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
4-Panel Manga Generation Prompt
comic-storyboardA prompt used to generate a 4-panel slice-of-life manga in one shot using Nano Banana 2, featuring the cat 'Matatabi' and the red-haired girl 'Zan-chan'.
展开提示词全文
Create a slice-of-life heartwarming 4-panel manga starring the cat "Matatabi." Also, feature the red-haired girl "Zan-chan."
Wild West Sci-Fi Time Travel Scene Prompt
comic-storyboardA highly specific, cinematic prompt comparing Nano Banana Pro and Nano Banana 2. It describes a low-angle, wide shot of a 2027 astronaut from SpaceX walking down a desolate 1852 street, featuring a Tesla with rocket boosters, a burning jail, and a woman lighting dynamite, all shot on 35mm film with a muted color palette.
展开提示词全文
low angle wide shot at 45-degree side view of an astronaut walking down a desolate street at night, the time period is 1852, the astronaut is from 2027 and works for space x. The street is dirt and the air is hazy with light fog, there are two horses by a water trough in front of a hotel on the left of frame, there is a sign on the hotel that says Hilton, and on the right in the background a small building with a sign that says jail is just beginning to burn on fire, flames from inside the windows and licking up out of the roof, none of the other buildings in the small town street are on fire. on the right in the foreground slightly out of focus is a tesla with rocket boosters strapped to the back of it and standing near it is a beautiful woman in a mid 1800's dress is lighting a stick of dynamite, she has a devious smirk on her face. this scene is shot on a 35mm film camera with kodak film that has a daylight hue and has been graded with a muted color pallet
Mad Max Wasteland Survivor Film Still
comic-storyboardA detailed prompt for generating a photorealistic cinematic film still (no CGI) in the style of Mad Max: Fury Road. It emphasizes preserving the exact identity and imperfections of a subject from a reference photo, featuring them as a wasteland survivor gripping an improvised shotgun in a harsh, sun-blasted desert environment with strong teal and orange color grading.
展开提示词全文
Photorealistic cinematic film still live-action (no CGI). Preserve the subject's identity exactly from the reference photo: same facial structure, asymmetry, skin texture, pores, dirt, sweat. No beautification. Three-quarter body portrait, vertical. Torso angled sideways, head toward camera. Hands gripping a rugged improvised shotgun at waist level. Wasteland survivor - Mad Max: Fury Road visual language. Practical, battle-worn realism. Environment: open desert wasteland, orange sand and dust clouds, saturated turquoise sky. Background: slightly blurred post-apocalyptic pursuit vehicles, sense of imminent chase. Subtle motion blur and heat haze. Lighting: harsh overhead desert sun, extremely hard shadows. Rich detail in sun-bleached highlights and deep crushed shadows. Wardrobe & details: distressed leather, scarf around neck, dusty welding goggles on forehead. Windblown messy hair. Face smeared with engine grease and sand (naturalistic). Look & color: shot on 35mm film, Kodak Vision3 feel. Organic film grain, high contrast. Strong teal & orange grading, realistic skin tones. Emphasis on tactile realism: rusted metal, sand particles, sweat, grease, fabric weave. Final: raw, tense, sun-blasted, high-energy cinematic still.
Epic Car Chase Action Shot
comic-storyboardA simple prompt for Adobe Firefly using Nano Banana 2 to generate a cinematic action shot of five characters in a car chase, punctuated by Onomatopoeia-style graphic text.
展开提示词全文
action shot of all 5 [character references] in an epic car chase, Onomatopoeia style graphic punctuates the action, cinematic shot
Manga Retelling of a Novel Opening
comic-storyboardA story prompt designed to instruct an AI (Nano Banana 2 in Firefly) to read the opening of a specified novel and visually retell the beginning scene across five manga panels (one large, four small), using a classic black and white manga style with expressive ink lines.
展开提示词全文
Read the opening of the novel [{argument name="book" default="BOOK"}] by [{argument name="author" default="AUTHOR"}]. Create a manga page with one opening panel on the left side and four panels on the right side that visually retell the very beginning of the story. Each panel should follow the narrative progression of the opening scene. Classic black and white manga style, expressive ink lines, cinematic framing, strong storytelling composition.
Monster Hunter Alatreon Battle Scene
comic-storyboardA prompt used with Nano Banana Pro to generate an image of the Monster Hunter creature Alatreon in a scorching background, being attacked by ballista fire.
展开提示词全文
Background: Scorching heat Monster Hunter Alatreon etc Alatreon Illustration of repeatedly firing ballista shots
Treasure Map Adventure Prompt for Nano Banana 2
comic-storyboardA detailed prompt designed to generate a hand-drawn treasure map on aged parchment, where the map elements transition into a three-dimensional adventure scene, complete with landmarks, dangers, and a guardian element.
展开提示词全文
A hand-drawn treasure map on aged parchment, with the adventure erupting into three-dimensional quest. {argument name="starting point" default="STARTING_POINT"} rises at the map's edge with {argument name="departure scene" default="DEPARTURE_SCENE"}, the dotted path becomes an actual trail traversing {argument name="terrain 1" default="TERRAIN_1"} with {argument name="danger 1" default="DANGER_1"}, passing {LANDMARK_1} where {OBSTACLE_1} awaits. {TERRAIN_2} features {WILDLIFE_1} and {ENVIRONMENTAL_HAZARD}. The X marking the spot glows beneath {FINAL_LOCATION}, treasure partially visible, {GUARDIAN_ELEMENT} protecting it. Miniature expedition party frozen mid-journey at various points along the route. Torn edges of the map become cliffs. Coffee stains become lakes. Burn marks become scorched earth from battles past. Candlelight flicker, adventure novel lighting, 8K, the map as the story it promises.
Cel-Shaded Comic Strip Prompt for LOTR Poem
comic-storyboardA simple prompt for Nano Banana 2 (compared against Nano Banana Pro) to create a cute style, cel-shaded cartoon comic strip with textures depicting the One Ring poem from Lord of the Rings.
展开提示词全文
create a cute style cel shaded cartoon comic strip with textures that depicts the One Ring poem from LOTR.
Nano Banana Pro Dynasty Warriors/Final Fantasy Prompt (Full Screen)
comic-storyboardAn image generation prompt for Nano Banana Pro (Gemini 3 Pro Image) requesting a battle scene between Zhuge Liang and Sima Yi, styled like Final Fantasy X with a Water Dragon vs. Fire Dragon, performing a 'Shin Musou Ranbu' (True Musou Rampage), and filling the screen with as many minor characters as possible.
展开提示词全文
Zhuge Liang (person) VS Sima Yi Like Final Fantasy X Water Dragon VS Fire Dragon True Musou Ranbu Send as many minor characters as possible flying across the screen!
Nano Banana 2 Comic Coloring Prompt
comic-storyboardA prompt used to test Nano Banana 2's ability to color comics, requiring the model to translate Japanese text to Chinese, color the comic in a style matching the content and atmosphere, use master-level coloring, and maintain the original aspect ratio and perfect consistency.
展开提示词全文
Translate the Japanese text in this image into Chinese, and color this comic strip. The style must match the content and atmosphere of the comic, use master-level color matching, maintain the original aspect ratio, and maintain perfect consistency.
Haunting Cinematic Cliff Scene with Red Rose
comic-storyboardA prompt for generating a haunting cinematic scene featuring a pale woman in a medieval gown on a mist-shrouded cliff, reaching for a red rose offered by a figure in black armor (first-person perspective), emphasizing moody, desaturated blue-gray tones.
展开提示词全文
A haunting cinematic scene of a pale woman in a flowing white medieval gown standing at the edge of a towering cliff shrouded in mist. Her long dark hair moves softly in the wind as she reaches forward with both hands toward a single deep red rose being offered by a figure in black armor (first-person perspective). The atmosphere is moody and ethereal, heavy fog rolling over dramatic cliffs in the background. Desaturated blue-gray tones dominate the scene, with the
Funny 4-Part Story: Primitive Men and a Mobile Phone
comic-storyboardA prompt for generating a 4-part story and corresponding images about three primitive men encountering a mobile phone, maintaining character consistency and featuring emotional highs and lows, ending happily.
展开提示词全文
Create a funny 4-part story featuring 3 primitive men around a mobile phone. The story has emotional highs and lows and ends in a happy moment. Maintain consistent identity across the 3 characters. Generate 4 images in 16:9 format
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。