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 702 条
Cinematic 12-Panel Timeline of a Subject's Epic Day
comic-storyboardThis is a detailed image generation prompt designed to create a 12-panel (4x3) cinematic timeline. It captures an epic, chaotic, or hilarious day in the life of a specified subject, complete with timestamps, punchy captions, and richly detailed scenes. The overall visual UI, backdrop, and panel frames are themed to match the subject's universe, such as arcane scrolls for wizards or chrome HUD for cyborgs.
展开提示词全文
"In the Day of {argument name="subject" default="[SUBJECT]"}": Design a 12-panel (4x3) cinematic timeline capturing an epic, chaotic, or hilarious day in the life of {argument name="subject" default="[SUBJECT]"}. Add this title in a style that matches the subject to the top of the image. Each panel must be [PHOTOREALISTIC], large, and show:
a timestamp (e.g. 06:00, 08:00...)
a short, punchy caption in quotes (e.g. "Potion Mishap", "Midnight Bounty Run")
a richly detailed, high-energy scene tailored to that moment of their day.
The overall backdrop, panel frames, textures, and visual UI elements must match the subject’s universe — e.g., {argument name="theme example" default="leather + studs for rockstars"}, arcane scrolls for wizards, chrome HUD for cyborgs, jungle vines for pirates, etc.
Panels are arranged in a grid or storyboard, with rugged or themed dividers. Final panel (06:00 next day) shows collapse, rest, or post-chaos resolution.
Daily Nano: Playing with Shadows 4-Panel Comic
comic-storyboardThis tweet shares a 4-panel comic created using the Nano Banana Pro tool, centered around the theme of 'playing with shadows.' The comic aims to bring a little chuckle to the reader in the final panel.
展开提示词全文
[Today's Nano]
Today's theme is {argument name="theme" default="Playing with Shadows"}
I'd be happy if the last panel makes you chuckle a little 😊
👉This 4-panel comic was also created with nano banana pro
Cinematic Storyboard Contact Sheet Prompt for Nano Banana Pro
comic-storyboardThis is an image generation prompt designed for Nano Banana Pro to create a 3x3 cinematic storyboard contact sheet. It details a sequence featuring a young woman in a frozen alpine winter setting, specifying the arrangement of nine distinct panels, including close-ups, medium shots, and wide shots, all unified by a moody blue-hour twilight aesthetic and high-quality film photography style.
展开提示词全文
A 3x3 cinematic storyboard contact sheet consisting of 9 distinct panels arranged in a grid. The sequence features a young woman with {argument name="hair color" default="platinum blonde"} hair in a frozen alpine winter setting.
The panels display various angles and shots:
Close-ups: Focusing on her rosy cheeks, blue-grey eyes, and snowflakes on her eyelashes.
Medium shots: Showing her wrapped in a {argument name="coat color" default="black"} wool coat and blue knit scarf, holding a bouquet of dried white flowers.
Wide shots: Capturing her standing alone on the frozen lake with towering snowy mountains in the background.
The lighting is consistent moody blue-hour twilight across all frames. High-quality film photography aesthetic, photorealistic, 8k resolution, coherent character and color grading.
16:9 Contact Sheet Generation from Reference Image
comic-storyboardA prompt for generating a stacked contact sheet of 16:9 aspect ratio images, derived from an original uploaded picture, featuring close-ups of the characters and a final panel showing a phone screen recording audio, while respecting the original image's details and lighting.
展开提示词全文
I want a stacked contact sheet of 16:9 aspect ratio images that respect the details of the character and setting details and well as the lighting of the original picture. Top panel: Original uploaded image Next panel: Medium close up of her Next panel: Medium close up of him Bottom panel: close up of the phone screen with a graphic showing it is recording audio
Cinematic Storyboard of Woman and Bear in Forest
comic-storyboardA prompt for generating a 3x3 grid storyboard collage featuring a young woman in traditional patterned clothing sitting beside a large, calm bear in a misty mountain forest. The style is highly realistic, cinematic, and emphasizes detailed textures and golden hour lighting.
展开提示词全文
{
"subject": "3x3 grid storyboard collage of a young woman sitting beside a large calm bear in a natural mountain forest setting",
"clothing": "Traditional patterned clothing with beads and earth-tone fabrics, textured material with handcrafted details",
"hair": "Long dark braided hair, neat braids resting over shoulders",
"face": "Serious, calm, focused expression with natural skin texture, subtle emotion and intensity",
"accessories": "Handcrafted bead details, natural fabric elements, no modern items",
"environment": "Outdoor mountain landscape with trees, misty forest background, soft depth of field, atmospheric wilderness",
"lighting": "Warm sunlight rays, gentle shadows, golden hour tones with soft natural highlights across face and fur",
"camera": "Full body, medium shots, dramatic close-ups, over-the-shoulder, cinematic low angle, atmospheric wide establishing shots",
"style": "Highly realistic, cinematic, film still aesthetic, warm tones, natural imperfections, detailed textures on fur, skin, and fabric"
}
Style Change Prompt for Damaged Areas: Lost Love Girls
comic-storyboardPart of a 'Tennen's Prompt Festival' series, this prompt is designed to change the art style specifically in damaged or torn areas of an image, originally intended for illustrations and likely compatible with realistic images.
展开提示词全文
Lost Love Girls Gathering energy while picking up trash. [Prompt to change the art style only in torn areas]
IT Education Manga Generation Prompt
comic-storyboardA user is testing Nano Banana Pro's ability to create educational manga, specifically focusing on the concept of Microsoft Azure subscriptions. The results and prompt details are shared in a linked note.
展开提示词全文
I'm testing if I can create IT education manga. The subject is the concept of Microsoft Azure subscriptions.
Nano Banana Pro Prompt for Generating 'Viral Diagrams'
comic-storyboardAn announcement about an updated guide that includes a 'secret prompt' for generating 'viral diagrams' instantly using Gemini 'Nano Banana Pro,' along with prompts for creating diagram bots and four-panel comics.
展开提示词全文
Secret prompt revealed for instantly generating "viral diagrams" with Gemini "Nano Banana Pro" ・ Diagram creation Bot ・ Four-panel comic creation
Existential Cinematic Solitude Film Still
comic-storyboardA prompt for creating a cinematic film still drenched in emotional weight, inspired by 1970s existential cinema (Vilmos Zsigmond). It focuses on profound solitude, cold blue hour lighting, rain-streaked glass distortions, and a muted, desaturated palette, using technical details like analog grain and ray-traced reflections to create crushing atmospheric pressure.
展开提示词全文
[{argument name="subject" default="Subject"}], profound solitude captured in cinema, hyper-real film still drenched in emotional weight, cold blue hour lighting with dying warmth at the edges, rain-streaked glass creating liquid distortions, shallow depth of field emphasizing loneliness, muted desaturated palette with isolated color accents, slow-motion implied stillness, fine analog grain reminiscent of 1970s existential cinema, lens flares bleeding into darkness, ray-traced reflections in pooling water, breath visible in cold air, negative space dominating the frame, crushing atmospheric pressure, intimate yet distant camera positioning, Vilmos Zsigmond-inspired melancholic cinematography, the weight of unspoken grief.
Detective Evidence Board Generation
comic-storyboardA prompt designed to generate a visual concept of a detective's evidence board, simulating an obsessive, late-night noir atmosphere. It details the cork board's contents: polaroids, maps, newspaper clippings, sticky notes, and red string connecting the evidence, emphasizing dramatic shadows from a single bare bulb and realistic clutter like coffee stains.
展开提示词全文
"A detective's evidence board investigating \\{argument name="subject/mystery" default="[SUBJECT/MYSTERY]"}\\\. Cork surface covered with pinned items: polaroid photographs with handwritten dates, a street map with circled locations, newspaper clippings with highlighted passages, sticky notes with theories and question marks, and printed documents with redacted black bars. Red string connects related evidence across the board, creating a web of connections. Thumbtacks in primary colors. A single bare bulb casts dramatic shadows. Coffee ring stains on some papers. The atmosphere is obsessive, late-night, noir—someone has been piecing this together for months. A few pins have fallen, suggesting frantic recent activity."
Gemini Nano Banana Pro 3.0 Stranger Things Edition Prompt
comic-storyboardThis prompt is designed for the 'Gemini Nano Banana Pro 3.0' model, specifically for generating content related to the 'Stranger Things' theme. The prompt instructs the model to create a story or scenario where a {argument name="character name" default="young boy"} discovers a mysterious {argument name="object" default="glowing orb"} in the woods, setting the stage for a supernatural adventure.
展开提示词全文
You are a storyteller for the Gemini Nano Banana Pro 3.0, specializing in the aesthetic and narrative style of 'Stranger Things'. Write a short story about a {argument name="character name" default="young boy"} named {argument name="boy's name" default="Mike"} who, while exploring the woods near his suburban home in the 1980s, discovers a mysterious {argument name="object" default="glowing orb"} that hums with an otherworldly energy. The discovery must lead to the first encounter with a supernatural element, setting the tone for a thrilling adventure.
Eraser Gun Style Prompt for Nano Banana Pro (Fighting Pose Stage)
comic-storyboardA multi-stage prompt designed to generate a character performing an 'Eraser Gun' style energy wave attack, similar to Dragon Ball techniques. This is the first stage prompt, which changes the character's pose to a fighting stance while strictly preserving the original art style from a reference image.
展开提示词全文
subject: > The character exactly as shown in the reference image, preserving the original art style, proportions, line quality, coloring, texture, and overall visual appearance without alteration. composition: > Bust-up shot, frontal view, framing from the upper chest to the top of the head, balanced composition consistent with the reference image style. Aspect ratio is 16:9. action: > The character performs a clear pre-attack pose, crossing both arms above the head with clenched fists, slightly lowering the hips (implied through posture and shoulder angle), while shouting loudly with mouth wide open. The posture conveys physical tension and preparation. No additional visual effects. location: > Same environment as the reference image, unchanged background and setting. style: > Identical to the reference image. Do not modify or reinterpret the art style in any way. camera_lighting: > Same camera angle, lighting direction, and shading as the reference image, without enhancement or dramatization. colors: > Preserve the original color palette exactly as in the reference image. text: > None. edit_instructions: > Change only the character’s pose: bust-up framing, arms crossed above the head, shouting facial expression. Lowered hips are implied through upper-body posture only. Do not add effects, glow, motion lines, or stylistic changes. references: > Reference Image A: character identity, art style, and environment. extras: > High fidelity reproduction of the reference image style, no stylization, no reinterpretation.
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。
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。
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。