Nano Banana 2 vs Pro Comparison (Character Art)

Woman in Mall with Chanel Bag - Heart Gesture

A young woman with long, dark hair sits at a wooden table in a modern shopping mall. She is casually dressed in a white tank top and black fitted pants, smiling and playfully making a heart gesture with her hands. A silver Chanel bag and a clear iced drink sit on the table in front of her. The background features a multi-level shopping area with various stores and greenery.

Split Fantasy Portrait Comparison

Create a side-by-side comparison image showing two versions of the same dreamy fantasy portrait. Canvas is a horizontal 16:9 split-screen composition with a perfectly vertical divide down the center, no gap, left panel and right panel each occupying exactly half the image. In both panels, depict the same ethereal young woman in a luminous fairytale garden, shown as a close-up bust portrait with pale porcelain skin, soft gray-blue eyes, delicate lips, and loosely pinned wavy brown hair. She wears an ornate pastel floral crown with pink roses, tiny crystal flowers, pearls, translucent butterfly ornaments, and soft feathers, plus dangling crystal earrings and a sheer embroidered gown with iridescent floral appliqué. Her hand is raised gently near her chin, giving a calm, romantic, slightly wistful expression while looking toward the viewer. The scene is filled with pastel blossoms, sparkling bokeh, floating dust motes, translucent butterflies, crystal petals, and soft backlit haze. Use an ultra-detailed high-fashion fantasy photography style, shallow depth of field, pearly highlights, glittering refractions, delicate skin texture, and pastel lavender, blush pink, silver, and pale blue tones. Make the left panel slightly more textured, crisp, and detailed in skin and fabric microtexture; make the right panel slightly smoother and more airbrushed, with softer pastel lighting and gentler facial texture. Add exactly 2 label boxes: one white rounded rectangle at the top left of the left panel reading {argument name="left label" default="OpenAI 官方"}, and one white rounded rectangle at the top left of the right panel reading {argument name="right label" default="Azure West US 3"}. Use clean black sans-serif text inside the labels. Keep both portraits similar enough to clearly compare rendering differences, but not identical; avoid watermarks, logos, extra captions, borders, or additional text.

Photo to Cozy Crayon Drawing Comparison

Goal: Create a vertical 3:4 comparison image showing a warm original-photo scene on top and its cozy crayon-drawing interpretation on the bottom. Canvas: Vertical image, approximately 900 x 1200 px, split into exactly 2 horizontal panels of equal width. The top panel is a soft, sunlit realistic photo; the bottom panel is an off-white paper illustration with wax-crayon texture. Top panel: Show {argument name="character description" default="a young woman with long dark hair"} sitting sideways on a narrow old balcony railing outside a weathered apartment doorway. She is relaxed and slightly introspective, looking down at an acoustic guitar while playing it. She wears {argument name="outfit" default="a loose patterned short-sleeve shirt, dark shorts, white socks, and chunky white sneakers"}. The guitar is a glossy honey-brown acoustic cutaway guitar with a dark tortoiseshell pickguard. Include iron balcony bars, leafy green vines, a cream stucco wall, an open aged door, and a dim interior room in the background. Use golden late-afternoon sunlight with dappled leaf shadows across her legs, guitar, wall, and floor; dreamy lens softness, cozy summer atmosphere, shallow depth of field. Bottom panel: Recreate the same subject as a loose hand-drawn crayon sketch on textured cream paper. The woman, pose, guitar, balcony railing, and shoes should be simplified but recognizable, drawn with sketchy overlapping crayon strokes in warm yellow, teal blue, coral red, green, and charcoal gray. Keep the style childlike yet stylish, soft and cozy, with visible wax grain and imperfect outlines. Add exactly 7 decorative crayon elements around the main figure: 1 simple yellow sun in the upper left, 2 small yellow flowers on green stems on the left, 1 blue musical note near the center-right, 1 short gray handwritten phrase reading {argument name="quote text" default="Better Days Ahead"}, and 2 small yellow flowers on green stems in the lower right. Add a few loose green and blue ground scribbles below the seated figure. Text and branding: The only readable phrase inside the drawing is {argument name="quote text" default="Better Days Ahead"}, set in a small gray typewriter-like handwritten style to the right of the illustrated guitar player. Add a subtle white watermark reading {argument name="watermark text" default="Promptsref.com"} in the bottom-right corner. Constraints: Use exactly 2 panels, with the top photorealistic and the bottom crayon-drawn. Do not add extra people, extra guitars, or additional readable text. Preserve the warm sunny mood and the cozy hand-crafted crayon aesthetic.

Weather Vending Machine Comparison

Create a split-screen comparison image showing two premium cinematic advertising photographs side by side, separated by a thin vertical white divider. The scene is a vast red desert at dusk with dramatic storm clouds, orange sunset glow on the horizon, distant mesas and rock spires, and wet reflective patches on the desert floor. In both panels, place a colossal dark metallic vending machine standing alone, labeled at the top with glowing warm-white text: “CHOOSE YOUR WEATHER”. The machine sells weather instead of snacks, with exactly five large glass display shelves containing: 1) a miniature thunderstorm with dark clouds and lightning, 2) a swirling blizzard over snowy mountains, 3) a glowing sunset sky, 4) a tornado over dusty plains, and 5) green-purple aurora lights over a night landscape. Include a woman in a long cobalt-blue coat and black boots standing beside the vending machine, seen from behind or side-back, reaching toward the selection buttons. The vending machine has a side payment/control panel with small glowing code buttons, a digital price display reading “SKY: $2.00”, and a collection slot. Add black rectangular title tags at the top of each panel: left tag reads {argument name="left model label" default="MONA-LISA-1"}, right tag reads {argument name="right model label" default="GPT IMAGE 2"}. Make the left panel slightly closer and more imposing, with readable small shelf labels such as A01 THUNDERSTORM, B07 BLIZZARD, C03 SUNSET, D09 TORNADO, and E05 AURORA; make the right panel a cleaner vertical machine design with the same five weather windows. Use ultra-realistic photography, cinematic lighting, high contrast, glossy glass reflections, moody atmosphere, premium sci-fi advertising style, sharp detail, 16:9 landscape composition, no extra text beyond the vending machine signage, shelf labels, price display, and model tags.

Three-Panel AI Billboard Comparison

Goal: Create a clean comparison graphic showing three AI-generated urban billboard photos side by side, as if comparing image model outputs. Canvas: Wide 16:9 presentation slide with a warm off-white background and generous margins. Place three tall vertical photo panels evenly spaced across the canvas, each framed by a pale beige mat/border. Under each panel, add a centered caption. Layout: Exactly 3 vertical street-photo panels in one row. Panel 1 on the left, Panel 2 in the center, Panel 3 on the right. Each panel shows a realistic New York City street scene with parked cars in the foreground, tall buildings, sidewalks, traffic signs, and a large square billboard mounted high on a building. Use slightly different street angles and lighting in each panel, like three separate model outputs of the same concept. Panel details: Left panel: a rear view of a black SUV parked on a city street, looking toward storefronts and buildings; a large white billboard above the street reads like a social-media quote card with a small circular animal avatar, the heading “What do you think?”, a short quote, and small ChatGPT branding. Center panel: a black SUV parked on a narrow Manhattan street with the Empire State Building visible in the distance; a large dark billboard with white text, a circular animal avatar, and ChatGPT branding. Right panel: a black sedan parked along a busier avenue with storefront signs such as “I ♥ NY GIFTS”; a large black billboard with a bright cyan border, white quote text, a circular animal avatar, and ChatGPT branding. Caption text: Use exactly 3 captions beneath the panels. Left caption: “ChatGPT Images 2.0” on the first line and “MEDIUM” in bold quotation marks on the second line. Center caption: “mona-lisa-1” in bold quotation marks. Right caption: “ChatGPT Images 2.0” on the first line and “HIGH” in bold quotation marks on the second line. Customizable text slots: The comparison labels should read {argument name="left model label" default="ChatGPT Images 2.0"}, {argument name="center model label" default="mona-lisa-1"}, and {argument name="right model label" default="ChatGPT Images 2.0"}. The left quality tag should be {argument name="left quality tag" default="MEDIUM"} and the right quality tag should be {argument name="right quality tag" default="HIGH"}. Visual style: Photorealistic smartphone street photography inside each panel, but arranged as a polished social-media comparison slide. Keep the overall slide minimal, with no decorative graphics beyond the three framed images and their captions. The billboard text inside the photos may be small and partially imperfect, but it should clearly resemble AI quote-card advertising with ChatGPT logos.

Real Woman and Line Art Cartoon Comparison

"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."

Rainy Night Fashion Comparison

Goal: Create a side-by-side comparison image showing two vertical 4:5 photorealistic fashion-editori…

Nine-Model Scarecrow Yokai Comparison

Goal: Create a 3 by 3 comparison chart showing nine different AI image model outputs for the same ch…

Skin Comparison Portrait — Nano Banana Pro

Split comparison portrait, vertical split center, close-up face, eye-level. Subject: same young woman shown in two skin conditions, facing forward. Left side: neutral tired expression. Right side: soft confident smile. Appearance: dark brown hair, straight middle-parted. Left skin: severe acne, pimples, redness, uneven texture, dull and oily. Right skin: clear smooth glowing skin, even tone, healthy radiant look. Outfit: cream knitted sweater. Environment: car interior, soft daylight, brown seat, blurred outdoor greenery. Lighting: natural light, left side slightly dull and flat, right side brighter and glowing. Left title: 'Foods that ruin skin'. Right title: 'Foods that save skin'. Left foods: instant noodles, fried snacks, sugary sweets, white bread, pizza / fast food, cold drinks, ice cream, packaged chips, chocolate. Right foods: sprouts, methi seeds, lemon water, green tea, amla, almonds, tomato, cucumber, leafy greens. Style: social media comparison graphic, educational, clean contrast, natural tones with strong visual difference. High resolution, sharp facial texture difference clearly visible.

Transparent Background Comparison Grid

Goal: Create a clean comparison grid demonstrating background handling for cutout portrait images generated by {argument name="image model" default="GPT Image 2"}. Canvas: Square 1:1 canvas, approximately 1200 x 1200 px, with a very light gray page background and narrow gutters between panels. Layout: Use exactly 6 rectangular panels arranged in a 2-row by 3-column grid. Each panel contains one full-body studio cutout subject centered vertically and horizontally with ample margin. The three columns compare background types: left column shows a gray-and-white checkerboard transparency pattern, middle column shows a plain white background, right column shows a solid black background. No captions, no logos, no text. Subjects: Use exactly 2 human models. Top row: a {argument name="female model description" default="young woman with long voluminous curly brown hair, neutral expression, barefoot, wearing a loose cream chunky-knit cardigan over a light camisole and wide beige lounge pants"}. She stands front-facing in a relaxed fashion pose, one arm folded across her body and the other hanging down, soft studio lighting, realistic photographic detail. Bottom row: a {argument name="male model description" default="middle-aged man with short dark hair and salt-and-pepper beard, serious expression, walking toward camera, wearing a long dark charcoal overcoat, gray knit sweater, navy trousers, and polished dark brown dress shoes"}. He appears mid-stride with one hand in his trouser pocket and the coat slightly flaring outward. Panel details: Count of repeated elements is exactly 6 panels: 1) woman on checkerboard transparent-style background, 2) woman on white background, 3) woman on black background, 4) man on checkerboard transparent-style background, 5) man on white background, 6) man on black background. Keep the same subject pose, scale, lighting, and crop consistent across each row so only the background changes. Visual style: Hyperrealistic studio product-demo photography, crisp full-body cutouts, clean edges around hair and clothing, neutral soft shadows only if subtle, high contrast on black backgrounds, bright clean white backgrounds, and a standard transparency checkerboard pattern made of evenly sized alternating light gray and white squares. Constraints: Do not include any visible text, labels, watermark, interface chrome, decorative icons, or extra objects. Maintain realistic proportions, full bodies visible from head to feet, centered composition, and consistent spacing between all grid cells.

3D Footstool Mesh Comparison

Create a realistic architectural visualization comparing two 3D-generated ottoman stools in an interior showroom scene. Canvas: wide landscape 16:9 render, camera at low eye level looking slightly downward. Scene: two small Barcelona-style footstools placed side by side on a dark charcoal tiled floor, in front of a tall glossy stone wall with dramatic brown, cream, rust, and gold onyx/marble veining; a narrow strip of green-tinted glass or window appears at the far right edge, with pale exterior floor tiles visible beyond. Subjects: exactly 2 footstools: left stool is the HD version, slightly smaller and lower, with a white tufted square cushion divided into a 4-by-4 grid, rounded soft edges, light gray leather straps underneath, and reflective polished metal X-shaped legs; right stool is the Smart Mesh version, slightly larger and cleaner, with a thicker smooth white cushion, parallel white underside straps, and gray polished X-shaped metal legs. Add thin black 3D viewport guide lines or wireframe axis lines crossing through and around both stools, including vertical and horizontal alignment lines, as if shown in a 3D modeling comparison viewport. Materials: white leather cushions with subtle seams and soft highlights, chrome legs with reflections, dark matte floor tiles with faint grout lines, glossy veined stone wall. Lighting: soft indoor studio lighting, moderate shadows, realistic but slightly CGI-rendered look. Composition: left stool around one-third of the frame, right stool around two-thirds, both facing forward at a slight angle, enough floor visible in front, marble wall filling the background. No people, no labels, no UI panels, no watermark.

Hairstyle Analysis Comparison Portrait

Create a {argument name="task" default="hairstyle analysis graphic"} using this portrait. Show side-by-side {argument name="subject" default="hairstyle"} comparisons to highlight which {argument name="plural_subject" default="hairstyles"} suit the subject best

AI Model Portrait Comparison

Goal: Create a clean side-by-side comparison graphic showing two AI image model outputs as realistic street portraits. Canvas: Horizontal 3:2 social media comparison image, white background, high resolution. Use a simple two-column layout with a narrow vertical white divider between the image panels. Layout: Top header area contains exactly 2 black logos centered above exactly 2 bold model names. Left column: OpenAI knot logo above the heading “{argument name="left model name" default="GPT-Image 2"}”. Right column: Grok-style black circular slash logo above the heading “{argument name="right model name" default="Imagine Image 2.0"}”. Below the headers are exactly 2 equal-size rectangular photo panels: one on the left and one on the right. Photo content: Both panels show a cinematic, photorealistic urban street portrait of the same young woman in a crowded city. She has {argument name="hair color" default="dark brown"} hair, natural makeup, full brows, soft lips, and a calm direct gaze. She wears a dark coat. The background is a busy city sidewalk with motion-blurred pedestrians, shallow depth of field, muted gray urban tones, and warm bokeh traffic lights. Left photo panel: The woman is slightly left of center, turned partly toward the camera, with loose voluminous hair around her face. A large blurred pedestrian crosses the foreground on the right, partially obscuring the lower face/body area; another blurred figure appears on the left. The image should feel like a candid real-camera street photograph with natural imperfections and documentary realism. Right photo panel: The woman is centered closer to camera, facing forward with slightly tousled hair pulled back loosely and face-framing strands. Her facial detail is sharper and more polished, with visible skin texture and freckles. Blurred pedestrians pass on both sides, including a gray figure on the left and a warm brown motion blur on the right. Visual style: Photorealistic DSLR street photography, natural light, shallow depth of field, 50mm lens feel, realistic skin texture, subtle filmic color grading, high detail in faces, strong motion blur on passing pedestrians, no illustration style. Text and element count: Include exactly 2 logos, exactly 2 headings, exactly 2 photo panels, and exactly 2 main female portraits. Do not add extra captions, scores, labels, borders, watermarks, or interface elements.

Four-Panel Anime Face Comparison

Goal: Create a wide comparison graphic showing four generated anime-style close-up portraits of the…

NYC Romance Grade Comparison

Goal: Create a cinematic side-by-side comparison frame showing how different grading constraints aff…

Rakuten Happy Bag Banner Comparison

Goal: Create a wide comparison image showing three side-by-side Japanese beauty serum promotional ba…

VFX Comparison Image Prompt (Before/After) for Nano Banana Pro

【テーマや内容の具体的な説明　例：{argument name="テーマ" default="海の上を飛んでいる女性"}】のシーンに基づいた、添付画像の人物によるVFX比較映像。 中央の垂直線で正確に整列された分割画面によるVFX比較構成。 **重要：登場人物の人数、性別、外見特徴は、提供された入力画像と完全に一致させること。人物を増やしたり減らしたりしないこと。** **左半分（完成ショット）:** テーマ「**【テーマを入力】**」を完璧に描写したフォトリアルな映画のワンシーン。 * **人物:** 入力画像の人物が、テーマ「**【テーマを入力】**」に合った演技（ポーズや表情）をしている。 * **背景:** テーマに適合した詳細でリアルな環境（屋外や屋内）、映画的な照明と雰囲気。 **右半分（グリーンスクリーン撮影）:** 左半分に映っている人物と**全く同じ構成・ポーズ**で、巨大なブルー/グリーンスクリーン（クロマキー）のスタジオに立っている。 見える白いホリゾント壁、頭上の複雑な照明リグ、ケーブル、立ち位置を示す黒いバミリ（テープ）、撮影用レールのドリートラック、遮光されていないきついスタジオ照明、端に映り込む撮影クルーの薄い影。背景は合成用に完全に平坦な緑一色のスクリーンになっている。 2000年代初頭の日本映画のVFXビフォーアフター風のルック、極端に劣化した低画質のアナログビデオの質感、ノイズ、色褪せ。

Three Character Asset Comparison Board

Goal: Create a dark-background comparison board showing character asset sheets for three office-dressed people, comparing two image-generation systems side by side. Canvas: 16:9 landscape presentation image, approximately 2048×1152, with a deep navy-black background, clean white typography, and six large white image panels arranged in a 3-row by 2-column grid. Header text: At the top left, place the large Chinese title {argument name="headline text" default="3组 女生人物资产 · 同提示词对比"}. Under it, add a smaller subtitle line: {argument name="comparison subtitle" default="左：历史 GPT Image 2 右：ChatGPT Images 2.5 网页"}. Layout: Use exactly 6 rectangular white panels with thin spacing: left column represents the older model, right column represents the newer model. There are exactly 3 character rows: Clara, Julian, and Evelyn. Each row has a small Chinese row label above the left panel: “纯文字角色资产 - Clara”, “纯文字角色资产 - Julian”, and “纯文字角色资产 - Evelyn”. Each of the 6 panels contains exactly 4 character depictions on a white studio background: 1 large cropped head-and-shoulders portrait on the left, plus 3 smaller full-body turnaround views on the right: front view, side profile view, and back view. Total visible character depictions: exactly 24. Row 1 subject details: Clara, a young fair-skinned woman with long wavy dark brown hair, soft natural makeup, neutral serious expression, wearing a cream ribbed turtleneck, brown cropped blazer, high-waisted wide-leg cream trousers, a black belt, and low heels. In each Clara panel show 4 views: close portrait, full-body front, full-body side, full-body back. Row 2 subject details: Julian, a young slim fair-skinned man with light brown/blond swept hair, rectangular glasses, calm serious expression, wearing an off-white linen suit, white open-collar shirt, narrow trousers, brown belt, and tan loafers. In each Julian panel show 4 views: close portrait, full-body front, full-body side, full-body back. Row 3 subject details: Evelyn, a middle-aged woman with medium tan skin, dark hair pulled back into a low bun, composed neutral expression, wearing a black business suit, dark gray blouse, small gold necklace, small earrings, black trousers, and black flats. In each Evelyn panel show 4 views: close portrait, full-body front, full-body side, full-body back. Visual style: Realistic photography-like character asset sheets, clean studio lighting, white seamless backgrounds inside each panel, consistent professional wardrobe styling, neutral expressions, no decorative graphics except the dark board and labels. The left and right columns should be visibly similar but not identical, as if comparing outputs from two systems. Footer text: At the bottom left, add two small Chinese notes: {argument name="footer note one" default="历史成品 2048×1152 / 网页新图 1672×941 · 仅排版缩放，无修图、无超分。"} and {argument name="footer note two" default="提示词正文相同，两页端仅补充16:9比例。"}. Constraints: Keep the exact 3-row by 2-column comparison layout, exactly 3 named characters, exactly 6 panels, exactly 4 depictions per panel, with no watermark, no extra logos, and no additional characters.

Five-Page Manga Quality Comparison

Goal: Create a wide monochrome comparison sheet showing five nearly identical Japanese manga pages placed side by side, like an image-generation quality comparison. Each page should depict the same cute fox-eared girl food-shopping scene, with tiny labels centered above each page for different quality settings. Canvas: Extremely wide horizontal canvas, about 5:1 aspect ratio, white background, crisp black-and-white manga printing. Place exactly 5 complete manga pages in a row with narrow white gaps between them. Each page is vertical and identical in overall composition, using clean screentones, thin panel borders, speed lines, and detailed manga backgrounds. Layout per page: Each of the 5 pages contains exactly 8 panels arranged in 4 tiers: 1 wide top panel, 2 panels in the second tier, 3 panels in the third tier, and 2 panels in the bottom tier. Keep the repeated pages almost the same, with only subtle quality/detail differences between them. Page labels: Add 5 tiny English labels above the pages, one per page: “quality low”, “quality medium”, “quality high”, “quality ultra”, and “quality max”. Story and panel details for every page: 1. Top wide panel: A cheerful anime fox girl with large fox ears, long light hair, and a casual hoodie smiles brightly in a cozy room with a window, curtains, plants, and a round lamp behind her. She raises one hand in excitement. Include a vertical oval speech bubble containing {argument name="top speech bubble" default="今日はお弁当を買いに行こう"}. 2. Second-tier left panel: Close-up of prepared boxed lunches or bento trays in a display case, drawn with detailed food textures and packaging. 3. Second-tier right panel: Exterior of a modern convenience store or deli storefront with glass windows, a signboard, sidewalk, and small background figures. Add two vertical speech bubbles with small Japanese manga text. 4. Third-tier left panel: Rear view of two or three customers standing in line inside the shop; the fox girl is visible among them holding a basket. 5. Third-tier middle narrow panel: A small dialogue/reaction panel with a simple speech bubble, suggesting hesitation or ordering. 6. Third-tier right panel: The fox girl at a counter or table looking at a bento box, smiling and holding chopsticks or a tray, with another speech bubble. 7. Bottom-tier large left panel: Dramatic close-up of the fox girl shocked and overwhelmed by delicious food or the amount she bought; wide eyes, open mouth, blush, speed lines radiating behind her, and a basket or bento boxes in the foreground. Include a bold speech bubble with {argument name="reaction speech bubble" default="やべぇ ついつい買ってるじゃん"}. 8. Bottom-tier small right panel: A simplified stunned reaction portrait of the fox girl facing forward, blank expression, large ears, and a tiny vertical bubble with ellipsis. Character details: The main character is {argument name="character description" default="a young anime fox girl with fluffy upright fox ears, long pale hair with bangs, bright eyes, and a playful expression"}. Her outfit is {argument name="outfit" default="a loose casual hoodie with a simple collar"}. Use a cute modern manga style, expressive face acting, clean linework, and soft grayscale screentone shading. Visual style: Black-and-white manga page art, high detail, sharp ink lines, halftone shading, traditional Japanese comic paneling, realistic convenience-store backgrounds, readable panel borders, no color except grayscale. The five pages should feel like a side-by-side technical comparison, not separate unrelated illustrations. Constraints: Use exactly 5 repeated pages and exactly 8 panels per page, for a total of 40 visible comic panels. Do not add extra characters beyond small background shoppers and staff. Keep all nonessential dialogue as tiny Japanese-style manga lettering, and avoid watermarks or logos.

Three-Panel Chinese Aesthetic Model Comparison

Goal: Create a vertical three-panel comparison collage showing the same Chinese traditional aesthetic portrait generated in three different styles. Canvas: Portrait format, approximately 4:5 aspect ratio, 960×1200 feel. Divide the image into exactly 3 equal horizontal panels separated by thin white horizontal lines. Overall subject: In all three panels, show the same young East Asian woman in a warm, cinematic ancient Chinese interior, wearing a soft ivory hanfu robe. She is adjusting a peach-pink flower hair ornament near her ear with both hands. Her black hair is loosely pinned up with wispy strands around her face. The atmosphere is golden-hour, backlit, romantic, and traditional, with wooden lattice windows behind her, soft haze, shallow depth of field, warm sunlight, and floating flower petals or dust motes. Panel count and labels: Use exactly 3 panels with large white sans-serif text labels in the lower-left area of each panel: 1) “Midjourney V8.2” on the top panel, 2) “GPT-Image 2” on the middle panel, 3) “Seedream 5.0 Pro” on the bottom panel. Top panel: Label “Midjourney V8.2”. Make this the most dramatic and cinematic version: stronger contrast, moody shadows, glowing rim light, more dynamic pose, windblown hair, petals crossing the foreground, refined facial features, realistic skin texture, premium film still quality. The woman faces slightly toward camera with a serious, elegant expression while placing the flower by her ear. Middle panel: Label “GPT-Image 2”. Make this cleaner and softer, with a slightly polished beauty-retouch look. The woman is turned three-quarters to the right, looking sideways while carefully adjusting the flower. Keep warm window light, cream hanfu fabric with subtle embroidered floral details, and a more smooth, influencer-like face. Bottom panel: Label “Seedream 5.0 Pro”. Make this brighter and slightly more plastic/smooth than the top, with a gentle smile and softer realism. The woman holds the peach flower close to her ear, looking down-left or sideways, with intense backlight from the lattice window and a glowing edge around her hair and hands. Text styling: Large white text, simple sans-serif, no outline, subtle shadow if needed for readability. Place each label consistently near the bottom-left of its panel. Do not add any other text, logos, watermarks, or UI elements. Customizable details: The subject is {argument name="subject description" default="a young East Asian woman in ivory hanfu"}; the setting is {argument name="setting" default="a warm ancient Chinese room with wooden lattice windows"}; the hair accessory is {argument name="hair flower" default="a peach-pink flower"}; the top label is {argument name="top model label" default="Midjourney V8.2"}; the middle label is {argument name="middle model label" default="GPT-Image 2"}.

Starbucks Mountain Watercolor Comparison

Goal: Create a vertical comparison-style image showing a nighttime café-and-mountain scene transformed into a delicate watercolor art print. Canvas: Portrait 3:4 composition, divided into exactly 2 horizontal panels. The top panel occupies about the upper half and is a realistic night photograph; the bottom panel occupies the lower half and is a minimalist watercolor artwork on warm off-white paper. Top panel: A centered, single-story Starbucks café at night, seen from across a dark parking lot. Behind it is a large snow-capped Mount Fuji-like mountain rising in blue mist under a deep twilight blue sky. The café has a black roofline and glowing warm interior windows. Include exactly 2 visible Starbucks brand marks: 1 large bright yellow word sign reading {argument name="store sign text" default="STARBUCKS"} centered on the building, and 1 small circular green siren logo on the right side of the storefront. Surrounding silhouettes include exactly 5 prominent natural/urban elements: 2 tall conifer trees on the left, 1 leafless tree to the right of the building, 1 tall conifer tree near the far right, and 1 tall streetlamp on the far right with a simple rectangular lamp head. Keep the mood quiet, blue, misty, cinematic, and calm. Bottom panel: Recreate the same scene as a small hand-painted watercolor vignette centered on textured cream paper with lots of empty negative space. Paint the café, mountain, trees, and streetlamp in loose blue ink and pale watercolor washes. The miniature café should again include exactly 2 visible Starbucks brand marks: 1 tiny dark rectangular sign with yellow {argument name="store sign text" default="STARBUCKS"}, and 1 small green circular logo on the right. The watercolor version should include exactly 4 tree silhouettes: 2 thin conifers on the left of the café, 1 thin conifer on the right, and 1 simplified streetlamp beside it. Use soft bleeding edges, sparse brush marks, muted indigo shadows, and warm yellow window glow. Text content beneath the watercolor vignette: Add exactly 3 centered handwritten lines in small lowercase lettering: line 1 reads {argument name="caption line one" default="coffee · mist · mountain"}; line 2 reads {argument name="caption line two" default="a quiet moment"}; line 3 reads {argument name="year" default="2024"}. Use widely spaced, delicate gray-blue handwriting. Visual style: The top half should feel like a crisp realistic nighttime travel photograph; the bottom half should feel like a refined Japanese-inspired watercolor postcard or art print. Preserve the same subject alignment between panels: mountain centered behind the café, café centered below the mountain, tall lamp and conifer on the right, darker trees on the left. Constraints: No people, no cars, no extra signage beyond the counted Starbucks marks, no borders between panels except the natural transition from photo to paper, no watermark, keep the overall palette deep blue, pale cyan, cream paper, black silhouettes, and warm yellow café light.

Reasoning Effort Anime Comparison

Goal: Create a wide social-media comparison graphic showing an AI image generation experiment about…

Cinematic Anime Photo Comparison

Goal: Create a side-by-side comparison image showing a realistic reference-style photo on the left a…

Calamari Cone Model Comparison

Goal: Create a vertical comparison image showing the same appetizing fried calamari cone rendered in two stacked panels, like a side-by-side model comparison but arranged top and bottom. Canvas: Square 1:1 image, 768 x 768 style composition, split horizontally into exactly 2 equal panels. Use a clean bright {argument name="background color" default="vivid ocean blue"} studio background with a subtle gradient; the top panel is slightly deeper blue and the bottom panel slightly lighter blue. Layout: Top panel contains one floating paper cone of fried calamari centered slightly left, tilted upright, surrounded by airborne crumbs and flying calamari rings. Bottom panel contains the same paper cone larger and closer to camera, centered slightly left, with a few flying rings and a lemon wedge. Add a white italic serif label reading {argument name="top label" default="GPT image 2"} near the lower-right of the top panel, and another white italic serif label reading {argument name="bottom label" default="Nano Banana 2"} in the lower-right corner of the bottom panel. Subject details: The food is golden crispy fried calamari rings with rough crunchy breading, photographed as high-speed food advertising. Use exactly 2 lemon wedges total: 1 tucked into the top cone at the upper right, and 1 floating near the upper-right of the bottom panel. Use exactly 34 prominent calamari rings total: in the top panel, 18 rings, with 10 piled inside the cone and 8 flying around it; in the bottom panel, 16 rings, with 13 piled inside the cone and 3 flying outside it. Add many tiny orange breadcrumb particles and a few broken batter fragments suspended in midair, especially dense around the top cone. Packaging: Each cone is made from off-white faux newspaper paper printed in blue ink. The main circular logo on the cone reads {argument name="brand logo text" default="FISH & LOVE"} with a small fish illustration above it. Large blue newspaper headline text on the wrapper reads {argument name="wrapper headline" default="From the sea to love."}. Include smaller decorative seafood-newspaper details, thin blue rule lines, tiny columns of filler text, simple fish and lemon illustrations, and the phrase "Simple ingredients, unforgettable taste." on the wrapper. The top cone is slightly smaller with more dramatic exploding crumbs; the bottom cone is larger, more polished, and has clearer wrapper text. Visual style: Ultra-realistic commercial food photography, crisp texture, sharp focus on calamari, high-speed freeze-frame motion, bright natural highlights, appetizing warm orange-gold food color against saturated blue, shallow depth of field, clean advertising composition, no people, no plates, no extra objects, no watermark.

Naive doodle-style subject illustration

A doodle-style {argument name="subject" default="[subject]"}, naive lines, humorous shape exaggeration

Sora video prompt for Macho Meal McDonald’s commercial

Authentic vintage 1980s commercial for the {argument name="product name" default="Macho Meal happy meal"} at {argument name="brand" default="McDonalds"} featuring {argument name="celebrity" default="Macho Man Randy Savage"}.

Elegant woman in brown mini dress portrait prompt

{ "prompt": "A beautiful woman with long, flowing brown hair poses confidently. She is wearing a form-fitting, light brown mini dress that accentuates her figure. Her left hand is raised to her head, and she looks directly at the viewer with a captivating gaze. The background is dimly lit, featuring warm wall sconces and a glimpse of a dark leather couch, creating an intimate and stylish atmosphere. The lighting highlights her hair and the contours of her body." }

Anti-Plastic/Hyper-Realism Protocol for Human Skin Texture

When generating images of humans: use ANTI-PLASTIC/HYPER-REALISM protocol. All images must be EVER in 8K resolution. OVERRIDE default smoothing. Render skin as biological topography. [1] ADAPTIVE SETUP: Adapt Subject/Light/Style to query. SCALING: Close-Up->Force Macro/Micro-details. Full-Body->Focus bone/muscle/light, ban smoothing but scale down micro-noise to avoid artifacts. [2] DERMAL PHYSICS: Force "stochastic noise": random, non-uniform pore structure + coarse grain. Ban smooth/waxy surfaces. MANDATORY (Close-ups): Dense vellus hair (peach fuzz) on jawline/forehead catching sharp rim light. [3] SUBSURFACE SCATTERING: Reject uniform tones. Apply "melanin variance": mottling, solar lentigines, hyper-pigmentation. Simulate thin-skin translucency. Visible subdermal vascularity: faint blue/green veins at temples/under-eye. Erythema + telangiectasia around nostrils/tear ducts. [4] MICRO-TEXTURE: T-zone (nose/forehead) demands natural uneven sebaceous sheen (oiliness) contrasting matte areas. Highlights must reveal skin micro-relief [5] EYES: Irises: deep, chaotic fibrous striations + crystalline refraction. Sclera: distinct red vascular mapping. Lower waterline: thick, pooling liquid reflection (tear film) [6] LIPS: Texturally dry/dehydrated. Deep vertical fissures, micro-cracks, peeling flakes. Uneven specular highlights [7] FAIL STATE: If skin appears smooth, doll-like, or airbrushed, GENERATION FAILS. Maximize texture defects, asymmetry, topographical imperfections

Sgraffito Mechanical Blueprint of NVIDIA 4090 GPU

A Sgraffito Mechanical Blueprint of {argument name="GPU model" default="NVIDIA 4090 GPU"}

Simple 'Happy New Year' Prompt

{argument name="greeting"…

4-Panel Bikini Mirror Selfie Collage

{ "type":"img_prompt", "ref_lock":"strict", "layout":{ "format":"4-panel 2x2 collage",…

Mixed Media Y2K Street Style with Cartoon Companion

Transform this image [UPLOAD YOUR IMAGE into a 64K DSLR shot resolution of A fashionable young man (…

Edo-style woodblock print ninja character

キャラクターが見栄を切ってカッコいいポーズを取っている、タイトル「{argument name="タイトル" default="からくり忍者　朧"}」の版画の画像、江戸時代の作風

Golden hour rooftop portrait photography prompt

A person standing on a city rooftop during golden hour, warm sunlight wrapping around their face, subtle lens flare, wind brushing their hair, shallow depth of field, 35mm photography vibe, natural skin texture.

Anthropic-style warm academic PPT workflow prompt

帮我根据下面这个文章做一套专业的的中文PPT。 先写1个PPT大纲，规划出每一页的PPT的内容。 然后将每一页的PPT内容分别扔给Nana Banana pro生成对应页面的PPT，需要确保风格一致。 PPT的具体风格应该为“Anthropic/Claude 风格”的“温暖学术人文主义”设计。 背景：使用暖米色/奶油色 (# F3F0E9) 作为纯色底色，略微高级纸张质感。 字体：标题使用优雅的衬线体（Serif），正文使用现代无衬线体（Sans-serif）。 配色：主色调为赤陶红 (# D67052) 和芥末黄 (# F0B857)，搭配深海军蓝作为点缀。避免使用霓虹色或纯黑色。 视觉元素：使用注重排版的网格布局，插图风格应为抽象的、有机的黑色手绘线条画，置于赤陶红纯色色块之上，你需要非常克制的使用插图和点缀类的插图元素，插图需要为内容服务。 图表：扁平化、极简的图表，强调数据对比，去除多余边框。 文字和图像都由 Nano Banana Pro 生成，另外不要将PPT 变成一整张图，一页一张图。 文章内容为：

Violet Ghost in a Golden Room K-Pop Aesthetic Image Prompt

A violet ghost within the golden room, Where silence weaves a soft and velvet gloom.The fringe of silk falls heavy on the brow,A curtain drawn before the silent vow.Upon the palm, the weary cheek finds rest,A bored warmth rising in the quiet chest.With glass and stone circling the slender wrist, She stares through time, shrouded in purple mist. The gaze is sharp, yet soft as morning rain,A portrait painted on a window pane. Ambient Purple Lighting, K-Pop Aesthetic, Soft Focus, Shallow Depth of Field, High ISO Noise, 8k Resolution, Candid Selfie Angle, Bangs Hairstyle.

Photorealistic Leaf Shaped Like a Dragon

A photorealistic image of a leaf that looks like it’s in the shape of a dragon.

Conceptual Frame: Absurd Specimen Jar Study

{ "creation_intent": "娱乐或玩笑", "generation_logic": "瞬间叙事", "subject_kit": { "primary_subject": "标本罐",…

Grunge Street Photography Portrait with a Sports Car

{ "prompt_name": "grunge_man_with_car_street_pose", "scene_type": "urban_grunge_photography",…

Flash Photography Portrait of Taylor Swift in Latex Dress

{ "generation_parameters": { "topic": "Portrait Photography", "aspect_ratio": "3:4", "…

Infographic about Google’s early years

please create an info graphic about google's early years and its major milestones

Cinematic close-up portrait with green eyes and knit sweater

Cinematic close-up portrait of a young woman with dark messy bangs and striking green eyes, resting chin on a hand covered by a chunky grey knit wool sweater. Her face is pale with a heavy dusting of natural freckles and rosy cheeks, illuminated by a beam of warm golden-hour sunlight creating a dramatic chiaroscuro contrast. 35mm analog film photography style, f/1.8, bokeh, visible film grain, highly detailed skin texture, raw and emotional mood, Kodak Portra 400 aesthetic.

Character Design Expression Style Guide Prompt

Make a character design expression style guide of image

Game of Thrones Ice and Fire Isometric Diorama

Present a clear, 45° top-down isometric miniature 3D cartoon scene of the central thematic concept {argument name="thematic concept" default="Ice and Fire"} from {argument name="series name" default="Game of Thrones"}, with soft refined textures, realistic PBR materials (emphasizing glittering frost contrasts against glowing embers and scaled skin), and gentle lifelike lighting that creates a dramatic clash of cool blue and warm orange light. Create a small raised diorama-style base that is split down the middle. The left side features a section of The Wall made of ice with tiny stylized White Walker figures on snowy terrain. The right side features a stylized dragon ({argument name="dragon name" default="Drogon"}) perched atop a burning castle turret, with tiny stylized Unsullied soldiers on charred ground. A crack runs down the center of the base where the ice meets the lava. Use a clean solid {argument name="background color" default="Neutral Slate Grey"} background. At the top-center, display {argument name="series name display" default="Game of Thrones"} in large bold text, directly beneath it show {argument name="thematic concept display" default="Ice and Fire"} in medium text, and place the official logo associated with {argument name="series name logo" default="Game of Thrones"} below the subtext. All text must automatically match the background contrast (white). Composition: perfectly centered layout, square 1080x1080, ultra-clean, high-clarity diorama aesthetic.

Photorealistic Portrait Prompt for Gemini Nano Banana Pro

{   "prompt_type": "photorealistic_portrait",   "subject": {     "demographics": "Young woman, estim…

Premium Beverage Package Design Prompt

Premium beverage package design

Playful Studio Portrait with Sydney Sweeney Vibes

{ "style": "ultra-realistic studio portrait", "subject": { "gender": "female", "age": "y…

Photorealistic Cosplay of Alice: Madness Returns

{ "prompt_data": { "subject": { "character": "Alice Liddell", "source_material": "…

Rosé (BLACKPINK) at Sunset Beach

{   "raw_prompt": "A high-resolution portrait of Rosé (BLACKPINK) at a beach during sunset. She has long, strawberry blonde hair with blunt bangs, styled in a ponytail. She wears a soft pastel pink crochet two-piece set consisting of a strapless bandeau top and a matching high-waisted skirt. She is adorned with large, gold floral statement earrings. She stands with her back to the camera, looking over her shoulder with a soft, cinematic gaze. The background features a white-clothed table on a sandy beach, a wooden chair, and the ocean under a warm, golden hour sky. Shot on 35mm lens, soft natural lighting, warm color grading. --ar 9:16",   "aspect_ratio": "9:16",   "subjects": [     {       "name": "{argument name=\"subject name\" default=\"Rosé (BLACKPINK)\"}",       "physical_features": "Long strawberry blonde hair with bangs in a ponytail, fair skin, soft elegant makeup with winged eyeliner.",       "outfit": {         "bottom": "Pastel pink crochet knit form-fitting midi skirt.",         "top": "Pastel pink crochet knit strapless bandeau top.",         "accessories": "Oversized metallic gold triple-flower drop earrings."       },       "pose_and_expression": "Standing with back to camera, torso turned 45 degrees, head turned back to look directly at the lens; calm and sophisticated expression."     }   ],   "environment": "Outdoor luxury beach dining setup at sunset, white linen table, wicker chair, driftwood, calm sea, and orange-hued sky.",   "photography_and_lighting": {     "camera_style": "35mm professional photography, cinematic depth of field.",     "lighting": "Golden hour backlight, soft diffused glow on skin.",     "color_grading": "Warm tones, high saturation in oranges and golds, soft shadows."   } }

Cinematic Breakfast Scene

朝の食卓で両親と楽しく朝食をとるシネマティックなシーン。サクッとトーストを割り、美味しそうに頬張って微笑む可愛らしい表情や、マグカップを合わせて乾杯する心温まる様子。椅子の音や咀嚼音、カップが鳴る心地よいASMRサウンドが響く。

Voluptuous Beach Portrait with Natural Lighting

{ "subject": { "description": "Young woman with a voluptuous and curvy physique, sitting on a wooden beach chair. She has a tan complexion with visible, natural freckles scattered across her nose and cheeks. Her face is oval-shaped with full lips and soft features.", "hair": "Long, wavy, dirty blonde to light brown hair with balayage highlights, parted in the center and falling loosely over her shoulders.", "body_type": "Curvy hourglass figure with prominent physical features. Shoulders are soft and relaxed. The bust is naturally large, heavy, and full, showing significant volume and clearly affected by gravity (natural teardrop shape). There is visible deep cleavage and projection. The waist is tapered, leading into wide, curvy hips and thick thighs.", "attire": "A {argument name="bikini pattern" default="black and white zebra-print"} string bikini. The top features triangular cups that are filled completely by the bust volume, with thin straps around the neck. The bottoms are side-tie style with a matching zebra pattern. She wears a beaded bracelet on her right wrist, a thin gold bangle on her left wrist, and small stud earrings." }, "pose": { "posture": "Sitting centrally on a weathered wooden lounge chair. Her torso is upright but relaxed, facing directly forward.", "limbs": "Both arms are extended downwards at her sides, with her hands resting or gripping the wooden slats of the chair seat. Her legs are positioned with thighs resting on the chair, knees slightly apart.", "head": "Head is straight, facing the camera directly. Eyes looking straight into the lens.", "alignment": "Symmetrical frontal pose." }, "environment": { "location": "Tropical beach resort setting.", "ground": "White sand visible beneath and around the chair.", "background_elements": "Behind her is a low white wall and lush green vegetation (bushes). Further back, there are tall palm trees and several thatched-roof structures (palapas). To the right, other resort guests can be seen relaxing on lounge chairs.", "sky": "Overcast, cloudy white/grey sky." }, "camera": { "shot_type": "Medium shot, capturing the subject from the mid-thighs up to the top of the head.", "angle": "Eye-level to slightly high angle, looking down at the seated subject.", "perspective": "Standard focal length (approx 50mm-85mm), creating a natural representation without wide-angle distortion.", "focus": "Sharp focus on the subject's face and body, with a gentle depth of field softening the background elements." }, "lighting": { "type": "Natural, diffuse daylight (overcast).", "quality": "Soft, even illumination with no harsh shadows. The light wraps around the body, highlighting skin texture and the curves of the physique.", "direction": "Overhead diffuse ambient light.", "shadows": "Subtle, soft shadows under the chin, bust, and limbs where they contact the chair." }, "mood_and_expression": { "emotion": "Neutral, calm, and confident.", "expression": "Lips are closed and relaxe" }

Photorealistic Glass-Skin Portrait

A hyper-photorealistic shot of the same subject in the attached image. Ultra 8k HD, sharp facial det…

Depth of field shift to focus on man’s face

Focus on man's fa…

Photorealistic High-Contrast Indoor Portrait Prompt

{ "image": { "general": { "style": "photorealistic", "mood": "candid, playful", "lighting": { "type": "natural", "intensity": "harsh", "effect": { "high_contrast": true, "highlights": { "intensity": "strong", "focus": "on the subject and couch" }, "shadows": { "intensity": "deep", "focus": "on the subject, couch" } } }, "image_ratio": "3:4" }, "scene": { "location": { "type": "indoor", "style": "modern living room", "elements": { "sofa": { "type": "plush", "color": "white", "texture": "soft, luxurious" }, "lighting_source": { "type": "sunlight", "direction": "streaming from a large window", "effect": "bright and direct" }, "room_features": [ "minimalistic decor", "large windows", "open space with natural light" ] } } }, "subject": { "identity": { "name": "{argument name="subject name" default="Ana de Armas"}", "age_range": "mid-20s to early 30s", "characteristics": [ "Latin descent", "light skin", "youthful appearance" ] }, "physical_appearance": { "hair": { "color": "brown", "texture": "wavy", "length": "long", "style": "high pigtails", "details": "loose strands around the face" }, "eyes": { "expression": "playful", "focus": "winking at the camera" }, "facial_expression": { "emotion": "playful", "details": "slight smile with a wink" }, "body_type": { "build": "slender", "focus": "natural curves" } }, "outfit": { "top": { "type": "corset-style", "color": "black", "details": "fitted design accentuating the figure" }, "bottom": { "type": "mini dress", "fit": "tight", "material": "stretch fabric" }, "style": "elegant yet casual" }, "pose": { "body_position": "seated", "position_details": { "sitting": "on a white plush sofa", "legs": "crossed at the knees", "arm_position": "one arm resting on the sofa, the other holding a strand of hair" }, "facial_focus": "winking and playful expression", "gesture": "subtle motion, holding hair with one hand, the other hand resting casually on the sofa" } }, "visual_effects": { "lighting_effects": { "shadows": { "depth": "deep", "focus": "on the figure and sofa, creating a dramatic effect" }, "highl

Overhead Shot of Bookshelves with Floral Arrangements

A detailed, close-up, overhead shot shows four shelves of books, each shelf adorned with vibrant floral arrangements. The books are of various sizes and colors, with some spines featuring intricate patterns and others appearing plain. The floral arrangements consist of lush green foliage and brightly colored flowers, predominantly in shades of {argument name="flower color 1" default="pink"}, {argument name="flower color 2" default="red"}, and {argument name="flower color 3" default="teal"}. The overall aesthetic is rich and textured, with a slightly painterly or illustrative quality.

Moody Low-Light Portrait with Voluminous Curly Hair

{ "main_prompt": "intimate moody low-light portrait of a stunning young woman in her early-mid 20s with warm olive-to-medium tan skin and natural dewy glow, long voluminous dark brown curly hair with tight defined ringlets cascading wildly over shoulders and chest, slightly messy and voluminous natural curls, subtle glamorous makeup with defined arched brows, dark winged eyeliner, long thick lashes, glossy deep nude-pink lips in soft seductive pout, dreamy sultry expression with half-lidded eyes gazing directly at camera, head tilted slightly downward and to the side, wearing tight black halter-neck mini dress with deep plunging neckline and cut-out sides revealing toned midriff and hips, delicate gold chain necklace and bracelet visible, posing in dimly lit bedroom or hotel room at night, warm tungsten lamp light (~2800K) from side creating strong golden rim light on hair curls, cheekbones, collarbone and shoulders, cool moonlight or window fill from behind adding soft blue-purple shadows, subtle phone flash fill for catchlights in eyes, vintage film camera aesthetic with light leaks in corners, slight orange color cast, vignette edges, light film grain and soft bokeh, photorealistic, ultra-detailed skin texture with realistic pores, freckles and natural imperfections, individual curly hair strands catching warm-cool light with subsurface scattering, cinematic color grading with warm golden skin tones, deep shadows and muted contrast, shot on iPhone in night mode portrait with flash or vintage 35mm film, shallow depth of field focus on face and hair with creamy bokeh on dark background, dreamy intimate late-night bedroom energy, raw unfiltered sensual vibe, high fashion editorial meets candid selfie aesthetic --ar 3:4 --stylize 350 --v 6 --q 2", "negative_prompt": "blurry, lowres, deformed hands, extra fingers, fused fingers, bad anatomy, poorly drawn face, bad proportions, extra limbs, mutated hands, ugly, disfigured, tiling, out of frame, jpeg artifacts, signature, watermark, text, error, cropped badly, worst quality, low quality, cartoon, 3d render, plastic skin, doll-like, airbrushed skin, overexposed flash, harsh shadows, pale skin, heavy makeup overload, instagram face, duck lips, smiling happy expression, elderly, child, male, group shot, bright daylight, clean minimalist room, no curls, straight hair, desaturated colors, cold blue dominant tones, synthetic look, perfect symmetrical face, no grain, modern high-res filter, visible phone in frame, cluttered foreground, no halter-neck dress", "style_tags": [ "photorealistic", "moody low-light intimate portrait", "voluminous dark curly hair focus", "warm tungsten + cool moonlight mix", "raw sensual nighttime vibe", "cinematic warm grading", "film grain and light leaks", "dreamy sultry expression", "high fashion editorial meets candid", "deep plunge halter dress", "golden rim light on curls" ], "technical": { "aspe

Cyber Imperial Floating Palace City

Create a highly detailed vertical cinematic concept art scene of a lone {argument name="character role" default="ancient Chinese court official"} seen from behind, standing on a stone balcony at night and gazing over an immense futuristic megacity built from traditional East Asian palace architecture. The figure wears a dark red flowing robe and black official hat, framed in the lower left foreground beside a glowing square lantern and a carved stone guardian lion. The city is a vast layered maze of red palace walls, tiled pagoda roofs, bridges, towers, terraces, and suspended buildings, all interwoven with luminous blue holographic wireframe construction lines like an architectural blueprint overlay. Massive floating pagodas, cranes, scaffold-like towers, circular sky platforms, and elevated walkways fill the deep perspective, creating a surreal cyber-imperial capital that rises into a clear deep-blue evening sky. Use dramatic scale, dense architectural detail, cool blue ambient light with warm orange lantern accents, realistic painterly rendering, intricate linework, atmospheric depth, and a sense of awe and quiet contemplation. Style should combine {argument name="visual style" default="cyberpunk ancient Chinese architectural fantasy"}, ultra-detailed matte painting, cinematic lighting, sharp perspective, vertical 9:16 composition, no text, no logos.

Vogue Style Fashion Illustration

Turn this photo into a {argument name="style" default="Vogue-style"} {argument name="format" default="fashion illustration"}, preserving identity and facial features. Minimalist hand-drawn fashion sketch with elegant elongated proportions, bold black ink contours, loose confident linework, flat marker colors, abstract blush accents, graphic lips, stylized eyes, expressive ink hair, and simplified geometric clothing. Clean white background, scanned paper texture, modern luxury editorial fashion illustration.

Generating an Instagram Post based on Persona

インスタに投稿したpostを見せて。 <{argument name="ペルソナ情報" default="ペルソナ情報をコピペ"}>

Modern Japanese Graphic Design Poster Prompt

Modern Japanese graphic design poster of stylized water ripples, abstract water surface pattern, organic biomorphic shapes, flat design, vector art style. Monochromatic {argument name="color palette" default="blue"} color palette, {argument name="color 1" default="indigo"} and {argument name="color 2" default="azure"} and white, high contrast, clean hard edges, no gradients. Rhythmic flowing composition, screen print texture, minimalist aesthetic, typography elements in Japanese kanji. {argument name="style reference" default="Shinmura Suisan"} style, fresh and cool atmosphere

Doraemon Movie Scene Generation

のび太の魔界大冒険 VS{argument name="敵キャラクター" default="デマオン"}

172-color-grading-trick-using-nano-banana-pr

Change the color grading of this image to match this color palette

Business Office Manga Task Comic

manga style business office comic page · clean modern Japanese manga illustration with soft realistic anime rendering, polished linework, warm muted office colors, cinematic lighting, speech balloons with vertical Japanese text, subtle emotional storytelling, professional corporate atmosphere · single page comic with 4 horizontal panels stacked vertically · modern open-plan office meeting area with large windows overlooking a city skyline · late afternoon toward sunset · wood meeting table, 2 ceramic mugs, spiral notebook, black pen, sticky notes, desktop monitors, office chairs, potted plants · employee 1 · young Japanese office woman, brown hair tied in a low ponytail, beige blazer over a white blouse, small earrings · employee 2 · young Japanese office woman, long brown hair worn down, light blue blouse, dark skirt, small earrings · Panel 1 · top · 1 · two women seated across a table in conversation · Panel 2 · upper-middle · 1 · close-up of notebook showing this week's task list with priorities · Panel 3 · lower-middle · 1 · close-up reflective reaction shot of employee 2 · Panel 4 · bottom · 1 · rear view of both women standing before the glowing sunset window · top panel · medium two-shot at a meeting table in the office · 5 · steaming pink mug on the left, spiral notebook in employee 1's hands, blue mug near employee 2, office chairs, background windows and desks · 1 · 今週のタスク、整理しとこうか · second panel · close-up of an open spiral notebook on a wooden desk, viewed diagonally from above · 今週のタスク · 8 · ① 企画書の作成, ② データ集計・分析, ③ クライアント連絡, ④ 社内ミーティング準備, ⑤ 資料レビュー, ⑥ 経費精算, ⑦ メール返信対応, ⑧ 業務改善アイデア検討 · 優先度 · 8 · A, A, B, B, B, C, C, C · 3 · black pen, pink sticky note pad, multicolor sticky tabs · 1 · 優先度もちゃんと振ってあるよ · third panel · close-up profile of employee 2 looking thoughtful, office window blurred in background · 1 · このリスト、先週も見た気がする… · bottom panel · wide rear shot of both women standing side by side facing a large sunset over the city, notebook open on the table in foreground · 6 · open notebook on table, pink mug on left, blue mug on right, smartphone or planner beside the blue mug, potted plant on the left, city buildings outside the window · 2 · うん、来週こそ, 来週こそやろう · lightly humorous workplace procrastination, relatable business comic, bittersweet but hopeful ending · high detail, print-ready manga page, crisp panel borders, legible handwritten-style Japanese notebook text

Photorealistic Architectural Edit: Couple in Window

{ "generation_request": { "meta_data": { "tool": "NanoBanana Pro", "task_type": "photoreal_architecture_lifestyle_editorial_edit", "version": "v1.0_WINDOW_COUPLE_CLOSEUP_WINE_YELLOW_FACADE_FLOWERS", "priority": "highest" }, "references": { "reference_image_1": { "source": "UPLOAD_REFERENCE_IMAGE (REQUIRED)", "purpose": "BASE_ARCHITECTURE + PERSPECTIVE + WINDOW_PLACEMENT_LOCK", "strict_lock": true, "lock_strength": "high", "preserve_perspective": true, "preserve_building_geometry": true, "preserve_window_position": true, "preserve_overall_framing": true, "no_layout_drift": true } }, "output_settings": { "aspect_ratio": "match_reference", "orientation": "portrait", "resolution": "ultra_high_res", "render_style": "ultra_photoreal_editorial", "sharpness": "crisp_but_natural", "film_grain": "subtle_analog", "color_grade": "clean_filmic_warm", "retouch_level": "editorial_minimal_keep_texture", "noise_reduction": "low" }, "hard_constraints": [ "Photorealistic only (no illustration, no CGI).", "Keep the same building perspective and window placement as the reference.", "Do not warp architecture lines; keep straight edges and realistic proportions.", "Exactly TWO people in the window only; no extra people anywhere else.", "Remove any existing watermark/text from the reference; output must contain NO text, NO logos, NO watermarks.", "Hands and wine glasses must be anatomically correct and physically plausible." ], "creative_prompt": { "scene_summary": "Edit the reference photo of the European building facade (tall portrait). Keep the same perspective, window placement, and architectural geometry.\n\nKey edits:\n1) Building facade color: Change the main facade (currently blue) to a {argument name="facade color" default="warm, rich yellow painted plaster"}, realistic texture, slightly weathered, European old-town vibe.\n2) Window couple emphasis: Make the couple in the open window appear closer and more prominent (a subtle zoom/crop or optical framing adjustment that brings them forward), while still keeping the window in the same location on the building.\n3) Couple mood & props: The couple is happy and smiling, looking at each other with warm, joyful expressions. Each holds a wine glass (clear stemware) with red or white wine. Natural hand grip, correct reflections and refraction in glass.\n4) Flowers: Add tasteful flowers around the window area (e.g., a small window box or pots with blooming flowers such as {argument name="flower type" default="geraniums"}), and optionally subtle greenery climbing or placed nearby—must look natural and consistent with the architecture.\n\nLighting & realism:\n- Preserve the original time-of-day feel and ambient light; keep it realistic and soft.\n- Ensure natural skin tones and fabric textures; no plastic smoothing.\n- Maintain realist

Comparing Nano Banana Pro and 2 with a Profile Flyer Prompt

プロフィール欄の画像を添付して「{argument name="作成内容" default="このアカウントの人物をPRするためのチラシを作って"}」

Cinematic Low-Key Portrait in Red Rose Room

{ "generation_request": { "meta_data": { "task_type": "cinematic_lowkey_valentines_rose_…

Rebellious Party Portrait with Flash Photography

{ "image_prompt": { "subject": { "description": "Young woman with long, wavy red hair tied back loosely", "expression": "Playful and rebellious, sticking her tongue out and looking slightly off-camera to the side", "pose": "Standing facing the camera, raising both hands to show the middle finger gesture" }, "clothing_and_accessories": [ "White crop top with bold black text reading '{argument name="shirt text" default="ALL YOU CAN EAT"}'", "Black leather jacket worn open", "Classic blue denim jeans with a black belt", "Black platform shoes with silver chain detailing", "Silver cross necklace" ], "environment": { "setting": "Indoor house party", "background_elements": [ "Crowd of young adults standing and mingling in the background", "Wooden table filled with party food, pizza boxes, and red plastic cups", "Bright neon sign on the wall reading 'PARTY NIGHTS'" ] }, "lighting_and_atmosphere": { "lighting": "Direct flash photography aesthetic typical of a smartphone camera", "ambient_effects": "Colorful disco lights (red, blue, green) projected onto the white ceiling", "vibe": "Candid, energetic, casual, realistic party atmosphere" } } }

Ultra Realistic McLaren Supercar Portrait Prompt

{ "prompt_settings": { "style": "Ultra Realistic Photography", "quality": "8k UHD, HDR", "aspect_ratio": "16:9", "model_version": "v6.0 or latest" }, "structured_prompt": { "subject": { "description": "A stylish young woman sitting casually on the front hood of a dark grey McLaren 720S supercar.", "appearance": "Long straight dark hair, wearing dark sunglasses, confident expression.", "outfit": "Crisp white short-sleeve t-shirt, fitted black trousers, white sneakers." }, "vehicle": { "make_model": "{argument name="car model" default="McLaren 720S"}", "color": "Metallic gunmetal grey", "state": "Butterfly doors open upwards, sleek aerodynamic design, luxury sports car details, visible distinct headlights and front bumper." }, "environment": { "location": "Open paved waterfront promenade with light concrete tiling.", "background": "Distant modern city skyline across the water, hazy daylight atmosphere, Dubai-style architecture.", "lighting": "Natural bright sunlight, soft shadows, high dynamic range (HDR), golden hour warmth." }, "technical_specs": { "camera": "Shot on Sony A7R IV, 35mm lens, f/1.8 aperture for depth of field.", "visuals": "Hyper-realistic, 8k resolution, highly detailed textures, sharp focus, ray tracing reflections on car body, cinematic composition, volumetric lighting." } }, "full_combined_prompt": "Ultra realistic 8k UHD HDR photo of a woman sitting on the hood of a metallic grey McLaren 720S with butterfly doors open. She has long dark hair, sunglasses, white t-shirt, black pants, white sneakers. Background is a waterfront city skyline with modern architecture and paved ground. Bright natural lighting, cinematic shadows, highly detailed car reflections, raw photography style, masterpiece.", "negative_prompt": "cartoon, illustration, anime, drawing, painting, blurry, low resolution, pixelated, bad anatomy, distorted features, watermark, text, signature, bad hands, missing limbs, extra limbs, dull colors, noise, grain." }

Flash photography portrait of a woman in a blue mini-dress

"appearance": { "hair": { "color": "Dark", "length": "Long" "pose_and_action": { "orientation": "Looking over sky", "framing": "Full-body", "stance": "Standing"} "fashion_and_attire": { "item": "{argument name="dress item" default="mini-dress"}", "color": "{argument name="dress color" default="Blue"}", "fit": "very tight", "design_elements "accessories": { "jewelry": { "item": "Back-drop necklace", "material": "silver", "carry_items": { "item": "hand bag", "material": "Leather", "color": "Black" "scene_composition": { "environment": { "location_type": "Urban/Studio","background_elements": { }, "lighting_setup": { "technique": "Flash photography", "skin_interaction": "Soft glow", "shadows": "Slight shadow cast against background" }

Diagram Generation Template for Nano Banana Pro

------- ◼️内容：{argument name="内容" default="書きたい内容を入力"} ◼️キャラクター：{argu…

Portal Scene Generation Prompt

発光する楕円形のポータルが、{argument name="現実世界のシーン" default="伏見稲荷大社"} と {argument name="ポータル内のシーン" default="青いホログラムと屈折するネオンに照らされた、実写調・フォトリアルな未来都市のストリート。シネマティックな現実感を持つ。"} の間に存在している。 ポータルの外側には {argument name="現実世界のシーン" default="伏見稲荷大社"} が広がっており、リアルなテクスチャ、地に足のついた空気感、荒さや自然さを感じさせるトーンで描かれている。 ポータルの内側には {argument name="ポータル内のシーン" default="青いホログラムと屈折するネオンに照らされた、実写調・フォトリアルな未来都市のストリート。シネマティックな現実感を持つ。"} が存在し、完全にフォトリアルかつ実写調、シネマティックな表現で描かれている。 ユーザーが添付した参照画像の種類に関係なく、ポータル内の世界は常に実写・現実的な表現を維持する。 {argument name="ポータル内のキャラクター" default="ユーザーが添付した画像を完全に基準とし、そのメディア特性・表現形式・質感を一切変更しない。"} はポータルを通り抜けながら、観る者の手をやさしく引いている。 前へ進みつつも振り返り、少し物悲しそうな、控えめな表情でこちらを見つめている。 その視線には、わずかな悲しさ、ためらい、言葉にできない感情が静かに表れている。 キャラクターの外見、画風、質感、レンダリング方式、メディア特性は、ユーザーが添付した画像のテイストを完全に保持すること。 ・参照画像がイラストの場合、キャラクターはイラスト表現のままとする ・参照画像がアニメ調の場合、キャラクターはアニメ調のままとする ・参照画像が写真の場合、キャラクターは写真表現（フォトリアル）のままとする いかなる場合でも、キャラクターの表現スタイルを他の表現形式へ変換してはならない。 ポータルは神秘的な青紫色の光を放っている。 ポータルは二つの世界をつなぐ視覚的な境界として機能するが、キャラクター本来の表現テイストに影響を与えてはならない。 光や縁の処理は、キャラクターの元の描画・撮影スタイルを尊重した形でなじませる。 任意の全体ビジュアルスタイル: {argument name="アートスタイル" default="添付画像由来のキャラクター表現と、実写世界との意図的なコントラスト。"} カメラアングル: 三人称視点。 観る者の手が新しい世界へ引き込まれている様子が明確に見える構図。 ブラーなし。 キャラクターと環境は、それぞれの表現特性を保ったまま、シャープに描き分ける。 アスペクト比: 2:3。

Parkour Specialist Montage Sheet

editorial character concept montage / storyboard reference sheet · clean high-key studio photography mixed with urban concrete parkour action shots, matte white and light gray background, realistic full-body model composites, magazine layout, documentary sportswear catalog aesthetic, soft diffused lighting, minimal shadows, crisp cutout collage edges, muted monochrome palette · {argument name="specialist title" default="PARKOUR SPECIALIST"} · young adult female freerunner, face intentionally anonymized with a soft square blur, medium height, athletic slim build · {argument name="age" default="22"} · {argument name="height" default="165cm"} · oversized charcoal gray pullover hoodie with drawstrings, loose black cargo jogger pants with side straps, white athletic sneakers · {argument name="hair color and style" default="medium-length chestnut brown hair, loose and slightly tousled"} · square 1:1 poster, lots of white space, asymmetric montage with strict typography on the left and action poses sweeping diagonally across the page · {argument name="headline text" default="PARKOUR SPECIALIST"} · top-left · bold condensed uppercase sans serif, dark gray, two lines, thin horizontal rule underneath · PROFILE · upper-left below title · 6 · Age: 22, Height: 165cm, Occupation: Freerunner / Parkour Athlete, Affiliation: Independent · NOTES · bottom-left · 5 · Agile and observant, Quick thinking, Urban environment expert, Strong core and explosive power, Calm under pressure · 7 · front-facing standing neutral full-body pose · upper-left center · left side profile standing neutral full-body pose · upper-middle left · back view standing neutral full-body pose · upper-middle · low crouch on a concrete block with one knee bent and one arm lowered for balance · lower-left · large central dynamic crawl / landing pose, one hand near the floor, one knee tucked, body leaning forward · center · top-right wall vault pose, one hand planted on a concrete ledge, knees lifted sideways, body suspended above the wall · top-right · right-side balance run along a narrow concrete wall, arms extended like wings · mid-right · large cropped close foreground running or leaning action pose, face blurred, right arm extended out of frame · bottom-right · MOVE / ADAPT / OVERCOME · near upper-right action pose · small rough handwritten uppercase notes with short underlines · KEY MOVES · bottom center · 5 · PRECISION, SPEED, FLOW, CONTROL, BALANCE · five small black silhouette icons of parkour movements separated by thin vertical dividers · Create a non-linear montage that removes strict chronological order but preserves physical dynamism and spatial direction. Use concrete ledges as minimal environmental fragments, mainly on the right and lower-left. Keep all faces blurred/anonymized. Avoid bright colors; use charcoal, black, white, and pale concrete gray.

Seductive Oriental Fortune Teller

一位极美性感东方占卜师，25岁左右，魅惑却高级的气质，长直黑发微卷带光泽，穿着{argument name="服装颜色" default="深紫色"}低胸露肩奢华汉服，完美勾勒身材曲线，金色饰品点缀。优雅侧坐在古桌边缘，左手轻抚发光紫色水晶球，右手持紫微命盘，微微侧头眼神魅惑。背景是梦幻紫色星云与柔和霓虹光晕，戏剧性光影突出身材与脸部，电影级质感，超现实主义，8K，Cinematic lighting，高级妖娆氛围 --ar 16:9 --stylize 250 --v 6

81-midjourney-magnific-power-couple

Candid shot, hyper-realistic full-body portrait of a A sharply woman wearing an elegant red dress striding forward, front-facing. A giant Rhinosaurus walks beside her, at least four times taller than the her. The rhino's textured white skin is artistically cracked with depth and contrast. Intense editorial atmosphere. --ar 2:3 --profile veclfmo 3a492ds zrmykh6 --stylize 500 --v 7

Raw High-Contrast Mirror Selfie (iPhone Ultra-Wide)

(Vertical 9:16 smartphone aspect ratio). A raw, high-contrast [Candid Mirror Documentation] captured with an iPhone 17 Pro using the 0.5x ultra-wide-angle lens. NO ARTIFICIAL BOKEH. Every focal plane remains SHARP and in focus from the subject's skin to the distant wardrobe textures. Subject & Identity Locking: •Identity: Strictly preserve the exact face and unique features of the woman in Image 1 (Selfie). •Bio-Fidelity: Render high-fidelity "TrueLens" biological physics: visible micro-pores, a natural "satin-finish" night hydration glow, and fine vellus hair catching the light ONLY along the jawline. Her lower limbs show a healthy, smooth, and radiant surface texture. •Silhouette Calibration (MAXIMUM UFF-FACTOR): Prioritize a dominant structural upper-torso volume and substantial, thick-toned anatomical depth in the lower extremities. Focus on an aggressive architectural tapering at the midsection to maximize the S-curve geometry and fit, symmetrical proportions. Outfit & Textural Interaction: •Clothing: A high-density matte-black strapless compressed textile bodice paired with a high-tension {argument name="skirt pattern" default="leopard-print"} technical mini-skirt featuring an adjustable cinch-drawstring on the lateral thigh. •Tension: The technical fabrics exhibit extreme mechanical tension and a vacuum-tight fit, creating realistic textural expansion, skin-to-textile indentations, and "compression lines" where the materials contour to her fit silhouette. •Detail: A small minimalist architectural ink marking is visible on the interior aspect of the right wrist. Pose & Composition: •Pose: A straight-on frontal mirror composition. She is standing with a bilateral hip-pop and an arched spine to maximize the visual impact of her fit, symmetrical 3D volume and lower-body prominence. •Action: Her LEFT HAND holds a smartphone with a patterned protective casing, capturing the full-body "fit-check" reflection. Environment & Social Realism: •Lighting: Direct indoor illumination creating high-contrast specular highlights and deep, defining shadows that amplify her 3D form. •Background (SHARP): A detailed domestic interior showing uncurated realism. A white faux-fur rug on light wood-grain flooring, a beige wardrobe with vertical structural lines, and a minimalist white wall are all perfectly IN FOCUS. No artificial blur. Quality: Raw unedited social-media dump aesthetic, high dynamic range, visible digital grain in the deep shadows (ISO 800 style), 8k resolution. Everything is sharp, detailed, and physically real.

Tang Dynasty Aesthetic CG Illustration

{argument name="风格" default="国风CG插画"}，唐风美学，{argument name="人物设定" default="古代绝美女子"}，半身近景特写，画面重心聚焦面部与上半身，高级人像构图，电影级镜头语言与空间透视 人物设定： 东亚古典美人，冷白通透肌肤，细腻真实皮肤质感，柔润微光； 五官精致立体但自然不过度夸张，狭长凤眼，眼尾微挑，眼神含情带羞、微醺朦胧，长睫毛投下细微阴影； 唇色如胭脂晕染，微启唇，神态柔美而富有情绪张力，呈现“含蓄东方美” 造型设计： 粉色系华丽唐风服饰，轻柔贴合身体曲线，层次丰富但不过度堆叠； 适度低领设计，强调锁骨与颈肩线条，视觉引导自然不过分直白； 头戴精工凤冠（金属、珍珠、宝石、流苏），材质真实反光，随动作轻微摆动 动态与姿态： 身体微侧或轻旋转姿态，颈部延展，肩线舒展，手部形成柔性引导线，增强画面韵律与女性柔美张力 光影系统： 电影级布光 主光：暖金侧前方光聚焦面部与肌肤高光 辅光：冷色环境光塑造体积与空间 边缘光勾勒发丝与肩颈轮廓 高光控制不过曝，阴影保留细节，面部光影柔和过渡 画面风格： 超写实CG人像融合东方写意气韵，轻微朦胧美学 氛围与质感： 梦幻、含蓄、东方审美的高级氛围； 背景虚化，弱化环境强化人物； 轻微胶片颗粒+ 柔焦辉光，增强情绪与质感 色彩体系： 主色：胭脂粉、鎏金 辅色：冷青蓝灰 整体低饱和高质感，避免艳俗 镜头参数： 85mm portrait lens, f1.4–f2, shallow depth of field, cinematic framing 画质： ultra detailed, 8K–16K, extreme detail, high resolution, cinematic lighting 比例： {argument name="比例" default="9:16"}

Brand Concept Generation Prompt: Unexpected Functional Objects

{argument name="品牌名称" default="[品牌名称]"}： 一本高端、光泽的概念艺术杂志编辑摄影照片，展示由该品牌概念化和设计的一个独特、意想不到的功能性物体。 **1. 概念与物体（AI发明）：** 基于指定品牌的的设计哲学、传承和材料词汇，AI必须发明一种新型实用产品（非标准服装、鞋子或包袋）。示例可包括家居用品、科技配件、工具或运动装备，通过品牌的视角重新诠释。该物体应感觉雕塑般却实用功能性。 **2. 材料与细节（超高端）：** 物体采用品牌特色的高端、极具触感材料制成（例如，氧化异国皮革、拉丝航空级钛金属、雕塑般哑光陶瓷、模压碳纤维或技术高定纺织品）。每个细节都极度逼真：可见缝合、微观材料纹理、精密雕刻，以及复杂的纹理对比。 **3. 摄影与灯光（电影级工作室）：** 使用中画幅Phase One相机搭配100mm微距镜头拍摄。极浅景深，物体主角细节锐利聚焦，背景呈奶油般柔滑虚化。灯光为精致的工作室柔光箱照明：柔和环绕填充光，结合精确轮廓光以突出轮廓和材料纹理。 **4. 环境：** 无缝、无暇的纯净超浅色调工作室环形背景（例如，去饱和薄荷绿、浅粉红或微黄白），无阴影。 **5. 布局与UI元素（严格放置）：** - **右下角：** 品牌的小型、低调单色灰色标志。 - **左下角：** 小型、极简单色灰色文本，描述发明的產品。字体风格类似于Manrope Regular，极紧跟踪（字距）和平衡行距。示例格式："CONCEPT STUDY: [AI插入发明产品名称]。MATERIAL: [AI插入主要材料]。SS25。"

Mirror Selfie Prompt (Clean Girl Aesthetic)

{ "subject": { "gender": "Female", "hair": { "color": "Jet black", "style": "S…