GPT Image 2 prompts

Photorealistic high-end commercial food product photography, adjustable aspect ratio according to target setting, first-person POV shot, two fair-skinned human hands holding the left and right edges of a large crisp white newspaper. At the center of the newspaper, a {argument name="product" default="hyper-realistic glossy 3D pop-out display of the exact uploaded featured item"}, the product is placed on a {argument name="serving style" default="rustic wooden plate paved with green leaf decorations"}, matched with small side dishes and delicate garnishes. The {argument name="background" default="background behind the newspaper is a softly blurred dark emerald green cafe interior environment"}. Strict standardized typography layout rules: 1. Small bold white text wrapped in "" placed at top center of dark green background area; 2. Two-line ultra-bold dark green thick sans-serif headline text wrapped in "" at the top of newspaper page, decorated with horizontal dividing lines above and below the headline; 3. Medium-weight black sans-serif text wrapped in "" on the left lower part of the newspaper, separated by a thin vertical line from large bold green price text wrapped in "" on the right side; 4. Small white bullet point text wrapped in "" on the left bottom of green background, small white URL text wrapped in "" on the right bottom of green background. Bright directional studio soft lighting, sharp focal point locked on newspaper and the popped-out product, clear layered depth of field, 8K ultra high resolution, exquisite material texture rendering, cinematic color grading, neat and standardized typography hierarchical layout, clean commercial advertising aesthetic, no redundant messy elements, no distorted product shape.

Ultra-realistic cinematic portrait of a young woman relaxing outdoors in a lush garden during golden hour, eyes gently closed with a peaceful smile, short slightly messy black bob haircut, thin round metal glasses, oversized olive-green linen shirt layered over a ribbed beige tank top, reclining comfortably in a wooden lounge chair, soft breeze moving her hair, warm golden sunlight illuminating her face, vibrant blue sky with fluffy white clouds, leafy branches framing the scene, creamy bokeh, natural skin texture, Kodak Portra 400 film look, subtle film grain, soft pastel greens and blues, Leica M11, Summilux 50mm f/1.4, shallow depth of field, editorial lifestyle photography, serene summer atmosphere, timeless nostalgic aesthetic, HDR, 8K. Ultra-realistic cinematic side-profile portrait of a young woman in a quiet mountain landscape during golden hour, wearing a soft white knit sweater and reflective round sunglasses, short black bob hair gently blowing in the wind, warm rim light from the setting sun, dramatic lens flare, blurred mountains in the background, soft golden haze, natural skin tones, dreamy atmosphere, Kodak Portra 400 color grading, subtle analog film grain, Leica M11, 85mm Summilux lens, f/1.4, shallow depth of field, editorial outdoor fashion photography, peaceful and contemplative mood, HDR, 8K. Ultra-realistic cinematic lifestyle portrait of a young woman reading books beside a peaceful riverside at sunset, short wavy black bob haircut, round glasses, black lightweight jacket over a white T-shirt, books and notebooks scattered around, holding a smartphone while smiling softly, golden sunlight filtering through surrounding plants, distant city skyline reflected on the water, warm backlighting, creamy foreground blur, Kodak Portra 400 film aesthetic, natural skin texture, subtle film grain, Leica M11, 50mm Summilux lens, shallow depth of field, documentary-style photography, calm academic atmosphere, HDR, 8K. Ultra-realistic cinematic side-profile portrait of a young woman standing on a hill overlooking a city during sunset, wearing a black sweater and delicate round glasses, short sleek black bob haircut softly moving in the breeze, eyes closed enjoying the warm sunlight, glowing sun rays and cinematic lens flare, soft bokeh city skyline in the distance, minimalist composition, Kodak Portra 400 film colors, natural skin texture, subtle analog grain, Leica M11, 85mm portrait lens, f/1.4, shallow depth of field, dreamy editorial photography, peaceful golden-hour atmosphere, HDR, 8K.

Create a hyper-realistic, cinematic editorial portrait of the {argument name="subject" default="same young woman with long wavy dark-brown hair, soft natural makeup, and a calm, confident expression"}. She wears a {argument name="clothing" default="blue denim jacket over a fitted top, matching blue jeans, and black high heels"}, maintaining the exact same facial identity, hairstyle, body proportions, and outfit throughout the composition.

Blend two surreal concepts into one seamless scene:

On one side, depict the woman as a giant standing waist-deep in a modern international shipping port, surrounded by container terminals, cargo cranes, warehouses, turquoise seawater, and multiple cargo ships. She gently holds a miniature container ship in one hand while several real cargo vessels navigate around her, leaving realistic water wakes. A dramatic overcast sky with dark storm clouds creates a cinematic atmosphere, with a futuristic city skyline visible in the distance.

On the other side, merge the environment into a black-and-white Japanese manga collage wall filled with dynamic comic panels featuring motorcycles, office scenes, city streets, livestreaming, friendship, expressive characters, speed lines, Japanese sound effects, and speech bubbles. The woman stands naturally in front of the manga artwork with a relaxed editorial pose, creating a striking contrast between the colorful realistic subject and the monochrome manga background.

The transition between the shipping port and manga collage should feel smooth and artistic, combining surreal scale, fantasy, editorial fashion photography, and comic-book aesthetics into one cohesive composition. Ultra-detailed textures, realistic lighting, sharp focus, natural skin tones, HDR, 8K resolution, volumetric lighting, cinematic color grading, professional fashion photography, highly detailed environment, masterpiece quality.

A dynamic, joyful photograph of {argument name="subject" default="eight young Asian women, around 20 years old — six Japanese, one Korean, one Chinese"}, holding hands and {argument name="action" default="spinning together in a loose circle in the Piazza del Duomo during blue hour"}, the cathedral's floodlights just switched on against a still-deep-blue twilight sky, motion slightly blurred.

The two or three women facing the camera directly show clear, distinct East Asian facial features with genuine laughing expressions; the remaining figures are captured mid-turn with faces partially in profile or softly motion-blurred, consistent with the natural blur of spinning motion. Their skin shows realistic subsurface scattering where the floodlight catches their faces, specular micro-highlights visible on the clearly-lit figures, natural texture preserved.

Hairstyles vary across the group, hair swinging outward with the spinning motion, strands caught mid-air by centrifugal movement. They wear an {argument name="clothing" default="eclectic but coordinated mix of fashion-forward coats and slip dresses in jewel tones"}, fabric flaring outward with their spin.

The lighting mixes the last deep-blue ambient twilight with the cathedral's warm architectural floodlights just turned on, creating a striking cool-warm contrast across the group. Subtle ISO 400 film grain sits in the shadow areas. Aspect ratio 2:3. No watermark, no text overlay, not cartoon, not illustration, not anime.

"A realistic full-body photograph of a {argument name="subject" default="young South Asian woman"} leaning casually against a white wall. She has dark brown hair tied in a low messy bun with soft strands framing her face, warm medium skin tone, and a bright cheerful smile. She is wearing {argument name="clothing" default="an oversized black button-down shirt with sleeves rolled up over a plain white crew-neck t-shirt, paired with black skinny jeans"}. Her right hand is raised making the ‘rock on’ hand gesture (index and pinky fingers extended), left hand resting behind her head. Soft warm lighting with out-of-focus bokeh lights visible in a dark hallway on the right. Clean studio composition, high detail, photorealistic.

To her left on the white wall is a large black-and-white line-art cartoon illustration of the same woman in a matching pose: right hand making the ‘rock on’ gesture, smiling, with the bold {argument name="text" default="handwritten text “ROCK STAR!”"} above her head, plus several star shapes and sparkles around her. The cartoon figure has the same hairstyle, open shirt over t-shirt, and jeans, drawn in a clean modern cartoon style with bold outlines and motion lines.

Vertical portrait orientation, natural colors, sharp focus on the real woman, artistic contrast between photorealism and line art."

Masterpiece, best quality, ultra-detailed anime illustration, dynamic first-person POV from directly above a {argument name="vehicle" default="motorcycle fuel tank"}, camera positioned at the rider's chest looking downward, cinematic perspective, intense sense of speed with strong vertical motion blur streaks across the road, highly detailed {argument name="bike color" default="blue"} retro roadster motorcycle with glossy fuel tank, round digital speedometer with glowing blue-white display, black handlebars, phone holder mounted on the left handlebar, ignition key hanging below the gauge cluster, realistic controls and cables.

A young couple riding together. The male rider is wearing a {argument name="clothing" default="red and white plaid flannel shirt"} with rolled-up sleeves and light blue ripped jeans. His right hand grips the throttle while his left arm naturally controls the handlebar. The female passenger sits closely behind him, wrapping both arms around his waist in a warm embrace. She wears an oversized red plaid shirt layered over a white sweater. One hand gently rests on the rider's stomach while holding a purple smartphone with dual rear cameras. Her bare legs are visible on the left side of the frame, creating a relaxed casual look.

Only the riders' torsos, arms, hands, lap, and legs are visible. Faces are completely outside the frame. The blue motorcycle fuel tank dominates the center composition. The road below is blurred into long speed lines, emphasizing fast forward motion. Soft ambient daylight, clean reflections on the fuel tank, realistic fabric folds, natural skin tones, crisp motorcycle details, cinematic lighting, subtle depth of field, vibrant colours, highly polished digital anime artwork, modern manga aesthetic, dramatic composition, vertical 9:16 aspect ratio, 8K resolution.

A highly detailed photorealistic portrait of a beautiful young woman with fair skin, soft features, full lips, and warm brown eyes, shown in a dual side-by-side composition. She has rich chestnut-brown hair styled in a voluminous high messy bun/updo. On her head she wears an {argument name="headress" default="elaborate festive headdress made of large vibrant turquoise-blue ostrich feathers"} mixed with {argument name="flowers" default="bright orange, yellow, and marigold-like flowers"}, plus smaller green leaves. She wears large circular turquoise beaded chandelier earrings with dangling turquoise beads, multiple layered necklaces of turquoise beads and silver/metal accents, turquoise stone rings, and matching turquoise beaded bracelets. Her outfit is a {argument name="clothing" default="richly embroidered bohemian/folk-style blouse"} featuring intricate floral embroidery in orange, teal, red, and gold on a sheer and lace base, with long turquoise beaded fringe hanging from the sleeves and bodice, and delicate white lace details. Left panel: she faces the camera directly with a soft neutral expression, one hand lightly touching her chin, the other pointing gently. Right panel: she looks slightly to the side with a serene expression, both hands gently clasped near her chest. Background: weathered turquoise-blue wooden doors with peeling paint and metal handles, set in a sunlit rustic Mediterranean or Mexican courtyard with potted plants and soft natural daylight. Cinematic lighting, ultra-detailed textures on feathers, flowers, embroidery, beads and skin, warm golden hour tones, high fashion editorial style, 8k resolution.

Ultra-detailed 16:9 pirate character design sheet, official AAA RPG character bible, clean editorial layout, weathered parchment-tan background with nautical UI accents. Character name "{argument name="character name" default="MARINA"}", title "{argument name="title" default="Storm Captain"}", subtitle "{argument name="subtitle" default="A fearless privateer"}"

Goal: Create a clean comparison grid showing the same e-commerce product rendered by four AI image models: a glossy white true wireless earbud charging case with the lid open, on a white studio background.

Canvas: Wide 16:9 image, divided into exactly 4 equal quadrants by thin light-gray vertical and horizontal divider lines. Minimal white background, soft shadows under each product, high-key product photography look.

Layout: Arrange exactly 4 product renders in a 2 × 2 grid, each centered in its quadrant with a bold black model label beneath it. Keep generous whitespace and align all labels near the lower part of each quadrant.

Quadrants and labels:
1. Top-left: white rounded rectangular charging case open at a three-quarter angle, two earbuds resting inside, semi-transparent lid, soft reflections. Label: “{argument name="top left label" default="gemini-3-pro-image-preview(Nanobanana Pro)"}”.
2. Top-right: rounded pill-shaped white charging case open, two AirPods-style stem earbuds inside, subtle green indicator dot on the front. Label: “{argument name="top right label" default="doubao-seedream-5-0-pro"}”.
3. Bottom-left: front-facing glossy white charging case with open lid, two stem earbuds standing upright, small black oval speaker vents on the buds, tiny dot indicator on the case front. Label: “{argument name="bottom left label" default="gpt-image-2"}”.
4. Bottom-right: front-facing glossy white charging case with open translucent lid, two rounded earbuds sitting low inside without long stems, small white indicator dot and tiny black charging port on the front. Label: “{argument name="bottom right label" default="gemini-3.1-flash-image-preview (Nanobanana 2)"}”.

Visual style: premium e-commerce main image, realistic white plastic and silicone materials, polished surfaces, subtle gray reflections, soft studio lighting, crisp product structure, shallow contact shadows, no decorative props.

Constraints: Use exactly 4 quadrants and exactly 4 labels; do not add logos, watermarks, extra text, hands, packaging, or colored backgrounds. Keep all products white and centered, with the bottom-left render corresponding to {argument name="highlighted model" default="gpt-image-2"}.

Goal: Create a dynamic comic-book storyboard/collage showing an anime-style futuristic superhero battle on a rainy cyberpunk rooftop at night, featuring {argument name="spider hero name" default="a black-and-red spider-themed hero"} and {argument name="armored hero name" default="a blue armored tech hero with a round shield"} fighting surveillance drones and laser attacks.

Canvas: Square 1:1 image, arranged as a polished comic page with thick clean white gutters separating exactly 7 panels. Use cinematic lighting, high-contrast neon reflections, rain streaks, wet rooftop puddles, storm clouds, and a neon city skyline in the background. Overall mood: intense, heroic, dramatic, action-heavy.

Layout: Use exactly seven discrete panels: 3 narrow panels across the top row, 1 large wide action panel across the middle row, and 3 smaller panels across the bottom row.

Panel details:
1. Top-left panel: wide rooftop establishing shot. The spider-themed hero crouches low in the foreground on a wet rooftop, black suit with red web patterns and glowing white eye lenses; the armored hero stands farther back. Neon signs, antenna towers, rain, and glossy reflections fill the scene.
2. Top-middle panel: close-up portrait of the spider hero’s masked face under a red hood, white glowing eyes, red web pattern, clenched red fist raised beside the face, red lightning-like web energy crackling around the hand.
3. Top-right panel: close-up portrait of the armored hero, sleek dark blue and metallic armor, cyan glowing visor, circular cyan chest reactor, raised round shield with red-white-blue rings, heroic three-quarter view.
4. Middle large panel: main battle scene. On the rooftop, the spider hero slides or lunges through splashing rainwater while projecting a glowing cyan circular energy web-shield from one hand toward the armored hero. The armored hero stands braced with cape flowing, shield ready, cyan energy beam firing upward. Multiple drones hover in storm clouds, shooting red laser beams across the panel; sparks, water splashes, and neon city buildings intensify the action.
5. Bottom-left panel: the spider hero crouches alone on the wet rooftop, pointing one hand forward as if preparing to shoot a web; rain, antenna mast, and dark buildings behind.
6. Bottom-middle panel: the armored hero stands in a battle stance holding the round shield while generating a bright cyan energy sphere; concentric red and cyan circular energy rings swirl around him.
7. Bottom-right panel: both heroes pose together on the rooftop beneath a giant glowing red spiderweb spread across the sky, with a blue drone caught at the center; the spider hero crouches in front while the armored hero stands behind holding the shield.

Visual style: Modern anime superhero illustration mixed with American comic-book paneling, sharp clean line art, saturated neon cyan and red effects, glossy wet surfaces, dramatic rim lighting, detailed armor highlights, expressive action poses, cinematic depth, rain-soaked cyberpunk atmosphere.

Text content: No speech bubbles, captions, logos, or readable text.

Constraints: Keep the exact 7-panel comic layout and the two main heroes consistent across all panels. Use {argument name="primary energy color" default="cyan"} for the armored hero’s technology effects and {argument name="secondary energy color" default="red"} for lasers and spider energy. Background should remain a rainy neon rooftop city at night throughout.

Create a dramatic square sports poster featuring {argument name="football player" default="Cristiano Ronaldo"} as an iconic Portugal national team legend. The composition contains exactly two depictions of the same player: one large heroic bust portrait in the upper center, cropped at the chest, looking slightly upward with a serious determined expression; and one full-body action figure in the lower center sprinting forward toward the viewer while dribbling exactly one blurred soccer ball near the bottom edge. The player has short black hair, sharp rugged facial structure, realistic skin texture, sweat highlights, and an athletic muscular build. Dress him in a Portugal-style red home jersey, green shorts, red socks, and football boots, with the number {argument name="jersey number" default="7"} clearly visible on the chest and on the shorts, plus a captain armband on one arm. Use an explosive radial starburst background that starts behind the running player’s upper body and expands outward to all edges, made of hundreds of multicolored light trails in red, magenta, orange, blue, green, white, and purple, like hyperspace motion streaks mixed with stadium sparks. The overall look is high-contrast, cinematic, glossy, gritty, and energetic, with sharp poster lighting, strong rim light, motion blur on the ball and limbs, and a dark textured pitch under the runner. Include exactly three small typography areas: large bold glitch-style white text on the upper left reading {argument name="main title" default="CR7"}; a thin spaced subtitle line split across the upper middle reading {argument name="upper subtitle" default="ICON    PORTUGAL"}; and small spaced text near the lower left reading {argument name="lower caption" default="LEGEND IN MOTION"}. Keep the text minimal and integrated into the poster with thin horizontal guide lines. No extra players, no crowd, no logos beyond subtle kit-style details, no watermark, no frame border.

Create a vertical Japanese summer fashion magazine poster featuring {argument name="character name" default="a beautiful young Japanese woman"} walking through shallow, crystal-clear turquoise seawater on a bright sunny day. She is centered full-body, photographed from a slightly low front angle, looking off to the viewer’s right with a calm elegant expression, wind-blown short brown bob hair, natural makeup, pearl earrings, and luminous sunlit skin. Outfit: a pale blue ribbed tank top, high-waisted white tailored shorts with a small belt, and a sheer loose white long-sleeve cover-up shirt slipping open and flowing in the sea breeze. The water reaches her lower calves with sparkling splashes around one stepping foot, visible rippling sand patterns under the water, a flat ocean horizon, soft white clouds, and an intense clear blue sky. Use a clean airy editorial photography style, high-key lighting, pastel cyan and white color palette, glossy Japanese lifestyle magazine aesthetic, realistic fashion-photo detail, gentle lens flare, crisp fabric texture, and refreshing summer atmosphere. Add large translucent Japanese typography integrated into the sky and sea: oversized white characters near the top reading 「夏透明」 with pale blue vertical text on the right reading 「の涼風」 and oversized pale blue characters near the lower left reading 「海」. Add one small vertical Japanese tagline at upper left-center: 「夏が来る きらめく海辺で、私らしく。」 Add small English footer text: bottom left “SUMMER COLLECTION” and “2024”; bottom right “LIGHT / CLEAR / BREEZE”. Keep the composition minimalist and elegant, with text partially blending into the bright sky and water, no extra people, no buildings, no logos, no watermark. Customize the mood with {argument name="season theme" default="refreshing midsummer seaside"}, outfit color with {argument name="tank top color" default="pale blue"}, and the main large Japanese title with {argument name="headline text" default="夏透明の涼風海"}.

Goal: Create a soft healing morning poster combining typography and a miniature Beijing landscape scene on warm knitted fabric.

Canvas: Wide horizontal poster, 16:9 aspect ratio, warm cream and beige palette, generous negative space on the left, cinematic shallow depth of field.

Layout: Place all typography in a vertical block on the upper-left third. The right and lower areas show a tiny diorama-like winter morning landscape made from fuzzy cream yarn and knitted textile folds. Use the knitted fabric as rolling hills, ground, and foreground ridge, with visible wool fibers and soft loops.

Text content: Include exactly 7 text elements on the left: 1) bold uppercase English headline “GOOD MORNING”; 2) very large thin Chinese characters “早安”; 3) a short horizontal divider line; 4) location line “北京 BEIJING”; 5) date line “2026-07-28”; 6) quoted sentence “迎着晨光，步步自有回响。”; 7) two-line blessing text “愿你今日自信从容 / 让清晨点亮新的开始”. Use dark warm brown typography, clean modern sans-serif for English and dates, elegant thin Chinese type for the large characters.

Subject details: The miniature scene contains exactly 7 visible human figures: 1) a delivery cyclist in the lower-left foreground riding a black bicycle with tan delivery boxes; 2) a standing person near center-left waving one arm; 3) a tiny distant figure pair near the middle background; 4) a runner in dark shorts near center; 5) a photographer or traveler standing center-right with a backpack; 6) a tiny distant walker near the temple stairs. Add one central traditional Beijing-style pavilion/temple with stairs in the right background, one partial traditional roof building at the far right edge, and a few pale flowering or frosted trees. Make all people look like tiny scale-model figures.

Visual style: Macro photography of a handcrafted miniature scene, cozy wool texture, soft sunrise light from the upper left, gentle misty atmosphere, creamy highlights, realistic fabric fibers, warm shadows, premium lifestyle poster aesthetic, calm and comforting mood.

Parameters: Use {argument name="headline text" default="GOOD MORNING"}, {argument name="large greeting text" default="早安"}, {argument name="city label" default="北京 BEIJING"}, {argument name="date" default="2026-07-28"}, and {argument name="quote" default="迎着晨光，步步自有回响。"}.

Constraints: Keep the image uncluttered, preserve the left-side text hierarchy, avoid watermarks or logos, do not add extra people beyond the 7 specified figures, and maintain a soft beige morning color grade.

Goal: Create a cinematic 16:9 PowerPoint cover slide for a children’s AI art course, blending premium Chinese aesthetics, futuristic AI education, and warm imaginative storytelling.

Canvas: Wide presentation slide, 1366×768 or 16:9 ratio. Dark black-to-burgundy background with a strong vertical glowing portal slightly right of center. Use a luxury black, deep red, ivory, and gold palette with soft haze, dust particles, and luminous light trails.

Layout: Left side is the typography area; right side is the fantasy visual scene. Place a large two-line Chinese title on the left: first line “小孩AI绘图”, second line “培训版”, with elegant Song/Ming-style serif Chinese typography, ivory on top and warm gold accents below. Under the title, add one subtitle line: “让孩子用AI打开想象力 · 创造力 · 未来视觉表达”. Below that, add a small caption: “儿童AI创意绘画课程介绍”. In the top-left corner, include a tiny vertical four-line motto reading “想象力 / 表达力 / 未来力 / 创造力” with a small red seal-like square beneath it.

Subject details: On the right, show one small child silhouette standing at the base of the glowing portal, facing away from the viewer and reaching one hand toward floating visual panels. The child should look about 5–7 years old, short, with a rounded head silhouette and simple clothing, rendered as a warm backlit figure. Around the child, include exactly 5 floating art panels: 2 small dark red abstract landscape panels near the upper right, 2 pale Chinese ink landscape panels stacked near the middle-right, and 1 small translucent rectangular panel near the portal. Add exactly 4 main geometric accents: 1 large translucent red moon/circle behind the portal, 1 thin outlined circle in the upper right, 1 small outlined square near it, and 1 beige sphere near the lower left. Add a red ribbon-like orbit around the child and golden wave particles sweeping from lower left toward the portal.

Visual style: High-end course-presentation cover, cinematic lighting, subtle Chinese ink landscape silhouettes along the bottom left, faint bamboo silhouette on the far right, layered transparent rectangles, thin technical lines, warm golden vertical beam, glossy floor reflection, dramatic contrast, refined editorial composition, premium education brand aesthetic.

Customizable text: Main title should read {argument name="main title" default="小孩AI绘图\n培训版"}. Subtitle should read {argument name="subtitle" default="让孩子用AI打开想象力 · 创造力 · 未来视觉表达"}. Small course label should read {argument name="course label" default="儿童AI创意绘画课程介绍"}. Motto should read {argument name="vertical motto" default="想象力\n表达力\n未来力\n创造力"}. Overall theme should remain {argument name="course theme" default="children’s AI creative drawing course"}.

Constraints: Keep the composition uncluttered and presentation-ready. Do not add extra people, extra title text, logos, watermarks, or UI elements. Preserve the luxurious black-red-gold palette and the exact counts of 1 child, 5 floating art panels, and 4 main geometric accents.

Goal: Create a vertical Japanese recipe infographic poster for {argument name="recipe title" default="4種野菜のスタミナガーリック炒め"}, with a warm hand-drawn cookbook aesthetic and perfectly legible Japanese typography.

Canvas: Portrait 2:3 layout, off-white paper background, rounded corners, thin double green ornamental border with small leaf flourishes in the corners. Use soft watercolor-style food illustrations, friendly rounded Japanese fonts, dark brown main title text, green section ribbons, orange accents, dotted divider lines, and subtle sparkles.

Top header: Large centered headline text: {argument name="recipe title" default="4種野菜のスタミナガーリック炒め"}. Directly underneath, orange subtitle: {argument name="subtitle" default="（バター不使用版）"}. Add a small Japanese tagline below: "シャキッ！ほくっ！にんにく香る、食べごたえ抜群のスタミナおかず♪". Place a large illustrated cabbage on the upper left, a small garlic bulb icon near the upper right, and a black frying pan on the upper right filled with stir-fried cabbage, green bell pepper, potato slices, and garlic.

Main layout: Use five distinct content blocks arranged like a recipe card: 1 ingredients box at upper left, 1 preparation box at upper right, 1 cooking steps box at middle left, 1 technique tips box at middle right, and 1 serving memo box across the bottom.

Ingredients block: Green ribbon header "材料（2人分）". List exactly 10 ingredients with dotted leader lines and amounts: 1) キャベツ — 1/4玉（約250g）, 2) じゃがいも — 2個（約300g）, 3) ピーマン — 2個, 4) にんにく — 2かけ, 5) サラダ油 — 大さじ1, 6) ごま油 — 小さじ1, 7) しょうゆ — 大さじ1, 8) 鶏ガラスープの素 — 小さじ1, 9) 塩 — 少々, 10) こしょう — 少々. Include three small illustrations at the bottom of this box: green bell peppers, potatoes with one cut open, and garlic cloves.

Preparation block: Green ribbon header "下準備" with explanatory text: "じゃがいもはあらかじめ火を通しておくと、炒め時間が短くなり、味がしみ込みやすくなります。" Include exactly 2 preparation methods in rounded subcards. First green subcard titled "レンジで加熱する場合" with microwave icon and exactly 3 numbered steps: 1) じゃがいもは皮をむき、1.5cm幅の半月切りにする。 2) 耐熱容器に入れ、ふんわりとラップをかける。 3) 600Wで約5〜6分加熱する。 Add note: "※竹串がスッと通るくらいが目安です。" Second orange subcard titled "ゆでる場合" with pot icon and exactly 3 numbered steps: 1) じゃがいもは皮をむき、1.5cm幅の半月切りにする。 2) 鍋に水とじゃがいもを入れ、沸騰したら中火で3〜4分ゆでる。 3) ザルに上げて水気を切る。 Add note: "※固めに火を通すのがポイント！".

Cooking steps block: Orange ribbon header "作り方". Show exactly 7 numbered orange circles with Japanese step text: 1) キャベツはざく切り、ピーマンは縦にひと口大の細切りにする。にんにくは薄切りにする。 2) フライパンにサラダ油を中火で熱し、にんにくを炒める。香りが立ってきたら、じゃがいもを加えて焼き目がつくまで炒める。 3) ピーマンを加えてさっと炒める。 4) キャベツを加え、強めの中火でシャキッとするまで炒める。 5) 鶏ガラスープの素を加えて全体を炒め合わせる。 6) しょうゆを鍋肌から回し入れ、さっと絡める。ごま油を回しかけて香りをプラス。 7) 塩・こしょうで味をととのえ、全体をさっと混ぜて完成！ Add a tiny pan illustration near the lower right of this block with vegetables flying and a handwritten note "強火でサッと炒めてシャキッ！".

Technique tips block: Yellow-orange header "スタミナを盛る裏技" with sparkles. Include exactly 3 tip rows, each with an orange check icon and a small illustration on the right: 1) "にんにくは「香りを立てる」！" with garlic bulb, 2) "じゃがいもは「焼き目」をつける！" with potatoes, 3) "仕上げのごま油でコクUP！" with a sesame oil bottle labeled "ごま油". Use short explanatory Japanese text beneath each tip.

Bottom serving memo block: Green ribbon header "いただき方のメモ". Include the text "熱々のうちにどうぞ！ごはんが進む味つけで、スタミナ満点♪" and exactly 3 green check bullet points: 1) 白ごはんとの相性抜群！ 2) お弁当のおかずにも◎ 3) 冷めてもおいしいので、作り置きにもおすすめです。 Add three food illustrations along the bottom: a bowl of white rice, a plated serving of the vegetable garlic stir-fry, and a speech bubble saying "にんにくの香りと野菜の甘みで、やみつきになるおいしさです♪" with a small heart.

Visual constraints: Keep all Japanese text crisp and readable, maintain a balanced magazine-recipe layout, use no photographs, no watermark, no extra sections, and no additional ingredients or steps.

Goal: Create a vertical 2-column by 3-row collage of exactly 6 separate illustration panels, all in a unified retro Japanese modernist poster style with flat geometric shapes, hard-edged composition, limited palettes, subtle paper grain, ink texture, and strong black/cream/red/orange accents. Each panel should look like a distinct generated artwork sharing the same visual language.

Canvas: Tall portrait canvas, approximately 675 × 1024 px or 2:3 ratio. Use thin white gutters between panels and a narrow white outer border. No captions, no logos, no watermark.

Visual style: A fusion of mid-century graphic design, Japanese printmaking, Constructivist geometry, art deco poster composition, and contemporary anime/editorial illustration. Use flattened perspective, blocky shapes, textured paper, muted cream backgrounds, deep black shadows, burnt orange, vermilion red, slate gray, charcoal, and occasional navy blue. Keep details stylized rather than realistic.

Layout: Arrange exactly 6 panels:
1. Top-left panel: A geometric night scene with an orange kangaroo-like animal standing upright beside a gray koala-like animal, a cream full moon in the upper left, small star/firework dots, and a grid of orange, beige, black, and gray rectangles in the background. The animals should be angular and origami-like.
2. Top-right panel: A dark gothic anime-style girl with long pale hair sitting on stone steps before ruined cathedral arches. Use black, gray, lavender, and hot magenta accents, with one red eye visible and a moody ruined-city atmosphere.
3. Middle-left panel: A reclining elegant long-haired person in black clothing holding a round fan near their face, surrounded by red and black geometric circles, grids, rectangles, and cream negative space. The mood is languid and stylish.
4. Middle-right panel: A close-up portrait of a pale bob-haired girl with straight black bangs, red eyes, small red vertical face markings, and a black-white-red abstract geometric background with circles and rectangular blocks.
5. Bottom-left panel: A minimalist city-walking scene with a person in a long gray coat holding a leash attached to a low, stretching orange-and-white corgi. Background includes red circles, black blocks, cream walls, stairs, and sharp architectural geometry.
6. Bottom-right panel: A back-view portrait of a traditional Japanese woman or geisha in a patterned kimono, standing before pagoda rooftops and a lantern. Include a bright blue sky with cream clouds and bold black, red, cream, and tan architectural shapes.

Subject customization: Keep the collage structure fixed, but allow the overall subject set to be interpreted as {argument name="theme" default="six unrelated retro Japanese poster scenes"}. Use {argument name="main palette" default="cream, black, vermilion red, burnt orange, charcoal gray, navy blue"}. Set the mood to {argument name="mood" default="stylish, mysterious, nostalgic, graphic"}. Use {argument name="art style" default="retro Japanese modernist poster illustration with anime influence"}. Make the image suitable for {argument name="use case" default="a social media showcase of varied GPT Image 2 outputs from one consistent style prompt"}.

Constraints: Exactly 6 panels, exactly 2 columns and 3 rows, no text inside the artwork, no photorealism, no extra panels, no floating UI, no frame labels. Maintain consistent texture and design language across all six panels while making every panel visually distinct.

Create a vibrant anime idol celebration portrait featuring {argument name="character name" default="a cheerful young idol princess"} in a close-up vertical composition, reaching one hand toward the viewer with her index finger pointing playfully at the camera. She is winking with one eye closed and the other eye bright amber, smiling widely with an open happy expression. Give her shoulder-length {argument name="hair color" default="warm chestnut brown"} hair with soft layered bangs and loose wind-swept curls, plus a delicate silver tiara with small jewel details. Dress her in a glossy white stage-idol costume with gold trim, a cropped fitted bodice, ruffled hem, colorful bead-like decorations on the sleeves, a large blue bow and orange-yellow ribbon at the chest, red and gold accents, and sparkling jewelry including small dangling earrings and chain ornaments. The background should feel like an alcohol-ink art festival: soft blooming clouds of watercolor-like pigment in pink, cyan, blue, purple, yellow, and red, with organic translucent stains and splashes. Add exactly 5 large visible party decoration groups: two multicolor pennant bunting strands across the upper left and upper right, two fluffy flower garland clusters near the top left and top right, and one oversized iridescent pink-orange bow/ribbon cluster at the lower left. Scatter many tiny confetti pieces and petal-like color chips throughout the scene, especially around her hand and hair. Use bright saturated colors, crisp clean anime linework, luminous highlights, glossy fabric reflections, soft depth of field, dynamic celebratory motion, and a polished high-detail gpt-image-2 anime illustration look. No text, no watermark, no extra characters.

Create a wide 16:9 anime-style humorous night scene on a grassy hill overlooking a city. Three chibi military-girl characters are having a picnic-like surveillance session under a dark blue starry sky, with glowing apartment buildings in the valley below. On the left foreground, show exactly 3 chibi girls: first, a small pale lavender-haired girl in a white sailor-style military uniform and white peaked cap, wearing oversized red glasses, standing beside a giant red popcorn bucket labeled “Popcorn” and a hot dog; second, a blonde girl in a dark gray military outfit with a red-accented cap and rifle, standing with a skeptical expression; third, a blonde girl in black-and-orange tactical clothing sitting on a checkered picnic blanket, holding large binoculars to her eyes while drooling comically. Add a second pair of binoculars lying on the blanket in front. Include exactly 2 Japanese speech bubbles above the standing girls: {argument name="left speech bubble" default="元アイドルですね。"} and {argument name="right speech bubble" default="アイドルよね？"}. On the right upper half, add a large fluffy thought bubble from the binocular girl showing a romantic fantasy: a young woman in a white wedding dress with long light-brown hair and a handsome dark-haired man in a decorated black military dress uniform, almost kissing, surrounded by sparkles, soft pink light, and falling rose petals. On the lower right over the city, add one circular inset speech-bubble frame showing a room interior where a seated woman watches a screen or framed image of the romantic couple. Use clean high-detail anime line art, soft cel shading, cute chibi proportions for the observers, more polished romantic shoujo rendering inside the fantasy bubble, saturated colors, crisp outlines, playful comedy mood, no watermark, no extra characters, no extra text beyond the specified labels.

Goal: Create a minimalist commercial New Year countdown poster with a premium paper-cut aesthetic, centered on a huge embossed countdown number {argument name="countdown number" default="1"}.

Canvas: Vertical poster, 3:4 aspect ratio, warm off-white paper background with subtle grain and soft studio shadows.

Layout: Place a large rounded-corner red card centered on the canvas, occupying most of the poster. The card has a small downward pointed tab/notch at the bottom center like a speech-bubble marker, plus soft drop shadow against the background. Add one small red eight-point starburst decoration near the top-right outside the card. At the bottom-left outside the card, add a tiny designer credit line.

Main card: Use a rich festive red paper texture with slight tonal gradients and tactile surface grain. At the top center of the card, set small widely spaced white uppercase text: “NEW YEAR COUNTDOWN”. In the center, create an enormous sculpted numeral {argument name="countdown number" default="1"}, tone-on-tone red, recessed/embossed into the card with bevels, inner shadows, and subtle highlights, giving a clean 3D paper relief effect.

Text content on the lower-left of the card: Add bold white Chinese headline text in two lines: “新年倒计时” and “最后 {argument name="days left text" default="1 天"}”. Below it, draw a thin horizontal divider. Under the divider, create exactly 3 small information items with white outline icons and compact labels: 1) calendar icon with “跨年时刻” and “12.31 24:00”; 2) map pin icon with “地点” and “世界各地”; 3) heart icon with “一起迎接” and “2025”. Beneath these items, add the small Chinese slogan “新岁将至，万事可期，所愿皆成真。” and below that widely spaced uppercase English text “HAPPY NEW YEAR”.

Designer credit outside the card: Bottom-left on the off-white background, small muted red text reading “Designed by” followed by a handwritten script signature {argument name="designer name" default="Sunline"}, then “| 2024”.

Visual style: Modern Chinese commercial poster, clean editorial typography, festive but restrained, monochrome red-on-red relief, realistic paper material, soft shadows, high-resolution print design, balanced negative space.

Constraints: Keep exactly one giant numeral, exactly one red card, exactly one starburst, and exactly 3 info items. Do not add extra logos, people, fireworks, confetti, or additional numbers.

Goal: Create a photorealistic vertical image of a transparent acrylic tabletop menu sign for a cute futuristic anime collaboration cafe, styled with glowing pastel neon graphics and Japanese cafe-menu typography.

Canvas: Vertical 3:4 composition, close-up product-photography framing. The acrylic sign is centered and fills most of the image, standing on a clear base on a wooden cafe table. Background is softly blurred with warm cafe bokeh, a latte on the right, a small succulent in a paw-print pot, pink flowers, soft window light, and faint glowing cat-ear shapes in the distance.

Main sign: A clear rectangular acrylic board with rounded corners, subtle reflections, glossy edges, and printed/neon-looking pastel graphics. Use pink, cyan, lavender, and white glow effects as if the graphics are lit from within.

Headline text: Large glowing title at top: {argument name="cafe name" default="Kiraria Neon"}. Under it, glowing subtitle: {argument name="event subtitle" default="Collaboration Cafe"}. Beneath that, include Japanese collaboration text: 「きらりあ・ネオン × サイバー猫アシスタント」 and 「コラボカフェ」.

Decorations: Include exactly 2 character stickers near the top area: 1 pastel frilly cat-ear headband sticker on the left, and 1 cute blue cyber cat robot assistant sticker on the right. Include exactly 2 paw icons near the headline, many small star sparkles, tiny hearts, flowers, and holographic accents. Along both vertical edges, place repeated glowing triangle icons in pink and cyan; make exactly 10 large triangle outlines total, 5 on the left edge and 5 on the right edge.

Menu layout: White semi-transparent printed menu panel on the acrylic, with two centered neon section headers.

Section 1 header: “SWEETS” with sparkle symbols. Include exactly 3 sweets items, each with Japanese name, English name, short Japanese description, and price aligned on the right:
1. 「ネオンのきらめきベリーパフェ」 / “Neon Shimmer Berry Parfait” / price “¥980”.
2. 「ミニAI猫ユニットパンケーキ」 / “Mini AI Cat Unit Pancake” / price “¥900”.
3. 「きらきら星のわたあめクレープ」 / “Sparkling Star Cotton Candy Crepe” / price “¥850”.

Section 2 header: “DRINKS” with sparkle symbols. Include exactly 3 drinks items, each with Japanese name, English name, short Japanese description, and price aligned on the right:
1. 「サイバーにゃんラテ」 / “Cyber Nyan Latte” / price “¥700”.
2. 「きらりあソーダ」 / “Kiraria Neon Soda” / price “¥680”.
3. 「デジタルミルクティー」 / “Digital Milk Tea” / price “¥650”.

Bottom notes: Add a pastel outlined box labeled “SPECIAL COLLAB NOTES”. Inside, include exactly 3 note lines: 「ご注文はカウンターまで」, “Please order at the counter”, and 「期間限定 7/7〜」 plus hashtag “#きらりあネオンカフェ”. At the very bottom, add a tiny support message in Japanese: 「サポートはおまかせにゃ！ キラキラ＆もふもふお待ちにゃん♡」.

Visual style: Hyper-detailed realistic cafe photography mixed with kawaii cyber-neon graphic design, shallow depth of field, soft pastel lighting, clean readable printed text, glossy transparent acrylic, dreamy bokeh, cozy wood tabletop, no people, no watermark. Keep the menu cute, polished, and highly legible.

Create a square, top-down cinematic fantasy cosplay portrait of two young East Asian noblewomen lying side by side on an ornate antique floor, surrounded by soft cherry blossoms and gauzy fabric. The composition is an overhead view with the figures forming a graceful yin-yang swirl: the left woman wears {argument name="left character outfit" default="a black and deep crimson imperial hanfu-style gown"} with voluminous layered skirts, translucent red and black veils, gold embroidery, floral brocade, dangling gold chains, red tassels, and an elaborate black hair updo with red-and-gold hair ornaments; the right woman wears {argument name="right character outfit" default="a white, lavender, purple, and pale gold imperial hanfu-style gown"} with layered flowing robes, sheer golden organza sleeves, white outer drapery, a purple bodice, intricate gold floral embroidery, and a large jeweled flower ornament at the waist. Both women have long glossy black hair, pale porcelain makeup, soft red lips, delicate anime-inspired facial features, and calm playful expressions; each raises one finger near her lips in a secretive pose while their other hands curve elegantly above them, almost touching. The fabrics should be extremely abundant and decorative, spreading across the floor in circular arcs with translucent overlays, embroidered blossoms, metallic gold thread, and lace-like textures. Use warm diffused studio lighting from above, shallow depth of field at the edges, painterly realism, ultra-detailed costume texture, dreamy romantic atmosphere, muted bronze and sepia background, scattered pale pink sakura petals and blurred cherry blossom branches framing all four corners. Color palette: rich black-red on the left, luminous white-purple-gold on the right, balanced symmetrically. No text, no watermark, no modern objects, no extra people. High-resolution fashion editorial cosplay photography blended with fantasy illustration aesthetics.

Create a cute single-panel watercolor illustration of one extremely round, fluffy golden hamster acting like a pendulum. The hamster is centered on a warm cream background, sitting on a small mound of pale wood shavings. It has golden-brown fur on the head and sides, a soft white belly and muzzle, tiny pink paws, a pink nose, fine whiskers, small rounded ears, rosy cheeks, sleepy half-closed eyes, and a tiny slightly open mouth. Show its body tilted gently to one side as if swaying, with exactly 2 pale translucent ghosted silhouettes behind it, one to the left and one to the right, indicating previous swing positions. Add exactly 7 motion marks: 3 large curved arc lines above the hamster following the swing path, 2 short curved wobble marks near the left side, and 2 short curved wobble marks near the right side. Style it as delicate hand-drawn children’s book art with soft pencil outlines, warm watercolor washes, visible fur texture, gentle shading, rounded proportions, and an adorable calm mood. No text, no border, no extra animals, no props beyond the wood shavings.

Create a high-resolution monochrome anime-style illustration of one elegant young businesswoman in a modern city business district. She has {argument name="hair color" default="dark shoulder-length wavy hair"}, soft realistic anime facial features, large reflective eyes, a slight confident smile, and a small earring visible on one ear. She is shown from the waist up in a three-quarter pose, looking back toward the viewer over her shoulder while walking through a busy downtown street. She wears {argument name="outfit" default="a black tailored business suit over a white collared shirt"} and holds exactly one structured black leather briefcase with a handle and metal clasp in both hands at the lower left foreground. The scene includes exactly one main subject, exactly one briefcase, and 12 blurred background commuters in dark business suits walking away or crossing behind her. Set the background in {argument name="location" default="a canyon of tall glass-and-steel office towers"}, with strong morning or late-afternoon backlight streaming between skyscrapers, glossy pavement reflections, deep shadows, rim lighting on her hair, and cinematic depth of field. Use pure black-and-white grayscale only, no color, no text, no logo, no watermark. The style should combine polished Japanese manga character rendering with semi-realistic urban lighting, delicate linework, soft gradients, and a dramatic business-city atmosphere.

Create a dramatic anime-style fantasy action illustration set in a moonlit graveyard at night. The scene contains exactly 2 main characters: on the left, a frightened young blonde girl, {argument name="heroine name" default="girl Arthur"}, running toward the viewer-left while looking back over her shoulder with wide blue eyes and an open screaming mouth; on the right, a sinister magician/jester monster, {argument name="villain name" default="evil magician"}, standing on one leg near a treasure chest and pointing at her as he casts a spell. The girl wears an orange long-sleeve dress, a white frilled apron, a white bonnet with an orange bow, white socks, and pale blue Mary Jane shoes; her long wavy blonde hair streams backward, and puffs of white transformation smoke surround her dress and trail behind her. The villain wears a blue jester hood with two floppy points tipped by red balls, glowing red eyes, a skull-like gray face, sharp teeth, a purple ruffled collar and cuffs, a blue tunic with red buttons, orange tights, red curled boots, and a dark cape. Between them, show exactly 1 rainbow spiral magic projectile, glowing like a colorful vortex with red, orange, yellow, green, cyan, blue, and magenta trails, flying from the villain’s pointed finger toward the girl. Include exactly 1 large full moon centered high in the sky, partly veiled by dark purple storm clouds. Include exactly 1 closed wooden treasure chest with brass bands and a central lock in the lower right-middle foreground. Include 7 prominent gravestones: 1 large tilted stone on the far left, 1 rounded stone near the center behind the girl, 1 small dark stone behind the treasure chest, 1 narrow stone just right of the villain, 1 large tilted stone at the far right foreground, and 2 additional partially obscured stones in the midground. The graveyard ground should be dark, muddy, and rocky with scattered tufts of grass, bare twisted trees on both sides, and a gothic horror atmosphere. Use dynamic composition, cinematic lighting, strong rim light from the moon, saturated anime colors, crisp linework, detailed fabric folds, expressive faces, and motion blur only in the smoke and magic trails. No captions, no UI, no watermark, no extra characters. Use a 16:9 landscape canvas. The overall mood should be {argument name="mood" default="spooky but adventurous"}, inspired by retro side-scrolling dark fantasy game art transformed into a polished modern anime illustration.