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 725 条
Workflow for Style Transfer and Storyboard Generation
game-assetThis is not a single prompt but a description of a multi-step workflow using Nano Banana Pro for style transfer and storyboard creation, requiring both a character image and a reference image for the desired style ('inflated' character).
展开提示词全文
realistic image of my character + reference image of an "inflated" character
Character Turnaround Sheet Generation
game-assetA simple text prompt used with Nano Banana Pro to generate a three-view turnaround sheet (front, side, back) of a character based on an uploaded source image created with Stable Diffusion. This demonstrates how to quickly create character design assets.
展开提示词全文
Please create a three-view turnaround sheet for the attached girl.
Pixar-Style 3D Avatar Generation
game-assetA prompt designed to convert an uploaded profile picture into a high-quality 3D avatar using a Pixar-style aesthetic, emphasizing cheerful expression, smooth textures, and exaggerated, cute proportions.
展开提示词全文
Create a high-quality 3D avatar of the person in the uploaded image with a cheerful, expressive face. The character should have a warm smile, bright eyes, and soft facial features that feel friendly and approachable. Render in a Pixar-style aesthetic with smooth textures, subtle skin shading, and slightly exaggerated proportions for a cute, animated look. Lighting should be soft and even, creating a clean studio look with gentle shadows for depth.
Dramatic Character Transformation Prompt
game-assetA Nano Banana Pro prompt designed to transform an original photo into four different photorealistic, ultra-detailed character styles, using mid close-up wide-angle shots and extreme, dynamic camera angles.
展开提示词全文
Transform the original photo into a dramatic, photorealistic, ultra-detailed set of 4 different styles characters are included , each a mid close up wide-angle shot with an extreme, dynamic camera angle with different positioned right next to the lens and appear huge.
Selfie to Claymation Transformation
game-assetA prompt used with Nano Banana Pro to transform a selfie into a claymation style, focusing on realistic clay texture, visible fingerprints, and the warmth of stop-motion animation. The prompt is shared in the second image of the tweet.
展开提示词全文
A close-up shot of a man with scissors, claymation, stop motion animation, miniature diorama, realistic clay texture, visible fingerprints, warm lighting, high detail, 8k
Generating an Isometric Room Illustration Based on a Character Concept
game-assetA prompt used with Nano Banana Pro to generate an isometric illustration of a room that reflects a specific character's personality, explicitly excluding the character themselves from the image.
展开提示词全文
Please describe this character's room in an imaginary isometric illustration. No depiction of the person is requested.
3D Isometric Diorama of a Household Object as Architecture
game-assetA prompt for generating a clean, minimal 3D isometric diorama where a specified household object is transformed into a small architectural structure. It emphasizes realistic materials, soft studio lighting, and a miniature architectural model style.
展开提示词全文
A clean, minimal 3D isometric diorama transforming a {argument name="household object" default="HOUSEHOLD OBJECT"} into a small architectural structure. Functional elements are abstracted into doors, windows, and volumes, realistic materials, soft studio lighting, rounded edges, miniature architectural model style, neutral background.
360-Degree Equirectangular Panorama Prompt
game-assetA highly technical prompt designed to generate a seamless 360-degree equirectangular panorama image, optimized for consistent lighting and composition across the full spherical view. It specifies a historical scene and includes rules to prevent visual artifacts like seams or directional shadows, making it ideal for virtual reality environments.
展开提示词全文
[SCENE] = {argument name="scene description" default="Troy, Anatolia, approx. 12th century BC. The moments after the Trojan Horse is pulled inside the city walls."}
Make a 360-degree equirectangular panorama in 21:9 aspect ratio.
Render the scene as a full spherical panorama with correct equirectangular projection.
Set the entire environment strictly based on [SCENE].
Place the camera at the exact center of the scene with a fixed viewpoint.
Design the environment as a continuous, circular world with no left or right edge.
Ensure the first and last horizontal edges align perfectly.
Distribute architecture, people, and objects evenly around the full 360° view.
Use realistic real-world lighting, materials, and physical behavior.
Keep sharp focus across the entire panorama.
Use uniform natural daylight with no dominant light direction.
Ensure lighting intensity and color remain consistent across the full 360° panorama.
Treat the environment as lit by an evenly diffused sky dome rather than a single sun source.
Apply soft global shadows that do not favor any horizontal direction.
Avoid directional sunlight gradients that could cause seam lighting mismatches.
Avoid modern elements, UI overlays, borders, frames, cropped views, fantasy styling, or broken panorama seams.
2000s Character Design Prompt
game-assetA simple, high-level prompt intended for the Nano Banana Pro model to generate character designs reminiscent of the 2000s aesthetic. The full, detailed prompt is implied to be in the linked image, but the core instruction is provided.
展开提示词全文
2000’s character design
Wingman Character Fighting Pose Generation
game-assetA detailed prompt for generating an image of a character from 'Wingman' in a fighting pose, based on an uploaded character sheet. It specifies faithful reproduction of details and coloring, a dynamic camera angle (diagonal side view), and a specific setting (posing on a cliff overlooking the sea). The output is requested in a realistic photo style with a 16:9 aspect ratio.
展开提示词全文
Please create a fighting pose for the attached character based on the character sheet. Faithfully reproduce the character's details and coloring. Recreate the scene with a camera angle from a diagonal side view, depicting the character posing on a cliff overlooking the sea. Use a realistic photo style, and output the aspect ratio as 16:9.
Transform Portrait into 3D Action Figure
game-assetA prompt designed for image-to-image transformation, instructing the AI to convert an uploaded portrait into a stylized 3D action figure. It specifies the style (glossy plastic toy, simplified features, big eyes) and the background (toy store shelf with blurred boxes), while requiring the main facial characteristics of the original person to remain recognizable.
展开提示词全文
Turn this portrait into a stylized 3D action figure of this person. Style: plastic toy with glossy finish, big eyes, simplified features. Background: toy store-style shelf with blurred boxes. Constraints: keep main facial characteristics recognizable.
Minimalist 3D Isometric Exhibition Pod Diorama
game-assetA template prompt for generating a clean, minimal 3D isometric diorama image. It is designed for visualizing a pop-up exhibition space, allowing the user to customize the type of exhibition, the objects displayed, and the structure of the pod, all rendered in a miniature architectural model style with soft studio lighting.
展开提示词全文
A clean, minimal 3D isometric diorama of a {argument name="exhibition type" default="[EXHIBITION TYPE]"}, featuring {argument name="display objects" default="[DISPLAY OBJECTS]"} arranged within a {argument name="pod structure" default="[POD STRUCTURE]"}, subtle lighting accents, smooth floor surfaces, soft studio lighting, realistic materials, rounded edges, miniature architectural model style, high detail, neutral background.
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。