Ai Image Prompts
产品介绍
从包含10,000+真实图像生成提示的精选库中推荐提示。兼容任何AI图像模型,包括Nano Banana Pro、Nano Banana 2、Seedream等。
资源信息
许可证信息摘自官方源,可能过时或缺失。商用前请以原仓库的 LICENSE 文件为准。
提示词库 · 2.3万
数据源:社区提示词库(MIT 许可,每日同步)共 15141 条提示词,按 11 个用途归类;同一条可归入多个用途,因此分类条数相加会大于去重后的总数。
命中 702 条
Cinematic Android in Nature
comic-storyboardA cinematic prompt for Nano Banana Pro used to generate an android character set against a lush, natural meadow background.
展开提示词全文
Cinematic {argument name="character" default="Android"} in {argument name="setting" default="Meadow"}
Editorial Nurse in Opulent Salon
comic-storyboardA high-fashion editorial portrait of a nurse in a white ensemble, set in a gold-damask luxury salon with classical decor.
展开提示词全文
Inside an opulent salon wrapped in golden damask and rich parquet, an aura of quiet defiance takes hold. A close-up of a poised young {argument name="subject" default="nurse woman"} commands the room with an unwavering gaze and heavy-lidded confidence, sitting on a {argument name="furniture" default="old red armchair"}. She wears a {argument name="outfit" default="white crop top, a white skirt with white stockings and white high heels with red cross on it, and a nurse hat with red cross on it"}. Her tailored ensemble and delicate lace textures contrast sharply against the heavy heritage decor. Warm amber directional light sculpts her features and drapes across the scene with luminous clarity. Antique marble fireplaces and receding classical rooms dissolve into a painterly palette of warm umber and gold. A huge golden painting of Delacroix is hanged from floor to ceiling on backdrop.The scene captures pure editorial power where timeless tradition meets fierce contemporary self-possession.
Velvet Afterlight System Prompt
comic-storyboardA sophisticated system instruction set for creating painterly, anime-styled image prompts with specific lighting and relational focus.
展开提示词全文
VELVET AFTERLIGHT Rewrite the user’s text, image, or both as one prompt for GPT Image Gen V2 or Nano Banana Pro. Use GPT unless Nano is named. Preserve language, exact text, and requested or source ratio. Use three systems. Relation Chamber organizes one gaze, reach, contact, reflection, path, or shared-light relation through height, posture, dark framing masses, and an open interval. Painted Cel Register uses age-appropriate anime anatomy, thin colored contour, broad hand-painted values, grouped hair, selective soft transitions, and material-specific highlights. Afterlight Veil uses one cool rear or side source, narrow edge illumination, weak returned fill, localized violet-blue halation, and selective contour loss. Preserve subject, count, identity, action, setting, clothing, objects, colors, text, and references. For edits, preserve unrequested content. Choose one exact moment and one relational axis. Height, reach, gaze, support, and contact need physical causes. Keep one open interval and one quiet region. A single subject relates to an object, light, reflection, threshold, shadow, or off-frame target rather than gaining an invented companion. Use thin indigo, plum, brown, or charcoal contour. Strengthen line at eyes, hands, seams, rims, and overlaps. Reduce it on bright edges, soft face planes, distant forms, mist, and dark-on-dark contact. Use two to four value groups with selective airbrushed transitions. Do not use uniform outlines, vector edges, plastic skin, or smooth 3D rendering. Hair uses one large mass, secondary locks, and limited strands. Materials retain separate responses. Edge light appears only on source-facing contours and breaks under occlusion. Returned light reveals selected face, hand, garment, or object planes and remains weaker than the direct source. Bloom stays near real bright edges. No complete glowing outline, global purple filter, random particles, or full-frame blur. GPT: return 500 to 800 words in five paragraphs covering scene, subjects, relation, painted construction, light, transitions, composition, references, text, and failures. NANO: return JSON only, 1000 to 1800 tokens, using “aspect_ratio”, “references”, “scene”, “subjects”, “relation_chamber”, “painted_cel_register”, “afterlight_veil”, “transitions”, “composition”, “surface_and_palette”, “text”, “avoid”. Omit unused fields. No metadata, IDs, weights, comments, or repetition. Return only the finished prompt.
Surreal Flamingo in Tutu
comic-storyboardA detailed surrealist illustration of a flamingo wearing a voluminous ruffled tutu on a checkered floor, set in a moody vintage atmosphere.
展开提示词全文
A black and white, highly detailed, surrealist illustration depicts a {argument name="animal" default="flamingo"} standing on a checkered floor. The {argument name="animal" default="flamingo"}'s body is adorned with a voluminous, ruffled {argument name="clothing" default="tutu"}, resembling layers of delicate fabric. Its long, slender legs are visible beneath the {argument name="clothing" default="tutu"}, and its neck is gracefully curved, with its head turned to the side. The background is dark and atmospheric, with hints of abstract shapes and textures, suggesting a dreamlike or theatrical setting. The overall mood is elegant and slightly melancholic, with a vintage aesthetic due to the grainy texture and dark, moody lighting.
The Cat CEO Office Interview
comic-storyboardA deadpan humor prompt featuring a tiny orange cat sitting in a CEO chair interviewing humans in a futuristic skyscraper office.
展开提示词全文
{
"title": "The Interview",
"scene": "A luxurious corporate office on the 98th floor overlooking a futuristic city.",
"subject": "A tiny orange cat sits confidently in a CEO chair while six nervous humans wait across the table for their interview.",
"detail": "One human's resume reads '12 years experience.' The cat slowly pushes it aside without looking.",
"image_text": "\"Next.\"",
"atmosphere": "deadpan humor, cinematic, premium aesthetic",
"style": "hyper realistic, Hollywood movie still, ultra detailed, Roger Deakins lighting, 8K"
}
Cinematic Train Station Traveler
comic-storyboardA wide-angle cinematic prompt depicting a man with a vintage suitcase at a misty mountain train station, featuring moody atmospheric lighting and god rays.
展开提示词全文
A realistic, wide-angle cinematic shot from behind a man standing on a wet outdoor train station platform, looking toward a vintage passenger train on the tracks. He is wearing a black beanie, a dark winter jacket, dark trousers, and a backpack, holding a worn brown vintage leather suitcase at his side. On the left side of the frame stands an old brick and wooden train station building with a weathered sign reading "MOUNTAIN PASS STATION". To the right of the station, an old, slightly rusted passenger train sits on the tracks, its windows softly illuminated with warm glowing orange interior light. In the background, dramatic, towering mountain peaks are surrounded by dense fog and low clouds, with visible sunbeams (god rays) piercing through the misty overcast sky. The ground is damp with small puddles, fallen autumn leaves, and overgrown weeds along the tracks. Moody, cool color palette, cinematic lighting, 35mm lens photography, 8k resolution. Recommended Parameters Aspect Ratio: 16:9 Style: Photographic, Cinematic, Moody Lighting: Atmospheric, God rays, Soft backlighting. A realistic, wide-angle cinematic photo of a young man walking along an outdoor train station platform in a dramatic mountain landscape. He is wearing a dark blue winter parka coat with a hood, dark pants, sturdy boots, and a backpack, carrying a classic brown vintage leather suitcase in his hand. To his right, a vintage green and beige passenger train is stopped along the tracks, with warm yellow light glowing inside the train windows. The stone train station has a vintage sign that reads "OCN". In the background, towering, rugged alpine mountains are shrouded in atmospheric low-hanging mist and clouds. Soft, diffuse morning sunlight breaks through the foggy air, casting gentle highlights on the damp platform and wet train tracks. Moody, cool color palette with high cinematic realism, subtle cinematic grain, 35mm lens,depth of field 8k resolution.
Colored Pencil Meadow Landscape
comic-storyboardA serene colored-pencil style prompt depicting a couple walking through a field of blue cornflowers at sunset.
展开提示词全文
A vibrant colored-pencil illustration in portrait orientation. A young couple walks hand in hand away from the viewer along a narrow winding path through a vast field of vivid blue cornflowers (Centaurea cyanus) in the foreground, among tall golden-yellow grass, with stems and buds interspersed. The woman wears a flowing white dress, the man a white shirt with rolled-up sleeves and dark trousers, their heads tilted gently toward each other. Gentle rolling hills stretch toward the horizon. A soft summer breeze bends the grass and flowers as the evening light falls across the scene. In the distance, sunlight peeks over warm amber fields. The sky fills the upper third and is colored from deep dusky blue at the top down to warm shades of orange, gold, and pale yellow near the low sun, with soft wispy backlit clouds. The perspective is wide and slightly elevated, showcasing the detailed cornflowers, the couple, and the expansive sunlit meadow. The style is reminiscent of colored pencil art, with visible textures creating a soft, serene mood. The overall atmosphere is peaceful, romantic, and nostalgic, with warm golden tones contrasting against the cool electric blue of the flowers. A vibrant colored-pencil illustration in portrait orientation. A vast field of vivid blue cornflowers (Centaurea cyanus) blanketing the foreground, among tall golden-yellow grass, with stems and buds interspersed. A narrow winding dirt path meanders through the flowers toward the distance. A soft layer of morning mist and light haze drifts gently over the field and the far shore, softening the horizon. Beyond the field, a serene ocean stretches to the horizon, where a single sailboat drifts gently on the still water. The water reflects the warm glow of the sky. The sky fills the upper third and is colored from deep dusky blue at the top down to warm shades of orange, gold, and pale yellow near the low sun, with soft wispy backlit clouds. The perspective is wide and slightly elevated, showcasing the detailed cornflowers, the misty meadow, and the expansive calm seascape with the distant sailboat. The style is reminiscent of colored pencil art, with visible textures creating a soft, serene mood. The overall atmosphere is peaceful, dreamy, and nostalgic, with warm golden tones contrasting against the cool electric blue of the flowers.
Aerial Surreal Clone Photography
comic-storyboardA complex prompt for creating an aerial high-angle view of a central subject surrounded by identical clones walking in various directions.
展开提示词全文
Transform the uploaded person into a premium ultra-realistic surreal clone-photography scene. Create an aerial high-angle view of the same person standing completely still in the center of a large empty street or pathway while multiple identical copies walk around them in different directions.
IDENTITY LOCK
Use the uploaded image as the only identity reference. Preserve the exact recognizable face, facial structure, hairstyle, skin tone, eyebrows, eyes, nose, lips, jawline, hair texture, facial proportions, age, and overall appearance. Every clone must clearly be the same person. Do not change or redesign the identity.
CENTRAL SUBJECT
The central person remains perfectly sharp and motionless, standing confidently with both hands in the pockets. Dress them in {argument name="sweatshirt color" default="RED / PINK / ANY COLOR"} oversized sweatshirt, black loose pants, and white sneakers. The central figure is the primary focal point.
CLONES
Create numerous identical copies of the same person wearing the exact same outfit and maintaining the same identity. Position the clones walking naturally in different directions around the central subject. Use varied walking poses and distances to create a believable repetitive “NPC crowd" effect. Moving clones may have controlled directional motion blur while the central subject stays completely sharp.
ENVIRONMENT
Large empty tiled street or pathway in an understated urban outdoor setting. Minimal distractions. Clean architectural surroundings. Realistic pavement textures. Spacious composition with strong depth and perspective.
CAMERA & COMPOSITION
Aerial high-angle perspective looking downward. Compressed cinematic perspective. Tilt-shift depth effect. Central subject positioned precisely in the middle with surrounding clones creating a radial visual flow. Strong negative space around the group.
LIGHTING & STYLE
Soft natural sunlight. Warm neutral tones. Subtle atmospheric haze. Realistic shadows. Cinematic depth of field. Gentle film grain. Hyper-realistic skin texture. Natural proportions. Street photography mixed with luxury fashion editorial aesthetics. Surreal identity concept. Premium cinematic color grading. Ultra-detailed 8K quality.
VISUAL HIERARCHY
Central subject = sharp and still.
Surrounding clones = moving and slightly blurred.
Background = clean and atmospheric.
The contrast should communicate loneliness, individuality, and calmness while everything around the subject remains in motion.
Japanese School Uniform Classroom Portrait
comic-storyboardA photorealistic portrait of an East Asian woman in a traditional Japanese sailor school uniform sitting in a sunlit classroom.
展开提示词全文
A young {argument name="subject" default="East Asian woman"} with a short black bob haircut and straight bangs, fair skin, and a soft neutral expression looking directly at the camera. She is wearing a classic Japanese sailor-style school uniform (seifuku): short-sleeved white blouse with a navy blue sailor collar, {argument name="ribbon color" default="red"} ribbon necktie, and a long {argument name="skirt color" default="navy blue"} pleated skirt. She is sitting on a polished wooden classroom floor, leaning slightly against the wall under tall windows with cream curtains, one hand resting on the floor for support, legs folded to the side. Soft natural sunlight streams through the windows, casting bright geometric patches of light and long shadows across the warm wooden floorboards. Rows of empty wooden desks and chairs in the background, traditional Japanese classroom interior, shallow depth of field, photorealistic, natural skin texture, soft cinematic lighting, high detail, 85mm lens look
Fairy on Robotic Vacuum Ink Painting
comic-storyboardA unique Gongbi-style ink painting prompt featuring a Tang Dynasty fairy standing on a modern robotic vacuum cleaner.
展开提示词全文
A traditional Chinese Gongbi ink and color painting on aged, textured rice paper. A {argument name="character" default="fairy"} in elaborate Tang dynasty robes of red, beige, and teal ribbons, with a peony flower in her high hair bun, is standing on a {argument name="modern item" default="circular black robotic vacuum cleaner"}
Subterranean Cathedral and Mechanical Whale
comic-storyboardCinematic prompts for generating ethereal scenes involving forgotten cultures in ice cathedrals or mechanical creatures in surreal deserts.
展开提示词全文
Ultra-sharp cinematic still of four women from different forgotten cultures standing in perfect silence inside a vast subterranean cathedral carved entirely from living black ice, their traditional garments fused with crystalline armor that refracts frozen starlight, each woman holding a different glowing fragment of a shattered constellation map, dramatic volumetric god-rays piercing through fractures in the ice ceiling, anamorphic lens flares, hyper-detailed frost textures on skin and fabric, shallow depth of field, filmic color grade with deep cyan and amber highlights, 8K, photorealistic, never-before-seen composition. Ultra-sharp cinematic wide shot of a solitary colossal mechanical whale suspended mid-air above an endless desert of shattered porcelain plates, its brass and glass body slowly leaking liquid time that freezes into cascading hourglasses mid-fall, the whale’s eye reflecting an inverted sky filled with slow-motion lightning, dramatic side lighting with long shadows and volumetric dust, anamorphic bokeh, hyper-detailed rivets and cracked ceramic ground, film grain, 8K, photorealistic, never-before-seen perspective.
Felt Frog Diorama Beach
comic-storyboardCreates a whimsical, handmade diorama scene of a felt frog enjoying a day at the beach with intricate craft-style details.
展开提示词全文
A felt frog wearing {argument name="clothing" default="blue polka-dot swim trunks"} stands on a {argument name="setting" default="sandy beach"}. The frog is in the center of the frame, facing forward with a wide smile. The ocean with blue and white waves is behind the frog, and a {argument name="background object" default="small red boat"} is visible in the distance. The sky is a bright blue with fluffy white felt clouds. To the right of the frog, there are palm trees, a beach umbrella, a striped towel, and various shells and driftwood scattered on the sand. The overall scene is a whimsical, handmade diorama of a frog enjoying a day at the beach.
提示词模型无关,可直接用于 Midjourney / DALL·E / Flux / Stable Diffusion 等任意文生图模型。
信息边界说明
本页信息摘自官方文档,仅作技术信息呈现,不代表本站的判断或推荐。价格、配额、可用性以官方最新说明为准。你离开本站后的任何行为(申请 Key、付费、部署、商用),本站不做任何承诺与担保。
同类推荐
视频短视频图片音乐音频配音口播数字人全能创作
官方标注收费通过同一个AI创作工具完成AI图片、视频、音乐与语音创作,查找公开社交数据,编辑视觉成果,并集中查看和管理生成资产。Beatra 全能创作支持AI图片生成(文生图)、AI视频生成(图生视频)和AI视频编辑,通过AI音乐生成把想法做成歌曲或纯音乐,也可用AI语音生成(文字转语音)、多语言旁白和AI语音克隆完成跨媒介内容;还能查找抖音数据、小红书数据,以及 YouTube、TikTok、Instagram 与 X 上的公开帖子、笔记、评论、账号和趋势,把社交媒体数据用于竞品调研和创作。它是一款面向AI内容创作与多模态内容创作的AI创作套件,用起来就是一个把图片、视频、音乐与语音收在同一处的AI创作助手,适用于社交内容、产品展示、营销素材、课程、播客、短片和跨媒介项目;还能在不同媒介间复用原始素材、已有成果和查到的公开资料,查看制作进度、返回文件、实际用量和积分记录。
AI数字人口播与虚拟主播视频
官方标注收费用一张人像和一段短脚本或语音,制作有明确讲述内容的数字人口播视频。可使用现成录音,也可以先选择音色,把脚本生成旁白,让画面中的人物随声音完成稳定、自然的口播。适合 AI 主播、虚拟主播视频、数字人讲解、让照片说话、照片说话视频、产品讲解视频、数字人培训视频、公告和社交口播,并在交付后检查人物一致性、声音清晰度、口型同步和动作稳定性。
罗斯蒙德可视化图形生成
官方未说明【罗斯蒙德可视化图形生成】南京罗斯蒙德基于已交付项目沉淀的可视化图形生成场景:根据业务描述或系统需求,自动生成可编辑的架构图、流程图、ER 图、时序图、状态图与 C4 图。采用「统一图模型」一次建模、多格式输出:结构化文本(Mermaid / PlantUML,可嵌入 Markdown、进 Git 版本管理)、可编辑图形文件(drawio / Excalidraw,可拖拽修改节点与样式)、静态图(SVG 自渲染,PNG 给转换命令),并输出图形说明(图的含义 + 关键节点解释)。内置样式系统统一配色与命名,内置布局引擎自动排布,校验脚本拦截孤立节点、悬挂连线与语义缺漏。触发词:画架构图、画流程图、画 ER 图、画时序图、画状态图、C4 图、系统架构图、部署架构图、数据流程图、实体关系图、生成 drawio、生成 Excalidraw、导出 mermaid、导出 PlantUML、导出 SVG、导出 PNG、可编辑的图、图转可编辑、架构图可编辑、流程图二次修改、画图、出图、画个图。
架构图一键生成
官方标注收费需申请 Key使用 ContextWeave 生成或修改架构图、流程图、思维导图和复杂信息图。适用于需要从代码、文件或自然语言中提取结构与关系并实际产出 CW、SVG、HTML、可编辑 PPTX 或原生 VSDX 的请求;未特别说明时,PPTX 与 Visio 使用原生形状和连接器导出。不适用于统计图表、手绘插画或像素级排版。
AI Image Prompts · 绘画提示词库
官方标注免费Recommend curated prompts from a 10,000+ real-world image generation prompt library. Works with ANY AI image model — Nano Banana Pro, Nano Banana 2, Seedream 5.0, GPT Image 1.5, Midjourney, DALL-E 3, Flux, Stable Diffusion, and more. Use this skill when users want to: - Find proven image generation prompts (any model) - Get prompt inspiration for portraits, products, social media, posters, etc. - Create illustrations for articles, videos, podcasts, or marketing content - Browse categorized prompt templates with sample images - Translate and understand prompt techniques
架构图一键生成
官方标注收费需申请 Key使用 ContextWeave 生成或修改架构图、流程图、思维导图和复杂信息图。适用于需要从代码、文件或自然语言中提取结构与关系并实际产出 CW、SVG、HTML、可编辑 PPTX 或原生 VSDX 的请求;未特别说明时,PPTX 与 Visio 使用原生形状和连接器导出。不适用于统计图表、手绘插画或像素级排版。
什么是技能
技能(Skill)是封装好的单项能力,比如文字识别、文档摘要、关键词提取。开发者把调用逻辑和提示词打包,使用者像用插件一样加载即可,无需了解底层模型。启枢技能 收录大量技能,可直接试跑或编入方案。