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
Neo-Noir Sci-Fi Sky Portrait
comic-storyboardA cinematic neo-noir prompt featuring a low-angle portrait with massive negative sky space and a shearling-collar coat.
展开提示词全文
Create a low-angle neo-noir sci-fi still, chest-up portrait of a person with a {argument name="gaze" default="slight upward gaze"}. Place the subject in the lower-right third, leaving vast negative space with about 80 percent empty sky above. The subject wears a {argument name="coat" default="matte shearling-collar heavy coat"} over a dark knit sweater in a desaturated olive and charcoal palette. The background is a {argument name="sky" default="blank, overcast sky"} with subtle haze. Use soft ambient daylight with negative fill on camera-left. Use image for face reference.
Dark Fantasy Paladin Duel
comic-storyboardA cinematic dark fantasy prompt depicting a paladin facing off against a terrifying shadow creature in a rainy, cursed forest.
展开提示词全文
A {argument name="warrior" default="heavenly paladin"} stands in a {argument name="setting" default="muddy clearing inside the cursed forest"} with his longsword raised in a defensive stance. A terrifying {argument name="monster" default="shadow creature"} with glowing red eyes has landed several meters in front of him, crouched low like a predatory beast with elongated claws and a twisted humanoid body. Rain pours heavily as thick fog swirls around them. Ancient dead trees surround the clearing while tension fills the air moments before the battle begins. Ultra realistic medieval dark fantasy, cinematic lighting, heavy rain, volumetric fog, photorealistic, terrifying atmosphere, highly detailed armor, 16:9.
Handcrafted Paper Diorama Transformation
comic-storyboardAn image-to-image prompt that converts a portrait into a whimsical, layered paper-craft diorama.
展开提示词全文
Transform the {argument name="input" default="uploaded portrait"} into a {argument name="style" default="whimsical handcrafted paper diorama illustration"} with a soft cute aesthetic. Reimagine the people using {argument name="elements" default="simplified layered paper shapes, rounded forms, and minimal facial details"} suitable for paper craft art. Preserve the affectionate pose and emotional warmth of the original image while giving everything a charming handmade appearance.
Cinematic B&W Noir Rain Portrait
comic-storyboardA high-contrast graphic noir portrait of a figure in heavy rain, based on a face reference for character consistency.
展开提示词全文
A stunning cinematic black and white portrait of a {argument name="subject" default="young male figure"} standing alone in {argument name="weather" default="heavy rain"} at night, shown in three-quarter profile with head bowed slightly downward and gaze directed downward — expression heavy, melancholic, and deeply introspective, conveying quiet grief or solitary burden. He wears a {argument name="clothing" default="dark leather jacket"} with a high structured collar turned up slightly at the neck, layered over a dark turtleneck or base layer — the jacket surface catching rain droplets and glistening with wet leather texture. His dark curly-wavy hair is soaking wet, matted and sculpted by the rain against his forehead and temples. The rain falls heavily and dramatically throughout the entire frame — individual rain streaks rendered sharp and bright against the near-black background, falling at a very slight diagonal angle, some streaks motion-blurred into bright vertical lines while others are frozen as individual droplets. The rain is the dominant visual texture of the entire image — filling every inch of the dark background with bright falling streaks creating an almost graphic, painterly quality. The lighting is a single cold directional light from the upper left — catching the top of his wet hair, the left side of his forehead, the ridge of his nose, and the edge of his jaw and collar in bright silver-white highlights, while the right side of his face and body fall into deep black shadow. The overall black and white treatment is high contrast and graphic — deep rich blacks, bright silver highlights, no mid-grey — creating a Sin City or graphic novel aesthetic. Color palette: pure black and white, no color — deep black, bright silver-white rain streaks, grey skin tones. Photography style: cinematic high-contrast black and white, graphic noir rain portrait, 85mm lens, shallow depth of field, photorealistic, 8K.
Use the provided face reference image for all facial details — bone structure, profile shape, nose, jawline, and skin tone should be taken entirely from the reference photo. Apply only the high-contrast black and white treatment, heavy rain, bowed melancholic expression, and cold directional lighting on top of the reference face.
Mixed Media Cinematic Portrait Illustration
comic-storyboardAn extremely detailed prompt for a semi-realistic, neo-editorial portrait that blends architectural drafting elements with expressive oil painting and digital textures.
展开提示词全文
Ultra-detailed {argument name="style" default="neo-editorial cinematic portrait illustration"} rendered in a hybrid semi-realistic painterly-engineering style, combining refined anatomical realism with expressive sketch abstraction and futuristic conceptual drafting. The artwork fuses elegant graphite fashion illustration, architectural blueprint aesthetics, and richly layered digital painting into a visually immersive mixed-media composition. Human anatomy is highly accurate and sculptural, featuring luminous skin gradients, tactile pores, subtle wrinkles, refined facial contours, and soft glossy highlights. Facial rendering is extremely expressive and emotionally cinematic, with sharp eyes, delicately shaded brows, natural lips, and dramatic warm rim lighting blending golden-orange glow with cool bluish atmospheric reflections. Smooth polished rendering transitions coexist with rough textured brushwork, etched shading, and visible painterly grain. Fine ultra-thin micro-line drafting overlays merge seamlessly with loose hand-drawn sketch strokes, cross-hatching, technical contour lines, and schematic construction marks. Portions of the composition intentionally retain unfinished artistic energy: faded edges, dissolving contours, partially erased strokes, and fragmented geometric segmentation inspired by cubist blueprint structures. Certain body and fabric areas transform into layered painterly abstraction with watercolor diffusion, acrylic textures, expressive oil-like sweeps, and deconstructed mixed-media detailing. Lighting is highly cinematic and directional, creating deep volumetric shadows and glowing highlights with dramatic editorial contrast. The composition balances softness and structure—warm sepia shadows, sculpted highlights, and atmospheric diffusion enhance emotional depth while maintaining precision-engineered visual control. Background features a fusion of textured parchment surfaces and futuristic technical collage aesthetics: faint diagrams, circles, architectural annotations, handwritten marks, layered scratches, drafting elements, grain textures, faded paper imperfections, and atmospheric painterly haze. The environment feels both vintage and futuristic, combining analog artistic charm with advanced conceptual design language. Color palette blends earthy sophistication with vibrant cinematic accents: {argument name="colors" default="warm beige, creamy ivory, ochre, burnt orange, golden yellow, sepia brown, muted charcoal, deep bluish-green, cobalt blue, and subtle black-red highlights"}. Tonal harmony emphasizes warm desaturated realism contrasted by luminous energetic accent colors. Overall aesthetic is intimate, melancholic, elegant, high-fashion, cinematic, and emotionally powerful—an artistic fusion of vintage sketchbook illustration, futuristic engineering draftsmanship, cubist fragmentation, expressive oil painting, and contemporary editorial digital realism. No text, no logo and no watermark. R 9:16.
4-Panel Manga Vision Test
comic-storyboardA prompt for generating a surreal 4-panel manga featuring an eye exam using brand symbols, created with Nano Banana Pro.
展开提示词全文
{argument name="format" default="4-panel manga"}
{argument name="theme" default="vision test using symbols"}
Eye exam using {argument name="brand name" default="Chanel"}'s Azura Azura!
Night City Cinematic Triptych
comic-storyboardA cinematic triptych prompt for Nano Banana that uses a reference photo to create three urban night-themed portraits.
展开提示词全文
Use the uploaded photo as the exact identity reference. Keep the same person, same face, same facial features, same proportions, skin tone, and natural expression — do not alter identity. Preserve the subject's actual gender presentation, body type, and outfit from the reference photo unless otherwise specified. Create a photorealistic cinematic triptych portrait (three-frame composition in one image). Scene: {argument name="setting" default="Night city, bridge over a busy road, moving cars, glowing street lights, evening sky, city skyline in the background"}. Atmosphere: {argument name="mood" default="freedom, motion, youth, urban romance, feeling of wind and road"}. Frame 1 (top) — Wide cinematic shot: The person standing on a bridge above a busy road, slight motion blur from head/body movement, city lights and cars below, strong urban night mood. Frame 2 (middle) — Medium shot: Person leaning on the bridge railing, looking up at the sky, relaxed and confident pose, cars and headlights glowing behind them. Frame 3 (bottom) — Close-up emotional portrait: Wind in hair, city lights in bokeh behind, thoughtful and dreamy expression. Style: Real photography, cinematic lifestyle portrait, urban fashion photography. Lighting: Natural city night lighting, street lamps, car headlights, soft glow on skin. Camera: Full-frame DSLR, 85mm lens look, shallow depth of field. Color grading: Warm city lights mixed with cool blue night tones, film-style mood. Outfit: Preserve exact outfit from the reference photo — do not change clothing, accessories, or styling. Quality constraints: Ultra photorealistic, natural skin texture, real candid moment. No illustration, no CGI, no plastic skin, no text, no logos, no watermark.
Candid Phone Photography Triptych
comic-storyboardA detailed prompt for creating a realistic vertical triptych of phone-style photos in a forest setting, featuring identity preservation from a reference image.
展开提示词全文
A vertical triptych collage of three amateur phone shots featuring a subject in a {argument name="setting" default="dark forest"} at {argument name="lighting" default="sunset"}.
***IDENTITY INSTRUCTION: Completely copy the facial appearance, bone structure, hair, and unique features (piercings, tattoos, moles) from the user's uploaded reference photo. Map the user's face onto the subject in these poses exactly.
SHOT 1 (Top): Medium shot, slightly tilted angle. Subject stands among dark trees wearing {argument name="clothing" default="casual everyday clothes"} (random selection matching subject's gender - hoodie, jacket, shirt, etc.). Off-center composition, looking sideways. Warm red-orange sunset light filters through trees, hitting one side of face and neck. Shadows are deep and crushed.
SHOT 2 (Middle): Extreme macro close-up of eye. SHARP FOCUS on iris - high detail, visible iris patterns and texture. Red sunset glow reflects in the eye. Natural eyelash clustering, visible skin pores around eye. Slight phone camera noise.
SHOT 3 (Bottom): Low-angle close-up, head tilted back. Face turned upward. Warm sunset light illuminates jaw, neck, nose profile. Expression of calm or exhaustion. Dark blurred forest background.
TECHNICAL & ATMOSPHERE:
- Camera: Smartphone camera (iPhone/Android), not professional.
- Quality: Slightly degraded, phone sensor noise, minor compression artifacts, subtle blur in parts.
- Composition: Tilted horizon, asymmetrical framing, imperfect crop - looks candid/amateur.
- Color: Natural sunset red-orange tones, not artificial lighting. Deep shadows, warm highlights.
- Texture: Visible digital noise, slight motion blur, lens imperfections typical of phone cameras.
SKIN PARAMETERS:
- Hyper-realistic skin with visible pores, micro-creases, peach-fuzz hairs catching sunset light, natural skin sheen, subtle warm/reddish cast from sunset, soft lip texture, natural eyelash clustering.
- Skin must look fresh and young but NOT airbrushed - keep all natural imperfections.
DETAILS:
- Nose shape visible in sunset light.
- Clothing is casual, random, gender-appropriate.
- Background: dark forest trees, out of focus, moody atmosphere.
- Overall vibe: raw, candid, imperfect phone photography from golden hour.
Supermarket Discount War
comic-storyboardA chaotic and humorous scene depicting elderly women fighting over discounted items in a supermarket.
展开提示词全文
{argument name="scene" default="In the middle of a scramble with older women for discounted side dishes at a supermarket"}
8-Panel Retro Game Manga
comic-storyboardA creative 8-panel manga concept depicting the world as a frustrating retro game where the protagonist decides to hit the reset button.
展开提示词全文
8-panel manga
A retro game called 'The World'
{argument name="dialogue" default="Yikes! This is a total ultra-super-special crap game!"} I pressed the reset button.
Cinematic Rainy Night Noir Triptych
comic-storyboardA triptych layout prompt for Nano Banana Pro featuring a woman in a melancholic rainy city scene with cyan and teal neon lighting.
展开提示词全文
Use the uploaded person image as the ONLY strict identity reference. Preserve the exact facial features, face shape, eyes, eyebrows, nose, lips, skin texture, age, hair color, hairstyle and overall identity with maximum resemblance. The woman must be instantly recognizable as the reference image. Do not beautify, retouch or alter facial proportions in any way.
Create a cinematic vertical triptych of the reference woman during a {argument name="weather" default="heavy rainy night"} in an {argument name="location" default="empty city"}.
Top panel: Extreme close-up portrait through a rain-covered window. Wet hair sticks to her face. She looks slightly away from the camera with a distant, melancholic expression. Cold cyan and teal neon lights illuminate her face. Large neon bokeh glows behind her.
Middle panel: The woman lies on rain-soaked asphalt. Camera at ground level beside her face. Wet pavement creates a mirror-like reflection. Rain falls continuously, creating ripples and splashes around her. Her soaked hair spreads across the street.
Bottom panel: The woman stands alone in the middle of an empty city street under heavy rain. {argument name="clothing" default="Black clothing"} completely soaked and clinging to her body. She looks directly toward the camera with a calm but emotionally exhausted expression. The city behind her fades into blue neon haze and reflections.
Color palette: deep cyan blue, teal neon, turquoise reflections, dark navy shadows, wet black asphalt, cool white highlights. Minimal warm colors.
Atmosphere: heavy rain, wet skin, rain droplets on lens, atmospheric haze, reflective streets, cinematic loneliness, emotional noir.
Inspired by Blade Runner 2049, The Batman, Korean noir cinema, Wong Kar-wai night scenes.
Ultra-realistic photography, photorealistic skin texture, realistic rain simulation, shallow depth of field, cinematic bokeh, subtle film grain, anamorphic lens characteristics, masterpiece cinematic storytelling, vertical composition 9:16.
Additional Banana Pro emphasis:
VERTICAL TRIPTYCH COMPOSITION, HEAVY RAIN, WET HAIR AND SKIN, CYAN TEAL NEON, REFLECTIVE WET ASPHALT, EMOTIONAL NOIR, FEMININE GRACE, MELANCHOLIC EXPRESSION, SOAKED BLACK CLOTHING, CINEMATIC RAIN EFFECTS, LATE-NIGHT LONELINESS.
text, watermark, logo, extra people, beauty filter, CGI look, cartoon, illustration, plastic skin, distorted anatomy, dry hair, warm color grading, bright lighting, altered identity, masculine features.
Noir Alleyway Cinematic Portrait
comic-storyboardA moody, high-contrast black and white noir photography prompt set in a narrow urban alleyway featuring a woman in a trench coat.
展开提示词全文
A young woman stands in a narrow brick alleyway at night, looking over her shoulder with a serious expression.
Subject: A young woman with long hair wearing a {argument name="accessory" default="wide-brimmed hat"} and a {argument name="outerwear" default="trench coat"}.
Clothing: She wears a {argument name="hat style" default="dark fedora-style hat"} and a belted trench coat with visible lapels and pockets.
Action: She stands in profile facing left but turns her head to look directly at the camera with a neutral, intense gaze.
Environment: A narrow urban alleyway flanked by brick buildings, featuring a metal fire escape on the right and a hanging sign on the left.
Camera: Medium shot framed from the waist up, utilizing a shallow depth of field that keeps the subject sharp while blurring the background slightly.
Lighting: High-contrast black and white lighting with a bright street lamp overhead creating a strong rim light effect on her hair and face against deep shadows.
Style Details: Black and white photography with a noir aesthetic, featuring atmospheric smoke or fog drifting through the alleyway to enhance the moody atmosphere.
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。