GPT Image 2 prompts

Create a photorealistic vertical smartphone selfie-style image of an adult woman cropped from just below the nose to mid-thigh, with no face or eyes visible. She is wearing a fitted {argument name="shirt color and style" default="white short-sleeve button-up blouse with a pointed collar"} and a {argument name="skirt style" default="high-waisted black pleated skirt"}. Her {argument name="hair color and length" default="straight dark brown shoulder-length hair"} falls over both sides of her chest, with a few strands resting on the blouse. The camera is held slightly above and close to the body, angled downward in a casual mirrorless selfie perspective, showing the left arm entering from the lower-left edge. Use soft indoor natural lighting, realistic fabric wrinkles, visible shirt buttons, subtle collar shadows, and shallow depth of field. Background is an indistinct indoor room with pale flooring and a muted curtain or wall, softly blurred. Keep the composition candid and realistic, vertical 9:16 aspect ratio, no text, no logo, no watermark, no exaggerated anatomy, no explicit nudity.

Create a cinematic dark-fantasy portrait of {argument name="two central warriors" default="a regal blonde woman in ornate silver full-plate armor and a towering shirtless barbarian man"} standing side by side in front of a grand medieval stone cathedral. The composition is vertical and symmetrical, waist-to-full-body framing, dramatic realistic lighting, high-detail photorealism, gritty fantasy-film atmosphere. Include exactly 2 main foreground figures: the left figure wears intricately engraved polished silver armor, gauntlets, greaves, a pale embroidered tabard, and a long cream-white cape; the right figure is extremely muscular, wet or oiled skin, long dark curly hair, black leather-and-fur war skirt, wrapped bracers, rugged boots, and a sheathed sword at his side. Place exactly 6 background guards in reflective steel helmets and armor, holding tall polearms or spears, arranged behind the main pair like a royal battle escort. Add deep navy banners with ornate gold heraldic patterns hanging on the cathedral walls, stone paving underfoot, and a ceremonial military formation feel. Cover the visible faces with plain opaque brown rectangular censor blocks: one on the left main warrior, one on the right main warrior, and one on the left background guard. Use {argument name="visual style" default="ultra-detailed photorealistic cinematic medieval fantasy"}, rich metallic reflections, high contrast, shallow depth of field, no modern objects, no text, no watermark.

Create a vertical 9:16 anime-style fashion illustration of a slender androgynous young adult model in Y2K streetwear, shown from upper thighs to head in a low-angle studio photo pose. The character has {argument name="hair color" default="messy golden blond"} medium-length layered hair with long face-framing strands, but the face is intentionally hidden by a centered opaque beige square censor block. Pose the model with the left hand tucked in a pants pocket and the right arm raised, fingers near the ear as if adjusting an earring, giving a cool runway attitude. Include exactly 7 visible fashion elements: 1 oversized pale blue denim jacket worn open and slipping off one shoulder, 2 cropped plain white T-shirt exposing the midriff, 3 teal-blue low-rise ripped jeans, 4 black waistband with tiny abstract white markings but no readable brand logo, 5 chunky silver ear jewelry, 6 black bracelet or wrist accessory, and 7 small gold chain detail hanging from the jeans pocket. Make the jeans have exactly 3 major torn knee/thigh openings: one large rip on the left thigh, one large rip on the right thigh, and one smaller rip lower on the right leg. Use crisp high-detail Japanese anime rendering with glossy fabric highlights, sharp ink lines, warm skin shading, dramatic sunlight from above, and a bright white photography-studio background with visible black light stands, ceiling rigging, and round studio lights. Add a faint white social-media watermark across the upper hair area reading {argument name="watermark text" default="Yume@yumeK"}. Avoid any recognizable brand logos or real fashion trademarks.

Goal: Create a luxurious photographed paper-craft pop-up business card for an original anime character, like an official dimensional calling card with a full storybook world unfolding from the card.

Canvas: Vertical 4:5 image, realistic close-up product photography on a soft beige tabletop, shallow depth of field, warm natural light from the left, blurred antique mirror/gold ornament in the back left and cream roses in the back right.

Main subject: A freestanding layered pop-up card in ivory, dusty blue, pale silver, and pearl white. The card forms an arched miniature room with ornate laser-cut paper layers, filigree borders, floral decorations, and a seated anime girl in the center. The character is {argument name="character name" default="Nozomu"}, a delicate blonde girl with long straight hair, soft gray-blue eyes, faint blush, and a melancholy gentle expression. She wears a muted blue dress or oversized blouse with white frilled trim, layered necklaces, earrings, and a blue headband with white flower hair ornaments and ribbons. She sits curled up with one knee raised, one hand resting near her cheek, facing slightly right but looking toward the viewer.

Pop-up construction and countable elements: Use exactly 5 major vertical paper layers: 1 front nameplate base, 1 floral sofa/ledge layer, 1 character cutout layer, 1 ornate arched window layer, and 1 rear blue-and-ivory room backdrop. Add exactly 1 cream chandelier centered at the top. Add exactly 8 hanging crystal/star ornaments around the arch: 2 star charms, 3 diamond-shaped crystals, and 3 small teardrop crystals. Add exactly 2 decorative side lattice panels, one on each side. Add exactly 4 visible flower clusters: front left blue-white cluster, front right blue-white cluster, rear left pale cluster, rear right pale cluster. Add exactly 2 small pillows, one on each side behind the character.

Text content: On the large front plaque, write the name in elegant serif capitals: {argument name="main name text" default="NOZOMU"}. Under it, write {argument name="subtitle text" default="Silent Blue Muse"}. Under that, in smaller type, write {argument name="small descriptor text" default="official pop-up business card"}. On a tiny bottom label, write {argument name="serial number" default="No. 0001"}. On a small vertical side tag at left, include the Japanese hiragana text 「のぞむ」 in black ink.

Visual style: Highly detailed anime illustration printed on layered die-cut paper, elegant rococo and Victorian stationery motifs, pale blue floral fantasy aesthetic, thin silver linework, pearl accents, soft shadows between paper layers, realistic paper thickness, glossy highlights on crystal ornaments, refined handmade craft quality.

Constraints: The image should look like a real physical pop-up card being photographed, not a flat poster. Keep all text legible and centered on the plaques. Do not add extra characters, extra labels, watermarks, logos, hands, or packaging.

Goal: Using REFERENCE_0 as the base photo, transform it into a warm Japanese hand-drawn watercolor-and-colored-pencil scrapbook journal page while preserving the same subject, pose, school-uniform jacket, seated convenience-store window composition, rainy night mood, and anonymized/obscured face.

Style transformation: Convert the realistic photo into a cozy illustrated “late night journal” spread on beige grid notebook paper, with soft ink outlines, muted watercolor textures, visible paper grain, rounded page corners, tape scraps, doodles, arrows, hearts, raindrops, and handwritten Japanese notes. Make it feel nostalgic, cute, and slightly messy like a personal travel diary.

Scene changes and additions: Replace the plain convenience-store snack setup with a richer Japanese convenience-store meal scene. Add exactly 7 visible food/drink items on and near the counter: 1 oden cup with large Japanese label, 1 melon bread held in the subject’s hand, 1 bottled milk tea, 1 wrapped onigiri, 1 packaged snack bag, 1 small plate with an extra melon bread, and 1 small receipt/slip. Outside the window, emphasize a rainy Shinjuku night skyline with blurred neon and Tokyo Tower-like red landmark lights.

Journal layout elements: Add exactly 10 scrapbook/annotation elements around the illustration: 1 large handwritten Japanese headline at top left, 1 small English phrase “late night journal,” 1 taped label reading “Daily Konbini Life,” 1 top-right note card, 1 left-side handwritten thought box, 1 left checklist box for today’s purchases, 1 small convenience-store tote-bag doodle, 1 bottom-left Polaroid photo labeled “Shinjuku Rainy Night,” 1 bottom-right memo checklist card, and 1 speech bubble near the subject. Use arrows and tiny doodles to connect notes to the food and window view.

Text: Use mostly handwritten Japanese with a few casual English accents. Main headline text: {argument name="headline text" default="コンビニ日和。"}. Top-left English phrase: {argument name="journal phrase" default="late night journal"}. Taped label text: {argument name="tape label" default="Daily Konbini Life"}. Polaroid caption: {argument name="polaroid caption" default="Shinjuku Rainy Night"}. Memo card title: {argument name="memo title" default="MEMO"}.

Constraints: Keep the composition based on the reference rather than inventing a new character angle. Preserve the anonymous blurred/blank face. Do not make it photorealistic; it must look like an illustrated notebook page. Avoid extra characters, logos, watermarks, or clean digital UI styling.

Create a realistic high-end product photo of an anime-style action figure sealed inside a collectible retail box. The figure is {argument name="character name" default="EMA"}, a cheerful original girl character with very long flowing {argument name="hair color" default="orange-red"} hair and two front braids, but her face is intentionally covered by a centered square blur censor block. She is posed dynamically on one leg with her right hand raised in a V-sign peace pose and her other hand on her hip. Outfit details: exactly 7 main clothing pieces — yellow cropped jacket with orange sun motifs, white sleeveless top, orange high-waisted shorts, brown belt, yellow thigh-high socks, orange sneakers, and an orange backpack. Place her in a clear molded plastic blister tray with a round transparent stand at the bottom. Include exactly 3 visible accessories in separate molded compartments on the right side: a black smartphone with an orange case, a small orange spiral notebook with a sun emblem, and a matching orange pen. Packaging: tall rectangular premium toy box photographed at a slight front-right angle, white and orange gradient cardboard with gold trim, rounded clear window, star and sparkle decorations, and an elegant orange top label. Use accurate readable package text: top center says "AIDear" with "Collection" beneath it, top right says "No.001", bottom nameplate says large "EMA" with smaller "Researcher Edition" beneath, and a gold circular seal at lower right says "LIMITED EDITION". The overall style should resemble a real Japanese collectible action figure package, glossy plastic reflections, warm studio lighting, sharp product photography, orange-and-gold color theme, clean gray background, no extra figures, no extra accessories, no watermark.

Goal: Create a nostalgic anime-style scrapbook album page about {argument name="theme" default="sisters ten years ago"}, showing three pasted childhood memory photos on an open vintage photo album page.

Canvas: Vertical 3:4 image, warm cream paper background with visible book spine and page edges, soft sepia lighting, delicate old-photo texture, cozy sentimental mood.

Layout: One open album page filled with exactly 3 Polaroid-like illustrations, dried flowers, tape, handwritten notes, and a ribbon. At the top left, place an ornate label frame with the Japanese title {argument name="album title" default="思い出の1ページ"}. Use soft beige ink and small floral decorations around it.

Photo count and contents: Include exactly 3 pasted photos:
1. Upper-left photo: two young anime sisters sitting in a sunny garden preparing for a picnic or outdoor play. The older-looking girl has pink twin-tail hair and wears a brown classic lolita dress over a white blouse; the other girl has pale lavender hair and wears a black gothic lolita dress. They hold toys and dolls, with flowers, teddy bears, a jump rope, and a vintage handheld game-like object around them. Add Japanese handwritten caption below the photo: {argument name="left photo caption" default="お庭でいっしょにおひるねの準備♪\nねこちゃんもうれしそう。"}
2. Upper-right photo: the same two sisters sitting in a dreamy pink-purple bedroom near a window, reading a picture book together. Add toy blocks, a small castle, pencils, plush toys, a bunny plush, warm sunlight through curtains, and a lavender tape strip at the top corner. Add Japanese handwritten caption below: {argument name="right photo caption" default="お気に入りの絵本を読んだ日。\nお部屋いっぱいの夢をみたよ......"}
3. Bottom-center photo: the two sisters sitting together on a wooden swing under a large tree in an elegant mansion garden. Pink-haired sister in brown dress on the right, lavender-haired sister in black dress on the left, both wearing Mary Jane shoes and stockings, surrounded by rose beds and a distant European-style house. Add a diagonal tape strip at the top of this photo.

Character details: The sisters should look like cute young girls in ornate vintage lolita fashion, with large ribbon bows in their hair. Their faces should be softly obscured by simple pale rectangular blur patches, preserving the nostalgic album look while hiding facial features.

Decorations: Add exactly 5 notable scrapbook embellishments: 1 beige masking tape strip on the upper-left photo, 1 lavender tape strip on the upper-right photo, 1 beige tape strip on the bottom photo, 1 pressed flower arrangement on the lower-left margin with a daisy, tiny white flowers and a pink rosebud, and 1 purple satin bow with ribbon tails at the bottom-right corner. Also add a small pressed purple flower near the upper-right photo.

Text content: On the right side near the bottom photo, add a small handwritten Japanese note: {argument name="side note" default="10年前、花寮家の庭園にて\n一結衣と友麻\n\nいつもとなりで\n笑ってくれた大切な友だち。"}. Keep all Japanese handwriting natural, small, and slightly imperfect, like personal album annotations.

Visual style: Highly detailed pastel anime illustration, warm sunlight, soft watercolor and colored-pencil texture, delicate floral motifs, vintage scrapbook composition, cream paper, slightly curled photo edges, realistic paper shadows, gentle depth, refined shoujo atmosphere.

Constraints: Use exactly three main photos and the listed embellishments, keep the image as a single album page, avoid modern UI elements, avoid watermarks, avoid extra captions beyond the specified handwritten notes.

Goal: Create a screenshot-like collage showing a pile of unusable AI-generated fictional world map attempts on a pale gray workspace, as if viewed on an image-generation history board. The subject is not one map, but a messy contact sheet of many map thumbnails for a future fictional nation.

Canvas: Wide 16:10 landscape canvas, light gray background with a faint dotted grid pattern. Leave generous gutters between thumbnails. The entire composition should feel like a zoomed-out browser or design-board view, with some thumbnails cut off by the right edge.

Layout: Arrange exactly 35 visible map thumbnails in an irregular grid. Count them as: 8 small thumbnails across the top row, 10 large landscape thumbnails in the middle two rows, 12 smaller portrait/landscape thumbnails in the lower middle arranged in paired columns, and 5 large purple-themed thumbnails along the bottom row. Include several partially cropped thumbnails on the far right edge to imply the board continues off-screen.

Thumbnail content: Each thumbnail is a different failed variation of a futuristic world map for {argument name="fictional nation name" default="United Federation of Valoria"}. Most maps show altered Earth-like continents but not an accurate real-world map. Use dark navy or black ocean backgrounds, neon blue coastlines, cyan glowing borders, faint green landmasses, satellite-map textures, grid overlays, small HUD-like ticks, and occasional white title text. Some thumbnails should look like color tests: one bright blue-and-yellow terrain map, one simple black-outline map on white, and multiple glowing cyberpunk versions. The bottom row should use a different purple faction label, {argument name="bottom faction name" default="Empathia Union"}, with purple-highlighted landmasses around Eurasia/Australia-like shapes.

Visible labels: Repeat the title text on many thumbnails, usually centered or near the lower third, reading {argument name="main map label" default="United Federation of Valoria"}. Vary the typography and size slightly so some labels are tiny, misaligned, or awkwardly placed. Bottom-row thumbnails should instead read {argument name="purple map label" default="Empathia Union"}. A few labels may be partially illegible due to scale, cropping, or glow.

Visual style: Make it look like a collection of generated image results, not a polished infographic. Use inconsistent map compositions, inconsistent coastline shapes, different zoom levels, different title placements, and slightly mismatched aspect ratios. The dominant palette is black, deep navy, electric cyan, blue, green, and purple, with occasional white thumbnails and one or two bright terrain-map thumbnails.

Constraints: Do not create a single clean world map. Do not make the continents match the real Earth exactly. Do not add people, UI controls, large captions, watermarks, or a polished final design. Preserve the feeling of many discarded attempts scattered on a pale dotted canvas.

Goal: Create a photorealistic wide-angle documentary photo of a Japanese railway station platform featuring a full-size commuter train covered in a dark purple anime/mecha collaboration wrap for {argument name="campaign name" default="Volklasse Stängel"}, styled like a limited memorial special train.

Canvas: 16:9 horizontal image, eye-level perspective from the opposite platform, realistic station lighting, sharp details, no illustration filter.

Scene and layout: A silver commuter train is stopped along the left and center of the frame under a metal station roof. The front cab is visible at the far left with a black windshield and red LED destination text. The side of the train dominates the image and is wrapped in glossy purple graphics. On the right side of the platform, exactly 3 visible passengers stand near the train: 1 person in black holding up a phone to photograph the train, and 2 people farther right near a pillar. The platform has gray tile flooring, a yellow tactile safety strip, rails at the far left, overhead beams, fluorescent lights, and urban buildings visible beyond the station canopy.

Train wrap details: The wrap is a dramatic dark violet and black sci-fi design with gold accents. It features exactly 2 main illustrated subjects on the train side: 1 large armored purple mecha with glowing green eyes and a huge cannon on the left-center, and 1 blonde anime-style female officer seated in a cockpit-like frame on the right-center. Include layered angular panels, subtle starry textures, metallic highlights, and gold crest emblems.

Visible signage and repeated elements: Include exactly 4 campaign sign/decal elements besides the train wrap: 1 large overhead hanging banner above the platform, 1 vertical pillar poster on the right, and 2 purple square floor decals on the platform. The overhead banner should read Japanese-style promotional text plus English lines: "SPECIAL WRAPPED TRAIN" and "Limited Memorial Line," with a small gold label reading "today only service." The pillar poster should repeat the purple mecha artwork and special-train branding. The 2 floor decals should be purple squares with gold crest marks.

Text content on the train: Add large white Japanese-style title text on the train side using {argument name="main Japanese title" default="フォルクラッセ シュツェンゲル"}, smaller Roman text "Volklasse Stängel," gold serif text "SPECIAL WRAPPED TRAIN," and additional white promotional copy across the panels. Text should look like real printed train-advertising typography, integrated into the wrap, not floating.

Visual style: High-resolution realistic photography, natural daylight mixed with station shade, accurate reflections on windows and glossy vinyl, strong perspective lines, authentic Japanese commuter-station atmosphere, promotional event feel.

Constraints: Keep the train and station photorealistic, avoid extra characters or extra decals beyond the counted elements, do not add watermarks, do not make it look like a toy or miniature, and keep all advertising graphics printed on physical surfaces.

Goal: Create a vertical two-panel comparison image showing the same pair of beautiful twin sisters, {argument name="character names" default="Linlin and Lanlan"}, seated together at an outdoor European-style café, with the upper half rendered as a realistic photograph and the lower half rendered as a polished anime illustration based on the same composition.

Canvas: Tall vertical image, approximately 9:16 aspect ratio. Split the canvas horizontally into exactly 2 equal stacked panels with no large gap: top panel photorealistic, bottom panel anime style.

Layout and subjects: Show exactly 2 adult twin sisters seated shoulder-to-shoulder at a round café table, centered in both panels. They are framed from the waist or bust upward. Both have slim-to-curvy figures, warm light skin, dark brown to black hair, and relaxed café poses. The left sister has a chin-length bob haircut and wears a {argument name="left sister outfit" default="white sleeveless scoop-neck tank top with thin vertical black pinstripes"}. The right sister has long wavy dark hair and wears a {argument name="right sister outfit" default="black sleeveless scoop-neck tank top with thin horizontal white stripes"}. Their shoulders touch, and they sit in woven rattan café chairs.

Top panel: Photorealistic lifestyle photograph in bright midday sunlight. The sisters sit at a marble-topped round table; include exactly 2 visible coffee cups or small glasses near the bottom foreground. Background is a leafy boulevard café with trees, large patio umbrella overhead, wicker chairs, flower planters with white daisies, pedestrians, storefronts, and soft urban depth of field. Natural skin highlights, realistic fabric texture, realistic hair shine, documentary travel-photography feel.

Bottom panel: High-quality anime illustration of the same scene and pose, more saturated and clean-lined. Keep exactly 2 sisters, matching hair lengths and outfits from the top panel. Use glossy anime shading, warm sunlight, crisp line art, bright daisies in the foreground and sides, leafy branches overhead, lampposts, European street buildings, pedestrians, café awnings, and an umbrella pole centered above or between the sisters. The bottom foreground should show the curved edge of a café table.

Face treatment: In both panels, obscure the faces with simple soft-edged rectangular censor blocks, exactly 4 total face-obscuring rectangles: 2 in the photorealistic top panel and 2 in the anime bottom panel. The rectangles should be medium brown gradients matching skin tones and cover the facial features while leaving hair, shoulders, outfits, and pose visible.

Visual style: Top half realistic DSLR photo, bottom half modern detailed anime/comic rendering. Keep the composition aligned so the anime panel clearly echoes the photographic panel. Bright outdoor café atmosphere, lush greenery, white flowers, warm summer mood, attractive twin-sister character design.

Constraints: No text, no watermark, no logos. Do not add extra people in the foreground besides the 2 sisters. Preserve the exact two-panel structure and the exact count of 2 main women, 2 cups in the top panel, and 4 face-obscuring rectangles.

Create a highly realistic cinematic fantasy portrait of an anthropomorphic {argument name="animal species" default="gray tabby cat"} adventurer standing full-body on a narrow forest path. The character has a natural feline head and paws, short dense gray-beige fur, subtle tabby markings, bright blue eyes, upright ears, and a calm serious expression, with humanlike posture and proportions. Dress the traveler in worn medieval ranger clothing: layered frayed linen tunic, rough brown cloak and scarf, leather shoulder straps, belts, bracers, patched trousers, wrapped boots shaped around cat paws, and weathered fingerless gloves. Add exactly 7 prominent gear elements: 1 large overstuffed canvas-and-leather backpack with a rolled blanket on top, 2 leather chest straps with brass buckles, 3 belt pouches, 4 a coiled rope hanging from the pack, 5 a round metal cup or ring attached at the side, 6 two sheathed short daggers at the waist, and 7 a walking stick or wooden handle strapped behind the pack. Use an earthy palette of moss green, mud brown, taupe, tan, dark leather, and muted brass. Set the scene in an old woodland with tall tree trunks, damp leaf-litter ground, soft mist, and warm morning sunlight filtering from the upper left through blurred foliage. Compose as a vertical 2:3 image, centered subject, eye-level camera, full-body view, shallow depth of field, detailed fur and fabric textures, gritty practical costume design, photorealistic concept art, cinematic lighting, no text, no watermark, no cartoon styling.

Create a vertical cinematic dark fantasy portrait of {argument name="character name" default="a pale white-haired sword maiden"} standing in a moonlit gothic forest or ruined temple at night. The composition is a tight upper-body close-up: the character faces forward with her head slightly lowered, long messy silver-white hair glowing in cold moonlight, wearing an ornate black lace gothic outfit with sheer embroidered sleeves, dark metallic floral ornaments, a black lace choker, and a spiked black crown-like hair accessory on one side. Her face is intentionally hidden by one opaque muted gray square censor block centered over the eyes, nose, and mouth. She grips a vertical ornate longsword beside her face with one hand near the hilt at the upper left; the sword has a dark carved handle, an elaborate antique gold guard, and a luminous icy-blue blade covered in fine engraved filigree. Bright blue-white magical energy coils around the blade in swirling ribbons with sparks, particles, and mist. In the background, show exactly one full moon in the upper right, blurred dark trees and gothic silhouettes, drifting snow or dust motes, and deep blue-black atmospheric haze. Use high-detail photorealistic fantasy movie lighting, dramatic rim light on the hair, glowing sword illumination, shallow depth of field, high contrast, cold color grading, intricate textures, and no text or watermark. Aspect ratio 9:16.

Create a richly detailed anime fantasy illustration of two bubble-themed travelers planning a trip together inside a warm traditional Japanese tatami room. The scene shows {argument name="location" default="Shikotsu-Toya National Park"} travel planning, with a wooden low table covered in maps, guidebooks, photos, a tablet, a notebook, a pen, tea, and sweets. On the left sits {argument name="slime girl description" default="a translucent soap-slime girl with pearlescent clear skin, iridescent highlights, pale blue-white hair gathered into bubbly buns, and a neat blouse with a ribbon tie"}; she leans over the map thoughtfully, one hand at her chin and the other pointing to the route. On the right sits {argument name="tanuki girl description" default="a cute soap-bubble tanuki girl with fluffy brown hair, round tanuki ears, a huge striped raccoon-dog tail, layered traditional travel clothes, beads, charms, and botanical accessories"}; she holds up a small card or photo while gesturing with her other hand as if explaining the itinerary. Their faces and the raised card are deliberately covered by four flat opaque censor rectangles: one pale gray rectangle over the slime girl’s face, one medium tan rectangle over the tanuki girl’s main face area, one darker tan rectangle over the raised card/hand area near the center, and one dark brown rectangle over the tanuki ear/upper-right face area. Include exactly 24 visible soap bubbles: 8 larger scenic bubbles containing tiny miniature landscapes of lakes, mountains, forests, and travel spots; 7 smaller floating bubbles around the characters; and 9 clustered bubbles integrated into the slime girl’s hair. The room has sliding shoji doors, warm wooden beams, a scroll painting on the wall, a small flower arrangement, a glowing floor lamp, and a large open window revealing a sparkling river, rocks, and lush green forest outside. The table details should include exactly 7 main planning items: an unfolded map, an open photo guidebook, a tablet showing a landscape image, a spiral notebook with sketchy notes, a fountain pen, a cup of green tea, and a bowl of small sweets. Use luminous high-detail anime rendering, soft golden afternoon light, gentle depth of field, iridescent rainbow reflections on all bubble surfaces, cozy travel-planning mood, painterly background, intricate fabrics and accessories, no text, no watermark. Overall atmosphere: whimsical, serene, magical, and inviting, as if the two characters are building a dream itinerary for {argument name="trip theme" default="a national park hot springs and lake journey"}.

Create a vertical cyberpunk character portrait of a confident adult woman standing in a rainy neon city alley at night, framed from upper thighs to above the head. She has extremely long, thick {argument name="hair color" default="electric purple"} hair styled with a high voluminous crown, loose bangs sweeping across one side, multiple side braids, and one massive rope braid falling past her hips to the lower right. Her face is intentionally hidden by a centered solid square censor block in muted mauve-brown. She wears exactly 6 visible outfit elements: a cropped light gray tank top, a shiny metallic silver bomber jacket with purple trim, raised spiked shoulders, purple dragon embroidery on both sleeves, glossy black high-waisted short shorts, and a wide purple belt. Her pose is powerful and fashion-editorial, with one hand on her hip and the other arm relaxed, emphasizing athletic proportions and wet reflective skin. The background is a dense futuristic {argument name="city setting" default="Korean cyberpunk alley"} with wet pavement, purple and cyan reflections, dark skyscrapers, mist, and exactly 5 prominent neon signs: a pink sign on the left reading Korean-style characters with small English words like “GATCHA HOUSE,” a small blue vertical sign behind her, a tall right-side vertical pink-and-blue sign with Korean characters and “CYBER HO,” a blue right-side sign with Korean characters, and a smaller magenta sign lower right. Use cinematic ultra-detailed 3D realism, glossy materials, dramatic rim lighting, saturated violet/magenta/blue color grading, shallow depth of field, high contrast, rain-slick reflections, and polished concept-art quality. No extra characters, no watermark, no logos beyond the fictional neon signage.

Create a polished vertical anime-style cyberpunk character illustration of a confident young woman standing in the middle of a rainy neon city alley at night. She has long vivid {argument name="hair color" default="purple"} hair styled in a high messy bun with side-swept bangs and one very long thick braid falling over her shoulder down past her hips, with glossy highlights and a few smaller braided sections near the scalp. Her face is deliberately covered by a centered opaque rectangular censor block in muted dusty pink, hiding all facial features. She wears a cropped white tank top, a bright {argument name="jacket color" default="yellow"} bomber jacket with black ribbed cuffs, black spiked shoulder studs, zipper details, and embroidered blue-and-red dragon designs; count exactly 5 visible dragon embroidery motifs: 2 on the viewer-left sleeve/body area, 2 on the viewer-right sleeve/body area, and 1 near the right chest. She also wears shiny black high-waisted latex shorts, a hot pink belt with a silver buckle, and a small turquoise side accent. Pose her with a strong hourglass stance, one hand resting at her hip and the other arm bent back, torso facing forward. The background is a narrow futuristic street with wet reflective pavement, mist, dark building silhouettes, and glowing signage; include exactly 4 prominent neon signs: a pink sign on the left foreground with Korean-like characters and small English-style text, a small cyan vertical sign in the mid-left distance, a tall purple vertical sign high on the right with Korean-like characters, and a cyan sign on the right foreground. Use dramatic magenta and cyan rim lighting, rain-slick reflections, shallow depth of field, high-detail glossy rendering, clean linework, vibrant colors, and a cinematic 2:3 composition. Avoid extra characters, avoid readable brand logos, and keep the style as a high-end anime illustration with cyberpunk polish.

Goal: Create a futuristic ecommerce product overview poster for {argument name="product type" default="sheer black stockings"}, styled like a high-tech product launch page.

Canvas: Square 1:1 composition, glossy silver-gray studio background with soft gradients, faint transparent HUD lines, corner brackets, neon blue and violet accents, subtle sci-fi interface overlays, premium clean lighting.

Layout: Right side features the main fashion model occupying about 60% of the image. Left side contains the product information panel, product packaging, rolled stocking display, fabric stretch demo image, and a feature list card. Keep the composition balanced, luxurious, and minimal.

Main subject: A seated adult female fashion model on a metallic silver cube, wearing sheer black stockings, black high heels with small gold toe accents, and a fitted black dress with long sleeves, white pointed collar, and a small gold brooch. She sits with legs crossed to clearly show the stockings’ sheer texture and slim fit. Long brown hair, elegant pose, one hand near her hair. The face is intentionally obscured by a soft square blur for anonymity.

Product elements: Include exactly 3 visible product/demo elements on the left: 1 tall translucent silver product box with a silhouette of a leg wearing stocking, 1 rolled black stocking with a loose sheer section extending forward, and 1 inset close-up photo showing two hands stretching the stocking fabric horizontally.

Text content: Large English headline at upper left: “PRODUCT OVERVIEW”. Below it, show the Chinese product slogan {argument name="Chinese slogan" default="薄透丝袜，显瘦有质感"}. Under that, add the English descriptor line: “Sheer Texture / Slim Fit / Soft Matte Glow”. Use modern condensed sans-serif typography in dark gray.

Feature list card: At bottom left, include exactly 5 feature rows with small circular line icons and English labels: 1) Sheer Texture, 2) Slim Fit, 3) Soft Matte Glow, 4) High Elasticity, 5) Commuter Styling. Use thin dividers and a translucent frosted-glass panel.

Visual style: Premium fashion-tech advertising, photorealistic model and product, clean futuristic UI details, soft reflections on floor and cube, black stockings rendered semi-transparent with subtle matte glow, elegant commercial lighting, sharp focus on legs and product materials.

Constraints: No extra feature rows, no extra product demos, no watermark, no messy background text, keep all typography legible, keep the model modestly posed and fashion-catalog oriented.

Create a cinematic 3D cartoon illustration of a frightened young adult man in a gray hoodie and clear glasses, centered in a close-up medium shot, staring forward with wide eyes and an open anxious mouth. Behind him is a large futuristic slot machine with exactly 3 visible spinning reel columns, showing AI-themed symbols and gambling icons: blue “AI” letters, red 7s, and green circular symbols. The background is a glowing cyan-blue digital circuit board wall with neon data lines, particles, and a tech-lab atmosphere. The man holds exactly 2 poker chips in his cupped hands, one blue and one green, while exactly 3 red poker chips tumble downward in front of him. Torn lottery tickets and receipts curl upward from the bottom left and bottom right edges, suggesting wasted credits and gambling-like dopamine mechanics. Use dramatic teal lighting, shallow depth of field, glossy high-detail 3D rendering, expressive Pixar-like character proportions, high contrast, glowing particles, no watermark, no readable extra text except the slot symbols. Make the mood tense, ironic, and visually tied to AI image/video generation as a slot-machine gamble. Customizable details: {argument name="character expression" default="terrified and regretful"}, {argument name="hoodie color" default="gray"}, {argument name="slot machine symbols" default="AI letters, red 7s, and green circular icons"}, {argument name="background style" default="cyan futuristic circuit board"}, {argument name="gambling chips" default="2 chips in his hands and 3 red chips falling"}.

Using the provided reference image, enhance it into an ultra-premium cinematic 8K photo while preserving 100% of the original composition, pose, objects, lighting placement, and the face-obscuring censor block. Improve the image quality dramatically: recover sharp microdetails in the glass display case, the golden trophy, hair texture, hand, rings, clothing, reflections, and illuminated display bases. Make it photorealistic with studio-grade contrast, richer warm museum lighting, cleaner shadows, reduced blur and pixelation, crisp edges, realistic glass reflections, and a high-end editorial/cinema finish. Do not change the subject’s position, the trophy location, the black vertical display bars, or the overall framing. Use {argument name="output quality" default="ultra-premium 8K"}, {argument name="visual style" default="cinematic photorealism"}, {argument name="detail emphasis" default="sharp microdetails, realistic pores, hair, glass, and metal reflections"}, and {argument name="lighting mood" default="warm high-contrast museum display lighting"}.

Create a full-body anime fashion character illustration on a plain white background, centered vertically with lots of clean negative space. The subject is a slim young woman with medium-brown skin and {argument name="hair style" default="dark brown curly hair tied high in a puff"}, wearing oversized cream-colored over-ear headphones. Her face is intentionally covered by a flat square censor block in warm tan, hiding all facial features. She poses casually, standing with one hand tucked into her pants pocket and the other hand raised near her collar as if adjusting it. Outfit: an off-white cropped zip-up utility jacket with loose sleeves, an off-white fitted crop top underneath, very baggy high-waisted off-white cargo pants with a drawstring waist, large flap cargo pockets, dangling straps, wrinkled fabric folds, and chunky off-white sneakers. Add a small taupe crossbody bag with a thin strap running diagonally across her torso. Include subtle tattoo-like linework visible on one forearm and around the midriff. Use a refined fashion-concept-art style with thin sketchy ink outlines, muted beige and ivory tones, soft cel shading, delicate fabric creases, minimal shadows, and no text or background objects.

Using REFERENCE_0 as the source screenshot, create a clean dark-mode AI chat interface tutorial mockup that shows the same underwater photo being upscaled. Remove the Windows Photos app chrome, side information panel, filename details, and resolution callout from the reference; use only the underwater image content as the visual asset.

Layout: Place exactly 2 rounded-corner image previews of the underwater photo in the chat: 1 smaller uploaded-image preview near the upper right and 1 larger generated-result preview below it, slightly left of center. Keep the face-obscuring gray blur/block over the person in both previews.

Chat elements: Add exactly 1 user message bubble beside the upper preview with the Chinese text {argument name="user prompt text" default="将图片专为4K分辨率"}. Add exactly 1 assistant label reading “显示思路” with a small blue sparkle icon and a dropdown chevron. Under the larger image preview, add exactly 1 small rounded “来源” source button.

Callout: On the upper-right corner of the larger generated image preview, show the download icon and highlight it with exactly 1 red circular outline. Add exactly 1 thick red arrow pointing from the right side toward that circled download icon.

Bottom UI: Include a dark rounded message input bar at the bottom with placeholder text “描述你的图片”, small attachment/tool icons, a “制作图片” chip, a {argument name="model label" default="Pro"} dropdown, and a microphone icon.

Style and constraints: Match a modern Gemini/AI-chat dark theme with lots of empty black space, subtle gray UI controls, rounded corners, and a 16:9 screenshot composition. Do not add extra images, extra arrows, extra callouts, or additional explanatory text.

Create a dreamy anime-style fantasy portrait of {argument name="character name" default="a mysterious blue-haired girl"} standing under an ornate transparent art umbrella. The scene is a luminous celestial reverie in cool sapphire, lavender, and white tones, with backlit clouds and soft daylight bokeh behind her. The character has very long flowing {argument name="hair color" default="deep indigo-blue"} hair, pale skin, and an elegant off-shoulder frilly dress in navy and translucent pale blue, decorated with sheer ruffles, star beads, pearl chains, a dark blue bow at the throat, and a faceted blue gemstone pendant. Her face is intentionally hidden by a centered opaque square gradient mask in muted blue-to-lavender, covering the facial area while leaving hair, outfit, hands, and accessories visible. She holds the umbrella shaft with one hand near the lower left of her torso, posed calmly and serenely.

The umbrella is the main visual feature: one large transparent dome umbrella with a dark navy ruffled outer rim, visible black ribs, glossy reflections, and an inner fantasy sky design filled with clouds, constellations, glittering star trails, pearl strands, and celestial charms. Include exactly 4 prominent moon ornaments/designs on or inside the umbrella: 2 large pale crescent moons on the left side, 1 thin circular moon ring near the upper center-left, and 1 small crescent moon on the right side. Include exactly 3 larger hanging star charms that stand out among many tiny sparkles: one near the upper center, one near the right center, and one near the lower torso area. Add floral details: exactly 2 large blue-white roses, one tucked beside the left side of the hair near the temple and one at the lower right waist/sleeve area. Add delicate dangling pearl-and-star hair ornaments on both sides of the head.

Overlay a subtle transparent smartphone-style psychological scan UI that does not distract from the character. Include exactly 2 translucent UI panels: first, a small rounded rectangle at the top right reading “SCAN 100%” with tiny barcode-like lines and minimal sparkle marks; second, a larger frosted-glass rounded rectangle at the bottom left reading “INNER SCAN COMPLETE”, then “Type : {argument name="type text" default="Starlit Reverie"}”, then “Mood : {argument name="mood text" default="Serene / Pure / Longing"}”. Inside the bottom-left panel include exactly 3 simple line icons along the bottom: a rose icon, a star icon, and a crescent moon icon. Add a small cursive signature-like label at the bottom right reading “{argument name="signature text" default="Inner-Umbrella Archive"}”. Use high-detail Japanese anime illustration rendering, crystalline highlights, soft bloom, transparent fabric textures, ethereal lighting, and a polished vertical composition. Avoid extra text, avoid watermarks, and keep the face mask as a clean square overlay.

Goal: Create a richly detailed vertical dark-fantasy anime poster for {argument name="story title" default="Alice in Wonderland"}, reimagined as an elegant gothic tea-party character illustration.

Canvas: Tall 2:3 portrait poster, dense decorative composition, cinematic lighting, deep navy, violet, black, antique gold, muted cream, and ruby-red accents. Use ornate Victorian borders, filigree corners, glowing bokeh, floating cards, and magical dust throughout.

Main subject: A beautiful androgynous young male anime character seated in a plush vintage armchair at the center, looking tired, aloof, and melancholic. He has messy dark blue-purple hair, golden amber eyes, pale skin, and black cat ears, with a dark fluffy cat tail visible near the lower right. He wears an extravagant Mad Hatter-inspired gothic aristocrat outfit: oversized checkerboard top hat decorated with playing cards, blue roses, chains, gears, ribbons, and small charms; layered black and navy tailcoat with gold trim; ruffled white lace shirt; blue bow at the neck; ornate brooches; shoulder epaulettes; dangling chains; pocket watches; belts; gloves or lace cuffs; fitted dark trousers; and tall black lace-up platform boots. Pose him lounging with one leg crossed forward, one elbow resting on the chair arm, one hand near his face, and the other holding a delicate teacup.

Environment: A surreal enchanted Wonderland forest or tea-party room with blurred glowing lanterns, blue stained-glass-like lights, mushrooms, roses, antique bottles, tea sets, cakes, clocks, playing cards, ribbons, and magical floating fragments. The mood should feel mysterious, decadent, dreamlike, and slightly ominous.

Layout and text elements: Include exactly 6 distinct readable graphic text panels/signs:
1. Upper-left ornate arched title plaque with the large title “ALICE in WONDERLAND”, a smaller Japanese subtitle “不思議の国のアリス”, a tiny teapot icon, and story text: “Down the rabbit-hole he fell, chasing a whisper not meant for him— In a land where time is broken and rules are only a joke, ...is there a way to return?”
2. Upper-right wooden signpost with 4 arrow signs labeled exactly: “This Way”, “That Way”, “Tea Party”, and “Go Back”.
3. Lower-left parchment invitation card titled “Mad Hatter’s Tea Invitation” with smaller text: “You’re invited to a most unusual tea. Don’t be late. Or be. It doesn’t matter.”
4. Bottom-left ornate oval cameo frame showing a tiny silhouette tea-party scene with two seated figures, labeled “Who Are You?”
5. Lower-center handwritten chalk-like quote: {argument name="center quote" default="There’s no truth here. Only what you choose to believe."} with a small doodle cat face and sparkle marks.
6. Lower-right parchment tag titled “Drink Me” with smaller text: “A sip may shrink you, A sip may change you, Choose wisely.” plus a small potion-bottle illustration.

Additional visible objects: Include floating playing cards with suits, at least 3 red roses, at least 2 pocket watches, a teapot and cupcake tea set near the lower left, a glowing potion bottle labeled “Drink me” on the lower right, a crystal orb or glowing glass lamp, wax seals on parchment notes, ribbons, chains, and blue flowers.

Visual style: Ultra-detailed Japanese anime key visual, ornate gothic lolita / ouji fashion, Victorian fantasy poster design, high-contrast rim lighting, soft painterly rendering, crisp character details, luminous particles, intricate accessories, dramatic depth of field, premium collectible illustration quality.

Constraints: Keep the main character recognizable as the central focus, do not crop off the hat or boots, preserve all 6 text panels/signs, avoid modern objects, avoid minimalism, avoid flat colors, and make the typography decorative but legible.

Create a hyper-realistic surreal digital art portrait of a {argument name="subject" default="young adult man"} suspended in mid-air as if floating or leaping forward, full body visible, head tilted back in transcendent calm, face intentionally softened/blurred for privacy. He wears a {argument name="jacket color" default="mustard yellow"} outdoor rain jacket over a dark forest-green hoodie, camouflage cargo pants, rugged brown hiking sneakers, and a black backpack strap over one shoulder. His pose is weightless and dynamic: one knee bent upward, the other leg trailing down, one arm relaxed behind him, torso leaning back. The right half of his body is dissolving into a dramatic cloud of black-gray ash, dust, soil fragments, dry leaves, and small debris, as if he is disintegrating into the air. Include exactly 9 visible birds in flight around the explosion of particles, varying in size and distance, with a few close silhouettes and several smaller distant birds. Use a cinematic vertical composition with the figure slightly left of center, a split atmospheric background: smoky teal-gray mist on the left blending into vivid golden-orange on the right. Lighting is moody and high contrast, with warm rim light from the orange side and soft shadow on the teal side. Render with ultra-detailed fabric textures, realistic folds, dust particles, motion blur in the debris, volumetric smoke, shallow depth of field, and a polished hyper-realistic fantasy photography style. No text, no watermark, no frame.

Goal: Create a polished commercial storyboard presentation for a 15-second ultra-realistic cinematic vertical football campaign featuring the same female footballer in every frame, titled {argument name="headline text" default="UNSTOPPABLE STARTS NOW"}.

Canvas: Wide 16:9 black presentation board with thin white divider lines, a premium sports-agency layout, high contrast, realistic stadium photography in each panel, and a small top metadata bar. Use a black background, white condensed uppercase typography, and blue accent blocks for panel numbers and the word “STARTS.”

Header: Place a white Adidas-style three-stripe logo at top left, followed by the main headline “UNSTOPPABLE STARTS NOW,” with “UNSTOPPABLE” in white and “STARTS NOW” in electric blue. Under it, add small text: “COMMERCIAL STORYBOARD   CINEMATIC FOOTBALL CAMPAIGN.” On the top right add small production labels: “DIRECTOR / SPORTS COMMERCIAL UNIT,” “BRAND / ADIDAS FOOTBALL,” a small “16:9” badge, and “CINEMATIC STORYBOARD.”

Layout: Use exactly 6 storyboard panels arranged in a 3-column by 2-row grid. Each panel has a blue numbered square, an uppercase scene title, one ultra-realistic cinematic image, and three tiny notes underneath labeled ACTION, CAMERA, and NOTES. Keep the same consistent reference character in all 6 panels: {argument name="character description" default="a young athletic blonde female footballer with a high ponytail, wearing a white Real Madrid-style football kit with black shoulder panels, blue trim, white socks, and football boots"}. Make the face neutral or softly obscured rather than celebrity-specific.

Storyboard panels, exactly 6:
1. “THE ARRIVAL” — The player emerges from a stadium tunnel into a packed football arena at sunset, dramatic orange sky, Real Madrid-style flags in the crowd, huge stadium lights, low-angle wide entrance shot. Text below: ACTION: She emerges from the tunnel as the stadium erupts. CAMERA: Low-angle wide entrance shot with dramatic scale. NOTES: Sunset + stadium lights create cinematic contrast.
2. “CROWD REACTION” — Handheld sideline view as excited fans press forward cheering, filming on phones, flashes and stadium lights behind her while she walks past confidently. Text below: ACTION: Fans stand, cheer, and film her entrance. CAMERA: Handheld sideline perspective for energy. NOTES: Flashes, motion blur, and real crowd atmosphere.
3. “THE FIRST TRICK” — Close sports-action tracking shot as she juggles a {argument name="football type" default="black and white football"} effortlessly with her knee near the sideline, crowd roaring, bright stadium floodlights, blue Champions League-style ribbon signage. Text below: ACTION: She juggles the ball effortlessly with her knee. CAMERA: Close sports-action tracking shot. NOTES: Ball frozen mid-air, crowd reacts louder.
4. “MATCH-DAY ENERGY” — Wide cinematic stadium view with the player moving along the sideline, crowd packed and waving flags, confetti and smoke cannons, advertising boards, dynamic match-day atmosphere. Text below: ACTION: She moves along the sideline, crowd goes wild. CAMERA: Ultra-wide cinematic stadium view. NOTES: Confetti, smoke, banners, and vibrant atmosphere.
5. “THE MOMENT” — Dramatic low-angle portrait on the pitch as she controls the ball with one foot raised, stadium lights glowing overhead, shallow depth of field, intense heroic pause. Text below: ACTION: She stops, controls the ball, and owns the moment. CAMERA: Dramatic low-angle portrait shot. NOTES: Shallow depth of field, cinematic lighting on face.
6. “ICONIC EXIT” — Rear follow shot of the player jogging toward center pitch with a black backpack, jersey number visible, match continuing in the distance, giant stadium screen showing her, crowd and lights slightly motion blurred. Text below: ACTION: She jogs to the center pitch as the match continues. CAMERA: Rear follow shot with stadium scale. NOTES: Epic finale frame, motion blur on crowd and lights.

Visual style: Ultra-realistic sports commercial photography, cinematic grading, crisp detail, stadium floodlights, crowd energy, slight motion blur, premium brand-storyboard aesthetic, clean editorial spacing, thin white borders around images, tiny but legible production-note typography.

Constraints: Use exactly 6 panels and no extra panels. Maintain the same player, kit, hair, and body type across all panels. Keep the board landscape 16:9 even though it describes a vertical video campaign. Avoid random logos except the Adidas-style header mark and football-stadium branding cues. Make it look like a finished professional storyboard sheet, not a comic page.