" default=\"PARTS LIST (with LEGO / BrickLink IDs)\"}","section":"{argument name=\"section title\" default=\"Base & Ground\"}","accent_color":"{argument name=\"accent color\" default=\"brown\"}","page_style":"{argument name=\"document style\" default=\"LEGO instruction manual inventory sheet\"}"},"composition":"title aligned upper left, section label directly below, large 4-column table centered below with evenly spaced rows, all text left-aligned except quantity column visually narrow at right","quality":"high-resolution print-ready mockup, sharp vector-like text rendering"}

A young woman with {argument name="hair color" default="long red hair"} sitting on a towel at a {argument name="location" default="sunny beach"}. She is wearing a {argument name="outfit" default="fitted beige tank top and light blue denim shorts with a brown belt"}. She holds sunglasses in one hand and looks off into the distance while the other hand rests in her hair. The background features soft sand, palm trees, and a clear blue sky with warm golden sunlight casting natural highlights. A small handbag sits beside her. The atmosphere is bright, summery, and relaxed.

A dreamy minimalist square image of a single iridescent soap bubble floating in the center against a deep blue soft-focus background, with bright natural sunlight pouring from the upper left and creating delicate lens flare, circular bokeh, and glowing highlights. The main bubble is sharply rendered with rainbow reflections and a tiny star-like sparkle on its lower right edge, while 6 additional out-of-focus bubbles appear around the frame: 1 large partial bubble at the lower left corner, 1 small bubble near the upper center, 1 faint bubble at the left middle, and 3 soft glowing bubbles clustered along the lower middle to lower right area. Across the center, overlay large handwritten Japanese brush-style text in white that reads {argument name="headline text" default="はじける泡。"}, with an emotional hand-drawn ink feel, slightly uneven strokes, and natural organic spacing. The overall mood is poetic, airy, luminous, and nostalgic, with shallow depth of field, premium photography aesthetics, clean composition, and strong contrast between the crisp central bubble and the blurred dreamy background.

A candid nighttime balcony selfie of a young woman shot from a slightly high handheld phone angle, with the face mostly obscured by shadow and framing, emphasizing the outfit and mood rather than facial detail. She has {argument name="hair color" default="dark brown"} long loose wavy hair falling over both shoulders, medium tan skin, and wears 2 delicate gold necklaces, one a thin chain and one with a small cross pendant, plus a subtle bracelet on the wrist visible near the bottom edge. Her outfit is a fitted white sleeveless cropped tank top and {argument name="bottoms" default="light blue low-rise denim jeans"}, revealing the midriff. The pose is relaxed and slightly leaning, one arm extended to hold the phone, with a casual going-out aesthetic. Set the scene on a modern apartment balcony at night with a glass railing and a blurred distant city skyline filled with small bokeh lights. Use dim ambient lighting with a direct phone flash that illuminates the torso and hair, creating strong contrast, soft grain, slight motion blur, and an authentic late-night social-media selfie look. Vertical smartphone composition, close crop from upper chest to hips, realistic photography, moody, intimate, unpolished, natural proportions.

A high-fashion studio portrait of a seated woman in an ethereal bridal look against a seamless light gray background, framed vertically from headpiece to the trailing ends of her hair. She wears a flowing sleeveless white gown with a high gathered neckline, sheer pleated chiffon over the bodice, delicate white floral appliqué clustered at the neck, chest, waist, and upper skirt, and a soft draped skirt spread around her on the floor. Her hair is {argument name="hair color" default="deep dark brown"} and styled into 2 extremely long oversized bubble ponytails, one on each side, each segmented with white ties; the left ponytail shows 4 visible bubble sections and the right ponytail shows 3 visible bubble sections, with both tails extending onto the floor in thick glossy loops. She also wears an elaborate white fascinator hat tilted to one side, made of lace, netting, and sculptural floral details. Pose her leaning diagonally with one hand braced on the floor and the torso angled, creating an elegant editorial fashion posture. Keep the mood refined, bridal, and avant-garde, with soft diffused lighting, realistic skin texture, crisp textile detail, minimal shadows, and a clean luxury magazine aesthetic.

A warm, cozy Japanese home evening scene photographed in a natural lifestyle style. In the foreground, a right hand holds up a tall clear pint glass of golden beer with a thick creamy white foam head, positioned slightly right of center as if making a solo toast. In the softly blurred background, a small clay pot of oden simmers on a portable tabletop gas stove, with clearly visible ingredients including 1 shiitake mushroom, 2 round white items, several tofu pieces, and other assorted simmered items in broth. The setting is a tatami room with warm ambient indoor lighting, shallow depth of field, and a relaxed intimate atmosphere. Overlay large white handwritten Japanese text across the image reading {argument name="message text" default="今日も\nおつかれさま。"}, in an emotional hand-drawn marker style with uneven strokes, casual spacing, and a personal note-like feel. Emphasize comforting colors, soft bokeh, realistic skin tones, and the contrast between the crisp beer glass and the gently out-of-focus hot pot behind it.

Create a premium Korean palm reading guide image based on the uploaded palm photo.

All visible text in the final image must be Korean only. Use clean Korean sans-serif typography. The title must be exactly “손금 분석 가이드”.

Create a refined two-panel layout:
Left panel: place the uploaded real palm photo inside a clean rounded card. Preserve the original hand shape, palm lines, skin texture, and natural details. Do not distort or redraw the hand.
Right panel: create a separate black-and-white palm contour interpretation diagram based on the same hand. Highlight the main palm lines with thin precise lines and label them in Korean.

Include Korean labels and sections:
“손금 분석 가이드”, “전체 요약”, “생명선”, “두뇌선”, “감정선”, “운명선”, “재물선”, “태양선”, “결혼선”, “성격”, “직업운”, “재물운”, “연애운”, “조언”, “확인 불가”.

Analyze palm shape, finger proportions, life line, head line, heart line, fate line, wealth line, sun line, marriage line, line depth, length, direction, breaks, branches, and overlaps. If something is unclear, write “확인 불가”. Keep the Korean interpretation short, realistic, calm, and advisory.

Design style:
1:1 square format, white background, black and warm dark gray text, thin hairline dividers, rounded cards, subtle shadows, large margins, generous negative space, precise grid, minimal line pictograms, luxury editorial report, high-end wellness analysis, elegant and expensive-looking.

No English text, no roman letters, no broken Korean, no random glyphs, no colorful decoration, no cartoon style, no occult symbols, no tarot imagery, no horror mood, no messy background, no watermark.

A clean 2x2 conceptual entity model infographic on a soft light background, showing four separate floating isometric diorama tiles that personify branches of {argument name="theme" default="science"} in a polished 3D illustration style with pastel gradients, glossy materials, soft ambient lighting, subtle shadows, rounded futuristic forms, and high detail. Top left: BIOLOGY, a lush bio-lab island with a large central DNA double helix tower, curved glass greenhouse architecture, spiral stairways, layered organic pathways, greenery, plant beds, and fluid biomorphic structures; the word "BIOLOGY" is integrated on the front edge of the platform. Surrounding this tile are 4 small biology-related icons: a microscope, a DNA symbol, a sprouting plant, and a circular cell or petri-dish symbol. Top right: PHYSICS, a high-tech energy laboratory tile in cool blue tones with a central glowing platform, circular accelerator rings, copper-like electromagnetic coils, stairs leading up to the core, a monitor screen with waveform graphics, and a futuristic industrial base labeled "PHYSICS"; add 4 surrounding physics-themed icons: an atom, a horseshoe magnet, a lightning bolt, and a line graph waveform. Bottom left: CHEMISTRY, a modular molecular research structure in purple and silver, built from spheres-and-rods lattice frameworks, lab columns, beakers, flasks, and a glowing crystalline core; the platform prominently reads "CHEMISTRY" on two visible sides. Surrounding this tile are 4 chemistry-related icons: two molecular diagrams, a pair of lab test tubes or flasks, and a small burner. Bottom right: ASTRONOMY, a rocky lunar observatory island with cratered terrain, a dome observatory, a telescope, stairs carved into the rock, and a circular cosmic starfield backdrop behind it; the front edge reads "ASTRONOMY". Surrounding this tile are 4 astronomy-themed icons: a ringed planet, spark-like stars, a small rocket, and a crescent moon. Keep all 4 tiles evenly spaced in a quadrant layout, each with its own muted geometric backdrop shape, cohesive pastel palette tuned per discipline, and a premium gpt-image-2 style that makes each concept feel like a collectible miniature world. No people, no extra text beyond the four discipline labels.

high contrast street silhouette, strong directional sunlight from doorway, deep shadow foreground, bright overexposed exterior, {argument name="action" default="subject walking through doorway"}, full body silhouette, clear outline, minimal detail, cinematic composition, urban street photography style --2:3

A black-and-white manga page spread with 5 panels on a clean white background and thin black gutters, drawn in highly detailed modern seinen/shoujo hybrid line art with soft screentones, reflective highlights, and a quiet melancholic mood. The setting is a nighttime music studio classroom with large windows showing a city skyline full of lit buildings against a dark sky. Main subject: a slender high school girl with very long straight light hair and blunt bangs, delicate features, and a serious introspective expression, wearing a Japanese school uniform consisting of a white button-up shirt, loosened striped ribbon tie, and plaid skirt, seated and playing a solid-body electric guitar that resembles a Stratocaster. In the large upper-left panel, show her in three-quarter view holding the guitar across her lap, left hand on the fretboard and right hand near the pickups, surrounded by studio equipment including 1 drum kit in the back left, 2 stacked guitar amplifiers on the right, and a wall sign reading "Beat Box" near the door. In the narrow upper-right panel, show a close-up of the guitar neck and her fretting hand, with the small vertical Japanese sound effect text "トン…". In the tall middle-right panel, show a close side-profile close-up of the girl looking down at the instrument with a pensive, almost disappointed expression, with the night city lights blurred through the window behind her. In the lower-left panel, show 1 teenage boy in a school blazer and loosened tie, seated indoors and turned slightly to the side; his face is obscured by a large soft gray rectangular censor block, and beside him is 1 vertical speech balloon containing the Japanese text "……やっぱり違う". In the lower-right panel, show a closer view of the same boy from the chest up against a soft bokeh screentone background; his face is again obscured by a large gray censor block. Add printed page numbers centered at the bottom margins: "5" under the left page and "6" under the right page. Emphasize a subtle narrative theme of realizing that the sound feels wrong, as if this is a continuation page from a dramatic school-band manga. Keep everything monochrome, polished, cinematic, and emotionally restrained.

A photorealistic vertical beach portrait of a young woman kneeling on pale sand while building sandcastles, shot in bright natural midday sunlight with a shallow depth of field. She has long dark brown hair tied in a high ponytail, a slim figure, and wears a short deep-blue sundress with thin spaghetti straps, a plunging neckline, and a softly flared skirt. She is leaning forward toward the camera in a playful candid pose, both hands shaping the sand in front of her. Add a delicate thin necklace with a tiny pendant and a subtle bracelet. Place exactly 5 sandcastle elements in the foreground: 2 taller turret-like sand towers on the right, 2 smaller rounded sand mounds near the center front, and 1 partially formed sand piece in her hands. The background is a tropical beach with smooth beige sand, turquoise water along the left side, a green tree-covered shoreline in the distance, and palm trees arching overhead, including 1 large palm trunk on the right edge. Use soft bokeh in the background, clean summer vacation fashion photography, realistic skin tones, natural shadows from palm leaves across her arms and dress, and a serene luxury resort atmosphere. Frame it as a full-body to three-quarter portrait in portrait orientation, centered subject, eye-level to slightly low camera angle.

create a hyper-realistic 3D render of a transparent {argument name="platform" default="twitter"} profile card, designed like a futuristic glass ID badge held gently between two fingers. The card should be rectangular with rounded corners, made of clear glossy glass or acrylic, with glowing neon edges in {argument name="glow colors" default="pink, purple, and orange gradient"} inspired by the twitter color palette. Display the following profile information based on the screenshot image attached of my profile on the card using modern, minimal sans-serif typography.

{argument name="character" default="Pan Jinlian"} posting a beauty tutorial on {argument name="platform" default="Bilibili"} titled "{argument name="topic" default="How to Conceal Blemishes Using Ancient Methods"}," with bullet comments saying "Sister-in-law's technique is amazing!"

A dramatic cinematic action shot of a {argument name="child" default="12-year-old boy"} with messy dark hair powerfully kicking a soccer ball on a {argument name="setting" default="green grass stadium field"} at golden hour sunset. The soccer ball is massively oversized and zoomed-in in the foreground, dominating the lower part of the frame like viral "giant object" photos, extremely detailed texture, black and white panels, sharp focus. The boy is captured mid-kick with his right leg extended, dirt and grass particles flying dramatically. He wears a {argument name="clothing" default="crisp white t-shirt"} with bold black text "GPT IMAGE 2.0" printed on the chest, black athletic shorts, white socks with black stripes. Dynamic low-angle perspective, vibrant saturated colors, ultra-sharp clarity, high contrast, cinematic lighting with warm golden sun rays breaking through dramatic clouds, shallow depth of field, 8k photorealistic, hyper-detailed, National Geographic style --ar 3:4 --stylize 250 --v 6

Create a high-fidelity Chinese music app player interface screenshot in mobile portrait orientation, with refined visuals similar to a modern streaming player. Use dark mode, with the background derived from a blurred and diffused version of the album cover colors. Place a large square album cover in the center with subtle shadow and rounded corners.

Interface requirements:
- top status bar with time 18:26
- navigation bar with a back arrow on the left, a centered title, and a more-options icon on the right
- playback progress bar showing current time 01:42 and total duration 04:18
- playback controls for shuffle, previous, play/pause, next, and repeat
- lyrics section showing 5 to 7 scrolling lines, with the current line highlighted
- action row with like, comment, download, add to playlist, and share
- bottom area with device casting and playback queue entry

Use these exact Chinese labels and names:
- title: "正在播放"
- song name: "海边的晚风"
- artist: "林秋"
- album: "夏夜实验室"

The lyrics layout, button icons, reflections, shadows, and dark-mode layering should feel like a real production interface rather than a Dribbble concept.

Generate a Chinese fitness infographic for [topic].

The graphic should be both professional and practical for a normal adult to use as a training reference. Unless otherwise specified, assume the audience is a healthy adult with no major injuries, the goal is muscle gain plus basic strength improvement, the level is beginner to intermediate, the setting is a normal gym, and the total session length should stay within 40 to 60 minutes.

Choose the output format automatically based on the training topic:

1. If the topic is a muscle group or body part, such as chest, lats, biceps, abs, shoulders, or legs, generate a training-plan infographic for that body part.
2. If the topic is an exercise or skill goal, such as pull-up, push-up, dips, or squat, generate an exercise-unlock or progression-plan infographic.

Use a clear, modern, professional, easy-to-read Chinese infographic style in vertical format. The visual design should be clean and suitable for social sharing or personal training reference. Do not write long paragraphs. Each module should use short concise phrases, and numerical information should be prominent.

The infographic must include:
A. Title area with main title and subtitle
B. Training goal area
C. Warm-up area
D. Main training area with 4 to 6 core exercises
E. Progression or unlock logic area
F. Alternative exercises area
G. Execution reminders area
H. Recovery suggestions area
I. Visual design requirements: modern, clean, professional, modular card layout

The final result should be a complete infographic rather than plain text paragraphs.