← 返回首页
技能

Ai Image Prompts

tencent_skillhub · 1.0.9 · 下载量 2,041 · 热度分 56.4

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

作者:dophinl
分类:图文音视频多模态生成
版本:1.0.9
认证方式: 无需认证
是否付费: 官方未说明

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。

标签
图片生成

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 5717 条

Romantic Rose Editorial 3x3 Grid Prompt

product-marketing

A highly structured JSON prompt for generating a 3x3 editorial collage of a woman (identity preserved from reference image) holding a large bouquet of deep red roses, emphasizing romantic lighting, specific pose variations, and high panel consistency.

展开提示词全文
{
  "generation_request": {
    "meta_data": {
      "task_type": "romantic_rose_editorial_grid",
      "language": "en",
      "priority": "highest",
      "version": "v1.0_ROSE_EDITORIAL_GRID_3X3"
    },
    "input": {
      "mode": "image_to_image",
      "reference_image_usage": "very_high",
      "preserve_identity": true,
      "preserve_facial_features": true,
      "preserve_body_structure": true,
      "notes": "Keep the same adult woman, same hair length and color, same red off-shoulder dress, same neutral indoor wall. Create a 3x3 editorial collage with varied poses holding a large bouquet of deep red roses."
    },
    "output": {
      "aspect_ratio": "1:1",
      "resolution": "ultra_high",
      "num_images": 1,
      "layout": {
        "type": "grid",
        "rows": 3,
        "cols": 3,
        "gutter": "thin",
        "panel_consistency": "high"
      },
      "sharpness": "high",
      "grain": "subtle_analog_warm"
    },
    "scene": {
      "concept": "romantic valentine rose editorial",
      "environment": "minimal indoor studio with soft beige wall",
      "lighting": {
        "style": "soft on-camera flash aesthetic",
        "temperature": "warm indoor tone",
        "shadow_behavior": "soft short shadows behind subject",
        "highlight_control": "controlled shine on roses, no blown highlights"
      },
      "camera": {
        "lens": "50mm equivalent",
        "framing": "waist-up to half body",
        "focus": "face and roses sharp"
      }
    },
    "subject": {
      "type": "adult woman",
      "expression_range": [
        "soft romantic gaze",
        "eyes closed serene expression",
        "over-the-shoulder look",
        "gentle smile"
      ],
      "pose_variation": [
        "holding bouquet close to chest",
        "over shoulder pose showing back",
        "hiding half face behind roses",
        "looking down at bouquet",
        "turning head while holding stems",
        "hugging bouquet tightly"
      ],
      "anatomy_rules": "perfect hands, correct finger count, realistic wrist bend, no distorted shoulders"
    },
    "wardrobe": {
      "dress": "deep red off-shoulder dress",
      "fabric": "matte satin texture with natural folds"
    },
    "props": {
      "bouquet": {
        "type": "large bouquet of deep red roses",
        "petals": "velvety texture with layered detail",
        "leaves": "natural green leaves with subtle gloss",
        "stems": "visible natural stems",
        "density": "full, luxurious bouquet"
      }
    },
    "color_grading": {
      "palette": "deep red dominant with warm beige background",
      "contrast": "medium-high",
      "skin_tone": "natural warm tone",
      "avoid": "orange cast, plastic skin, oversaturation"
    },
    "negative_prompt": [
      "extra fingers",
      "missing fingers",
      "warped roses",
      "melted petals",
      "distorted face",
      "bad anatomy",
      "low resolution"
    ]
  }
}

Ana de Armas Skincare Influencer Portrait Prompt

product-marketing

A detailed prompt for generating a photorealistic, bright, and cheerful portrait of a woman (Ana de Armas) sitting on a picnic blanket by a lake, holding a skincare product, emphasizing natural lighting and a fashion influencer style, requiring the use of a reference image for facial features.

展开提示词全文
Use the same face from the reference image without changing facial features 

A beautiful young woman with fair skin, delicate features, soft natural makeup, subtle smile, hazel eyes, sitting relaxed on a cozy picnic blanket by a serene lake in early spring, surrounded by tall bare trees and forest in soft golden sunlight, she has her light brown hair styled in a cute messy high bun, wearing a vibrant hot pink puff-sleeve square-neck linen blouse with ruffled short sleeves and white high-waisted pants, holding up a small light purple skincare tube labeled "{argument name="product name" default="florence"}" with cute bubble designs toward the camera, casual outdoor picnic vibe, warm natural daylight, soft bokeh background with blue water and distant trees, photorealistic, high detail, fashion influencer style, bright and cheerful mood, shot on Canon EOS R5, 50mm lens, f/2.8, natural lighting, 8k

Steve Harrington Tangerine Fashion Editorial Prompt

product-marketing

A structured JSON prompt for generating a high-contrast, low-angle fashion editorial photograph of Steve Harrington in a tailored bright orange suit, set in a monochrome orange studio with a vintage orange car in the background.

展开提示词全文
{
  "prompt": "A high-contrast, low-angle fashion editorial photograph from a 24mm lens, capturing Steve Harrington in a tailored bright orange suit, white shirt, and orange tie. He leans against a sharp corner in a monochrome orange studio with clean geometric lines. A pair of oversized orange and black sneakers in forced perspective dominates the foreground. A vintage orange hatchback (e.g., a Ford Fiesta Mk1) is parked in the background. The lighting is dramatic, with strong shadows. The overall aesthetic is luxury street-style. 4:5 aspect ratio."
}

Sydney Sweeney Sock Advertisement Portrait Prompt

product-marketing

A highly detailed JSON prompt for generating a minimalist studio portrait of Sydney Sweeney wearing a teddy bear print bodysuit and white mid-calf socks with ruffled lace trim, focusing on a joyful expression and a specific seated pose on a bar stool.

展开提示词全文
{
  "prompt": {
    "subject": {
      "description": "{argument name=\"subject name\" default=\"sydney sweeney\"} woman with long, voluminous blonde hair styled in soft, loose waves cascading over her shoulders. Her hair is parted slightly off-center, framing her face symmetrically. She has a warm tan complexion with smooth, even skin tone and a subtle healthy glow. Her facial features are delicate and well-defined: arched eyebrows, almond-shaped eyes, lightly defined lashes, softly contoured cheeks, and a bright, wide smile showing straight white teeth. Her makeup is natural and polished, with neutral eyeshadow, light mascara, subtle blush, and soft pink glossy lips.",
      "expression": "She is smiling broadly with a joyful, confident expression. Her head is tilted slightly to her right (viewer’s left), chin slightly lifted, creating an open and playful body language. Her gaze is directed toward the camera lens, conveying warmth and approachability.",
      "clothing": "She is wearing a fitted sleeveless bodysuit in a soft pastel yellow tone. The fabric is smooth and slightly stretchy, hugging her torso naturally without visible wrinkles at the waist. The bodysuit features a repeating teddy bear print in warm brown and red tones evenly distributed across the fabric. The neckline is moderately scooped, revealing the collarbones and upper chest. She is also wearing white mid-calf socks with delicate ruffled lace trim at the top. The socks are slightly slouched around the lower calves and ankles, creating natural fabric folds and compression wrinkles.",
      "pose": {
        "body_position": "She is seated sideways on a tall wooden bar stool with her torso rotated slightly toward the camera. Her spine is elongated and upright, shoulders relaxed and gently drawn back.",
        "legs": "Her right leg (viewer’s left) is bent at the knee and raised, with the thigh angled upward and the lower leg angled downward, the foot hovering slightly off the stool’s lower rung. Her left leg is bent and positioned closer to the stool, with the foot resting lightly near the lower support bar. Both knees are clearly bent at approximately 90–110 degrees, creating a compact seated pose. The thighs are angled diagonally upward from the stool seat, with realistic muscle definition and natural skin tension.",
        "arms_and_hands": "Both arms extend downward along her sides, with her hands gripping the edges of the wooden stool seat for support. Her fingers are naturally curved around the seat’s edge, with visible gentle tension in the knuckles. Her elbows are slightly bent, positioned behind the line of her torso, subtly accentuating the curve of her waist."
      }
    },
    "environment": {
      "location": "Minimalist studio setting.",
      "background": "Smooth, seamless light gray backdrop with no visible texture, patterns, or props. The background is evenly lit and free of shadows or gradients.",
      "furniture": ""
    }
  }
}

Avant-Garde Louis Vuitton Ski Goggles Editorial Prompt

product-marketing

A structured JSON prompt for generating a high-fashion editorial photograph of avant-garde Louis Vuitton-style ski goggles, emphasizing high-contrast Chiaroscuro lighting, metallic details, and a dark background.

展开提示词全文
{
"action": "image_generation",
"input": {
"prompt": "High-fashion editorial photography of avant-garde Louis Vuitton-style luxury ski goggles. The goggles feature a sleek 'Deep Obsidian' frame with 'Champagne Gold' hardware and a subtle monogram-etched lens. The goggles are perfectly balanced atop an abstract, floating glass and black glossy 'V' sculpture. High-contrast Chiaroscuro lighting, deep black background, sharp focus on the metallic details and leather-trimmed strap. 3:4 aspect ratio."
}
}

3x3 Character Emotional Expression Grid Prompt

product-marketing

A prompt for generating a 3x3 grid of nine distinct emotional portraits of the same character, based on an uploaded reference image, using high-end commercial fashion photography style and ultra-sharp focus.

展开提示词全文
A 3x3 grid layout expression sheet of the same character based on the uploaded reference image, featuring nine distinct emotional portraits labeled A1 to C3 in the corner of each frame. 
Top row: A1 ({argument name="emotion 1" default="joyful laughter"}), A2 ({argument name="emotion 2" default="contemplative sadness"}), A3 ({argument name="emotion 3" default="intense anger"}). 
Middle row: B1 (surprised shock), B2 (neutral calm), B3 (playful wink). 
Bottom row: C1 (arrogant smirk), C2 (fearful anxiety), C3 (exhausted boredom). 
Consistent character features, high-end commercial fashion photography style, ultra-sharp focus on facial muscles and eyes. Studio lighting with soft shadows, 8k resolution, photorealistic, masterwork, Unreal Engine 5 render, Octane Render, Ray Tracing, detailed skin texture, volumetric lighting.

Editorial Fashion Photography with Structural Mimicry Prompt

product-marketing

A detailed prompt for editing an image into an editorial fashion photograph, featuring a model seated on a stool wearing architectural streetwear whose structure and color palette are explicitly modeled after a second uploaded reference image.

展开提示词全文
Edit image :
Editorial fashion photography featuring this subject as a fashion model with editorial charisma, seated dynamically on a minimalist black stool, twisting torso with an avant-garde attitude. She wears a masterpiece set of architectural streetwear [structurally mimicking the form of #2 uploaded image].
wardrobe set :
a hooded jacket defined by subtle 3D texture details, design shape explicitly modeled after [the #2 uploaded image object], [color palette faithful to the #2 uploaded image theme], reminiscent of advanced shibori sculpting. The garment features a moderen casual wear with asymetrical zipper and multiple strap and starp cordlock/stopper and pouch, industrial zippers. The lower silhouette consists of tactical baggy pants with detailed textures, paired with high-cut sneakers. Minimalist high-key studio environment with a seamless white cyclorama. Professional soft-box lighting creating ambient light scattering on skin, authentic dermal texture, natural skin-tone luminosity, shot on 35mm analog film stock, sharp optical precision, 85mm portrait lens.

ar : 9: 16

Ultra-Realistic Fried Snack Explosion Food Photography Prompt (Duplicate)

product-marketing

A detailed prompt for generating ultra-realistic, high-speed food photography of a crispy fried snack exploding mid-air, emphasizing texture, dramatic lighting, and a vibrant night market setting, optimized for the Nano Banana Pro model on Gemini.

展开提示词全文
Ultra-realistic high-speed food photography of a crispy golden fried snack breaking apart mid-air, creamy savory filling stretching between the halves, visible chunks of {argument name="filling ingredients" default="chicken, peas, carrots, minced meat, noodles, or egg"} inside. Crumbs and flakes flying in slow motion, hot steam rising, dramatic food explosion effect. Shot in a vibrant night street market environment with warm bokeh lights, blurred food stalls in the background. Shallow depth of field, 85mm lens, f/1.8, ultra-sharp focus on texture, crunchy coating detail, dynamic motion capture, commercial food photography, cinematic lighting, HDR, 8K resolution, hyper-detailed, masterpiece quality.

Ultra-Realistic Fried Snack Explosion Food Photography Prompt

product-marketing

A detailed prompt for generating ultra-realistic, high-speed food photography of a crispy fried snack exploding mid-air, emphasizing texture, dramatic lighting, and a vibrant night market setting, optimized for the Nano Banana Pro model on Gemini.

展开提示词全文
Ultra-realistic high-speed food photography of a crispy golden fried snack breaking apart mid-air, creamy savory filling stretching between the halves, visible chunks of {argument name="filling ingredients" default="chicken, peas, carrots, minced meat, noodles, or egg"} inside. Crumbs and flakes flying in slow motion, hot steam rising, dramatic food explosion effect. Shot in a vibrant night street market environment with warm bokeh lights, blurred food stalls in the background. Shallow depth of field, 85mm lens, f/1.8, ultra-sharp focus on texture, crunchy coating detail, dynamic motion capture, commercial food photography, cinematic lighting, HDR, 8K resolution, hyper-detailed, masterpiece quality.

Cinematic Cola Can Explosion Advertisement Prompt

product-marketing

A structured JSON prompt for Kling AI and Nano Banana Pro, designed to generate a hyper-realistic, ultra-dynamic cinematic advertisement of a blue cola can exploding in mid-air with neon liquid, ice, and dramatic lighting effects.

展开提示词全文
{
 "Ultra-dynamic cinematic advertisement of a blue cola can exploding with energy in mid-air, surrounded by splashing neon turquoise liquid, flying ice cubes, and fresh lime slices. Dramatic radial light streaks and particles bursting outward, high-speed action freeze, glossy water droplets on the can, vibrant electric colors, dark background with glowing effects, hyper-realistic 3D render, studio lighting, depth of field, motion blur on flying elements, premium beverage commercial style, 8k, ultra-detailed, sharp focus",
  "negative_prompt": "blurry, low quality, dull colors, flat lighting, distorted can, deformed text, watermark, logo errors, noise, grain",
  "style": "photorealistic, cinematic, commercial advertising",
  "aspect_ratio": "1:1"
}

Ana de Armas Valentine's Day Editorial Fashion Prompt

product-marketing

A detailed prompt for generating a high-fashion, cinematic portrait of a woman (Ana de Armas) in a pink velvet jumpsuit, emphasizing dramatic red lighting, deep shadows, and a fierce Valentine's Day editorial vibe, requiring the use of a reference image for facial features.

展开提示词全文
Use the same face from the reference image without changing facial features 

A stunning young woman with fair skin and delicate features, long straight blonde hair, dramatic makeup with bold red lipstick and dark smoky eyes with red accents, posing seductively bent forward at the waist with one leg forward, wearing a luxurious pink velvet strapless jumpsuit with high-waisted fitted bodice and wide-leg flared pants featuring a dramatic thigh-high slit on one side, long black sheer lace gloves, black patent high-heeled pumps, holding a small black feather-trimmed evening bag with sparkling beads and a long silver chain strap dangling, diamond choker necklace with large central pendant, standing on a vibrant solid red studio floor with a giant glowing red heart-shaped light or shadow projected dramatically behind her on the wall, romantic yet fierce Valentine's Day editorial fashion vibe, high-fashion photography, cinematic lighting with strong red glow and deep shadows, moody and glamorous atmosphere, sharp details on velvet texture and fabrics, professional studio portrait, 8k, highly detailed, photorealistic

Basic Instinct Cinematic Still

product-marketing

A highly detailed cinematic prompt designed to recreate the iconic interrogation scene from 'Basic Instinct' (1992). It specifies the setting (teal-blue tiled room), lighting (dramatic neo-noir, high contrast), camera settings (35mm anamorphic), and the subject's pose (legs crossed seductively) and attire (sleeveless white mini dress).

展开提示词全文
": { "location": "Cold interrogation room with teal-blue brick tiled wall, cinematic still from 'Basic Instinct' (1992)", "vibe": "Intense seductive power, classic film-noir tension, commanding presence", "lighting": "Teal-blue ambient room light, strong directional key from left casting long shadows, rim light sculpting figure and legs, high contrast, dramatic neo-noir mood", "camera_settings": "35mm anamorphic lens, f/2.0, shallow depth of field, cinematic film grain, subtle lens breathing, ultra-photorealistic 8k, 'Basic Instinct' color palette (cool teal shadows, warm skin highlights)" }, "primary_subjects": [ { "character": "{argument name=\"character type\" default=\"attached celebrity lookalike\"}", "role": "Interrogation subject / ultimate femme fatale", "action": "Seated in black metal chair, legs crossed seductively (right over left), right arm casually draped over chair back, left hand resting on thigh, upper body leaning back slightly, hips angled forward, piercing direct stare at camera, lips parted in confident half-smile", "details": "Sleeveless white high-neck mini dress clinging to curves, bare toned legs with glossy sheen, white pointed high heels, long dark glossy hair with loose waves, smoky cat-eye makeup, bold red lips, gold bracelet on right wrist" } ], "environment_details": { "crowd": "None – solitary cinematic intensity", "architecture": "Teal-blue brick tiled wall, black metal chair, concrete floor", "fidelity": "Hyper-realistic 8k, lifelike skin under cold light, fabric detail, hair shine, precise 'Basic Instinct' Catherine Tramell pose, lighting, and atmosphere" } }"
上一页 202 / 477 下一页

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。一节课的讲解也能做成课程口播。

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。

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。

海报设计工作室

免费增值需申请 Key

将一段活动描述、一张产品照片或品牌参考图,转化为抓人眼球的活动海报、宣传 banner 或社交媒体配图。这款 AI海报设计与制作工具生成图片丰富的海报,在海报排版上搭配清晰视觉层级、按品类匹配的风格和预留文字区域,覆盖活动、音乐节、电影、产品发布和促销场景。你可以把它当作 AI宣传单制作工具来制作促销宣传单,当作活动海报设计工具,当作电影海报生成器,当作音乐节海报设计工具,当作产品发布会海报的 banner设计 AI,或当作平面设计海报工作室。从活动主题出发,用品牌风格参考图变换产品或场景照片,或在已认可草稿上做定向精修,完成可印刷或可分享的成品。

自动化克隆数字人口播混剪视频

免费增值需申请 Key

抖音短视频双路径生产体系(单 Skill 版)。Path A[付费·高质量]:策略大脑→(可选:素材混剪/AI高光提取)→脚本优化→AI生图/素材准备→配音渲染(百炼/GPT-SoVITS/CosyVoice/VoxCPM2+剪映/Remotion/ffmpeg/数字人)。Path B[免费·动画风]:采集热点→脚本→edge-tts免费配音+HyperFrames开源渲染→MP4,零云费开箱快。触发词分层:①"抖音短视频/选题规划/合规闸门/运营策略" ②"口播脚本/AI生图/AI配音/视频渲染/Remotion渲染" ③"蹭热点/快速出片/免费做视频" ④"混剪/高光提取/素材粗剪/autoclip

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。