← 返回首页
技能

Ai Image Prompts

tencent_skillhub · 1.0.9 · 下载量 2,051 · 热度分 56.5

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

Generate a 9-way split image at 2K resolution

product-marketing

A prompt instruction for an AI image generator (Nano banana pro) to create a single image split into nine sections and upscaled to a 2K resolution. This is suggested as a cost-saving method for brainstorming, such as for logo designs.

展开提示词全文
create a 9 way split image and up the resolution to 2k

Cinematic Product Video Prompt for Keychain Style Portrait

product-marketing

A detailed JSON-formatted prompt designed for the Gemini AI Nano Banana 3 Pro to create a cinematic product-style video advertisement. The video features a keychain as the hero product, protected by a tiny, tough figurine bodyguard in a high-end studio setting, utilizing macro close-ups and smooth camera movements to achieve a humorous yet sleek aesthetic.

展开提示词全文
{
  "style": "cinematic product-style video",
  "environment": {
    "setting": "clean premium studio",
    "lighting": "soft directional studio lights, high contrast, glossy reflections, subtle rim light",
    "mood": "humorous yet high-end"
  },
  "subjects": [
    {
      "type": "tiny figurine",
      "role": "bodyguard",
      "actions": [
        "paces left and right",
        "crosses his arms",
        "adjusts tiny sunglasses",
        "stands protectively in front of keychain"
      ],
      "expression": "serious, tough, guarding"
    },
    {
      "type": "keychain",
      "role": "protected object",
      "details": "hero product, centered, sharp focus"
    }
  ],
  "camera": {
    "movements": [
      "smooth dolly tracking shot following the figurine",
      "macro close-up shots on sunglasses, figurine face, and keychain",
      "shallow depth of field transitions"
    ],
    "lenses": "macro lens, 85mm cinematic product lens feel"
  },
  "visuals": {
    "composition": "premium product advertisement aesthetic",
    "textures": "sharp micro-details on figurine and keychain",
    "tones": "clean neutral backdrop, polished surfaces"
  },
  "vibe": "playful bodyguard scenario but sleek and cinematic"
}

9-Shot Editorial Photo Grid Prompt for Nano Banana Pro

product-marketing

This is a detailed, multi-shot prompt designed for generating a 3x3 editorial photo grid in a clean, soft beige studio setting, specifically tailored for the 'Nano Banana Pro' style. It specifies character appearance, lighting, composition, camera settings (lens, aperture, DOF), and overall mood for nine distinct portrait shots, focusing on intimate, introspective, and character-led editorial minimalism.

展开提示词全文
Editorial 3x3 photo grid in a clean soft beige studio. 
Character (matches reference 100%) wearing lightweight dark navy shirt, ivory trousers, barefoot for raw simplicity. 
Lighting: large diffused key light directly front-right, silver reflector left, subtle rim from top. 
Shots to include: 1. extreme close-up of lips + cheekbone with blurred hand partially covering (85mm, f/1.8, razor-thin DOF); 
2. tight crop on eyes looking into lens with reflection of light strip visible (85mm, f/2.0); 
3. black & white close portrait resting chin on fist, face filling frame (50mm, f/2.2); 
4. over-shoulder shot, blurred foreground fabric curtain framing half face (85mm, f/2.0); 
5. very close frontal with hands overlapping face, light streak across eyes (50mm, f/2.5); 
6. tight angled portrait showing hair falling into eyes, soft-focus background (85mm, f/2.2); 
7. crop of hands touching jawline, eyes cropped out (50mm, f/3.2, detail-focused); 
8. half-body seated sideways on low cube, head turned sharply away, blurred foreground (35mm, f/ 4.5); 
9. intense close-up of profile with single tear-like water droplet, cinematic light slice across (85mm, f/ 1.9). 
Angles: mostly tight headshots with slight high/low tilts, maintaining variation. Capture RAW, professional muted grade, smooth tonal contrast, subtle cinematic grain. Mood: intimate, introspective, character-led editorial minimalism with delicate use of fabric as prop.

Inuyasha Plush Toy Generation Prompt

product-marketing

A prompt for generating an image of an Inuyasha plush toy using the Nano Banana Pro model, focusing on a cute, chibi, and fluffy aesthetic with specific details like the character's ears and clothing.

展开提示词全文
Inuyasha plush toy, chibi, cute, fluffy, soft, big ears, red kimono, white hair, sitting, simple background, studio lighting, high quality, detailed

Hyper-realistic portrait of a young woman in street style at night

product-marketing

This is an image generation prompt designed for Grok Imagine, focusing on creating a hyper-realistic, moody portrait of a young woman in street fashion. It specifies cinematic lighting, detailed textures, and a blurred urban background with neon signs, using specific photographic parameters like an 85mm lens and f/1.8 aperture for a shallow depth of field.

展开提示词全文
Hyper-realistic portrait of a beautiful young woman looking back over her shoulder, wearing a grey textured knit beanie and a black leather biker jacket with silver studs on the lapels. She is wearing a black turtleneck. The background is a blurred urban street at night featuring vertical neon signs in {argument name="neon color 1" default="bright pink"} and {argument name="neon color 2" default="cyan blue"}. Cinematic lighting, soft focus background, bokeh, 85mm lens, f/1.8, incredibly detailed skin texture, fashion photography, street style, moody atmosphere --ar 2:3 --v 6.0 --style raw

Modern Japanese Graphic Design Poster Prompt

product-marketing

A detailed prompt for generating a modern Japanese graphic design poster featuring stylized water ripples and abstract biomorphic shapes. The design emphasizes a minimalist aesthetic, high contrast, and a monochromatic blue color palette, suitable for vector art or screen print styles.

展开提示词全文
Modern Japanese graphic design poster of stylized water ripples, abstract water surface pattern, organic biomorphic shapes, flat design, vector art style. Monochromatic {argument name="color palette" default="blue"} color palette, {argument name="color 1" default="indigo"} and {argument name="color 2" default="azure"} and white, high contrast, clean hard edges, no gradients. Rhythmic flowing composition, screen print texture, minimalist aesthetic, typography elements in Japanese kanji. {argument name="style reference" default="Shinmura Suisan"} style, fresh and cool atmosphere

Game of Thrones Ice and Fire Isometric Diorama

product-marketing

A detailed image generation prompt designed for Gemini Nano Banana Pro, creating a 45° top-down isometric miniature 3D cartoon diorama based on the central Game of Thrones theme of Ice and Fire. The prompt specifies soft textures, realistic PBR materials emphasizing glittering frost and glowing embers, and a dramatic clash of cool blue and warm orange lighting. It includes specific compositional details like a split diorama base featuring The Wall/White Walkers on one side and a dragon/burning castle on the other, along with precise text overlays and a clean background.

展开提示词全文
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.

Advertising-Style Food Photography Prompt

product-marketing

A prompt designed for generating high-resolution, advertising-style food photography. It specifies arranging one subject on a rustic table while another subject floats above, with a splash of the first subject frozen in motion, emphasizing dramatic lighting and clean negative space for text.

展开提示词全文
Advertising-style food photography of {argument name="subject 1" default="[subject 1]"} arranged on a rustic table, with {argument name="subject 2" default="[subject 2]"} floating above in mid-air and a splash of {argument name="subject 1 repeat" default="[subject 1]"} frozen in motion. High-resolution photo manipulation with selective soft focus, clean negative space for text, dramatic lighting, and crisp detail.

Dramatic Ultra Wide-Angle Photo Transformation Prompt

product-marketing

A prompt designed for image generation models like Nano Banana Pro (Freepik) to transform an original photo into a dramatic, photorealistic, ultra wide-angle shot. It emphasizes extreme camera angles (below or above), forced perspective where body parts near the lens appear huge, and requires the subject to strike a stylish, powerful pose within a consistent, expanded version of the original environment.

展开提示词全文
Transform the original photo into a dramatic, photorealistic, ultra wide-angle shot with an extreme camera angle (including views from directly below or above), where one or more body parts are right next to the lens and look huge, the rest of the body recedes in perspective, and the same person strikes a stylish, complex, powerful pose in a consistent, expanded version of the original environment.

Anti-Plastic/Hyper-Realism Protocol for Human Skin Texture

product-marketing

A highly technical and detailed prompt protocol designed for Nano Banana Pro to eliminate the 'plastic skin' look in human images, focusing on hyper-realistic texture and natural flaws. It mandates 8K resolution, overrides default smoothing, and includes specific instructions for dermal physics (stochastic noise, vellus hair), subsurface scattering (melanin variance, vascularity), micro-texture (sebaceous sheen), and detailed eye/lip rendering.

展开提示词全文
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

Raw Beauty Portrait in Steamy Bathroom

product-marketing

A descriptive prompt for generating a striking, raw beauty portrait using Nano Banana Pro. The scene is set in a steamy, tiled bathroom, focusing on a woman with wet hair wrapped in a towel, emphasizing water droplets, glowing skin, and a sultry expression. It details the soft, diffused lighting and humid atmosphere.

展开提示词全文
A striking, raw beauty portrait in a steamy, tiled bathroom. A woman with wet hair slicked back, wrapped loosely in a white fluffy towel. Water droplets are visible on her glowing skin and shoulders. She is leaning against the sink, looking deeply into the camera with sultry, smoky eyes. The mirror behind her is foggy. Soft, diffused lighting, humid atmosphere, emphasis on skin texture and eyes.

Image generation prompt for a futuristic nano-banana-pro concept

product-marketing

This is an image generation prompt designed for Google Nano Banana Pro, shared via the ALT text of the tweet. It describes a futuristic, high-tech banana-shaped device with a sleek, minimalist design, emphasizing a clean, white background and soft studio lighting for a product photography aesthetic.

展开提示词全文
A futuristic, sleek, minimalist banana-shaped device, high-tech product photography, clean white background, soft studio lighting, ultra-detailed, 8k, concept art, {argument name="style" default="minimalist"}
上一页 468 / 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。