← 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

AKIRA 'Slide Brake Scene' Recreation Prompt

game-asset

A highly specific, multi-section prompt for Nano Banana Pro designed to recreate the iconic 'slide brake scene' from the anime AKIRA, without using the word 'AKIRA'. It details composition, subject, action, visual effects (smoke trails, neon-green energy arcs), and art style (1980s cyberpunk anime aesthetic).

展开提示词全文
(VARIABLE SCENE - EDIT HERE):
Nighttime, expansive {argument name="cityscape" default="Neo-Tokyo"} highway. Futuristic cityscape background with neon lights.
Strong one-point perspective: The road stretches straight from the bottom edge to the vanishing point in the center.

(CRITICAL COMPOSITION):
One-point perspective composition with the subject in the CENTER.
Subject Orientation: The motorcycle is shown in SIDE PROFILE (facing Screen Left).
TILT ANGLE: The motorcycle body is LEANING HEAVILY TOWARDS THE CAMERA (The top of the bike is closer to the viewer than the wheels).
Movement direction: The bike is sliding away from the camera, moving from the foreground deep into the background.
Placement: Bike is perfectly centered in the frame.

(SUBJECT):
A futuristic motorcycle and rider.
Motorcycle:
- Heavy, solid, rounded silhouette
- Minimal exposed mechanics, smooth cowling
- Wide, thick, high-grip tires
- Color scheme harmonized with rider
Rider:
- Face and outfit preserved from reference image
- Stare straight into the camera, glaring with a powerful, piercing gaze.
- Left foot planted firmly on the ground, struggling to support the heavy leaning bike
- Rider's leg is fully extended to brace against the fall

(ACTION & MECHANICS):
High-speed linear slide braking (NOT cornering).
The bike is sliding sideways while traveling backwards into the depth of the scene.
Instability: The bike is on the verge of falling over towards the screen.
Wheels are locked (not rotating).

(VISUAL EFFECTS - SMOKE TRAILS):
Three distinct, straight trails of thick white smoke.
Direction: Smoke stretches from the IMMEDIATE FOREGROUND (bottom of screen) directly to the motorcycle's wheels and rider's foot in the center.
The smoke trails act as leading lines pointing to the subject.
Violent debris and asphalt fragments kicking up.

(ENERGY EFFECTS):
Neon-green lightning energy arcs (1980s anime style) embedded within the white smoke trails.
Green energy flows through the smoke, following the straight lines from foreground to the bike.

(ART STYLE):
Cel-shaded animation, 1980s anime aesthetic (Cyberpunk).
High contrast, bold black shadows, dramatic lighting.
Poster-quality, ultra-high resolution, sharp focus.

Folded Paper Blueprint of a Character

game-asset

A prompt for Nano Banana Pro requesting a hyper-detailed image of a specified character constructed entirely from folded paper, resembling a blueprint with geometric folds, crease lines, and architectural art style.

展开提示词全文
A hyper-detailed folded-paper blueprint of [{argument name="character" default="character"}], where the character is constructed from precise geometric folds and crease lines, overlaid with subtle blueprint markings, measurement lines, and paper annotations. Minimal color palette, off-white paper with faint ink lines. Studio lighting, crisp shadows, architectural art style, photorealistic paper detail. 1080x1080 square format.

Image Synthesis/Composition Prompt

game-asset

A prompt used to composite two characters (Ukyo and a ninja girl) into a game screen image from Samurai Shodown (Samurai Spirits). This demonstrates Nano Banana Pro's image synthesis capabilities.

展开提示词全文
Make Ukyo-chan and a glasses-wearing Kunoichi fight in the image of the Samurai Shodown game screen

Generating Figure-Style Images from Still Photos

game-asset

A simple prompt for transforming a still image into two figure-style images, noting the high quality of the resulting image and text on the packaging.

展开提示词全文
Generate 2 figure-style images from a still image.

Y2K Style Translucent Motorbike Product Design

game-asset

A prompt for generating a hyper-realistic, high-contrast product design image of a translucent dark motorbike with large wheels, featuring a biker in baggy camo and an oversized black hoodie. The style is inspired by Teenage Engineering and Y2K aesthetics, rendered using Octane with dynamic side view and fast shutter effect.

展开提示词全文
Translucent Dark motorbike with big wheels with a biker pilot bended on his motorbike full speed with large camo baggy and black oversized hoodie and short hair, wearing {argument name="glasses brand" default="Gentle Monster"} glasses, visible complex motor on the back, dynamic side view, product design minimalism, in the style of {argument name="design style 1" default="Teenage Engineering"} and {argument name="design style 2" default="Y2K style"}. matte plastic surfaces, plain gray background studio lighting, hyper-realistic. Octane render, cinematic framing fast shutter effect, high contrast, sharp bike details, professional motorsport photography style, 4K ultra realistic high-speed feeling, shallow depth of field.

Object-to-Dystopian Building Transformation

game-asset

A multi-step prompt instructing the AI to transform a small uploaded desktop object (like a stapler) into a monumental, dystopian Brutalist concrete building, generating blueprints, an eye-level street view, and an interior lobby shot.

展开提示词全文
Task: Turn small desktop objects into monumental dystopian buildings. 

Step 1: Upload image.... e.g. a {argument name="object" default="stapler"}

Step 2: Scale this object up by 5000%. It is now the headquarters for a villainous mega-corporation in a Brutalist concrete future. Analyze the geometry to create habitable floors."

Step 3 Output: 2x2 Grid.
Grid 1 & 2: Blueprints of the "Object turned into Tower" showing elevator shafts and executive suites.
Grid 3: Eye-level street view looking up at the concrete mega-structure in rain and fog. Tiny people for scale. Neon cyberpunk signs attached to the exterior.
Grid 4: Interior shot of the lobby, retaining the plastic curves of the original object but rendered in cold concrete and glass.

Consistency Prompt for 360 Turnaround Views

game-asset

A pair of prompts designed for image-to-image consistency, instructing the AI to generate 360-degree turnaround views (headshots and full-body shots) of a subject from a previously generated reference image (@img1).

展开提示词全文
A 360 turnaround view of the subject in (@)img1 , Close up, straight in 4 different angles, headshots, all white background

A 360 turnaround view of the subject in (@)img1 , straight in 4 different angles, full-body shots, all white background

Thermal X-Ray Style Infographic Prompt (Nintendo Switch Example)

game-asset

A detailed prompt template for Nano Banana Pro to generate images in a high-contrast, scientific studio rendering style, specifically mimicking false-color thermal X-ray views. The example application generates a detailed internal view of a Nintendo Switch handheld console, specifying components, simulated temperatures, and color gradients.

展开提示词全文
A {argument name="subject" default="[subject]"} rendered in high-contrast scientific studio rendering against a pure black void background. This tight {argument name="viewpoint" default="[viewpoint]"} capturing the {argument name="angle" default="[angle]"} adopts a false-color thermal X-ray art style. Through the transparent outer shell, the {argument name="internal structure elements" default="[internal structure elements]"} clearly emerge, detailed with vivid heatmap gradients. The color palette transitions from deep, cool blue to intense yellow and red highlights, creating a futuristic, clinical appearance with orthographic projection and a soft, neon-like glow.

TEXT: "THERMAL X-RAY / ORTHOGRAPHIC VIEW / {argument name="subject name" default="[subject name]"} / TEMP: {argument name="temperature" default="[temperature]"}°C"
---

Nintendo Switch Prompt 👇
---
A Nintendo Switch console (handheld mode) rendered in high-contrast scientific studio rendering against a pure black void background. This tight profile view capturing the right side adopts a false-color thermal X-ray art style. Through the transparent body case and display glass, the precise internal structure of the handheld gaming device—consisting of the central NVIDIA Tega custom processor, 6.2-inch LCD display panel, battery cells, cooling fan and heat dissipation mechanism, left and right Joy-Con connection slots, game card slot, and circuit board wiring pattern—clearly emerges, detailed with vivid heatmap gradients. The Tega processor, slightly above center, is expressed in vibrant orange to yellow, indicating moderate heat during operation (55-65°C). The small cooling fan behind it shows efficient cooling effect in blue-green. The large capacity lithium-ion battery (4310mAh) at the bottom shows a uniform deep blue to blue-green, indicating safe operating temperature (20-30°C). The 6.2-inch display panel shows minor backlight heat (35-40°C) in green to yellow-green. The left and right Joy-Con connection rail parts show a low-temperature state in pale blue. The game card slot at the top shows an unused state in dark blue. The color palette transitions from deep, cool blue (battery cooling area) to intense yellow and orange highlights (Tega processor), creating a futuristic, clinical appearance with orthographic projection and a soft, neon-like glow. The power-saving design and efficient thermal management system required for portability are precisely arranged within the compact chassis, making visible the heat conduction paths via heat pipes, blue arrows indicating airflow, and the placement of electronic components on the board. The precision of the symmetrically placed Joy-Con connection mechanism and the beautiful design of the processing system centralized in the middle of the console stand out.

TEXT: "THERMAL X-RAY / ORTHOGRAPHIC VIEW / NINTENDO SWITCH HANDHELD MODE / TEGA CHIP TEMP: 58°C / BATTERY TEMP: 25°C"

Prompt for UV Unwrapping a 3D Model

game-asset

A prompt for Nano Banana Pro used for 3D asset processing, specifically instructing the model to unwrap the UVs of a provided 3D model. It specifies the desired output layout, requiring the UV layout for the head, body, and limbs to be flattened into a single 0–1 two-dimensional UV space, alongside a reference view of the 3D model.

展开提示词全文
unwrap the UVs of the 3D model shown in the image.
About one-third of the image should be a reference view displaying the 3D model itself.The remaining area should include the UV layout for the head, body, and limbs.Unwrap the surface of the 3D model and flatten it into a single 0–1 two-dimensional UV space.

Kratos in Three Blended Styles

game-asset

A prompt for blending multiple distinct artistic styles—Norse realism, anime battle effects, and stylized shadow-art silhouettes—to depict the character Kratos from God of War, with the instruction that he should appear in all three styles simultaneously within the shot.

展开提示词全文
With God of War’s Realm Composer, blending Norse realism, anime battle FX, and stylized shadow-art silhouettes becomes simple. In this shot, {argument name="character" default="Kratos"} appears in all three styles at once.

Fortnite Fusion Engine Prompt for Gamers

game-asset

A specialized prompt for Nano Banana Pro, utilizing a fictional 'Fortnite Fusion Engine' concept to merge disparate gaming aesthetics—low-poly survival, cel-shaded anime, and hyper-real battle characters—into a single scene on a floating island.

展开提示词全文
“With Fortnite Fusion Engine, you can merge low-poly survival style, cel-shaded anime skins, and hyper-real battle characters instantly. Here, a low-poly soldier, an anime ninja, and a realistic mercenary all team up on one floating island.”

Cute Chibi Diorama Lamp Generator

game-asset

A template prompt for creating cute, isometric 3D cube dioramas with internal lighting. It uses a chibi figurine style with matte PVC material, focusing on filling the scene with small, cute details and adding imperfections for realism.

展开提示词全文
A {argument name="subject" default="subject"} is {argument name="doing something" default="doing something"} in a {argument name="place" default="place"}. Isometric 3D cube diorama with internal lighting, cute chibi figurine style, matte PVC material, big head/small body. Neutral background on a table in a dark room. Enclosed in a cube. Fill the diorama with many cute little details. Add delicate imperfections like dust, scratches and textures to make it real.

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。

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。

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

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,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。

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。