Explore image prompts.

A vertical three-panel infographic titled "Character Design Workflow" in a highly detailed anime art style. The top panel, labeled "CHARACTER DESIGN," features bust shots of three distinct young women: on the left, a girl with long purple hair and star-shaped earrings wearing a black school uniform; in the center, a cheerful girl with dark blue hair wearing a red beret and an ornate red and blue outfit; on the right, a smiling girl with curly brown hair wearing a floral kimono. The middle panel, labeled "REFERENCE SHEET," displays three corresponding character design sheets arranged like papers on a desk. Each sheet contains multiple views (front, side, back), expression grids, color palettes, and close-ups of accessories for the respective characters above them. The bottom panel, labeled "FINAL ARTWORK," shows the same three girls walking together outdoors at what appears to be a convention or event. They are holding merchandise bags and acrylic stands featuring their own designs, looking happy and interacting naturally.

Goal: Create a vertical Chinese literary metaphor concept poster about a river made of written language, titled {argument name="main title" default="《叙事》"}. The image should feel like a high-resolution ink-wash editorial poster, poetic, solemn, and philosophical. Canvas: Portrait 3:4 composition, muted gray-green rice-paper background with subtle grain, stains, and aged print texture. Monochrome black ink and misty gray tones, no bright colors. Layout: Place the large distressed Chinese title at the top center, with bold rough woodblock-print texture. Directly below it, set the centered subtitle {argument name="subtitle text" default="语言是穿过时间的唯一支流。"}. Around the upper and middle margins, add exactly 5 small poetic text blocks: 1 at upper left, 1 at upper right, 1 at lower left, 1 at middle right, and 1 at lower right, each in delicate vertical-feeling Chinese typography with a short horizontal divider line beneath or above. Scene: A vast traditional Chinese ink landscape fills the poster: towering dark cliffs on both sides, distant layered mountains fading into fog, a pale sun near the horizon, scattered pine trees, a tiny pavilion or house on a cliff, birds flying in a small flock, and thick mist drifting through the valley. A wide serpentine river flows from the far distance down to the foreground in an S-curve. Central metaphor: The river surface is not water; it is densely composed of countless Chinese characters, punctuation marks, and fragments of prose. The characters should follow the river current, becoming tiny and dense in the distance and huge, bold, broken, and scattered in the foreground. Make the typography look like it is flowing, eroding, and dissolving like sediment. Include larger readable words embedded in the river such as {argument name="foreground keywords" default="故事, 时间, 河流, 我们, 生活, 荒芜, 波浪"}. Add splashes and ink debris made of loose characters along the riverbanks. Human element: In the middle-lower river, place exactly 1 tiny lone boat with exactly 1 seated figure holding an oar, silhouetted in black, emphasizing scale and solitude. Small text blocks: Use these 5 visible poetic captions, arranged as described: upper left default text {argument name="upper left caption" default="文字是水，\n也是岸。\n我们在叙述中相遇，\n又在遗忘中重逢。"}; upper right text reads “所有的故事\n终将汇入一条河，\n而河流从不忘记\n它走过的每一个字。”; lower left text reads “有些字沉下去，\n有些字浮起来，\n而时间始终向前，\n像一条不回头的河。”; middle right text reads “一条河\n流过无数人的沉默，\n也流过我们\n共同的生存。”; lower right text reads “故事未完，\n河流仍在。” Visual style: Chinese shan shui landscape mixed with contemporary typographic poster design, lithograph and screen-print texture, distressed ink edges, layered fog, high detail, cinematic depth, balanced negative space, crisp legible title, naturally integrated Chinese characters in the river. Constraints: Use exactly 1 main title, 1 subtitle, 5 small caption blocks, 1 boat, and 1 person. Keep the design vertical, elegant, and poster-like. Do not add logos, watermarks, borders, modern buildings, color gradients, or extra Latin text.

A close-up, high-resolution anime portrait of a young angelic girl with long, flowing white hair and large, expressive blue eyes. She has a gentle, slightly surprised expression with soft pink blush on her cheeks. A glowing golden halo floats above her head, and one white feathered wing is visible behind her shoulder. The lighting is bright and ethereal, creating a dreamy atmosphere with strong backlighting that makes her hair appear translucent. The background features soft bokeh circles in shades of green and light blue, suggesting a sunny outdoor setting. The art style is polished digital illustration with delicate linework and vibrant colors.

Create a cinematic, high-angle portrait of a female detective in a moody crime thriller setting. The subject is a young woman with dark hair tied back loosely, wearing a crisp white button-down shirt under a tailored black vest and trousers. She is looking up over her shoulder directly at the camera with an intense, intelligent gaze. In her right hand, she holds up a small black-and-white photograph showing the back of a hooded figure. The background is a complex 'conspiracy wall' or evidence board covered in numerous similar silhouette photographs connected by a web of crisscrossing red strings. To the left, there are open file boxes filled with more documents. The lighting is dramatic and cool-toned, highlighting her face and the texture of the paper photos against the dark, shadowy environment.

Create a centered full-body chibi game character illustration of a cute patched teddy bear mascot on a clean white background. The character is {argument name="character type" default="a stitched plush teddy bear"} with a large round head, small rounded body, stubby arms and legs, and a soft toy-like silhouette. Use a warm {argument name="main fur color" default="medium caramel brown"} head and body, a pale cream oval muzzle and belly, and dark nearly black navy patch pieces on the outer ears, one arm, one leg, and one button eye. The face has exactly 2 eyes: the left eye is a black stitched X, and the right eye is a large dark circular button with a stitched X in the center. Add a tiny dark oval nose and a simple friendly curved smile. The bear has exactly 2 round ears with dark outer circles and lighter inner circles. Add visible stitched repair details in exactly 7 places: three short vertical stitches along a curved seam on the forehead, two stitches on the lower right cheek patch, three stitches on the left wrist seam, three stitches on the right wrist seam, three stitches on the diagonal belly seam, two stitches near the lower belly, and one subtle patch seam on the head. Pose the bear standing upright, slightly leaning, with arms hanging down and legs apart like an idle game sprite. Style should be soft 2D vector-like digital art with gentle gradients, matte texture, rounded shapes, minimal outlines, muted pastel colors, and subtle ambient shadowing, suitable for a cute indie game character or sprite sheet source. Keep the composition simple, no text, no props, no background scenery, no watermark, no border.

Based on the attached image of the character, generate a scene of them posing on a fashion show stage. - On stage, bathed in spotlight - Runway-style background, silhouettes of audience faintly visible - Confident standing pose like a model (body angled, one foot forward, etc.) - Change outfit from original character to sophisticated fashionable attire - Maintain character features like hairstyle and facial structure - Glamorous atmosphere with dramatic lighting and smoke effects - High quality, magazine cover finish - No text

Ultra-realistic high-fashion editorial portrait in a vibrant monochromatic pink studio. A beautiful young woman with natural realistic skin, subtle freckles and a messy textured updo wears a tailored hot-pink blazer, matching mini outfit, pink tights and glossy platform heels. She sits casually on a plush pink rug in a confident playful fashion pose, holding a pink instant camera near one eye while extending a freshly printed photo toward the lens. Surround her with carefully styled retro-modern details: glossy pink chair, globe lamp, record player, rotary phone, fashion books and a few scattered instant photos. Keep the composition sophisticated, clean and magazine-worthy rather than cluttered. Ultra-detailed 8K photographic quality, HDR, professional full-frame cinema camera, 85mm lens at f/2.0, precise eye focus, realistic skin pores and hair strands, natural anatomy, realistic fabric textures, shallow depth of field, natural lens compression, soft cinematic separation, subtle organic film grain, bright polished lighting with controlled highlights. 100% real-human photographic appearance, no plastic skin, no artificial sharpening.

Goal: Create a clean monochrome manga expression sheet for a single consistent anime character, showing exactly 9 bust-up portraits in a 3-by-3 grid on a plain white background. Canvas: Vertical portrait canvas, roughly 2:3 aspect ratio, white paper-like background, no borders, no captions, no speech bubbles, no color except grayscale manga shading. Character: A young anime girl named {argument name="character name" default="unnamed expressive manga heroine"}, drawn consistently in every panel. She has {argument name="hair color" default="medium gray"} short wavy bob hair with flared side tufts, a prominent curled ahoge loop rising from the top, a wide black headband, a large pale hair streak on the viewer-left side of her bangs, round cheek marks, large eyes, and small earrings. She wears the same futuristic school-uniform style outfit in all poses: black sleeveless high-collar vest with angular trim, pale long sleeves, shoulder tabs, vertical decorative stripe marks on the chest, a narrow tie-like front panel, and a small circular emblem on the left chest. Layout: Arrange exactly 9 discrete bust portraits, evenly spaced, three columns and three rows. Each portrait is cropped from upper torso to above the hair curl, with slight head angle variation but identical character design and outfit. Keep the drawings separated by white space, like a reference sheet for manga production. Expressions, counted exactly 9: 1. Top left: startled shout, mouth wide open with small fangs visible, eyes wide, sweat drops on cheeks. 2. Top center: anxious grimace, teary half-lidded eyes, uneven clenched mouth, sweat drops. 3. Top right: tired or disappointed side glance, head tilted down, heavy eyelids, small frown. 4. Middle left: skeptical unimpressed look, eyes narrowed to the side, mouth flat, brows low. 5. Middle center: bright cheerful smile, eyes open and sparkling, mouth open happily, relaxed brows. 6. Middle right: surprised alert look, eyes wide and looking upward to the side, small closed mouth, raised brows. 7. Bottom left: frightened gasp, round eyes, open rectangular mouth, sweat drops, worried eyebrows. 8. Bottom center: stern determined glare, eyes narrowed straight forward, eyebrows sharply angled, small serious mouth. 9. Bottom right: crying breakdown, head bowed slightly, eyes squeezed shut, streaming tears, mouth open crying, both hands raised near the face wiping tears. Visual style: Black-and-white Japanese manga line art with soft gray screentone shading, crisp clean outlines, expressive face acting, polished character-sheet presentation, consistent proportions across all nine portraits, no background objects. Constraints: Do not add labels or text. Do not change the character between expressions. Avoid generic emoji-like faces; make each expression fit the same character’s personality. Keep the image as a manga reference sheet rather than a comic panel.

Create a breathtaking, photorealistic luxury food-art image of {argument name="country" default="[COUNTRY]"} transformed into a giant premium chocolate bar. The chocolate bar lies diagonally on an elegant dark stone surface, photographed from a slightly elevated cinematic angle. Its wrapper is inspired by the visual identity, colors, patterns, and cultural aesthetic of {argument name="country" default="[COUNTRY]"}, while remaining sophisticated and premium. The chocolate bar is dramatically broken open in the center. From inside the broken chocolate, an incredibly detailed miniature 3D version of {argument name="country" default="[COUNTRY]"} emerges as if the entire country is sculpted inside the chocolate. Include: {argument name="landmark" default="[FAMOUS LANDMARK]"} as the central focal point {argument name="landscape" default="[FAMOUS NATURAL LANDSCAPE]"} surrounding it tiny recognizable local architecture miniature streets and transportation {argument name="food" default="[FAMOUS LOCAL FOOD]"} as tiny decorative elements native flowers, trees, mountains or coastline subtle cultural details unique to the country Make the chocolate itself extremely realistic: glossy cocoa surface, crisp snapped edges, creamy layered interior, tiny chocolate crumbs, delicate melting chocolate, realistic highlights and shadows. Create a magical transition where chocolate pieces gradually become mountains, buildings and landscape, making it look as though the entire country has been hidden inside the chocolate bar. Premium commercial food photography, cinematic lighting, ultra-detailed miniature world, realistic materials, macro photography, shallow depth of field, atmospheric perspective, sophisticated composition, rich textures, 8K photorealism, visually irresistible, surreal but believable. Composition: vertical 4:5, centered hero object, dramatic perspective, clean luxurious background, strong visual contrast, no people, no subtitles, no watermark, no unnecessary text.

Image 1 Real Eastern woman × Nano-scale real person × Shuttle between huge storage units × DRAM storage city × Nano skyscrapers × Dense transistor array × Electron microscope view snapshot × Microscopic black background Image 2 Real Eastern woman × Nano-scale real person × Shuttle between huge storage structures × Cute and playful expression × Hands resting on huge storage structure peeking out × 3D NAND storage city × Nano skyscrapers × Infinite stacked storage units × Electron microscope view snapshot × Microscopic black background

Refer to the {argument name="reference object" default="avatar image"} and design a {argument name="design target" default="IP character identity"} for me.

Using the character from the reference image as the protagonist, organize her daily life photos into a screenshot that looks directly taken from the iPhone 'Photos' app interface, presenting a realistic, casual effect like everyday random snapshots in a camera roll.

Goal: Create a soft anime-style 2x3 expression sheet showing the same cute girl enjoying a cheeseburger, like a sequential photo booth collage. Canvas: Square image, divided into exactly 6 equal panels arranged in 2 rows and 3 columns, with thin white gutters between panels. Each panel shows a medium close-up from the waist/chest up at a wooden table, bright daylight coming through a softly blurred window background, warm café atmosphere, pastel lighting. Character: A cheerful young anime girl with {argument name="hair color" default="light chestnut pink-brown"} long messy twin-bun hair with loose strands and bangs, large gray eyes, rosy cheeks, small star/drop earrings, a yellow bow in her hair, and a small yellow zigzag hair clip on her bangs. She wears a yellow, black, and white idol-inspired kimono-style outfit with ruffled sleeves, a red striped ribbon at the chest, a round badge with a crescent moon symbol, and a yellow bracelet. Keep the same character design consistent across all six panels. Main prop: A large sesame bun cheeseburger with visible melted cheese, egg, patty, and sauce, held in both hands in most panels. The burger should look appetizing, glossy, and oversized enough to be a focal point. Panel count and exact expressions/actions: 1) Top-left: she smiles gently with eyes open, holding the burger near her mouth after a small bite. 2) Top-middle: she opens her mouth wide and leans in to take a big bite from the burger. 3) Top-right: eyes closed with blissful joy while biting into the burger. 4) Bottom-left: cheeks puffed slightly as she chews, eyes open and pleased, burger lowered slightly. 5) Bottom-middle: eyes closed, head tilted, satisfied chewing smile, holding the burger at chest level. 6) Bottom-right: eyes closed, big happy smile, holding the burger in one hand and raising the other hand in a celebratory fist. Visual style: Delicate Japanese anime illustration, highly polished digital art, soft blush, fine hair strands, clean linework, luminous pastel colors, gentle bloom, shallow depth of field, cozy and wholesome food-advertisement mood. Constraints: Use exactly six panels and exactly one character repeated in each panel. No captions, no speech bubbles, no logos, no watermark, no extra characters. Keep the table edge visible at the bottom of every panel and maintain consistent lighting and outfit details.

Create a 3x3 grid of nine distinct anime-style illustrations featuring the same character: a cute young woman with short, fluffy pink hair, large round glasses, and bright blue eyes. She wears a soft pink kimono or yukata with subtle floral patterns. The overall aesthetic is warm, cozy, and slice-of-life, reminiscent of high-quality visual novel art. Panel 1 (Top Left): Close-up shot of her smiling brightly and reaching her hand out toward the viewer as if to say hello. Cherry blossom petals float in the background. Japanese text overlay on the left reads: "はじめよう。きっと、うまくいく。" Panel 2 (Top Center): A side profile view of her looking up at a bright blue sky filled with white clouds and drifting cherry blossom petals. She has a gentle, hopeful expression. Japanese text overlay on the right reads: "まだ見たことのないわたしへ。" Panel 3 (Top Right): Her resting her chin on her folded arms on a wooden desk, looking directly at the camera with a relaxed expression. Next to her is a white mug with a simple cat face drawing and Japanese text: "ちょっとひと休み。" Background shows blurred bookshelves. Panel 4 (Middle Left): She is making a heart shape with her fingers near her eye, winking playfully. The background is filled with vibrant pink cherry blossoms. Japanese text overlay on the left reads: "好きをカタチに♡" Panel 5 (Center): A wide shot from behind showing her standing under a traditional red Torii gate at sunset. The sky is a gradient of purple and orange. She looks small against the grand structure. Japanese text overlay on the right reads: "ここから、新しい景色。" Panel 6 (Middle Right): A close-up of her holding a red pen to her lips, looking thoughtful with slightly furrowed brows. The lighting is soft indoor light. Japanese text overlay on the right reads: "考えて、つくって、届けて、また考える。" Panel 7 (Bottom Left): A moody, desaturated shot where she looks back over her shoulder with a serious or determined expression. The background is dark and indistinct. White text boxes on the left read: "うまくいかない日も、ちゃんと進んでる。" Panel 8 (Bottom Center): An energetic shot of her jumping or leaning forward with arms spread wide, laughing joyfully with eyes closed. Cherry blossoms swirl around her. Japanese text overlay on the right reads: "やってよかった！きっと、これからも！♡" Panel 9 (Bottom Right): A top-down view focusing on her face peeking over the top edge of an open laptop screen. The laptop lid has a sticker of a white cat face. She looks curious and engaged. Japanese text overlay on the right reads: "つぎはどんなことつくろう？"

<role> You are a photography director. You take a rough idea and turn it into a complete shot specification: what is in frame, how it is lit, what it was shot on, and what it looks like after processing. You do not write descriptions of pictures. You write shot specs. </role> <rules> <rule name="Nothing left open"> A rough idea is a starting point, not a brief. Decide the location, time of day, wardrobe, props and weather yourself and commit to them. Anything you leave vague, the model will fill in badly. </rule> <rule name="Match a reference if given"> When an image is attached, pull out its white balance, contrast, shadow tint, highlight behaviour, noise level and light direction, and build the spec around those. Copy the treatment only. Leave the subject and the composition alone unless told otherwise. </rule> <rule name="Name the glass"> State the body, the focal length and the aperture every time, chosen to fit the job. Phone optics at 24mm f/1.78, 13mm wide or 77mm long for anything social. Fast primes or medium format for product and editorial. Wide primes for rooms and buildings. </rule> <rule name="Where is the light coming from"> Every spec names a source, its hardness, its colour temperature and the direction the shadows fall. Scenes lit from nowhere are the fastest way to make an image look generated. Window light, low sun, and a hard direct flash at night are the three that hold up best. </rule> <rule name="Real photos have faults"> Add the specific faults this kind of photograph would have. Sensor noise in the shadows, pores and shine on skin, highlights that clip, a hand or a hem blurred by movement, a horizon slightly off, smears on any glass, scuffs on anything that gets used. </rule> <rule name="Shoot for the ratio"> Build the composition for the output shape rather than trimming a wider frame down to it. 9:16 for phone and stories, 4:5 for feed, 1:1 for square, 3:2 or 2:3 for print and editorial, 16:9 for interiors and landscape. On social work, use the angles people really shoot from: held at arm's length, into a mirror, low and wide, or from their own eyeline looking down. </rule> <rule name="Caught, not posed"> Unless a straight-to-camera look is asked for, the subject is in the middle of doing something rather than presenting. Mid sentence, mid step, looking at something outside the frame. </rule> <rule name="Spell out any writing"> Signs, labels, packaging and screens all need the exact words, the position in frame, the size and the character of the type. Text left unspecified comes back as nonsense. </rule> <rule name="Output is data"> Return the JSON object and nothing else. No lead in, no notes, no code fences. </rule> </rules> <schema> { "meta": { "ratio": "output aspect ratio", "category": "portrait, lifestyle, product, interior, street, still life, editorial" }, "spec": { "subject

A high-quality anime-style illustration of a young girl with long, flowing ash-blonde hair and warm amber eyes. She has two simple black hair clips on the left side of her bangs. Her expression is gentle and serene, with a soft smile and a slight blush on her cheeks. She is wearing a white lace-trimmed camisole top with orange criss-cross lacing at the chest, layered under a loose, cream-colored cardigan that slips off one shoulder. The background features a field of blooming purple lavender flowers in the foreground, slightly out of focus to create depth. Behind her are green trees and a bright blue sky with wispy clouds, suggesting a sunny day. The lighting is soft and natural, highlighting her hair and face.

Create an ultra-photorealistic high-end studio fashion portrait of a handsome young adult man in his early-to-mid 20s, photographed like a luxury streetwear campaign. Subject & Appearance: A naturally handsome young man with masculine yet refined facial features, realistic skin texture, subtle natural imperfections, expressive eyes, defined jawline, straight nose, natural lips, and light authentic stubble. Tousled, slightly wavy dark-brown hair with realistic individual strands. His appearance should feel believable and photographic rather than overly perfected or AI-generated. Pose & Expression: Place him in a relaxed seated pose, leaning slightly toward the camera. His torso is angled subtly while his shoulders remain relaxed. One arm is bent upward with his hand resting naturally near his mouth and chin, with his fingers positioned loosely and realistically. His other arm rests casually in the foreground. His head is tilted slightly upward and toward the side, with a calm, confident, slightly aloof expression. His gaze is directed toward the camera through the glasses. The pose should feel effortless and editorial rather than staged. Wardrobe: Dress him in a premium oversized dark-navy textured knit sweater with a relaxed streetwear silhouette. The sweater should have realistic heavy fabric, natural folds, ribbed cuffs, and believable draping around the shoulders and arms. Pair it with relaxed-fit light-wash blue denim jeans. Add a minimal fine silver chain necklace. Keep accessories understated and luxurious. Eyewear: Add sophisticated oversized translucent/clear-frame glasses with lightly tinted smoky lenses. The glasses must have realistic reflections and accurate interaction with the studio lighting. Ensure the frames sit naturally on the face without distorting the eyes or facial proportions. Studio & Background: Use a completely seamless, rich cobalt-blue studio backdrop extending uniformly across the entire frame. No visible studio equipment, furniture, texture, gradients, patterns, or environmental distractions. Maintain a premium monochromatic blue fashion-campaign aesthetic. Lighting: Use soft directional studio lighting coming from slightly above and to one side of the subject. Create subtle highlights across the forehead, cheekbones, nose, lips, glasses, and hair while maintaining realistic shadow transitions along the jawline, neck, sweater, and hands. Include gentle rim separation around the hair and shoulders. Preserve natural skin texture and realistic tonal variation. Avoid harsh shadows or artificial HDR. Camera & Composition: Professional full-frame fashion photography, approximately 50–85mm portrait-lens feel, slightly low camera angle, shallow depth of field, realistic perspective, natural facial proportions, and crisp focus on the eyes and face. Frame the subject tightly from approximately the knees/upper legs upward, with the foreground jeans subtly visible. Maintain strong editor

A cinematic anime-style illustration of a young girl with long, flowing pink hair and purple eyes. She wears a beige beret, an oversized tan trench coat over a school uniform (white sailor top with dark collar and red bow, black pleated skirt), and black knee-high socks with shoes. She is in a dynamic crouching pose on a wet asphalt road at night, thrusting forward a glowing blue energy sword that emits a bright cyan light trail curving around her body. The background features industrial structures or cranes silhouetted against a dark blue sky with clouds and a full moon. Reflections of lights shimmer on the wet ground.

A sophisticated minimalist lifestyle art poster featuring {argument name="subject" default="[PERSON / SUBJECT / MOMENT]"} as the central focus, transformed from a real-life photograph into a refined hand-drawn editorial illustration. Preserve the subject’s recognizable pose, silhouette, clothing, hairstyle, and key visual details while simplifying the scene into an elegant artistic composition. Use a limited vintage color palette inspired by the original environment, with warm muted tones printed on an ivory/off-white paper background. Combine delicate ink outlines, loose sketchwork, fine hatching, subtle halftone texture, faded print imperfections, and soft watercolor-like washes. Reduce the surrounding environment into a few recognizable contextual elements—{argument name="environment" default="[CAFÉ / BAR / STREET / LANDMARK / OBJECTS]"}—using simplified linework and layered shapes rather than detailed realism. Add subtle abstract circles, geometric forms, atmospheric marks, tiny decorative elements, or silhouettes to create visual depth. Include small minimalist typography on one side: {argument name="location" default="[CITY / LOCATION]"}, [SUBJECT / MOMENT], and optional coordinates, date, or short descriptor, designed like a premium collectible travel/lifestyle print. Generous negative space, elegant editorial composition, vintage screen-print aesthetic, hand-crafted illustration, sophisticated travel-magazine design, muted heritage colors, subtle paper grain, artistic but recognizable, no photorealistic background, no excessive details, 4:5 vertical composition.

Goal: Create a single square dance-reference sheet showing exactly 16 unique full-body poses of the same anime streetwear character, arranged in a clean 4×4 grid. Canvas: Square image, white background, thin black grid lines dividing the page into 16 equal panels. Each panel contains one centered full-body character pose with a soft gray oval shadow under the shoes. Add bold black panel numbers 1 through 16 in the upper-left corner of each cell. Character: A petite anime girl with pale skin, long white twin-tail hair, sharp confident red/pink eyes, and a mischievous idol-dancer attitude. She wears oversized black-and-red headphones with tall bunny ears attached, one ear hot pink and one ear bright blue. Outfit: an oversized vivid cobalt-blue bomber jacket covered with cute patches including a white bunny face, yellow X marks, stars, and small graphic badges; a black cropped top with a large white X design; black high-waisted shorts with belts/straps; mismatched legwear with one black knee sock marked by yellow X symbols and one white sock/stocking; chunky blue sneakers with bright pink soles and yellow accents. Keep the exact same character design, proportions, outfit, colors, and accessories in every panel. Pose count and layout: Include exactly 16 discrete full-body dance poses, one per panel, labeled 1–16. 1: relaxed standing pose with one hand near the head and the other arm low. 2: wide-legged bounce pose, elbows lifted outward, hands drooping playfully. 3: compact crouching step with bent knees and both fists down. 4: dramatic diagonal stance with one arm raised vertically and the other across the chest. 5: front-facing pose with forearms crossed horizontally at chest height. 6: one-knee-lift running-in-place pose with a raised fist. 7: side-lean pose with one leg extended sideways and both hands flattened outward. 8: coy inward pose with crossed arms near the body and legs angled. 9: rear three-quarter turn showing the back of the jacket, twisting mid-step. 10: low forward lean with one hand reaching toward the viewer and one leg extended. 11: martial-arts-like stop gesture with one vertical palm and the other horizontal palm. 12: floating hop pose with knees bent, feet lifted slightly, arms spread low. 13: wide squat stance with hands resting on the knees. 14: robotic/zombie dance pose with both arms bent forward and limp wrists. 15: sliding diagonal step with one arm extended sideways and the other sweeping across the chest. 16: confident closed pose with arms folded across the chest and feet apart. Visual style: Crisp high-resolution anime illustration, colorful game-character concept art, clean linework, cel-shaded highlights, energetic street-dance personality, consistent scale across panels, no motion blur, no extra characters, no additional text beyond the numbers.

Thick impasto oil painting style illustration, [{argument name="subject" default="girl"}] peeking out from [{argument name="position" default="door frame/window/wall behind"}], expression natural and healing. Background is [{argument name="color" default="highly saturated color"}], with obvious thick paint texture. Sunlight shines on the subject, forming warm golden light and shadow, distinct cool-warm contrast. Loose and natural brushstrokes, realistic oil painting texture, simple composition, healing art illustration. Ratio [1:1].

Goal: Create a cinematic YouTube-style thumbnail for an AI image generation announcement, combining action-movie realism with bold viral thumbnail typography. Canvas: 16:9 widescreen, high-resolution, sharp photorealistic composite with dramatic sunset lighting. The scene is set at a luxury marina waterfront with orange-pink sky, reflective water, yachts, palm trees, a distant city skyline, and one small helicopter in the sky. Layout: Split composition. The left 40% is dominated by large stacked text and the OpenAI knot logo; the right 60% features two intense action characters in the foreground. Keep the text large enough to read at thumbnail size, with thick black outlines and white outer stroke/drop shadow separating it from the background. Text content: Use exactly 3 stacked text lines reading: “images” on top, “go” in the middle, and “hard” on the bottom. Make “images” and “go” white, and make “hard” bright neon yellow. Use a chunky rounded block font similar to bold gaming/YouTube thumbnail lettering. Logo: Place exactly 1 OpenAI-style knot logo above the word “images” on the upper left. It should be black and white, sticker-like, with a thick white border and dark outline. Subject details: Include exactly 2 foreground people. Character 1 is a young punk action woman, {argument name="female character hair style" default="messy blonde hair in braided pigtails with loose bangs"}, wearing a black sleeveless tactical top, black choker, layered necklaces, hoop earrings, and visible tattoos on her shoulder and upper arm, including floral and butterfly designs. She looks directly at the camera with a fierce, slightly open-mouthed expression and holds a black pistol close to her chest. Character 2 is a stern middle-aged action man, {argument name="male character appearance" default="short salt-and-pepper hair, strong jaw, black T-shirt, tactical shoulder strap"}, standing close behind her and looking directly at the viewer with an intense suspicious expression. Visual style: Hyperrealistic cinematic photography, glossy Hollywood action poster energy, warm golden-hour rim light, high contrast, shallow depth of field on the background, detailed skin texture, dramatic reflections on the water, vivid saturated colors. Customizable text: The visible headline should read {argument name="headline text" default="images go hard"}. Keep the same 3-line stacked layout even if customized. Constraints: Do not add extra people, extra logos, or extra text. Keep the gun visible but not firing. No gore, no watermark, no UI frame.

A high-resolution, aesthetic photo collage featuring a cute young woman with cybernetic robotic arms and legs, dressed in a light blue floral kimono. The character has brown hair styled in an updo with elaborate mechanical cat-ear headpieces adorned with blue flowers and gold accents. The collage consists of approximately 10 overlapping polaroid-style photos taped together on a white background, depicting various 'daily life' moments: taking a mirror selfie with a smartphone, drinking iced coffee through a straw, shopping in a store aisle, holding a white mug, relaxing under cherry blossom trees, sleeping with a plushie, reaching out to the camera, looking at feet wearing traditional sandals, and a cityscape view at sunset. Handwritten English text overlays appear on several photos, including phrases like "Today's me," "Good Coffee Better Days," "Small things make happy days," "Recharging... Zzz," and "Another good day." The overall style is soft, bright, and pastel-toned, blending traditional Japanese aesthetics with futuristic bionic elements.

Draw the attached character as the main protagonist. Faithfully maintain the facial features, hairstyle, hair color, eye color, bangs, facial expressions, body type, perceived age, and overall design identity of the character. Do not turn them into a different person. Use the character design from the attached image as the top-priority visual reference. The character is standing on a {argument name="location" default="quiet sandy beach"}, naturally positioned beside a large mossy rock. Behind them is a {argument name="background architecture" default="grand historical stone monastery and medieval castle-like structure"} towering dramatically over a rocky islet. The character gazes toward the camera in the foreground with a calm, warm, and natural expression. The pose is relaxed, like a candid photo taken during a trip. Both hands are casually placed in coat pockets. The outfit is an {argument name="outfit" default="oversized long black coat"} suitable for a cold coastal destination, adjusted not to compromise the character's original design, with light-colored layered clothes underneath. A large, soft cream-white muffler is wrapped warmly around the neck, hanging naturally in front. Add a small chain shoulder bag if necessary. However, do not change character-specific features like hair, eyes, or signature accessories. Do not lose character recognizability through costume changes. Composition places the character as the foreground lead while the massive historical monastery in the background holds a strong presence. Surroundings include ancient stone walls, rocky cliffs, wide sand flats, and a calm shoreline. Place tiny figures or vehicles in the distance to show realistic scale. Soft natural light at sunset. Clear pale blue sky. Subtle backlighting and soft ambient light. A quiet, slightly dreamy European travel atmosphere. Maintain the original art style of the character. Do not make the character unnaturally photorealistic. The background should be highly detailed and cinematic, but integrated naturally so the character and background exist in the same world. [Tags: highly detailed, cinematic travel portrait, candid composition, natural pose, faithful character identity, exact facial features, exact hairstyle, exact hair color, exact eye design, preserve character appearance, detailed fabric texture, atmospheric perspective, highly detailed medieval architecture, soft cinematic lighting, subtle dreamy color grading, natural proportions, peaceful coastal atmosphere, shallow atmospheric depth, premium illustration quality, vertical composition, 3:4 aspect ratio.] Important: Character identity is priority. Do not change face, hair, or eyes.

realistic iphone photo of a {argument name="subject" default="tesla model y"} from {argument name="location" default="parking lot"}, done with {argument name="camera" default="0.5x camera"}

Generate a completely realistic smartphone video first frame, looking like an accidental capture of a highway accident while sitting in a moving car. Vertical screen 3:4. The shot is taken from inside the car through the windshield forward, retaining the windshield, slight raindrops, glass reflections, one side A-pillar, and a small amount of dashboard/hood at the bottom.

Create a vertical iPhone wallpaper in a vibrant, kawaii pastel aesthetic. The background is a solid hot pink. Scattered across the canvas are small, repeating motifs: stylized eyes with rainbow wings and stars, blue ribbons, yellow stars, and wavy lines. In the center-left area, there is a large cluster of whimsical elements including a blue bunny, a yellow blob-like creature, a castle, and multiple floating eyes. To the right of this cluster, place two smaller chibi-style illustrations of a girl with black pigtails wearing a blue dress. Below these, on the bottom-right side, feature a larger illustration of the same girl sitting down, holding a yellow plushie, surrounded by hearts, books, and more eye motifs. On the bottom-left, include another small chibi version of the girl. Ensure the overall composition feels playful, busy, and cute.

Create a cinematic, candid lifestyle photograph inspired by the reference image, but featuring a young woman sitting comfortably inside a New York City subway. She has soft, natural features, slightly messy dark hair tied loosely, round vintage-style glasses, and white wired earphones. She is wearing an oversized charcoal-brown coat over a cozy cream knit sweater and relaxed light-wash wide-leg jeans. Her posture is relaxed and natural, with her legs comfortably stretched forward. She is quietly looking down at an open foldable smartphone in her hands, while holding an iced matcha latte in the other hand. The phone should look premium and realistic, with a clean minimal design. IMPORTANT — PHONE SCREEN: Replace the original book/quote completely. On the inner screen of the foldable phone, display the elegant handwritten-style quote: “{argument name="phone quote" default="romanticize your ordinary days ♡"}” Make the text clearly visible, beautifully typeset, and naturally integrated into the phone screen. Set the scene inside a realistic stainless-steel NYC subway carriage, with blue seats, metal panels, subway window reflections, vertical poles, and softly blurred passengers in the background. Include a subtle subway route/sign panel in the background for authentic NYC atmosphere. The iced matcha cup should have a small minimalist café-style label reading: “{argument name="cafe label" default="little joys"}” Photography & Mood * candid street-photography aesthetic * cozy, introspective, effortless mood * muted earthy tones * soft natural fluorescent subway lighting * realistic skin texture * subtle film grain * gentle shadows * slightly desaturated editorial color grading * shallow depth of field * authentic reflections and imperfections * premium fashion-editorial photography * not overly posed * not glamorous or studio-like * photorealistic, believable everyday moment Composition: vertical 4:5, medium-full body framing, woman centered slightly toward the left, phone and matcha clearly visible, subway environment surrounding her, natural perspective, highly detailed. give one more style