Prompts de Imagem para Abstract Background

Create a clean demonstration image on a black canvas showing a white-framed four-pane window graphic with transparency effects. The main subject is a realistic front-facing window centered slightly left, with a thick glossy white frame, beveled edges, a horizontal and vertical crossbar dividing the glass into exactly 4 rectangular panes, and a small sill at the bottom. Behind and through the window is a gray checkerboard transparency pattern, and the glass panes should show the checkerboard faintly with about 50% alpha, plus subtle bluish tint, soft reflections, and two diagonal light streaks. Around the window, include a larger semi-transparent checkerboard rectangle with alternating dark gray squares on the black background to clearly indicate transparency. At the top right, add one rounded blue speech-bubble label containing the Japanese text {argument name="instruction text" default="窓枠と窓の画像、背景透過、窓の部分は50%のアルファ値とする"} in white sans-serif type. At the bottom left of the checkerboard area, add one small dark rounded button labeled 「編集」, and at the bottom right add one small circular dark button with a white upload/share arrow icon. Keep the composition minimal, with no extra objects, no watermark, and crisp UI-like presentation.

Goal: Create a clean screenshot-style chat interface showing an AI image generation result after a Japanese instruction. Canvas: Wide landscape canvas, about 1200×1000 px, with a very light gray-white background and lots of empty space on the right. The main generated image card sits left of center, with a user message bubble near the upper right. Text content: Include exactly 1 pale blue rounded message bubble in the upper right containing the Japanese text {argument name="instruction text" default="真正面直立にしてください。"}. Keep the text dark navy, simple sans-serif, centered vertically in the bubble. Main image card: Show exactly 1 large rounded white image card on the left, with soft corners and a subtle gray shadow. Inside it is a front-facing, full-body cartoon monster drawn like a cute sticker: a squat upright reptile/kaiju with a big rounded head, angry slanted eyes, thick black outlines, brown spotted skin, a yellow belly, short arms with black claws, chunky legs with black toenails, and a curved tail extending to the left. The creature faces straight forward in a rigid standing pose. It has a red forked tongue hanging from a jagged mouth, small nostril dots, and dark spots scattered over the head, arms, body, legs, and tail. Use a hand-drawn marker or watercolor texture with slightly uneven fills. Character colors: {argument name="body color" default="muddy brown"}, {argument name="belly color" default="warm yellow"}, {argument name="tongue color" default="red"}, with thick black outlines. Overlay controls: On the lower edge of the image card, include exactly 2 semi-transparent circular controls: a gray circle at bottom left labeled 「編集」 in white, and a gray circle at bottom right with a white upload/share arrow icon. A faint gray gradient appears along the bottom of the image card behind these controls. Bottom toolbar: Beneath the card, aligned left, include exactly 5 small gray outline icons in this order: copy/duplicate icon, thumbs-up icon, thumbs-down icon, share/upload icon, and horizontal ellipsis icon. Keep them minimal and unfilled. Style constraints: The whole scene should look like a cropped modern AI chat app screenshot, not a poster. Preserve the Japanese text exactly where specified. Do not add extra messages, captions, watermarks, borders, or additional characters.

Create a minimalist landscape social-media text card on a plain white background, approximately 1200×637 pixels. Use large black sans-serif typography similar to Arial/Helvetica, left aligned with generous margins, no borders, no icons, no watermark. The text block should occupy the upper-left and center area with wide line spacing and a clean screenshot-like look. Set the main quote in French using this exact content: {argument name="quote text" default="Le mot “complotiste” a souvent été utilisé non\npas pour juger la véracité d’une idée, mais pour\nempêcher sa diffusion et mettre fin à la\nrecherche intellectuelle.\nDans de nombreux cas historiques, si ce mot\nn’avait pas été utilisé, le débat aurait été plus\nouvert et la connaissance plus rapide."}. Use exactly 7 visible lines. Apply bold weight to exactly 5 emphasized text parts: “complotiste”, “empêcher sa diffusion et mettre fin à la”, “recherche intellectuelle.”, “le débat aurait été plus”, and “ouvert et la connaissance plus rapide.” Keep all other words regular weight. Use crisp high-contrast black text, with no additional decoration.

以一个明确主题为叙事核心，构成一幅摄影与平面构成相互穿透的编辑视觉作品：用一组真实、可触的主题物件或场景作为情绪锚点，保持自然光下的体积、反射、遮挡与微妙的不对称，让它们像被安置在一个安静的展示现场；再以两到三块具有强烈方向性的纯色几何面切入画面，几何面可以折叠、遮蔽、延伸并越过主体边界，像透明建筑、舞台框架或被拆开的版面，使前景、中景、背景被重新分层，同时留下大块深色或低信息量的呼吸空间。主题的关键轮廓、符号或动作从摄影区域抽象出来，在几何面之间形成一次清晰的视觉事件，保留少量细节让真实感与概念感并存。以一支承担最大视觉重量的窄长字形、标志性字标或主题文字作为结构梁，让文字拥有雕塑般的高度、连续的线条和克制的留白；其余信息以较小、规整、疏朗的编辑文字分布在边缘或空白处，形成主标题、辅助说明与时间地点等不同声部，文字方向可顺应几何切面的轴线，中文、英文或其他书写系统都保持字形个性与信息层级。让主色从主题本身、场景光线或文化意象中提取：一种深沉的结构色稳定背景与阴影，一种明亮的开启色撑起几何面，一种高辨识度的焦点色只落在主题事件或少量文字上，整体以清晰的明暗分区和有限的饱和度控制阅读顺序。表面呈现真实摄影的玻璃、陶瓷、金属、织物或纸张质感，几何面保持干净而有厚度的边缘，交界处用透明度、投影和色彩叠合建立空间，背景保留可辨认但不喧闹的环境线索；最终让信息、物件、色块和空白像同一座临时建筑，产生冷静、神秘、带有展陈仪式感的观看体验。 主题：{argument name="主题" default="International Conference on English and American Studies"} 用途：{argument name="用途" default="宣传海报"} 文本：{argument name="语言" default="英语"} 比例9:16

请将我上传的每一张照片分别制作成一张独立的高级设计海报，不多图拼接，每张照片单独输出。整体采用3:4竖版构图，上下两个区域高度严格1:1，各占画面50%。 上半部分保留原始照片，保持主体身份、结构、姿态、真实质感、自然光影和原有色彩氛围，仅进行轻微高级调色，使其具有艺术杂志、独立出版物与展览图像质感。为适配画幅，可自然扩展环境背景，但不得拉伸、扭曲或改变主体。 下半部分先理解原照片最值得被记住的**核心主题、主体关系、结构走势、情绪气氛与视觉记忆点**，再重构为**留白型数字混合媒介拼贴插页**。不要逐物复制照片，也不要把画面铺满，而是删去无关细节，只保留最能代表原物的结构、走势与视觉线索，通过照片片段、细黑线线稿、手写式标注、纸感元素与少量拼贴形状重新概括，使人能够一眼识别它与上方照片之间的对应关系。 构图采用**小画幅居中 + 四周大量留白**的逻辑。真正的视觉主体被控制在下半部分中央的一小块区域，可像杂志插页、手账内页或 collage card 一样，被安放在干净宽阔的背景之中。主体不必完整展开，可适度裁切、压缩或组合，周围仅保留极少量辅助线稿、纸片、箭头、符号或小字注记，与主体形成松弛而克制的编辑关系。留白不是空背景，而是与主体共同构成呼吸感、空间感和节奏感的重要部分。 画面语言采用**数字混合媒介拼贴**：可结合少量照片感局部、简洁黑色细线涂鸦、手写笔迹、纸片拼贴痕迹、轻微胶带感或便笺感元素，但整体必须克制、轻盈、安静，不做厚重手工堆叠，不做复杂装饰。主体保持清晰，辅助元素只起到强调主题、补充记忆 and 优化版式的作用，不形成新的视觉中心。 配色以**{argument name="色调" default="低饱和浅蓝与白色"}为主的轻空气感色系**为基础，并根据上方照片进行微调。整体以浅蓝、雾蓝、粉蓝、白色或米白作为大面积背景与承载区，辅以黑色细线建立结构，少量深蓝增强节奏，并允许一点浅黄、淡金或极少暖色作为点睛。颜色整体冷静、轻盈、治愈、干净，像柔和天空与纸面的关系，避免高饱和、杂乱跳色、灰脏、暗沉和过度复古。 文字少量介入，不限制语种。可根据主体、地点、动作、情绪或记忆自由提炼少量字词、短句或注记，采用**细小、克制、松弛、略带手写感或编辑感的文字样式**，自然分布在主体周围或留白边缘，像杂志插页中的轻注释，而不是商业标题。 整体呈现**小画幅主体、大面积艺术留白、浅蓝白主调、照片与线稿结合、纸感拼贴、轻盈松弛的编辑插页感**，参考 minimal mixed-media collage / whitespace scrapbook layout / centered editorial collage / airy zine-inspired layout。避免满版拼贴、复杂背景、装饰堆积、商业模板感、廉价手账感和逐物转绘。

Mine pulses red beneath a {argument name="shell color" default="black shell"}. {argument name="model id" default="JFC-01"}｜{argument name="name" default="VOID FANG"}

Goal: Create a clean social-media screenshot of an AI image generation interface showing a completed anime music-video storyboard request and its 3x3 output grid. Canvas: Horizontal screenshot, approximately 1200x884 px, white/light-gray background with lots of empty margin. Use a modern minimal web-app UI style with rounded cards, soft shadows, and gray system text. Top area: Near the upper center, show one rectangular reference image preview with a subtle shadow. The preview contains an anime character: a short-haired androgynous young person with {argument name="hair color" default="dark ash-brown bob haircut with straight bangs"}, pale skin, thin round glasses, one eye closed in a wink, one blue visible eye, wearing a white high-collar ceremonial robe with necklaces and a red tassel. Behind them is a dark fantasy cathedral city with a glowing golden circular arch and a blue vortex moon-like sky. Prompt bubble: Below the preview, place a wide black rounded speech bubble with white Japanese text, reading exactly {argument name="prompt text" default="このキャラクターのボカロmvの様々なカットを3x3で出力して 16:9　トンマナ合わせて"}. The bubble should span most of the center width and have large rounded corners. Status text: Under the bubble, aligned left above the output grid, add gray text reading {argument name="status text" default="Worked for 1m 7s"}. Output grid: Show exactly 9 cinematic panels arranged in a 3 columns by 3 rows grid, inside one large rounded rectangle with clipped rounded corners. Each panel is 16:9, separated by thin white grid lines, all sharing the same tone: dark blue, black, white, and warm gold, glossy anime/Vocaloid MV aesthetic, dramatic lighting, cathedral ruins, floating feathers or sparkles, wet reflective floor, glowing golden ring, blue vortex sky. The 9 panels are: 1. Top-left: frontal bust shot of the character under the glowing golden arch, calm expression, glasses, white robe. 2. Top-center: side-profile close-up with hair blowing, eyes closed, blue lights in the dark cathedral background. 3. Top-right: dynamic three-quarter shot, character extending a white sleeve toward the viewer, golden arch and blue vortex behind. 4. Middle-left: low-angle wide shot, character leaning or reaching forward with billowing white sleeves, cathedral towers around them. 5. Middle-center: full-body centered shot standing on a reflective wet floor, framed by a tall archway and distant glowing ring. 6. Middle-right: close shot of character reaching a hand toward the camera, one eye closed, foreshortened hand in foreground. 7. Bottom-left: rear wide shot of the character walking into the cathedral environment beneath the glowing arch. 8. Bottom-center: emotional close-up, character with eyes closed and hands near mouth or chest, surrounded by blue sparkles. 9. Bottom-right: very wide establishing shot of ruined gothic towers, glowing circular arch, blue vortex sky, tiny figure or distant character. Overlay controls: Add exactly 3 circular interface controls over the lower part of the grid: a dark circular button at bottom-left labeled {argument name="edit button text" default="編集"}, a light gray circular download button with a downward arrow near the lower center-right, and a dark circular share button with an upward arrow at bottom-right. Style constraints: The whole image should look like a real captured web UI, not a poster. Keep the interface text crisp, the grid slightly cropped by the bottom edge of the screenshot, and the anime panels high-detail, cinematic, consistent in character design and color grading.

Create a vertical surreal fantasy photorealistic image of a large transparent crystal hourglass floating against a deep star-filled cosmic background. Inside the hourglass are exactly two miniature ocean beach worlds: the upper bulb contains a bright daytime tropical beach with golden sand, turquoise waves, rocky green cliffs on the left, distant blue islands on the horizon, towering white cumulus clouds on the right, and exactly one blazing sun near the upper left; the lower bulb contains the same beach at night with dark blue water, moonlit waves, shadowy islands, dramatic clouds, and exactly one full moon centered above the horizon. A narrow waist in the glass connects the two scenes, with exactly one continuous stream of sparkling golden sand and stardust falling from the sunny upper beach into the moonlit lower beach, forming a glowing pile at the bottom. The hourglass glass should be thick, glossy, highly refractive, and rimmed with bright highlights and caustic reflections. Make the composition symmetrical and centered, with the upper scene feeling warm and radiant and the lower scene feeling cool, nocturnal, and magical. Use ultra-detailed cinematic realism, high dynamic range lighting, luminous ocean reflections, glittering sand particles, sharp focus, rich blues and golds, and a dreamlike contrast between day and night. Customize the setting as {argument name="beach location" default="tropical island beach"}, the upper sky as {argument name="daytime sky" default="bright blue sky with towering white clouds"}, the lower sky as {argument name="night sky" default="deep starry sky with a full moon"}, the sand effect as {argument name="falling sand effect" default="sparkling golden sand and stardust"}, and the overall mood as {argument name="overall mood" default="surreal magical cinematic realism"}.

Create a photorealistic mixed-media street-fashion collage portrait of {argument name="character description" default="a confident young woman with long wavy dark brown hair, warm tan skin, gold hoop earrings, and a soft closed-mouth smile"}. Frame her in a medium close-up from mid-thigh to above the head, shot from a slightly low angle as she faces the camera with relaxed confidence, one hand in the pocket of light blue high-waisted jeans. She wears {argument name="outfit" default="an oversized plain white T-shirt tucked loosely into light blue denim jeans"}. Place her on a sunny New York-style city street with tall buildings on both sides, black metal fire escapes, a distant glass skyscraper centered behind her, bright blue sky, strong daylight, and a shallow depth-of-field urban background. Use a vertical {argument name="aspect ratio" default="9:16"} canvas with vibrant editorial energy. Add a handmade collage overlay: cut-paper torn edges in the corners, textured scraps of white, teal, hot pink, and yellow paper, rough black marker doodles, and thick brushstroke graphics. Include exactly 8 visible graphic elements: 1 large hot-pink looped brushstroke sweeping across the upper left, 1 hot-pink curved brushstroke loop at the lower right, 1 neon outline tracing the woman’s silhouette in alternating hot pink and turquoise, 3 short turquoise emphasis strokes near the right side of her head, 3 short hot-pink emphasis strokes near her left hair/shoulder, 1 small black heart doodle on the left, 1 black star doodle on the lower-left paper scrap, and 1 black scribble mark on the upper-right paper scrap. Keep the photo realistic under the collage marks, with natural skin texture, realistic fabric folds, sunlit hair highlights, and crisp magazine-cover composition. Avoid text, logos, watermarks, extra people, distorted anatomy, or over-smoothed skin.

把上传图片重构成一张独立的 {argument name="画幅" default="3:4 竖版"}复古胶片档案海报，不是教程卡片，不是普通拼贴。 保留原图里的核心主体、空间关系、真实光线和物件结构。如果原图是桌面、笔记、产品草稿、电脑屏幕或工作区，请保留它们作为“创业现场”的真实证据，不要随意替换成豪华办公室或商业大片。 整体视觉像一份 {argument name="时代风格" default="90 年代到 2000 年代早期"}的私人项目胶片档案：主画面是一张真实照片，边缘叠加 35mm 胶片条、接触印相、拍立得碎片、旧纸文件夹、透明胶带和轻微漏光。画面可以有小的日期戳、编号、手写痕迹和元数据块，但必须全部不可读，只保留档案气息。 构图要有“被保存下来的瞬间”感：{argument name="主图占比" default="主照片占 60%-75%"}，旁边或底部放 2-4 个小胶片切片，切片内容可以是原图中局部细节的再解释，比如咖啡杯、便签、笔记、草图、屏幕光、窗边光影。不要把元素铺满，保留呼吸感。 色彩使用胶片质感：暖琥珀、褪色奶油纸、橄榄灰、炭黑、少量暗红漏光、低饱和青色阴影。颗粒要真实，划痕和灰尘要克制，不要脏到影响主体。 如果原图里有人，只保留姿态和工作氛围，不要强化脸部，不要变成肖像大片。如果原图里有屏幕或笔记，内容必须模糊或抽象，不出现可读文字、品牌、Logo 或真实界面。 最终效果：真实创业现场 + 复古胶片 + 私人档案 + 项目诞生前夜 + 高级叙事感。 避免：商业广告、赛博霓虹、儿童手账、过度怀旧滤镜、密集文字、可读品牌、可读界面、过分凌乱、廉价复古模板、AI 感很重的假胶片边框。

Create a premium editorial art poster for every uploaded photograph, treating each image as its own independent composition and never merging multiple photos together. Use a strict 3:4 vertical format with the canvas split into two perfectly equal horizontal halves: the upper half should remain a faithful, photorealistic presentation of the original image, preserving the subject’s exact identity, facial features, proportions, pose, clothing, objects, composition, lighting, shadows, mood, and natural colors, enhanced only with sophisticated editorial color grading and seamless environmental extension where necessary; the lower half should transform the visual story into an entirely different artistic interpretation—a tiny, carefully composed handmade mixed-media artwork centered within expansive warm {argument name="background hue" default="ivory"} negative space, occupying no more than 10–20% of the lower section, using expressive ink sketching, layered gouache-like color fields, subtle collage textures, torn-paper edges, imperfect brushwork, visible fibers, soft pigment variations, and charming human imperfections while retaining the most recognizable silhouette, gesture, objects, and emotional narrative from the original photo. Extract up to four dominant harmonious colors from each photograph and reinterpret them in a muted, sophisticated palette. Add only occasional understated editorial typography when it genuinely enhances the composition, such as a poetic title, place, date, or single word. The overall result should feel like a collectible contemporary art publication cover—minimal, poetic, tactile, elegant, emotionally quiet, visually distinctive, and unmistakably connected to its original photograph.

Create ONE independent high-end editorial poster for EACH uploaded photo. Never combine photos. Each photo must become a separate poster.\n\nFORMAT\nStrict 3:4 vertical. Divide the canvas into two exactly equal 50% horizontal sections.\n\nTOP 50% — ORIGINAL PHOTO\nPreserve the photo faithfully: identity, face, body proportions, pose, clothing, objects, composition, lighting, shadows, atmosphere, and colors. Keep it photorealistic with subtle premium editorial color grading. Seamlessly extend the background if needed; never distort or alter the subject.\n\nBOTTOM 50% — MINIMAL ILLUSTRATION\nReinterpret the most recognizable elements as a small, centered, hand-drawn paper illustration occupying only 10–20% of the bottom half. Preserve the key subject, silhouette, pose, objects, and narrative.\n\nUse delicate imperfect lines, bold flat acrylic-style shapes, rough paper grain, handmade brush marks, and organic edges. Keep the background warm white/off-white with generous negative space.\n\nCOLOR\nExtract dominant colors from the original photo and reduce them to a maximum of 4 restrained, harmonious colors.\n\nTYPOGRAPHY\nOptional minimal editorial text such as a short title, location, year, or keyword. Do not force text if unnecessary.\n\nSTYLE\nQuiet, poetic, refined, minimal, innocent, artistic, thoughtful, premium, and highly recognizable — like a contemporary art book or independent editorial cover.

画像の上に手描き風のオーバーレイを加えて。仕上がりは、おしゃれで、肩の力が抜けた、さりげなくカジュアルな雰囲気にして。描画ルール：ペンで描いたような白色の手描き線を使う。ラフで少しいびつな、一筆書き風のスタイルを保つ。対象物の外側の輪郭をなぞる線を加える。矢印や点線で視線を誘導する。文字ルール：{argument name="文字スタイル" default="手書き文字"}にする。短く、つぶやく感じの心の声のように。トーンは{argument name="トーン" default="日記風"}で、簡潔、感情重視。コメントは{argument name="コメント" default="前向きでやさしく"}。装飾：湯気、きらきら、ハート、小さな顔文字っぽい顔を控えめに加える。やりすぎず、「余白」も残す。

Using the provided reference image as a loose layout reference, replace the prompt-library interface with a clean 3-column by 3-row gallery of exactly 9 vertical retro graphic posters. Remove all website UI elements, author names, buttons, borders, Korean interface text, and card metadata. Keep only the idea of a tiled poster grid with narrow gutters on an off-white background. Style: Bold 1960s–1970s modernist poster design, flat vector shapes, cream paper backgrounds, high-contrast black typography, saturated primary colors, simple geometric compositions, minimal texture, crisp print-poster look. Create exactly 9 posters, arranged left to right, top to bottom: 1. Poster text: “Travel Farther” — radiating perspective road/fields leading to a yellow sun. 2. Poster text: “CREATE” — large rounded blue psychedelic type above flowing wavy color bands. 3. Poster text: “GROW TOGETHER” — abstract flower with orange sun/circle and layered leaves. 4. Poster text: “LISTEN MORE” — overlapping side-profile silhouettes in black, blue, orange, and cream. 5. Poster text: “FIND YOUR BALANCE” — stacked semicircles and circles in yellow, pink, blue, black, and orange. 6. Poster text: “DRINK MORE WATER” — oversized white block type on a solid blue field with a small orange circle. 7. Poster text: “LEARN SOMETHING NEW” — geometric staircase entering an archway. 8. Poster text: “SEE THE BEAUTY” — halftone illustrated eye over transparent colored circles. 9. Poster text: “CHOOSE KINDNESS” — abstract geometric collage with a pink heart and colorful blocks. Typography: Use bold condensed sans-serif headline lettering; make the text large, readable, and integrated into each poster. Use the headline set {argument name="poster message theme" default="uplifting lifestyle reminders"} while preserving the exact 9-poster count and grid structure. Use a palette based on {argument name="color palette" default="cream, black, yellow, orange-red, cobalt blue, forest green, and pink"}. Overall composition should feel like {argument name="poster era" default="1970s modernist motivational print posters"}.

Goal: Create a screenshot-like image of a dark sketch/drawing mode interface showing a deliberately crude digital doodle being edited, as if in an image-generation app's sketch tool. Canvas: Square-ish 4:3 screenshot, dark charcoal drawing panel centered with rounded corners over a dimmed gallery/app background barely visible at the right and bottom edges. Layout: The main drawing area fills most of the frame. A top toolbar floats near the upper center, with a close X at top left and undo/redo icons at top right. A vertical brush-size slider sits on the left side with one white circular handle. A horizontal color palette runs along the bottom. A green circular checkmark confirmation button sits at the bottom right. Main sketch: Draw a rough white line-art monster resembling a hunched fantasy boss creature, made with thick uneven brush strokes. It has one long pointed beak or snout facing left, a jagged open mouth, one scribbled oval eye near the top, a high arched back, a bulky torso, bent legs, and a long curved tail on the right. Add a small teal flower-like doodle on a stem at the lower left, facing the monster. Add an orange sketch of a sun or diagonal branch-like rays in the upper right corner. Interface details: Include exactly 6 visible top toolbar icons: pointer/selection arrow, squiggle brush icon, letter T text tool, overlapping shapes/copy icon, eraser/diamond icon, and the surrounding rounded toolbar container. Include exactly 2 top-right history icons: undo and redo. Include exactly 1 close X icon at top left. Include exactly 1 vertical slider with 1 white knob. Include exactly 16 bottom color swatches, from left to right: multicolor rainbow circle, white, gray, brown, red, orange, yellow-orange selected with a blue ring, green, teal-green, cyan, blue, indigo, violet, purple, pink, plus exactly 1 green confirmation check button at the far right. Visual style: Rough hand-drawn sketch mode, thick uneven strokes, dark UI, playful messy drawing, casual screenshot aesthetic. Use {argument name="creature outline color" default="white"}, {argument name="flower color" default="teal"}, {argument name="sun sketch color" default="orange"}, and {argument name="background panel color" default="dark charcoal"}. No polished rendering; keep it intentionally sloppy and simple.

Premium editorial poster for every uploaded photo never combine images. Use a strict {argument name="layout" default="3:4 vertical layout"} split into two equal horizontal halves. Keep the top half as a faithful photorealistic version of the original image, preserving the subject’s identity, pose, clothing, composition, lighting, colors, and atmosphere with only subtle high-end editorial grading. Transform the bottom half into a warm off-white minimalist art space featuring a small centered {argument name="art style" default="handmade paper-style illustration"} inspired by the main subject and key elements of the photo. Use imperfect sketch lines, flat acrylic-like shapes, visible paper texture, rough brush marks, and organic edges. Keep plenty of negative space and limit the palette to four harmonious colors sampled from the original image. Optional minimal editorial text may be added if it naturally fits. The overall result should feel quiet, poetic, artistic, refined, and like a premium contemporary art-book cover.

Create a serene futuristic biophilic interior lounge in a warm neutral palette, inside a {argument name="building type" default="large dome-like atrium"} with an overhead geometric glass-and-wood lattice roof made of triangular facets. Use a high-angle wide architectural photography view looking down into a circular sunken seating area. The space has smooth flowing organic architecture: pale plaster curved walls, light oak vertical wood paneling, rounded ramps and layered circular retaining walls, with one prominent terracotta-colored curved wall wrapping the front right edge. At the center is a circular conversation pit with exactly 3 cream curved sectional sofas arranged around the circle, exactly 2 round cream ottoman coffee tables, exactly 1 small round side table, and exactly 4 visible accent pillows in muted peach, beige, olive, and tan. Surround the lounge with lush green moss beds and ferns in exactly 4 planted zones: a large left garden bed, a narrow rear moss bed, a small raised rear planter, and a front-right curved planter. Make the atmosphere calm, cozy, luxurious, and nature-integrated, with soft diffuse daylight from the skylight, no people, no text, no clutter, photorealistic rendering, smooth tactile materials, gentle shadows, architectural digest style, ultra-wide composition, {argument name="main material" default="light oak wood and warm plaster"}, {argument name="accent color" default="soft terracotta"}, {argument name="mood" default="calming sanctuary"}.

【イベント情報】 ・イベント名: {argument name="イベント名" default="余白と構造"} ・開催日時: {argument name="日時" default="2026年10月12日〜11月24日"} ・会場: {argument name="会場" default="国立現代美術館"} 【画質・演出・構図指定】 ・スタイル: 現代美術展や現代デザインイベントのポスター、クリーンでミニマルなエディトリアルレイアウト。 ・ビジュアル要素: 幾何学的で抽象的なアートオブジェ、またはコンクリートやガラスの建築空間を背景にした、静寂と知性を感じさせる美しい実写構成。 ・タイポグラフィの配置（GPT-image / Nano Banana Pro向け）: 画面の余白部分に、{argument name="イベント名" default="余白と構造"}というイベント名、{argument name="日時" default="2026年10月12日〜11月24日"}という日付、{argument name="会場" default="国立現代美術館"}という会場情報が、洗練されたモダンなサンセリフフォントで美しくレイアウトされている。文字が画像全体の美しさを損なわず、調和している。 ・照明・色彩: 白を基調としたクリーンな空間、冷たい自然光とソフトな光のグラデーション、ニュートラルなトーンにアクセントカラー（例：ネイビーやダークグレー）。 【レイアウトおよび出力上の厳格な制約（必須）】 ・完成したデザインそのものを, 画面全体いっぱいに出力してください。デザイン内部の背景やシーン描写（壁・空間・影など）は本文の指示に従って構いません。 ・禁止事項：完成ポスターを額縁に入れた写真、壁に貼った状態の写真、机や紙の上に置いたモックアップ写真、紙の縁の遠近の歪みやドロップシャドウ。 ・Output the finished flat 2D design itself, filling the entire canvas. Scene elements inside the design (walls, rooms, shadows) described above are allowed. Absolutely NO photo-of-a-poster mockups: no picture frames, no poster-on-wall or poster-on-desk shots, no perspective warp or drop shadow around the artwork's edges. ・アスペクト比: --ar 3:4

基于我上传的图片，设计一套 3D 表情包 1:1 透明贴纸页，包含 9 个各不相同的贴纸，按 3X3 网格排列每个贴纸呈现不同的表情、姿势或反应。贴纸之间留出较宽且完全透明的间隔。无背景、阴影或重叠元素，融入{argument name="表情符号" default="🚀🎉🥳🤟"}

Using the provided reference image as the base landing page, keep the existing softmaple logo, top-right theme/menu buttons, left-side badge, headline, paragraph, and the two call-to-action buttons in the same clean minimal style and approximate positions. Expand the composition into a richer hero section by adding a large collaborative writing visual on the right half of the page. Additions: Create an elegant floating 3D paper-and-ideas collage on the right: a translucent glossy golden ribbon spiraling vertically through the composition, with warm light, soft shadows, and a thin golden orbit line with small dot nodes. Include exactly 5 floating paper/photo elements: 1 handwritten note reading “Ideas feel brighter together.”, 1 black-and-white mountain photo card with small vertical text beside it reading “A CALMER BRIGHTER PLACE TO THINK TOGETHER,”, 1 central text page reading “Same thoughts. Further together.”, 1 warm photo card with leaf shadows and small text reading “SMALL STEPS BIGGER IDEAS”, and 1 subtle small taped paper fragment behind the center cards. Add exactly 3 collaborator avatars with name pills: “Mina” near the upper right, “Jordan” near the center-left of the collage, and “Taylor” near the lower right; each should have a small cursor pointer accent. Add two subtle handwritten editorial details in the empty lower area: bottom-left script reading “Better thinking together.” and a tiny stacked word list near the lower center reading “IDEAS / PEOPLE / PERSPECTIVES / PROGRESS”. Add a soft golden glass sphere near the right side of the collage. Keep the background off-white, airy, premium, and editorial, with realistic depth but no clutter. Customization slots: brand text {argument name="brand text" default="softmaple."}, main headline {argument name="main headline" default="A little space. For big ideas."}, primary button text {argument name="primary button text" default="Start writing"}, collaborator names {argument name="collaborator names" default="Mina, Jordan, Taylor"}, note text {argument name="note text" default="Ideas feel brighter together."}.

gritty {argument name="style" default="horror-punk"} collage in newsprint, torn paper, xerox grain, and {argument name="color" default="blood-red"} paint.

【ポスター情報】 ・メインタイトル: {argument name="メインタイトル" default="創作する夜。"} ・イベント/ZINEテーマ: {argument name="テーマ" default="ライブ＆DJ ZINE & ART"} ・日付やその他の情報: {argument name="日付" default="2026.11.15"} 【画質・演出・構図指定】 ・スタイル: アナログな質感、DIYカルチャー、パンクZINEやインディーズレーベルのポスターのアートスタイル。 ・視覚効果: 手ちぎりの紙、新聞の切り抜き、モノクロ半ハーフトーン（網点）の写真、手書きの落書き、スプレーアートなどがコラージュされた重層的なグラフィックデザイン。 ・色調: モノクロを基調としつつ、ネオンピンク、アシッドイエロー、蛍光グリーンなどの差し色が1〜2色入った、コントラストの強い配色。 ・タイポグラフィの配置（GPT-image / Nano Banana Pro向け）: {argument name="メインタイトル" default="創作する夜。"}という文字がラフで歪んだ手書きフォントやステンシルで中央に力強く配置され、{argument name="テーマ" default="ライブ＆DJ ZINE & ART"}や{argument name="日付" default="2026.11.15"}の文字が端にコラージュの一部として貼り付けられている。 【レイアウトおよび出力上の厳格な制約（必須）】 ・完成したデザインそのものを、画面全体いっぱいに出力してください。デザイン内部の背景やシーン描写（壁・空間・影など）は本文の指示に従って構いません。 ・禁止事項：完成ポスターを額縁に入れた写真、壁に貼った状態の写真、机や紙の上に置いたモックアップ写真、紙の縁の遠近の歪みやドロップシャドウ。 ・Output the finished flat 2D design itself, filling the entire canvas. Scene elements inside the design (walls, rooms, shadows) described above are allowed. Absolutely NO photo-of-a-poster mockups: no picture frames, no poster-on-wall or poster-on-desk shots, no perspective warp or drop shadow around the artwork's edges. ・アスペクト比: --ar 3:4

Create a highly detailed fantasy anime portrait of a melancholic ethereal young man, {argument name="character gender" default="androgynous young man"}, centered waist-up in dark reflective water at night. He has pale porcelain skin, delicate features, soft sad blue-gray eyes, slightly parted lips, and messy windblown {argument name="hair color" default="icy blue"} hair with long wisps crossing his face. He wears a dark oversized hooded coat over a loose white shirt, the fabric wet and glossy. His two slender hands cup a radiant glowing orb at the center of his chest, emitting white moonlike light, tiny sparks, and magical reflections on his fingers, neck, shirt, and the water surface. Behind him, form a huge swirling vortex of ocean waves and clouds shaped like a luminous spiral moon halo, deep navy and cobalt with bright foamy highlights, as if the sea and night sky are rotating together. Add a star-filled cosmic background with exactly 6 visible black bird silhouettes flying around the vortex: two on the left side, three on the right side, and one small bird near the upper center-right. In the foreground water, place exactly 3 glowing lotus flowers: one large pale blue lotus at lower right, one medium lotus at lower left edge, and one small lotus near the lower center-left, all translucent with soft pink-blue inner light and sparkling dew. Scatter many pale flower petals drifting through the air and floating on the water, but keep them secondary. Mood: {argument name="mood" default="ghostly moonlit melancholy"}, dreamlike, mystical, serene, slightly tragic. Visual style: ultra-detailed Japanese anime illustration, painterly digital art, luminous rim lighting, deep blue monochrome palette with silver-white highlights, soft bloom, intricate water reflections, high contrast, cinematic composition, vertical 4:5 aspect ratio. No text, no watermark, no frame, no extra characters.

This poster illustration, created using the attached subject, adheres entirely to the aesthetic of modern cinematic concept art. It features a highly dynamic composition, a dramatic low-angle perspective, detailed and realistic clothing rendering, and a weathered texture achieved through semi-realistic, layered brushstrokes combined with sharp, ink-like contours. The illustration employs a limited earthy color palette dominated by {argument name="primary colors" default="warm burnt orange, deep navy blue, soft cream"}, sepia brown, charcoal black, and faded steel gray. The background incorporates abstract geometric blocks, distressed poster textures, rough paper grain, ink stains, paint splatters, and partially erased graphic elements. Key features include high-contrast lighting, moody shadows, subtle vintage print effects, a textured matte finish, and a highly detailed editorial poster 9:16!