← 返回首页
技能

Ai Image Prompts

tencent_skillhub · 1.0.9 · 下载量 1,827 · 热度分 55.6

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 725 条

Chibi-Style NBA Matchup

game-asset

A prompt for Nano Banana Pro to create a chibi-style screenshot of a fictional NBA game where a baby-style Kobe Bryant attempts a fadeaway jumper against LeBron James at the Lakers' home court.

展开提示词全文
Generate a screenshot of a real NBA game where Kobe Bryant is matched up against LeBron James at the Lakers' home court. James is defending Kobe's fadeaway jumper, and Kobe is depicted as a chibi-style baby.

Octane-Rendered Floating Ecological Island

game-asset

An extremely detailed prompt for generating a massive, photorealistic floating island that functions as a living ecological system. It specifies Octane-level rendering realism, physically plausible environments, and architecture grown from organic and mineral materials, viewed from a wide-angle aerial perspective.

展开提示词全文
[SUBJECT]
A massive floating island captured as a photoreal, physically plausible environment, rendered with Octane-level realism. The island is a living ecological system integrated with inhabitable architecture grown from stone, crystal, and bio-organic materials. The scene feels like a real, observable place suspended in the sky, not a stylized illustration.

[RENDERING STYLE]
Ultra-photoreal rendering with Octane Render characteristics: physically accurate global illumination, realistic light falloff, high dynamic range sky lighting, true-to-scale materials, micro-surface detail, subtle imperfections, and natural color response. No painterly effects, no stylization, no exaggerated fantasy lighting.

[COMPOSITION]
Wide-angle aerial shot, slightly offset perspective, as if photographed from a hovering drone or aircraft. The full vertical mass of the island is visible, with architectural elements clearly readable. Horizon visible in the distance with atmospheric haze for scale. Camera height slightly below the island’s midline, emphasizing weight and realism.

[UPPER ATMOSPHERIC ZONE]
Thin, stratified clouds interact with the island’s upper vegetation. Tall, vine-like atmospheric plants extend upward, realistically textured and wind-reactive. Small, semi-translucent floating organisms drift naturally, with believable motion blur and subsurface scattering. Sunlight diffuses through cloud layers, producing soft volumetric shafts.

[SURFACE ECOSYSTEM]
The surface terrain features realistic soil, rock strata, and dense vegetation with botanical variation. Graviroot trees anchor into the terrain with visible root tension and load-bearing structure. Meadows ripple subtly in the wind. Rivers flow toward cliff edges and disperse into mist through evaporation, captured with physically accurate fluid behavior.

[ARCHITECTURE – DWELLINGS & PUBLIC SPACES]
Architecture is seamlessly integrated into the landscape, appearing grown, carved, or accreted rather than constructed:
- Cliffside dwellings embedded into rock faces, with arched openings, layered terraces, and organically curved facades.
- Residential structures grown from mineralized coral-like stone, reinforced with crystal ribs.
- Public plazas formed as open stone platforms surrounded by vegetation, root-canopies, and light-filtering crystal growths.
- Sky-bridges and root-walkways connecting buildings, appearing load-bearing and structurally plausible.
- Transparent or semi-translucent roofing formed from bio-crystal membranes, allowing natural light into interiors.

No sharp industrial lines; all architecture follows structural logic and biological growth patterns.

[SUBSURFACE & STRUCTURAL CORE]
Through cracks and translucent mineral layers, a crystal–mycelium structural network is visible, acting as both load distribution and energy circulation. Subsurface glow is subtle, uneven, and realistic, suggesting biophysical p

Canva Asset Creation and Style Matching Prompt

game-asset

A prompt used to generate missing numbered assets (11 and 12) for a Canva design, ensuring the AI matches the style, texture, and color of the existing assets (1-10) provided as a reference image.

展开提示词全文
I need numbers 1 to 12 for a {argument name="theme" default="12 Zodiac Signs"} design, but I only have assets from 0 to 10. Based on this image, please create 11 and 12.

Collectible Toyline Forge Engine System Prompt

game-asset

A complex system prompt designed for an AI model acting as a 'Collectible Toyline Forge Engine.' It instructs the AI to interpret an object's form into a stylized character/figure, infer articulation, materials, and packaging language, and then output the design details. The prompt is used to compare model performance, specifically requesting a design for Nikola Tesla.

展开提示词全文
Do this for {argument name="subject" default="Nikola Tesla"}<analysis> You are the Collectible Toyline Forge Engine. An AI toy designer and packaging stylist. You interpret any object’s form into a stylized character/figure with accessories derived from its parts. You infer articulation points, surface finishes, and a packaging language that matches the object’s mood and “brand universe.” </analysis>  

[DESIGNER FIGURE TYPE] inspired by [OBJECT] Materials: [Toy/packaging materials inferred from source + finish logic] Key Features: [3 to 5 bullets: silhouette gimmick, accessories, articulation, micro-details] Colorway: [Palette derived from object] Edition: [Toyline name + drop/series tag]

3D Animated Scene of Chicks and a Monster on Lily Pads

game-asset

A prompt for generating a cinematic, ultra-detailed 3D animated film style image. It merges two concepts: two small fluffy chicks seen from behind on a floating lily pad, and a large purple stitched monster dominating the frame, set in a lush jungle pond environment with soft mist.

展开提示词全文
Two small fluffy chicks seen from behind, standing together on a floating green lily pad, their backs fully facing the camera, maintaining their exact proportions and silhouettes.

The chicks are positioned at the very bottom foreground of the scene, while the large purple stitched monster remains dominant in the frame and subtly lowers its gaze downward.

Lush jungle pond environment with floating lily pads, soft mist near the water surface and warm natural daylight.

Cinematic, ultra-detailed, high-end 3D animated film style, soft realistic textures, no distortion, no stylization shift.

Miniature Metropolis Inside a Vintage Pocket Watch

game-asset

A prompt for generating a hyper-realistic macro photograph of a sprawling miniature metropolis nestled within the intricate gears and springs of a vintage pocket watch. It specifies the architecture, lighting, and 3D render style for a detailed, fantastical scene.

展开提示词全文
Create a hyper-realistic macro photograph depicting a sprawling miniature metropolis nestled within a vintage pocket watch for the hyper-realistic isometric 3D render of a miniature. The intricate gears and springs of the watch form the foundational architecture for the city's towering skyscrapers, [amidst glowing filament streetlights and brass walkways, with soft cinematic lighting reflecting off the polished metal surfaces.]

Humanoid Mech Generator for Urban Life

game-asset

A prompt for generating a full-body humanoid mech adapted for everyday urban life. It specifies a mechanical head with an abstract silhouette (no human features), futuristic wear, exposed mechanical limbs, and a style of sci-fi illustration with clean linework, flat color fields, and a mood of calm, near-future realism.

展开提示词全文
Design a full-body humanoid mech adapted to everyday urban life. Mechanical head with a strong abstract silhouette, no human or anime facial features. Futuristic wear. Exposed mechanical limbs and joints with clean panel seams and functional details. Subtle sci-fi equipment, restrained and believable.

Style: Sci-fi illustration, clean soft linework, airy composition, flat yet nuanced color fields, vivid color palette
Camera: full-body, eye-level, neutral minimal background.
Mood: calm, confident, near-future realism.

Macro Shot of Miniature Sniper Scene

game-asset

A prompt for generating a hyper-realistic, high-fidelity macro close-up shot featuring a giant human hand holding a keyring. Attached to the keyring is a miniature character (with a specified face reference) in a ghillie suit, lying prone behind a highly detailed sniper rifle, set against a blurred forest background.

展开提示词全文
A hyper-realistic, 8k, high-fidelity close-up shot captured with a macro lens, showcasing a giant human hand holding a keyring against an extremely blurred background of a rugged outdoor forest range. The hand holds a rugged, olive drab paracord survival strap with a small metal dog tag reading "{argument name="dog tag text" default="DUET AI : One Shot"}". Attached is a miniature character lying in a prone firing position behind a highly detailed, tiny sniper rifle with a large scope. The character has a large head, [uploaded face as reference], and is wearing a full miniature ghillie suit (camouflage) that looks incredibly textured with tiny leaves and burlap. The miniature rifle has realistic metallic and polymer textures, bipod legs, and a tiny lens flare on the scope. Natural, dappled forest sunlight highlights the camouflage textures and the metal of the rifle.

Nanobanana Prompt Engineering Workflow

game-asset

A user describes their workflow for creating high-quality Nanobanana prompts using a custom tool. The process involves defining the subject (e.g., polar bear and panda on skates), generating the initial image, performing detailed annotation (labeling parts like pose, background, face, clothing) based on file names, and finally adding compositional and color information for the final generation. This highlights the importance of detailed language specification for effective prompting.

展开提示词全文
① Create a "{argument name="character 1" default="Polar Bear"}" and a "{argument name="character 2" default="Panda"}" wearing ice skates, and the background location. Normal chat-based input is also OK. Whether you generate it all at once or separately, the process is the same.

② Perform annotation on the image.
This is the most troublesome part, so I made it a tool.
Based on the file name, I create a prompt that organizes "which part of which image to reference."
(Pose / BG / Face / Clothing, etc.)

③ Add supplementary information such as composition and color scheme for the final generation.

Inflatable Character Creation Prompt

game-asset

A prompt share for creating inflatable characters, likely for graphic design or whimsical illustrations, using Nano Banana Pro.

展开提示词全文
Create inflatable characters using this prompt

Cardboard Submarine Design Generation

game-asset

A prompt used with NanoBananaPro to generate a design concept for a children's submarine made from a cardboard box, based on an input image of the box.

展开提示词全文
What would it look like if I made a submarine for children out of this [cardboard box]

Split Identity Vinyl Toy Engine

game-asset

A complex, structured prompt designed to generate a 2x2 grid of vinyl art toys, each representing a 'Split Identity' with duality. It specifies the artistic style (Bulbous toy proportions, clean bisected geometry), material (Soft vinyl, contrasting matte colors), and layout (symmetrical framing, product photography lighting).

展开提示词全文
Do this for a random character: <instruction> Split Identity Vinyl Toy Engine:
Input A is a Character with duality.

Select 4 lesser-known characters with internal conflict.

Sculpt each toy split vertically or horizontally into two contrasting halves.

Each half represents a different narrative state.

Layout:

2x2 grid, toys centered, perfectly symmetrical framing, name underneath

Style Stack:
Anchor: [Split vinyl art toy]::3.5
Morphology: Bulbous toy proportions, clean bisected geometry::3
Material: Soft vinyl, contrasting matte colors::2.5
Render: Product photography lighting, neutral backdrop::1
Negative: [organic gore, realism, asymmetry]::-1

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。