Upscaling to 4K Prompt for Clear Chinese Text

Classical Chinese poem illustration with text (duplicate)

根据以下古诗画一幅画，并附上原文。 汉皇重色思倾国，御宇多年求不得。杨家有女初长成，养在深闺人未识。天生丽质难自弃，一朝选在君王侧。回眸一笑百媚生，六宫粉黛无颜色。 春寒赐浴华清池，温泉水滑洗凝脂。侍…

Seedance - Cocktail Vlog (johnAGI)

风格: 高级商业氛围短片, 高清手机前置镜头质感, 电影写实色彩, 面部柔光打光, 单人出镜. 时长: 15秒. 场景: 卧室+调酒区一体空间，温馨台灯与紫黄霓虹氛围光交织, 微醺暖调. 角色: 顶级亚洲明艳神颜, 穿深蓝蕾丝吊带裙、长卷发, 全程形象高度一致. 00:00-00:03: POV慵懒起床, 主观视角俯视床上双腿, 手伸入画面掀开被子, 双腿落地起身, 丝滑转场至中景女主站床边, 慵懒霸道地说: 睡什么睡, 起来喝酒. 00:03-00:06: 优雅倒酒, 中景切至调酒区, 背景台灯暖光与紫黄霓虹, 女主拿白酒瓶倒酒入银色量酒器再加橙汁. 00:06-00:09: 挤柠檬特写, 双手对挤青柠, 柠檬汁滴落调酒壶, 抓冰块丢入壶中. 00:09-00:12: 摇酒近景, 女主双手持调酒壶举至脸侧快速摇晃, 长卷发摆动, 冰块撞击声清脆卡点, 微笑注视镜头. 00:12-00:15: 品尝与收尾, 手持蓝黄渐变鸡尾酒杯, 轻抿一口眉眼舒展微醺神情, 对镜头开心挥手定格.

Cup Noodles by a Clear Stream

{argument name="場所" default="清流"}で食べる{argument name="食べ物" default="カップ麺"}

Elegant Chinese Ink Poster

中国风高端艺术海报，水墨晕染背景，带有淡金色祥云和留白。 画面右侧用优雅的竖排书法字体清晰写着黑色大字「{argument name="大标题" default="东方美学"}」， 左侧横排用现代宋体写着小字「{argument name="副标题" default="传统与当代的对话"}」。 底部用细小的灰色楷体写着「{argument name="展会信息" default="限量艺术展 · 2026"}」。 文字清晰锐利、无变形，墨色自然，整体氛围高级、克制、有文化感， 高细节，专业海报排版

Modern Chinese Graphic Design

Build a modern flat graphic around {argument name="subject" default="any chosen subject object"}, with a huge Chinese theme character, geometric color blocks, and a single-line organic contour interlacing through one another. Keep an overall bright, clean background field, letting approximately two-thirds or more of the space remain empty, and concentrate the main weight in an off-center cluster: a saturated rectangular block in the theme's primary color first establishes a stable plane; a deeper, low-lightness, cool-toned circle overlaps from beneath it and extends beyond the boundary; the core Chinese theme character advances vertically in oversized, heavy, geometric black strokes across the white background, rectangle, and circle, with partial occlusion and cropping creating a strong scale jump; on the left, the date and a bilingual subtitle form a compact numeric column, while on the right, short vertical sentences set in two stroke-weight tiers balance the weight; a few miniature captions, short dashes, and linear symbols scatter along the edges, creating a three-level reading rhythm from main character to side notes to details. Abstract the dynamic relationship derived from the theme into one continuous organic contour, drawn as a broad sweeping loop with a clear, near-black single line that enters from the large empty field, passes through the color blocks, and crosses the edge; the curve intersects itself several times while remaining legible as a single path; keep most of its interior as the underlying background color, adding only localized, transparent, fading fills in the theme's primary color at the tips and extended sections, so the light line creates tension with the heavy giant character. Adapt the color scheme to the theme: let a clean, high-lightness neutral background carry the largest area; keep the theme's primary color vivid and highly saturated, using it for the rectangle and the localized transparent gradient; use a deep cool support color for the circle, separated in hue from the primary color and blending softly into the primary color at its end; use near-black for text and the contour, with a very small amount of light text reversed onto the primary color block; fix unequal areas, lightness hierarchy, and saturation differences, but do not fix specific color names. Render all elements as flat surfaces like matte digital printing, with sharp contour edges and gradients only as two localized, slowly feathered transitions; do not add dimensional shadows, paper grain, or global lighting effects. Keep typography in a low-contrast, broad, thick, near-geometric black sans-serif skeleton; allow the main character's parts to be elongated, offset, cut out, and switched between color-block backgrounds; give numbers a rounded futuristic structure and compress small text with narrow letterforms and loose tracking. Replace brand names, advertising copy, and concrete dates with new theme information. Preserve in the final result the extreme white

Futuristic Chinese Architecture Fusion

中式留白的未来主义杂交的中式美建筑::东方山水的可望可游可居::借景、框景、障景、留白::建筑现象学与场所精神::安藤忠雄的静默几何::路易斯·康的纪念碑性::卡洛·斯卡帕的细部边界意识::阿尔多·罗西的原型与记忆::批判地域主义::极简主义体块与大面积空场::图底关系::崇高美学::遮蔽与显露::宏伟建筑尺度::总有一处清晰受光::深阴影、雾气、空气透视::低饱和综合色彩::至少一个高辨识彩色元素作为视觉锚点::克制、寂静、神圣、未被解释的超现实空间::电影级获奖镜头构图::超广角镜头 主题：{argument name="主题" default="嫦娥奔月"} 比例16:9

Celestial Palace Ancient Chinese Fairy Portrait

9:16 竖版，古风仙侠灵动女主写真，写实偏精修角色海报风格，东方仙宫氛围，画面高级、明亮、通透、梦幻。画面主体是一位年轻成年东方女性，视觉{argument name="年龄" default="20–28 岁"}，精致东方淡颜，气质清雅、明亮、温柔、仙气。人物发型为黑色柔顺长发半披半挽，头饰华丽精致。服装为古偶女主式层叠纱裙，玉绿白金系配色。人物站在风铃回廊之中，拨动身旁的玉风铃流苏，{argument name="表情" default="温柔灵动"}。背景是{argument name="背景" default="天上仙宫、无边云海"}、远处天庭楼阁与高空宫阙群。光线为午后暖白柔光，人物面部细腻明亮。整体要求高精度、高完成度、写实感强。

Sunlit Forest Clearing Photo

Photo of a {argument name="scene" default="small clearing in the woods"} surrounded by dense {argument name="foliage color" default="vivid green"} foliage, shot from ground level with a wide-angle lens. The foreground is filled with ferns, grasses, small leafy plants, and dappled sunlight; the middle ground opens into a sunlit grassy patch; the background is enclosed by tall deciduous trees and dark evergreen conifers. Include one prominent mossy tree trunk leaning in from the left edge, arching branches overhead, thick leafy canopy, patches of bright blue sky peeking through the leaves, and strong summer daylight creating high-contrast shadows. Make it look like a realistic high-resolution nature photograph with highly detailed leaves, bark, moss, undergrowth, and natural textures, rich saturated greens, no people, no animals, no path, no buildings, no text, no watermark.

敦煌纸雕飞天 — 3D Layered Paper Cutout

Eye-level straight-on view, 3D layered paper cut-out diorama. Vermillion red, lapis lazuli blue, ochre gold. Flying apsaras with ribbon silk scarves, blooming lotus, swirling auspicious clouds, ornate medallion patterns. Deep drop shadows, matte paper texture, octane render, 8k --ar 3:4

Character Outfit and Text Overlay Edit

把人物上衣改成{argument name="服装" default="红色连帽衫"}，脸、发型、猫耳、项圈、姿势、手里的猫爪杯、背景完全不变。\n在右上角加红色角标文字「{argument name="文字内容" default="限时 9.9"}」，原图已有内容不要改动。

Moonlit Chinese Seascape

Create a tranquil classical Chinese ink-and-watercolor seascape at night, in a wide horizontal 3:2 composition. Show a vast blue moonlit ocean merging with a misty spring river estuary, with a large full moon slightly right of center above the horizon and a long shimmering silver reflection stretching down the water toward the foreground. Use soft washes, delicate brush texture, pale cyan-blue atmosphere, gentle mist, and subtle rice-paper grain. Include hazy mountain ranges and a low shoreline on the left distance, faint islands on the far right horizon, and layered clouds around the moon. In the foreground, frame the scene with two rocky promontories: left rocks with a small traditional pavilion partly hidden among pale pink blossoms and a drooping willow, and right rocks with another leafless/drooping willow silhouette. Include exactly 6 boats: 1 foreground sailboat near the lower center-left, 1 larger fishing boat in the left-middle water, 1 tiny boat near the left distant shore, 1 tiny boat on the central horizon under the moon path, 1 tiny sailboat right of center, and 1 small fishing boat on the right-middle water. Add vertical Chinese calligraphy in the upper left with the poem text {argument name="poem text" default="春江潮水连海平\n海上明月共潮生"}, plus a smaller dated signature column beneath it and a small red seal; add another small red artist seal in the bottom-right corner. The mood should be serene, poetic, luminous, and traditional, like a refined Song-dynasty-inspired landscape painting. Use {argument name="color palette" default="misty blue, pale silver, soft teal, muted ink gray, faint peach blossom pink"} and keep all details painterly rather than photorealistic.

Modern Chinese Graphic Design Layout

围绕{argument name="主题对象" default="任意主题对象"}构建以巨大中文主题字、几何色块与单线有机轮廓互相穿越的现代平面视觉。整体保持高明度纯净底场，让约三分之二以上空间留白，以偏离中心的聚集区承载主要重量：一块饱和的{argument name="主题主色" default="主题主色"}矩形先建立稳定平面，较深低明度的冷向圆形从其下方交叠并越出边界，主题核心汉字以超大重黑几何笔画纵向推进，跨过白底、矩形和圆形，不完整遮挡与裁切形成强烈尺度跳变；左侧日期与双语副标题组成紧凑的数字栏目，右侧以粗细两级竖排短句平衡重量，少量微型说明、短横线与线性符号散布在边缘，形成从主字到旁注再到细节的三级阅读节奏。把主题派生的动态关系抽象成一条连续的有机轮廓，采用清晰近黑单线勾勒宽阔回旋形态，从大片留白进入色块并越过边缘，曲线多次相交但保持可辨的单一路径；轮廓内部大部分保留底色，仅在尖端与延伸段加入局部透明的主题主色渐隐，使轻盈线条与厚重巨字形成张力。色彩随主题自适应选取：最大面积由干净高明度中性底承担，主题主色保持鲜明高饱和并用于矩形与局部透明渐变，圆形采用与主色拉开色相距离的深冷支撑色，末端混入主色形成柔和扩散，文字与轮廓使用近黑，极少量浅色文字反压在主色块上；固定不等面积、明暗层级和饱和度差，不固定具体色名。所有元素呈哑光数字印刷般的平整表面，轮廓边缘锐利，渐变只在两个局部缓慢羽化，不加立体阴影、纸张颗粒或全局光效。字体保持低对比、宽厚、近几何黑体骨架，主字允许部件拉长、错位、切出与跨色块换底，数字采用圆角未来感结构，小字以窄体和宽松字距收束；品牌、广告话术与具体日期均由新主题信息替换。最终保留极端留白、中央偏下的几何聚集、纵横文字对向拉力，以及有机线条穿越刚性图形的瞬间，避免把各部分均匀铺满或把轮廓简化成孤立装饰。

Chinese Silhouette Lantern Wallpaper

Create a vertical Chinese aesthetic wallpaper in a minimalist poetic silhouette style. Use a 9:16 portrait canvas with a deep midnight navy-blue background, softly textured like a dim interior wall at night. In the exact center, place one tall, narrow, vertical glowing rectangle of warm golden-yellow light, like a paper lantern or illuminated window slit, with softly feathered amber bloom around its edges. In the foreground, render black ink-like silhouettes: slender orchid or wild grass stems rising from the lower left, with long arcing blade leaves crossing the bottom and sweeping upward; include exactly 3 small flower clusters on thin stems in front of the glowing rectangle, each with delicate pointed petals and leaves. On the lower right, place exactly 1 small bird silhouette perched on a curved grass blade, facing left toward the flowers and light. Composition should feel calm, elegant, and asymmetrical, inspired by traditional Chinese ink painting and moonlit garden imagery. Keep all foreground plants and the bird as pure black silhouettes with crisp edges, while the golden rectangle glows softly against the blue. No text, no border, no people, no extra animals, no watermark.

Classical Chinese Red-Tea Rose Makeup

9:16 竖版，{argument name="身份" default="古风名门贵女"}墨金美妆特写，东方古典女性胸像近景，正面端坐，平静直视镜头，成熟、冷艳、矜贵、从容。年轻成年东方女性，轻熟古典美人脸，柔和鹅蛋脸，眉骨清晰，眼型修长含情，面中立体，鼻唇精致，妩媚但不风尘。 妆容为{argument name="妆容风格" default="墨金赤茶玫瑰妆"}：墨棕、赤茶与暗金珠光眼妆，眼尾自然拉长，茶玫瑰腮红，鼻梁与面中细腻高光，深豆沙水润唇，整体呈现成熟、冷艳、掌控感。 发型为黑色端庄高髻，搭配黑金镂空发冠小结构、赤玛瑙发簪、金色细流苏，耳饰为金色细链与红玛瑙垂饰。服装为{argument name="服装" default="黑曜色立领长袄"}，带暗金刺绣，搭配石榴红马面长裙，肩部加象牙白云肩，提升层次与贵气。 场景为深木厅堂、金色屏风、红梅枝、暖色烛光，背景柔和虚化。黑色服装不吞没面部，人物脸部有独立补光，肤色干净通透，发饰、刺绣和妆容细节清晰可见，高级古风贵女人像摄影质感。

Chinese Embroidery Art Poster

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，保持主体结构、真实质感、自然光影和原有色彩氛围，仅进行轻微高级摄影调色，使其具有艺术杂志、独立出版物和展览摄影质感。为适配画幅，可自然扩展天空、地面或环境背景，但不得拉伸、扭曲或改变主体。下半部分先理解原图真正的核心精神、情绪关系与潜在寓意，再提取其中最具识别性的主体、轮廓、姿态与叙事关系，只选择一个最能代表整张照片的核心意象进行中国刺绣式重构。不要把照片完整绣一遍，也不要把所有景物逐项转换成刺绣；应大胆删减次要信息，用一个姿态、一段轮廓、一种关系、一个动作或一个具有象征性的局部承载整张照片的内核，让人看到下半部分时，不只是认出“是什么”，还能够感受到原图“在表达什么”。刺绣语言融合中国传统织绣的丝线层次、针法变化、虚实关系与东方留白，可使用平针、长短针、盘线、缠线、打籽、压线等不同针迹，根据主体形态改变针向、密度和层次。局部可以精细，局部可以只留下几针、一道线或未完成的轮廓，让“绣与不绣”共同构成画面。真实呈现丝线光泽、针脚方向、叠线与轻微手工误差，但避免满版传统纹样、工艺品展示感和数字假刺绣。构图强调取舍、留白、气韵与生命感。不固定居中，不平均填满，根据主体的重心、动作、视线、走势和情绪自由安排位置、尺度、裁切与疏密。可以偏心、悬置、局部放大、越界或只出现一部分，让少量绣面与大片空白形成张力；一根游离的丝线、一个未完成的边缘或一小片颜色也可以承担情绪。留白应像空气、距离、停顿和余韵，而不是空出来等待填充的位置。背景必须干净、清亮、有空气感，不默认使用米黄、灰米、旧亚麻或脏浅色。 根据上方照片的色彩气质，自适应选择洁净白、冷白、柔和象牙白、极浅彩色或具有明确综合色相的清透丝绢底色，也可以在原图适合时使用更大胆但纯净的有色底。背景允许看到极轻微的丝绢、绫罗或织物纹理，但不得泛黄、蒙灰、发脏、做旧或出现污渍。刺绣的手工感来自丝线与针法，而不是靠脏旧背景制造。配色同样不设固定色卡。从原图中寻找最有神采、最有生命力、最能代表其精神的颜色关系，再转化成中国刺绣特有的灵动丝线色阶。不是平均吸取照片颜色，而是保留真正有意义的主色，并允许同一颜色在冷暖、深浅、明暗与纯度之间细微游移，通过近似色穿插、少量互补色点醒、高纯度小面积亮色和不同针向产生丝线闪烁。颜色可以清丽、鲜活、浓郁、柔美或素雅，由每张原图决定；丰富但不杂乱，明艳而不俗艳，柔和但不灰，传统但不死板。文字只作为轻巧的编辑性点睛，从原图没有直接说出的情绪、动作、关系或隐喻中提炼一个极短英文词或短句。可使用细线刺绣、纤细题签或极简小字，让文字顺着丝线走势、嵌入负空间、贴近主体边缘，甚至像一根线一样成为构图的一部分；少而有意味，不做说明标签，不抢夺刺绣主体。整体追求一图一核、一核一意象：先理解原图，再选择最值得被留下的东西；其他元素宁可舍弃，也不要为了丰富而堆砌。最终呈现中国刺绣特有的灵动色彩、丝线光泽、东方留白、含蓄寓意与当代编辑设计感，清亮、有神、有情绪、有生命力。避免整图复刻、元素堆积、脏米色背景、泛黄旧布、固定国风配色、满版刺绣、文创商品感和模板感。

Chinese Aesthetic Window Scenery Poster

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{argument name="海报比例" default="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，保持主体结构、真实质感、自然光影和原有色彩氛围，仅进行轻微高级摄影调色，使其具有艺术杂志、独立出版物和展览摄影质感。为适配画幅，可自然扩展天空、地面或环境背景，但不得拉伸、扭曲或改变主体。 下半部分提取照片中最具识别性的主体、轮廓、姿态与叙事关系，重构为一张柔和、朦胧而具有东方框景秩序的氛围插画。以中国传统建筑中的圆窗、花窗、漏窗、月洞、扇形窗、六角窗或几何棂格作为主要结构框架，根据主体形态选择最合适的一种，不机械套用。主体、枝影、光斑或抽象投影在窗形中显现、穿过、遮挡或溢出，使窗框既固定画面秩序，又形成虚实之间的空间层次。 构图强调视觉重心、比例关系、正负形与留白节奏。窗形不必绝对居中，可轻微偏置、局部裁切或悬置于画面一侧；主体与光影围绕窗形形成主次关系，通过一处主要光区、一处安静留白和少量柔和投影建立稳定而富有诗意的视觉三角。避免平均铺满、过度对称和复杂装饰，让画面看似简单，却具有明确的空间秩序与呼吸感。 背景不固定使用深蓝，而从上方照片中提取一个{argument name="背景色" default="非常浅、低饱和、干净且与原图协调的综合色"}，如雾蓝、浅青、淡杏、柔粉、灰绿、暖米白或极浅紫灰，使背景与主体之间产生温柔而清晰的明度落差。光影则从原图最有生命力的颜色中提炼，可适度提亮、提纯，形成柔和的冷暖呼应。整体避免脏灰、厚重暗底、荧光色和生硬高反差。 质感采用细腻的喷绘颗粒、色粉、空气感柔焦与漫射光，光影边缘自然虚化，带轻微颗粒、粉尘和色彩晕染。窗格本身可以比光影稍清晰，但仍保持柔和，不做硬质建筑描边；让画面像阳光透过传统窗棂投射在一面浅色墙上，被记忆和空气轻轻模糊。 文字作为构图中的微小秩序介入，从照片的情绪、时间、动作、温度或隐喻中提炼一个{argument name="英文标题" default="极短英文标题"}，并搭配少量地点词、状态词或微型短句。文字可沿窗框边缘、弧线、轴线或光影留白排布，与窗形形成对齐、环绕、错位或穿插关系，以极小字号、细字重和宽字距形成安静的高级编辑感。 整体呈现浅色呼吸感背景、传统窗形框景、柔和有色光影、喷绘颗粒、虚实投影与大面积留白共同构成的东方现代视觉。无论主体是人物、动物、植物、建筑、器物或自然景观，都应保持与上方照片清晰呼应，同时具有温柔、静谧、清透、诗意、治愈而高级的艺术气质，避免卡通感、廉价滤镜、厚重暗色、杂乱装饰和模板感。

博物馆图鉴式汉服拆解图 — GPT-image-2

请根据【主题】自动生成一张博物馆图鉴式中文拆解信息图。 要求整张图兼具真实写实主视觉、结构拆解、中文标注、材质说明、纹样寓意、色彩含义和核心特征总结。你需要根据【主题】自动判断最合适的主体对象、服饰体系、器物结构、时代风格、关键部件、材质工艺、颜色方案与版式结构，用户无需再提供其他信息。 整体风格应为：国家博物馆展板、历史服饰图鉴、文博专题信息图，而不是普通海报、古风写真、电商详情页或动漫插画。背景采用米白、绢纸白、浅茶色等纸张质感，整体高级、克制、专业、可收藏。 版式固定为： - 顶部：中文主标题 + 副标题 + 导语 - 左侧：结构拆解区，中文引线标注关键部件，并配局部特写 - 右上：材质 / 工艺 / 质感区，展示真实纹理小样并附说明 - 右中：纹样 / 色彩 / 寓意区，展示主色板、纹样样本和文化解释 - 底部：穿着顺序 / 构成流程图 + 核心特征总结 若主题适合人物展示，则以真实人物全身站姿为中央主体；若更适合器物或单体结构，则改为中心主体拆解图，但整体仍保持完整中文信息图形式。所有文字必须为简体中文，清晰、规整、可读，不要乱码、错字、英文或拼音。重点突出真实结构、材质差异、文化说明与图鉴气质。 避免：海报感、影楼感、电商感、动漫感、cosplay感、乱标注、错结构、糊字、假材质、过度装饰。

High Resolution Forest Clearing Photo

阳光明媚，{argument name="场景描述" default="林中一片空地"}，周围环绕着大量绿色枝叶，细节极其丰富，使用高品质高分辨率无反相机拍摄，动态范围出色，清晰无模糊，{argument name="比例" default="5:3"}

Chinese Pearl Makeup Beauty Portrait

9:16 竖版，古风贵女香槟珠光美妆写真，珍珠妆阁场景，东方古典女性半身近景。人物坐在妆台前，通过铜镜轻轻看向镜头，一只手抬起，用柔软粉扑轻触脸颊，姿态端庄自然，神情温润、矜贵、从容，带富养大小姐的华美与精致感。人物为视觉年龄约 20–28 岁、明确成年的年轻东方女性，珠圆玉润贵女脸，柔和鹅蛋脸，额头与面中自然丰盈，下颌线柔顺，清亮杏眼，眼裂自然修长，眼神温柔沉静，鼻梁秀气流畅，鼻尖精致圆润，唇形柔软饱满，五官比例协调，近景耐看。妆容为雪青香槟珍珠妆。底妆清透细腻，带柔和珍珠光泽，但保留自然皮肤纹理，不油腻。眼妆使用雪青粉、浅豆沙、香槟金渐层晕染，眼中与卧蚕加入细腻香槟珠光，眼尾自然加深并拉长；睫毛纤长分明。面中使用柔和豆沙粉与浅玫瑰腮红，鼻梁、鼻尖和面中加入细致珍珠高光。唇妆采用玫瑰奶茶色水润玻璃唇，唇峰与唇珠清晰。整体妆后气质温润、华美、柔和、矜贵。发型为柔顺乌发盘成圆润高髻，头顶自然饱满。发间搭配香槟金镂空发梳、雪青色琉璃花钗、层叠珍珠珠链、透明珠滴与细金流苏，结构华丽但不遮挡脸部。耳饰为珍珠、雪青琉璃与浅金细链组合，颈间可搭配精致珍珠项链与雪青色小型坠饰。服装为雪青色云肩襦裙，内层使用象牙白刺绣内衫，胸前有细腻浅金花纹与珍珠细节；外层使用雪青与香槟金刺绣纱衣，肩部、领缘和袖口带精细珠绣与金线纹样，外搭浅蓝灰柔纱披帛。服装颜色明确分层：雪青负责主视觉，象牙白提亮人物，香槟金增加华贵感，浅蓝灰负责冷暖平衡，避免整张图统一紫色罩染。场景为精致珍珠妆阁，人物前方是一面古铜色圆形妆镜，妆台摆放少量珍珠首饰盒、香粉盒、透明琉璃香瓶与首饰。背景使用白玉屏风、香槟金纱帘和淡色兰花，暖白灯影从后方形成柔和散景与金色光斑，整体精致但不喧宾夺主。光线采用暖白与香槟金柔光结合，人物面部有独立柔和补光，双眼、眼影、腮红、唇妆和皮肤纹理清晰可见。面部高光细腻克制，不形成全脸油光。背景保持浅景深柔和虚化，镜面边缘作为前景框景，增强妆阁生活感和画面层次。85mm 人像镜头，真实摄影质感，高级古风贵女美妆写真，珠光细腻，珍珠与金属材质清晰，服装刺绣精致，画面明亮通透，柔和华美，高完成度。

Realistic Chinese Street Smartphone Photo

A completely natural, photorealistic smartphone snapshot of a {argument name="subject" default="young East Asian woman"} walking through a {argument name="location" default="busy traditional Chinese shopping street"} during the daytime. She is captured from slightly behind as she turns her head naturally over her shoulder toward the phone camera, as if a friend casually photographed her while they were walking. She has {argument name="hair style" default="dark brown-black hair tied into a loose messy bun"}, with soft wispy strands falling around her temples and cheeks, a few flyaway hairs visible in the sunlight, natural fair skin, minimal everyday makeup, subtle pink lips, and a calm curious expression. She wears a fitted pale pink ribbed short-sleeve top with a white shoulder bag hanging naturally from her shoulder. Behind her is a real-looking old commercial street with traditional Chinese storefronts, wooden architecture, many red hanging lanterns, pedestrians walking in different directions, shop signs, pavement, and a distant city tower visible between the buildings. Bright natural afternoon sunlight, realistic shadows, slightly uneven exposure, mild background motion blur from moving people, natural depth of field, authentic smartphone HDR, subtle lens distortion, slight softness around the edges, realistic skin pores, individual hair strands, natural fabric texture, imperfect framing and focus, ordinary street details, no cinematic color grading, no studio lighting, no beauty filter, no excessive retouching, no perfect symmetry, no artificial sharpness. Make it look like an actual spontaneous photo taken on a modern phone by a friend, with tiny imperfections and realistic computational-camera processing, highly believable and indistinguishable from a real photograph, vertical 4:5 composition.

Chinese Idiom Bell Theft Poster

Goal: Create a vintage Chinese idiom visualization poster for {argument name="idiom title" default="掩耳盗铃"}, showing the literal scene of a man covering his ears while trying to steal a ringing bell. Canvas: Vertical poster, 3:4 aspect ratio, aged beige rice-paper background with subtle stains, worn ink texture, and an antique educational print feel. Layout: Large black brush-calligraphy title centered at the top. Directly below it, place the English subtitle in small serif capitals: “COVERING EARS DOES NOT STOP SOUND”. Under the subtitle, add a small red outlined label reading {argument name="story label" default="成语事故现场 02"}. The main illustration fills the lower two-thirds of the poster. Scene: An ancient Chinese courtyard rendered in monochrome black ink with muted sepia shading. On the left, a massive bronze temple bell hangs from a rough wooden beam and iron chains. The bell is tilted slightly, vibrating, with engraved patterns, rivets, and a scalloped lower rim. On the right foreground, a thief in dark traditional clothing crouches low and pulls a rope attached to the bell while pressing both hands over his ears; his posture is tense and foolish, one knee bent forward and one leg stretched back. Behind him are courtyard paving stones, an old wall, a traditional tiled roof gate on the right, and delicate tree branches above the wall. Annotated elements: Include exactly 3 red numbered callouts: “01” near the hanging bell and sound source, “02” near the thief covering his ears, and “03” near the stone ground in the lower left foreground. Draw thin red leader lines from each number to its target. Graphic effects: Use many thin red concentric sound-wave rings radiating outward from the bell across the whole courtyard, passing behind the thief and architecture. Add small black vibration marks around the bell. Keep the red lines slightly faded and printed like old ink. Visual style: Detailed hand-drawn Chinese historical engraving, ink wash and woodblock print aesthetic, high line density, muted black-gray sepia palette with red annotation ink, realistic perspective, weathered archival poster design. Constraints: Use exactly one bell, one thief, three numbered red callouts, and one set of expanding sound-wave rings. Do not add modern objects, bright colors, cartoon styling, extra characters, watermark, or logo.

Chinese Red University Anniversary Poster

Goal: Create a grand Chinese red anniversary celebration poster for a university centennial-and-beyond milestone, combining government-style ceremonial design with elegant campus line art. Canvas: Wide horizontal poster, 16:9 ratio, deep China-red background with subtle vignette and glowing gradients. Use a premium red-and-gold palette: crimson, scarlet, dark wine red, warm gold linework, and ivory-gold typography. Layout: Dominant oversized outlined number {argument name="anniversary number" default="120"} spans the upper half of the poster, drawn with many thin parallel gold contour lines. Integrate delicate gold architectural line drawings into the number and around it: an open book at the lower left of the 1, a campus clock tower and academic buildings inside the 2, and a ceremonial university gate inside the 0. Across the middle and lower half, create layered flowing red silk waves like a national flag, with luminous highlights and realistic satin folds, partially covering the bottom of the large number. Add small decorative elements in the sky: exactly 7 flying birds in pale gold, and exactly 4 radial firework/starburst ornaments placed around the upper left and upper right areas. Main text: Centered vertically over the silk waves, set large vertical Chinese title text {argument name="main title" default="百廿芳华"} in an elegant Song/Ming-style serif font, ivory-gold with a soft glow. To the left of the title, add a smaller vertical line {argument name="anniversary subtitle" default="某某大学建校120周年"}. To the right of the title, add a small outlined vertical seal-shaped label reading {argument name="seal text" default="学校限定"}. Beneath the main title, place a thin rectangular gold-outline date plaque reading {argument name="date range" default="1905-2025"}. Lower information area: Include exactly 3 event information blocks across the lower third, separated by two thin vertical divider lines. Left block: simple gold outline icon of a classical building, with two lines of Chinese text: “百廿校庆 · 共襄盛典” and “2025年10月18日-20日”. Middle block: simple gold outline icon of celebratory linked circles, with two lines: “全球校庆 · 闻贺华诞” and “线上线下 · 共赴未来”. Right block: simple gold outline play-button icon, with two lines: “云端校庆 · 精彩直播” and “关注官方平台观看”. Along the very bottom center, add widely spaced small gold Chinese values text: “传 承 · 创 新 · 卓 越 · 担 当”. Visual style: High-end official Chinese institutional poster, festive but refined, cinematic lighting, clean symmetrical composition, delicate thin gold lines, realistic red silk texture, no people, no watermark, no extra logos, sharp readable typography.

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"}.

Typographic illustration shaped like a, where the text forms the shape

Create a typographic illustration shaped like a [OBJECT], where the text [BRAND SLOGAN] forms the shape — bold and playful lettering style that fills the entire silhouette — letters adapt fluidly to the curves and contours of the [OBJECT] — [COLOR 1, COLOR 2] with [BACKGROUND COLOR] background that enhances the focus on the main shape — include [BRAND] logo positioned below the [OBJECT] — vector-style, clean, high resolution, 1080x1080 pixels, square format.

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": "…

Neon X Post 3D Walkout Portrait

{"type":"cinematic 3D social media profile photo illustration","scene":"A full-body adult man steps out of a giant floating X/Twitter post card as if breaking through the screen, blending realistic portrait photography with futuristic 3D UI design. Dark glossy studio background with cyan neon rim lighting, reflective floor, soft blue glow and high contrast cyberpunk atmosphere.","main subject":{"description":"one adult man, face intentionally left customizable, walking forward from the card with one leg extended outside the frame","pose":"confident forward stride, relaxed arms, body slightly angled toward the viewer","outfit":{"count":4,"items":["black turtleneck sweater","dark slim jeans","black leather shoes","small earring"]},"hair":"short dark hair, neatly styled","face":"use {argument name="character face" default="a realistic adult male face"}"},"floating post card":{"platform":"X / Twitter style post","appearance":"large vertical rounded-rectangle glass phone-like card with thick translucent edge, glowing cyan outline, beveled 3D depth, viewed in slight perspective from the front-left","top bar":{"count":5,"items":["circular profile avatar at top left","display name text: {argument name="display name" default="Dilshad Hussain"}","blue verified check badge","handle text: {argument name="handle" default="@DilshadAI1"}","large white X logo at top right"]},"main image area":"rounded-rectangle photo inside the post showing a futuristic city street tunnel with intense cyan, blue, white, and magenta motion-blur light trails converging behind the man, creating a speed warp effect","metadata row":{"count":3,"items":["time and date text: {argument name="timestamp" default="10:03 AM · 07 Jan 23"}","view count text: {argument name="view count" default="638K"}","small views label partially visible"]},"engagement bar":{"count":5,"items":["reply icon with count 30","repost icon with count 1.4K","bright pink heart like icon","bookmark icon","share/upload icon"]}},"composition":"The card occupies most of the frame, tilted slightly backward and to the left, with the man emerging from the image area and overlapping the UI at the bottom. Add depth shadows where his body crosses the card edge. Keep the neon border crisp and luminous, with subtle bloom around the entire card.","style":"ultra-realistic 3D render, cinematic portrait lighting, glossy sci-fi interface, shallow depth of field, high detail, dramatic cyan and teal color grading, vertical 9:16 composition, social media viral profile aesthetic","negative prompts":"avoid extra people, avoid distorted limbs, avoid unreadable main name and handle, avoid flat 2D UI, avoid cluttered background, avoid cartoon style"}

Google Fonts Japanese Tutorial Infographic

Japanese infographic · How to use Google Fonts · clean modern flat design, white background, soft pastel blue and mint corner blobs, rounded cards with subtle shadows, tech tutorial aesthetic, crisp vector typography and UI illustrations · 16:9 · Google Fontsの使い方 · 基本の3ステップ · 1. フォントを選ぶ · left · 1 · 1. フォントを選ぶ · rounded white panel with light blue border/shadow · blue numbered circle with 1 · browser window showing a font search interface, 3 visible font preview rows with large Aa あ samples, a search bar at top, small colored window buttons, light gray interface lines and blue accent dashes · Google Fontsのサイトで、好きな書体を探します。 · 2. 埋め込みコードを取得 · center · 1 · 2. 埋め込みコードを取得 · rounded white panel with light blue border/shadow · blue numbered circle with 2 · dark code panel with two labeled code examples separated by a thin divider · 2 · <link> (HTML), @import (CSS) · <link href="https://fonts.googleapis.com/css2?family=Poppins:wght@400;600&display=swap" rel="stylesheet">, @import url('https://fonts.googleapis.com/css2?family=Noto+Sans+JP:wght@400;700&display=swap'); · 表示された<link>やCSSをコピーします。 · 3. CSSで適用 · right · 1 · 3. CSSで適用 · rounded white panel with light blue border/shadow · blue numbered circle with 3 · white code card containing CSS with two selectors and font-family rules · 2 · .title, body · .title { font-family: 'Poppins', sans-serif; }, body { font-family: 'Noto Sans JP', sans-serif; } · font-familyを指定して、デザインに反映します。 · ポイント · bottom-left · 3 · 読みやすさで選ぶ, 日本語対応を確認する, 使いすぎず、2〜3種類に絞る · rounded white panel with pale blue tint · blue star in a circle · bullet list · よく使う組み合わせ · bottom-center-right · 2 · 見出し: Poppins, 本文: Noto Sans JP · rounded white panel with pale lavender tint · purple linked-rings symbol · two pill-shaped example boxes · 2 · large blue right-pointing arrows between the 3 top cards · 2 / 2 · bottom-right · blue rounded corner tab · Japanese · #2f80ff · #0f2b5b · #4285F4, #DB4437, #F4B400, #0F9D58 · #8b6cff · #ffffff

Ultra-realistic 16K selfie edit of a daydreaming girl on a blanket

Edit the photo in ultra-realistic 16K resolution. A young girl is taking a selfie inside a room. Her hair is long, layered ash brown, slightly messy at the top, falling forward naturally. She is wearing a black curly-strapped floral dress. Pose: She is lying face down on a blanket, with her right hand touching her lips, head tilted sideways, looking forward, appearing to be daydreaming. Her makeup is flawless, Korean-inspired with a modern touch: neatly shaped eyebrows, soft peach eyeshadow, thin eyeliner emphasizing her eyes, and soft gray contact lenses giving a captivating gaze. Her cheeks have a natural peach blush, and her lips are glossy, with a nude base lip color ombre'd into red, creating a soft yet striking contrast. The background is a cream marble wall. Photo is taken up-close at eye-level. Lighting: Cinematic and editorial, dim and dark to make the selfie look realistic. Retro purple contrast enhances skin glow. Photo captured with an iPhone 17 Pro Max. Do not alter her face in any way.

Hybrid Cache Execution Flowchart

Create a clean vertical technical workflow infographic on a light gray background, using a minimalist modern product-diagram style with rounded white cards, thin colored outlines, simple vector line icons, dark navy text, and navy connector arrows. The composition is a single centered top-to-bottom flowchart with 7 numbered main steps, plus 2 parallel cache-group panels branching from step 4 into step 5, and a thick dark return arrow on the far left looping from the bottom back to the top. Use crisp sans-serif typography, generous spacing, subtle pastel accent colors, no gradients, no shadows, and presentation-slide clarity. At the top center place step card 1 with a blue outline and a code/chat icon on the left. Title text: "1. {argument name="step 1 title" default="chat completions request"}". Subtitle beneath: "conversation_id + cache_salt + new suffix messages". Below it place step card 2 with a blue outline and a document/list icon. Title: "2. Frontend conversation ledger". Subtitle: "lease same id + track committed messages". Below it place step card 3 with a cyan outline and a database-with-magnifier icon. Title: "3. Exact conversation cache lookup". Subtitle: "conversation_id  committed turn state". Below it place step card 4 with a purple outline and a branching scheduler icon. Title: "4. Scheduler cache attachment". Subtitle: "set num_computed_tokens + attach committed state". From step 4, branch downward into 2 side-by-side group panels. Left group panel: a pale green rounded container titled "Full-attention KV cache group". Inside it, stack 2 inner cards. First inner card has a green block-grid icon, title "Committed block refs", subtitle "share aligned full KV blocks". Second inner card below has a green layered-sheets icon, title "Tail COW copy", subtitle "copy unaligned KV tail". At the bottom of the green panel add small footer text: "paged K/V tensors for transformer layers". Right group panel: a pale purple rounded container titled "Mamba terminal-state cache group". Inside it, stack 2 inner cards. First inner card has a purple database/network icon, title "Committed terminal state", subtitle "exact state at committed length". Second inner card below has a purple wavy-lines icon, title "Request-owned terminal copy", subtitle "copy SSM + conv state". At the bottom of the purple panel add small footer text: "align-mode terminal state placement". Merge both group-panel outputs into a centered step card 5 with a blue outline and a microchip icon. Title: "5. Hybrid model execution". Subtitle: "run only the uncached suffix". Inside the bottom area of this card, include 2 pill-shaped labels side by side: "Transformer layers" and "Mamba layers". Below it place step card 6 with a blue outline and a sparkle icon. Title: "6. Decode assistant tokens". Subtitle: "stream response token by token". Below it place step card 7 with a warm yellow-orange outline and a database-with-check icon. Title: "7. Commit completed turn". Subtitle: "publish pending state or discard on failure". Add a thick dark navy loop arrow running down the far left side, entering step 1 near the top from the left and returning from step 7 at the bottom back upward. Along this left loop, near the lower half, place stacked annotation text: "next request reuses committed conversation head". Add 2 dashed publish arrows rising upward from step 7 toward the cache-group panels: one green dashed arrow on the left pointing to the green cache panel, labeled "publish new state"; one purple dashed arrow on the right pointing to the purple cache panel, also labeled "publish new state". Keep the exact total count of 7 numbered main cards, 2 cache group panels, 4 inner cache cards, and 2 pill labels. Preserve a portrait aspect ratio similar to a conference-slide architecture diagram.

Tokyo Gothic Lolita Fashion Poster

Goal: Create a vertical fashion poster for a maximalist Tokyo gothic-lolita theme, styled like a glossy underground magazine cover and event flyer. Canvas: Tall vertical 9:16 poster, high-contrast flash photography, dark black-red palette, ornate gothic textures, no clean white margins. Main subject: A full-body young woman model stands slightly right of center in an elaborate black gothic lolita outfit. Her face is intentionally obscured by a soft square blur/mosaic censor block. She has long dark wavy hair with twin ornate hair accessories. Pose: legs crossed, one hand raised near her cheek, the other hand holding out the skirt edge. Expression is hidden; body language is cute, confident, and theatrical. Outfit details: Use exactly 8 visible outfit/accessory groups: 1) black lace off-shoulder corset bodice with deep neckline, 2) short layered black ruffle skirt with glossy crinoline volume, 3) burgundy satin bows on the bodice and skirt, 4) black lace fingerless gloves and lace arm coverings, 5) silver cross necklace at the chest, 6) multiple dangling silver chains and cross charms around the waist, 7) black platform ankle boots with buckles, straps, metal rings, and cross ornaments, 8) two black-and-burgundy gothic hair ornaments with flowers, bows, lace, chains, and cross charms. Background: A dense gothic interior with carved black frames, antique mirrors, red stained-glass panels, gold candle sconces, dim warm lights, and baroque decorative clutter. Make it look like a real flash photo taken in a dark gothic club or boutique, with wet glossy highlights and deep shadows. Left-side poster typography: Fill the left third with ornate layered gothic lettering and decorative graphics. Include exactly 4 main text blocks: 1) large silver-black medieval blackletter headline reading “{argument name="main headline" default="Tokyo Gothic Style"}”, 2) hot-pink dripping graffiti brush text reading “{argument name="graffiti phrase" default="Curse Cute!"}”, 3) small elegant cursive footer reading “{argument name="event title" default="The Ultimate Tokyo Gothic Fashion & Pose Championship"}”, 4) small magenta footer line reading “{argument name="award line" default="2024 Grand Prix"}”. Decorative elements: Use exactly 5 major gothic graphic motifs on the poster: 1) a large silver cross behind/overlapping the main headline, 2) spiderwebs in the upper-left corner, 3) black ornamental vines and filigree behind the text, 4) small pink hearts around the graffiti phrase, 5) an ornate silver cross near the lower-left area. Add red shadows, chrome highlights, distressed scratches, and layered embossing to the lettering. Style: “Gorri-gori” heavy gothic, Japanese street fashion editorial, dramatic direct camera flash, glossy latex/leather shine, intricate lace detail, chrome silver jewelry, burgundy accents, punk-goth cute-but-cursed energy, extremely detailed, sharp focus on clothing and text, slightly chaotic but readable poster composition. Constraints: The subject must remain full-body and right-centered; the face must be covered by a square blur. Keep the palette mostly black, silver, burgundy, and hot pink. Do not add extra people. Do not add extra text beyond the 4 specified text blocks. Make the gothic typography large, dimensional, and legible.

Night Forest Fantasy Camp

Create a dark cinematic anime-style travel camp scene at night in a dense forest, widescreen 16:9 composition. Two travelers rest beside a small campfire: on the left, a petite young girl with {argument name="girl hair color" default="short silver-white hair"}, a red flower hair ornament, a black cloak with deep crimson lining over a white blouse, red ribbon tie, dark tights, and black loafers, sitting on a low stump or stool while holding a plate of food and eating; on the right, a tall adult male knight or mage escort in an ornate black military uniform with gold trim, high collar, brass buttons, leather belts, gloves, tall boots, circular cloak clasps, and a sweeping black cloak lined in burgundy, seated calmly while holding a metal cup and a piece of bread. Both faces are deliberately covered by plain soft-edged beige rectangular censor blocks. In the center foreground, a bright orange campfire burns under a tripod supporting a black cooking pot filled with stew, casting warm light onto the characters and ground. Surround the campsite with travel props: exactly 10 visible camp and travel items including one brass lantern glowing on a wooden crate at far left, one metal cup near it, one loaf of bread on the crate, one cutting board with sliced cured meat, one shallow bowl of food, one stacked wooden chest at right, one rolled bedroll on top of the chest, one leather satchel in the lower right foreground, one sheathed sword leaning beside the luggage, and one horse-drawn carriage in the dark right background with a horse partly visible. The environment is a deep blue-black forest with tall tree trunks, heavy shadows, subtle foliage, and a dirt clearing; lighting should be moody and painterly with strong warm firelight, cool moonlit shadows, detailed textures, high-quality fantasy illustration, dramatic travel-story atmosphere, and no on-image text.

Golden Hour Product Photography on Rugged Rock

Cinematic product photography of a vibrant orange {argument name="product name" default="LOREMIA cre…

Generating a Korean Idol Style Image

プロンプトには韓国アイドルみたいにしてって笑

Clothing Item Cut-Out Sticker Prompt

Collect each clothing item worn by the girl in the first photo and place them on top of the same pho…

Golden Hour Mirror Selfie Realism

{   "meta": {     "camera": "iPhone 17 Pro",     "lens": "35mm",     "aspect_ratio": "4:5",     "style": "raw iphone indoor realism, natural HDR, soft grain"   },   "scene": {     "location": "bedroom mirror",     "time": "golden hour sunset leaking through window",     "atmosphere": "warm quiet room, soft shadows, intimate silence"   },   "lighting": {     "primary": "golden sunlight hitting from side",     "effect": "fabric slightly translucent, warm glow on skin, natural highlights"   },   "subject": {     "pose": {       "position": "standing in front of mirror",       "action": "mid-unbutton shirt moment",       "body": "one hand holding shirt open slightly, other holding phone",       "torso": "subtle forward lean"     },     "expression": {       "eyes": "locked into mirror",       "mouth": "barely parted",       "energy": "caught in a private moment"     },     "hair": {       "style": "soft messy natural fall"     },     "outfit": {       "top": {         "type": "oversized white button-up",         "state": "half unbuttoned",         "effect": "light passing through fabric, shape hinted not shown"       },       "bottom": {         "type": "minimal lounge shorts",         "color": "neutral"       }     }   },   "camera": {     "angle": "mirror selfie slight tilt",     "distance": "medium",     "imperfection": "tiny blur + fingerprint smudge on mirror"   } }

World Cup Throne Portrait

Create a cinematic vertical luxury football champion portrait in a dark studio arena. A {argument name="subject identity" default="young adult man with short dark hair"} sits centered and facing forward on an enormous black iron throne inspired by a fantasy sword throne, made from dozens of overlapping steel blades and swords fanning upward behind him like a crown. He wears a {argument name="outfit" default="plain black long-sleeved shirt, black jeans, and black-and-red high-top sneakers"}. His posture is powerful and relaxed: seated with legs apart, right hand gripping a gleaming {argument name="main trophy" default="FIFA World Cup trophy"} held upright near his knee, left forearm resting on the throne armrest. Place the throne on a circular glossy black metallic platform. Surround him with exactly 6 visible football awards and props on the platform: 2 large gold cup trophies standing at the far left and far right edges, 2 taller narrow gold trophies beside his feet, and 2 metallic gold footballs in the front left and front right corners. Add additional smaller gold football ornaments integrated into both throne armrests. Background: a vast dark stadium or arena with blurred crowd seating, cool blue stadium floodlights on both sides, deep black upper background, and subtle haze. Lighting should be dramatic and high contrast, with teal-blue rim light from the stadium and warm red-orange highlights on the throne, trophies, shoes, and platform edges. Style: ultra-realistic, premium sports editorial, heroic symmetrical composition, sharp metallic textures, glossy reflections, shallow depth of field, 9:16 vertical poster framing. Keep the face recognizable if a reference is provided, but do not add text, logos, watermarks, or extra people.

Millie Bobby Brown Sophisticated Portrait

{ "subject": "{argument name="subject name" default="Millie Bobby Brown"}", "known_for": "Actress and producer, breakout role as Eleven in Stranger Things", "appearance": { "age_look": "mature and sophisticated", "expression": "calm and confident, looking directly at camera", "pose": "seated, legs crossed, adjusting hair with hand", "hair": { "style": "long, soft waves", "parting": "center" }, "makeup": { "style": "understated, natural", "trend": "clean girl", "tones": "warm, complements outfit" }, "skin": { "tone": "luminous white", "texture": "natural, visible pores and micro-detail", "highlights": "subtle moisture highlights on collarbones, shoulders, cheekbones", "dynamic_reaction": "skin reacts to cinematic lighting" } }, "outfit": { "ensemble": { "type": "two-piece set", "color": "{argument name="outfit color" default="terracotta/russet brown"}", "top": { "style": "structured sleeveless waistcoat", "details": ["sharp lapels", "pointed hem"] }, "bottom": { "style": "matching skirt", "fabric": "heavy cotton or soft suede" } }, "accessories": { "necklaces": ["layered gold chains", "pendant"], "earrings": "small elegant hoops" } }, "setting": { "background": { "style": "industrial / behind-the-scenes", "elements": ["vertical metallic or wooden slats", "splashes of yellow paint", "weathered wooden crate or chest"] }, "color_palette": ["browns", "tans", "golds"] }, "image_specs": { "width": 504, "height": 1002, "orientation": "vertical" } }

High-End Studio Fashion Portrait

请基于我上传的清晰本人照片，生成一组 9 张单独成片的时尚写真，统一为 3:4 竖构图，不要拼图，不要九宫格。 人物必须严格保留我本人的真实长相和辨识度，包括脸型、五官比例、眼睛、鼻子、嘴唇、肤色、年龄感、发型基础和整体气质。9 张都必须明显是同一个真实女生，不能变成陌生人，不能欧美化，不能过度网红化，不能出现 AI 假脸。 主题：{argument name="主题风格" default="甜辣酷飒棚拍写真"}，风格参考高级时尚摄影棚样片，整体气质要成熟、性感、利落、很会拿捏镜头，带一点坏坏的酷感和强势的女性魅力，像很会打扮、很会出片的高阶辣妹。 服装造型：{argument name="服装" default="黑色挂脖/深V贴身连体短裤或超短裙造型"}，搭配金属链条腰饰、灰棕色毛绒腰部装饰或毛绒小围饰，腿部搭配毛绒腿套，脚穿细带高跟凉鞋。可搭配黑色项链、十字架吊坠、手链、戒指等配饰。整体造型要统一、完整、时髦、有攻击性。 妆发：长直黑发或微直顺长发，发质顺滑有光泽，轻微风吹发丝；妆容精致，高级感底妆，眼妆立体，唇妆饱满，皮肤有光泽感，整体偏时尚杂志风。 场景：{argument name="场景" default="纯色极简摄影棚"}，背景是干净的暖橘色到浅橙粉的渐变背景和地面，画面简洁，没有多余杂物。灯光为商业棚拍布光，人物皮肤通透发亮，轮廓清晰，带一点暖调和轻微红色边缘光，成片质感高级、昂贵、干净。 画面要求：9 张都要是单独完整成片，构图干净，姿态不同，包含全身、中景、半身和近景，风格统一但姿势和镜头变化明显，像一整组专业摄影棚时尚写真。不要夸张畸形，不要肢体错误，不要手脚异常，不要低俗擦边。 9 张镜头可分别为： 1）坐姿全身，双腿舒展，气场强，直视镜头 2）站姿半身，手扶腰部毛绒装饰，冷感表情 3）跪姿侧身，长发被风吹起，回头看镜头 4）俯身靠近镜头，突出脸和长腿，姿态张力强 5）站姿全身，微微转身展示身材曲线和腿部线条 6）近景半身，表情冷艳，发丝掠过脸部 7）侧背身回眸，突出背部线条和整体造型 8）坐地侧腿姿势，姿态慵懒但有攻击性 9）强气场封面感站姿，像时尚大片收尾图

Tokyo Night Travel Brand Mockup

travel magazine and mobile app promotional mockup · romantic Tokyo night travel branding · {argument name="brand name" default="旅色"} · TABIIRO · Tokyo Night Trip · luxury editorial design blended with modern travel app UI presentation · deep navy, black, warm gold, soft blush pink, white, city-light bokeh · cinematic nighttime glow with sparkling urban lights and warm highlights · elegant, romantic, aspirational, premium · glamorous adult East Asian woman in a fitted shimmering rose-gold long-sleeve evening dress, shoulder-length dark bob haircut, posed thoughtfully near a balcony railing overlooking Tokyo at night · high-rise terrace or rooftop with blurred skyline and Tokyo Tower visible · multi-panel marketing board showing print cover, double-page spread, website landing page, and smartphone app screen · magazine cover · top left · 1 · 旅色, Tokyo Night Trip, 東京の夜に。ときめく旅を。, Cover Woman TOKYOを旅する, Special Interview 東京の新しい魅力、再発見, 今行きたい 東京のスポット10選 · magazine spread · top center · 1 · Vol.56, 8, 東京の夜に、恋をする。, きらめく街と、特別な時間。, 見どころ, 01 絶景, 02 グルメ, 03 文化・体験 · weather and city info panel · top right · 1 · 現在の東京 リアルタイム天気, 27°C, 晴れのち曇り, 湿度: 62%, 風速: 2.1m/s, 体感温度: 28°C, 2024.5.20 15:00 更新 · smartphone app screen · right side · 1 · 旅色, 東京の夜に、ときめく旅を。, おすすめスポット, 特集, ホーム, 探す, 旅のしおり, お知らせ, マイページ · website landing page · bottom left and center · 1 · 旅色, 東京の夜に、ときめく旅を。, 心に残る体験を、旅色と一緒に。, 今すぐダウンロード, App Store からダウンロード, Google Play で手に入れよう, 旅色が選ばれる3つの理由, 厳選されたおすすめスポット, あなただけの旅プラン作成, リアルタイムの天気・情報, 人気のエリア · popular areas row · bottom center · 5 · 六本木, 浅草, 丸の内, 中目黒, お台場 · feature thumbnails on app · mid to lower right inside phone · 6 · 六本木ヒルズ展望台, 浅草寺, 中目黒の夜桜, ネオン街, 東京グルメ旅, 大人の東京さんぽ · reason icons row · bottom center upper · 3 · 厳選されたおすすめスポット, あなただけの旅プラン作成, リアルタイムの天気・情報 · bottom service features row · very bottom across website panel · 4 · 最新の観光情報をお届け, レビュー・口コミが充実, オフラインでも使える, 旅のしおりを簡単作成 · 2 · fine dining plate with wine in warm candlelit restaurant, smaller portrait of the same woman on a balcony with city lights · clean light tabletop or presentation board · overlapping printed pages and digital screens laid out like a branding case study · high-resolution commercial mockup · slightly elevated front view capturing all panels clearly · crisp typography, glossy print feel, realistic phone hardware, polished UI cards · {argument name="city" default="Tokyo"} · {argument name="main headline" default="東京の夜に、ときめく旅を。"} · {argument name="temperature" default="27°C"} · {argument name="dress color" default="rose-gold shimmer"}

Ultra-Photoreal Luxury Bar Editorial Portrait Prompt

{ "generation_request": { "meta_data": { "tool": "NanoBanana Pro", "task_type": "photoreal_bar_editorial_portrait", "version": "v1.0_LUXURY_BAR_GREEN_SATIN_DRESS_NO_TEXT_EN", "priority": "highest", "language": "en" }, "references": { "reference_image_face": { "source": "UPLOAD_REFERENCE_IMAGE (REQUIRED)", "purpose": "FACE_IDENTITY_LOCK", "strict_lock": true, "face_similarity_priority": "MAX", "no_identity_blending": true, "no_beautify": true, "no_age_shift": true, "preserve_skin_texture": true, "preserve_facial_proportions": true }, "reference_image_style": { "source": "UPLOAD_REFERENCE_IMAGE (OPTIONAL)", "purpose": "STYLE_COMPOSITION_ANCHOR", "strict_lock": false, "preserve_lighting": true, "preserve_palette": true, "preserve_vibe": true } }, "global_constraints": { "rating": "PG-13", "no_explicit_sexual_content": true, "no_nudity": true, "no_text": true, "no_logos": true, "no_watermark": true }, "output_settings": { "aspect_ratio": "4:5", "orientation": "portrait", "resolution_target": "ultra_high_res", "render_style": "ultra_photoreal_luxury_editorial", "sharpness": "crisp_but_natural", "film_grain": "very_subtle", "color_grade": "warm_amber_bar_lighting", "dynamic_range": "natural_not_hdr", "skin_rendering": "real_texture_no_retouch" }, "global_rules": { "camera_language": "35-50mm editorial bar portrait, full-body seated, shallow DOF, face + satin texture priority", "lighting_language": "warm amber/tungsten bar light, soft fill, satin highlights, no harsh flash", "authenticity_markers": "no AI glow/HDR, real skin texture, correct hands, clean anatomy, ID must match" }, "creative_prompt": { "scene_summary": "Photoreal luxury bar editorial portrait of the same adult woman (FACE EXACT match), seated on a bar stool in an upscale vintage cocktail bar. Backlit bottles on glass shelves (no readable labels), warm wood + marble bar. She wears an {argument name="dress color" default="emerald"}/olive green satin evening dress with a tasteful neckline and a high slit (no excessive cleavage). Crossed-legs seated pose, chic heels, minimal jewelry. Confident glamorous gaze. No text.", "wardrobe_and_style": { "outfit": "emerald/olive green satin evening dress, fitted bodice, high slit, elegant drape", "shoes": "neutral heels", "accessories": "minimal rings, delicate earrings", "makeup": "glam night makeup, soft smoky eyes, nude-rose lip", "hair": "sleek dark hair, soft bangs" }, "composition": { "framing": "full-body seated 4:5, face sharp, satin folds visible, background softly blurred", "background": "luxury bar shelves, bottles/glassware, no signag" } } }

Photorealistic Soft Grunge Y2K Mirror Selfie

{ "subject": { "description": "Young woman with long, wavy brown hair", "features": "Fair skin, winged eyeliner, soft makeup, neutral expression", "physique": "Slim build" }, "apparel": { "top": "Black ribbed sleeveless crop top", "bottom": "Black pleated mini skirt with a gothic grommet belt and hanging straps", "footwear": "White ankle socks with a small {argument name="graphic detail" default="Hello Kitty"} graphic" }, "accessories": { "jewelry": "Delicate gold chain bracelet, silver cross necklace", "tech": "Smartphone with a Hello Kitty phone case and stickers" }, "pose": { "action": "Taking a mirror selfie", "posture": "Kneeling on a bed, body angled slightly to the side", "gaze": "Looking towards the mirror/phone" }, "environment": { "setting": "Bedroom interior", "details": "Grey duvet/bedding, plain white walls, small window in background", "lighting": "Soft, diffused indoor lighting" }, "style": { "aesthetic": "Soft grunge, E-girl, Y2K fashion, kawaii accents", "quality": "Photorealistic, high resolution, social media aesthetic, sharp focus" } }

Operation Epic Furry Illustration Prompt

Draw an illustration that captures the essence of the war between Iran and the Uni…

AI Manga Nano Banana Pro

AI漫画　Nano Banana Pro 🍌

Y2K Denim-on-Denim Fashion Shot in Garden Setting

{ "subject": { "type": "Young woman", "appearance": "Fair skin tone, long wavy Brown hair with a center part, smiling expression", "face_detail": "Blue flower accessory tucked behind the left ear" }, "fashion": { "aesthetic": "Y2K denim-on-denim, monochromatic blue", "top": "Blue denim corset-style crop top with front lace-up detailing, worn with a matching blue cropped hoodie shrug", "bottoms": "Light wash wide-leg jeans with heavy distressing and rips on the thighs and knees", "footwear": "White and grey chunky sneakers with star design", "accessories": "Dark blue denim shoulder bag with a large silver buckle and chain strap held in hands" }, "environment": { "setting": "Outdoor garden entrance", "architecture": "Large black wooden archway gate with lattice sides", "text": "Gold '{argument name="brand name" default="RALPH LAUREN"}' lettering centered on the top of the arch", "flooring": "Red brick pathway arranged in a herringbone pattern", "landscape": "Lush green trees and manicured round topiary bushes on either side" }, "photography": { "style": "Influencer lifestyle shot, fashion photography", "framing": "Full-body shot, centered composition, eye-level angle", "lighting": "Soft natural daylight, even illumination", "quality": "High resolution, sharp focus, realistic" } }

Atmospheric Underwater Photography Template

A {argument name="mood" default="[MOOD]"} underwater photograph of a {argument name="subject" default="[SUBJECT]"} drifting through a {argument name="environment" default="[UNDERWATER ENVIRONMENT]"}, with {argument name="lighting effects" default="[LIGHT RAYS / BIOLUMINESCENCE / CAUSTIC PATTERNS]"} filtering through the water, captured in sharp 8k resolution with a color palette of [COLOR PALETTE].

Cel-Shaded Comic Strip Prompt for LOTR Poem

create a cute style cel shaded cartoon comic strip with textures that depicts the One Ring poem from LOTR.

Cinematic Sports Storyboard

Create a 9-shot cinematic storyboard for a {argument name="team name" default="Borussia Dortmund"} match intro TV broadcast animation. The sequence should feel like a high-end sports commercial blended with fantasy VFX and explosive motion design energy.

184-nano-banana-pro-on-gemini

A dramatic double exposure portrait of a professional football player, large side-profile face in black and white with intense expression, combined with a smaller full-body action shot of the same player running in a red jersey, dynamic motion, dust and smoke particles blending the layers, high contrast lighting, textured grain, minimal clean background, editorial sports poster style, ultra-detailed, sharp focus, cinematic composition, 8K resolution.

Cinematic Tropical Lagoon Travel Editorial Portrait

{ "generation_request": { "meta_data": { "tool": "NanoBanana Pro", "task_type": "photoreal_travel_boat_portrait_tropical_lagoon", "version": "v1.0_TROPICAL_LAGOON_LONGTAIL_BOW_PASTEL_DRESS_NO_TEXT_EN", "priority": "highest", "language": "en" }, "references": { "reference_image_style": { "source": "UPLOAD_REFERENCE_IMAGE (REQUIRED)", "purpose": "STYLE_COMPOSITION_LOCATION_ANCHOR", "strict_lock": true, "preserve_composition": true, "preserve_pose": true, "preserve_lighting": true, "preserve_palette": true, "preserve_vibe": true }, "reference_image_face": { "source": "UPLOAD_REFERENCE_IMAGE (OPTIONAL)", "purpose": "FACE_IDENTITY_LOCK", "strict_lock": true, "face_similarity_priority": "MAX", "no_identity_blending": true, "no_beautify": true, "no_age_shift": true, "preserve_skin_texture": true, "preserve_facial_proportions": true } }, "global_constraints": { "rating": "PG-13", "no_nudity": true, "no_explicit_sexual_content": true, "no_logos": true, "no_watermark": true, "no_readable_text": true }, "output_settings": { "aspect_ratio": "4:5", "orientation": "portrait", "resolution_target": "ultra_high_res", "render_style": "cinematic_photoreal_travel_editorial", "sharpness": "crisp_but_natural", "film_grain": "subtle", "color_grade": "bright_tropical_teal_water_clean_blue_sky", "dynamic_range": "natural_not_hdr", "skin_rendering": "real_texture_no_retouch" }, "creative_prompt": { "scene_summary": "Photoreal travel editorial portrait on the bow of a wooden longtail boat in a bright tropical lagoon. Water is vivid turquoise/emerald and crystal clear, with gentle ripples and sun sparkle. Background: dramatic limestone karst cliffs covered in lush greenery on both sides, creating a wide bay; a few distant boats are visible but small and unobtrusive.\n\nSubject: one adult woman sitting on the boat’s front deck (bow), centered lower frame. Pose: seated with one knee bent and the other leg extended along the wooden deck, one hand resting behind for support, the other relaxed on her thigh. Expression calm and dreamy, gaze slightly to the left.\n\nWardrobe: soft pastel pink off-shoulder knit mini dress with long sleeves (cozy texture), elegant and clean. Accessories: a single white tropical flower tucked behind the ear. Barefoot or minimal sandal; natural makeup.\n\nLighting: strong midday sun with clean, realistic shadows; natural highlights on skin and water; clear blue sky.\n\nImportant: REMOVE/AVOID any readable lettering or painted text on the boat; keep the wooden deck clean or make markings abstract/unreadable. No text anywhere in the image. Maintain realistic skin texture, fabric knit detail, and cinematic tra

Close-Up Portrait with Facial Reference and Glasses

Close up portrait using my facial reference image. Keep my face exactly as in the reference. Do not alter facial structure, eyes, nose, mustache, or skin texture. Add round black glasses, warm indoor restaurant lighting, soft diffused shadows, straw ceiling decor, candid expression, natural skin texture. Use 1:1 aspect ratio.

Retro Man-Eating Planaria Dossier

retro Japanese cryptid field-guide poster / tabloid monster dossier · dense 1970s pulp magazine layout, black distressed paper background, red and yellow emergency typography, grainy halftone printing, weathered borders, pseudo-scientific annotations, horror documentary mood, high-detail grotesque creature art, noisy tactile textures · 新発見!?, 謎の超生物を追え!!, UMA FILE.27 · 未確認生物大図鑑 · {argument name="headline text" default="人食いプラナリア"} · 強酸性体液で人間を溶かして食べる恐怖の生物! · {argument name="creature name" default="人食いプラナリア"} · giant translucent black-brown flatworm, glossy wet body, ruffled edges, two small black eye spots, circular gaping mouth, amber vein-like internal pattern, sluglike body crawling over wet rocks · the monster leans forward and vomits or secretes foaming acidic fluid onto partially dissolved prey remains in a dark muddy riverside scene · 強酸性体液の威力により人体を数分で溶解する! · left of main creature · Japanese explanatory column describing sightings in lakes and rivers across Japan, the creature being mistaken for a leech, and its acid secretion, feeding and regeneration abilities · 1 · 人食いプラナリアの特徴 · upper right · 1 · anatomical side-view illustration of the translucent creature with 6 callout labels · 眼点（光を感知）, 化学感覚器官（獲物の体臭を感知）, 強酸性体液腺（口周辺より噴出）, 咽頭（反転して獲物を吸引）, 粘液層（自己防御のバリア）, 消化腔（溶解した肉を吸収） · 体内構造（断面図） · right middle · 1 · cross-section diagram showing red-black internal organs inside the flatworm · 粘液層, 酸性溶腺, 分岐消化腔, 神経系, 再生細胞群 · 基本データ · right middle below cross-section · 6 · 分類：扁形動物？（詳細不明）, 生息地：淡水（湖・沼・河川）, 体長：3〜30cm（確認例）, 体色：黒褐色〜灰白色, 食性：肉食（人間を含む動物）, 危険度：★★★★★ · 目撃レポート · lower left inset · 1 · small grainy black-and-white lakeside photograph with a lone human figure and report text dated 1978年8月 · 捕食方法 · lower left wide strip · 4 · 1 獲物を感知, 2 強酸性体液の噴出, 3 肉を溶解, 4 吸収・摂食 · four numbered illustrated panels showing detection, acid spray, dissolving flesh, and feeding · サイズ比較 · bottom left · 2 · ruler comparison showing a specimen about 30cm long, human hand comparison holding a small specimen · 目撃情報が相次ぐ! · bottom center · 1 · map of Japan with many red sighting markers, a list of sighting years and locations, plus a tiny lakeside photo · 全国で目撃情報が後を絶たない!! · 驚異の再生能力! · right lower middle · 4 · 切断直後, 数時間後, 数日後, 新たな個体に! · four sequential regeneration illustrations showing one worm cut into two, then two pieces becoming four, then multiplying endlessly · 1匹が2匹に、2匹が4匹に…無限に増殖する恐怖!! · 遭遇したらどうする!? · bottom right · 1 · warning panel with a blurred human silhouette near water and a giant flatworm, red alarm text and four safety bullets · 絶対に素手で触るな!!, もし見つけても刺激するな!, 水に入る時は足元に注意せよ!, 噛まれると、数分で肉が溶ける!!, 逃げても追いかけてくることがある!! · {argument name="footer warning" default="人食いプラナリアは、すぐそこにいるのかもしれない…。"} · dirty black, aged cream, hazard yellow, deep red, muddy brown, gray-green water highlights · create a single vertical information-dense poster, extremely sharp but intentionally grainy, with realistic wet creature texture, distressed print edges, Japanese text blocks, boxed diagrams, arrows, warning stars, and dramatic horror-science composition

Cinematic Scene of a Man with Roses on a Wet City Street

confident man in an elegant black suit and overcoat, wearing sunglasses, standing on a wet city street after the rain. he is holding a huge bouquet of {argument name="flower color" default="red"} roses in one hand and talking on the phone with the other. reflections on the pavement, tall classic european buildings in the background, moody cloudy sky, cinematic urban atmosphere, luxury and sophistication.

Dunhuang Mural Water Moon Guanyin

请以 【{argument name="核心角色" default="水月观音"}】 为核心，创作一幅 敦煌壁画风的高端艺术画作。画面采用 圆光月轮中心构图，以主体角色为唯一主视觉核心，表现其 游戏坐姿、俯瞰澄水 的神圣瞬间。整体氛围应为 空灵、幽静、圆满，具有博物馆级审美、文化厚度与收藏级艺术感。 主体形象要求： 主体角色应呈现出优雅庄严、修长华贵、神性强烈的气质，姿态舒展，具有鲜明的敦煌壁画式神圣性与仪式感。面容需静穆、圣洁、含蓄、不可侵犯，带有敦煌壁画中神女 / 菩萨 / 飞天式的庄严气质，而不是普通古风美女。 发髻高挽，佩戴复杂精美的 金饰发冠、珠链步摇、耳饰、璎珞、臂钏、腰饰，服饰华丽，衣纹流畅，线条细劲有力，富有飞天韵律与宫廷级壁画质感。衣袂、飘带、裙摆与袖口应形成富有节奏感的流动曲线，强化神圣升腾感与画面韵律。 用金结构要求： 画面需强化 结构性用金，不是零散点金，而是形成明确的奢华秩序： 主体角色的发冠、首饰、衣缘、袖口、腰封、飘带边线、裙摆纹样采用 描金、泥金、鎏金、金线刺绣、残损金箔痕迹； 核心神圣元素，如月轮 / 佛光 / 法轮 / 宝盖 / 莲台、云纹、莲花花瓣、宝相花、藻井纹饰、团花纹、边框装饰也应带有 清晰可见但克制高级的金色装饰； 整体呈现 金碧辉煌但不俗艳、富丽精工但不廉价 的效果，表现出历经千年风化后仍保有金碧辉煌余韵的 残损奢华感。 色彩要求： 色彩以 赭红、朱砂、青绿、石青、石绿、土黄、象牙白 为主，辅以克制精致的 土金、鎏金。 整体色调要 浓郁、浑厚、古雅、贵气，避免轻飘糖水色。 背景可采用 暗金矿物底色 氛围，如深邃石青天幕 / 温润古壁底色 / 暗金矿物底色与古壁肌理结合，衬托出主体的神圣与尊贵。 装饰元素要求： 画面可融入 飞天、莲花、宝相花、藻井、祥云、伎乐、团花纹、楼阁宫阙、法器、圣光圆轮、古典边框装饰 等典型敦煌视觉语言，但必须围绕主体集中分布，层级清晰，避免平均铺满全画面。 陪衬人物控制在 1位 即可（善财童子），作为礼赞与陪衬，分布在主体周围或下方，形成朝向主体的仪式感动势。她们可陪衬动作，如持莲花 / 奏琵琶 / 吹笛 / 奉花 / 托灯 / 执幡，线条轻盈流动，与主体形成呼应，但不可喧宾夺主。 空间与构图要求： 构图中应保留适度的 云气空间、圣光留白、月光或天幕留白，让画面有呼吸感。 核心神圣元素需醒目、庄严、圆满，周围可有 鎏金光晕、圣光圆轮、细密金线轨迹，强化主题的神圣性。 远处可点缀远景元素，如月宫楼阁 / 云中宫阙 / 佛国建筑 / 仙界天幕，但不可过多，以增强空间层次与仙界气息。 材质表现要求： 需强调古老石窟壁画与矿物颜料肌理： 可见 斑驳、裂纹、风化、轻微剥落、历史包浆、粉化边缘、古壁肌理； 同时保留局部 描金、残损金箔、磨蚀后的鎏金光泽，形成 “旧而贵、残而华、古而神圣” 的高级艺术质感。

Cinematic Editorial of a Young Man Leaving a Café

Ultra-realistic, full-body portrait of the same young man (ensure strict facial consistency with prior reference), captured mid-step as he walks out through the glass doors of a modern café. His body is slightly angled forward, with one leg stepping ahead naturally, conveying motion. He holds a takeaway coffee cup in his left hand close to his chest, while his right hand rests casually inside his pocket. A black backpack hangs effortlessly over one shoulder. His head is turned slightly to the side, gaze directed away from the camera, with a calm, confident, and composed expression. He is dressed in an oversized red t-shirt, black cargo pants, black-and-white sneakers, and a minimal thin chain necklace, styled in a contemporary urban fashion aesthetic. The background features glass doors with visible Starbucks signage and logo, with warm indoor lighting spilling outward. The café interior appears softly blurred, creating depth, while natural daylight illuminates the subject from outside. Shot with a 50mm lens, shallow depth of field, cinematic composition, realistic lighting and shadows, high dynamic range, and ultra-detailed textures. Aspect ratio: 4:5 Resolution: 8K Style: photorealistic, cinematic, editorial fashion photography

Detailed Structured Prompt for Photorealistic Image Generation on a Train

{ “相机”：{ "angle": "稍低的角度", “光圈”：“f/2.8”， "composition_rule": "对角线构图", “距离”：“中距离”， "focus": "选择性焦点", “framing”：“中景”， "height": "低于眼睛水平", “镜头”：“35mm”， "perspective": "正常视角" }, “自定义指令”：“”， “环境”：{ “位置”：“室内”， "props": "金链青色手提包、白色手机充电器、黑色旅行包", "setting_details": "在现代客运列车内，坐在大窗户旁边的深色织物座椅上。" }, “照明”：{ "facial_shadows": "由于面罩和柔和的灯光，面部阴影最小化。在她的脸和脖子的右侧，远离窗户光线，可以看到微妙、柔和的阴影，创造出柔和的轮廓。", "key_light": "来自框架右侧大窗户的柔和、漫射的自然光。", “心情”：“平静而安详”， "shadow_direction": "从右到左", "shadows": "呈现柔和、扩散的阴影，边缘柔和。来自窗户的主光在拍摄对象身体的左侧投射出微妙的阴影，特别是在她的躯干和衣服的褶皱处。在座位和火车内部也可以看到柔和的阴影，增强了深度感。", “风格”：“自然光”， "time_of_day": "白天" }, “否定提示”：[ “模糊”， “扭曲的特征”， “糟糕的解剖结构”， “不自然的姿势”， “水印”， “文本”， “低分辨率”， 「卡通风格」 ], “质量目标”：[ “照片级写实”， “高细节”， “柔和的自然光”， “主题清晰、尖锐”， “逼真的织物纹理”， “平静祥和的气氛” ], “风格”：“真实感”， “主题”：{ "age_bracket": "年轻人", “身体”：{ "accessories": "带小吊坠的银项链、小耳环、戒指、金色胸针、白色面罩", "body_orientation": "四分之三视图", "hand_position": "手轻轻地放在腿上，与相机保持中等距离。", "hold_item": "无", "leg_position": "双腿在大腿上部交叉并向前伸展，位置比躯干更靠近相机。", "pose_details": "靠在座椅上，头偏向一侧，看起来像是在休息或睡觉。她的身体与镜头成一定角度，营造出轻松自然的姿势。", “姿势”：“坐” }, "body_curves": "修长的曲线，优雅的轮廓。构图突出上半身匀称，曲线分明，上半身优美。下半身修长的双腿，轮廓流畅，腿部线条优美。", "body_proportions": "身材修长，身材比例匀称。这个姿势强调了她的双腿相对于躯干的比例。", “类别”：“旅行者”， "description": "火车上，一位时尚的黑发年轻女子舒适地坐在座位上，头向后仰，仿佛在睡觉。", “脸”：{ “表情”：“轻松、平和”， "eye_camera_relationship": "不适用，因为眼睛是闭着的。头部向后倾斜并远离相机镜头，处于休息状态。", "eye_color": "不可见", "eye_contact": "无", "eye_expression": "闭上的眼睛传达出一种平静的休息状态，有助于营造安详平静的心情。", "eye_shape": "不可见", “眉毛”：“修饰得当且轻轻拱起”， “凝视”：“闭上眼睛”， "gaze_direction": "闭上眼睛", "gaze_intensity": "平静", “妆容”：“自然简约” }, "gender_presentation": "女", “头发”：{ “颜色”：“深棕色”， “style”：“从脸上向后拉，用黑色蝴蝶结固定” }, “体格”：“苗条苗条”， "skin_tone": "公平", “衣柜”：{ "bottom": "黑色短裙和黑色袜子", “颜色”：“黑色”， "fabric": "夹克是粗花呢，上衣是精致、轻质的针织品，裙子是皮革般的，袜子是精致、优质的材料。", “outerwear”：“带有金色胸针的黑色花呢夹克”， "patterns": "这件夹克具有花呢纹理；所有其他服装都是纯色的。", “style”：“优雅别致”， "texture": "外套有质感，裙子光滑略带光泽，上衣细腻柔软，袜子光滑。", “top”：“黑色长袖合身高领上衣” } } }