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
Structured Prompt for Automated Manga Generation
comic-storyboardA structured prompt template used in a pipeline combining Claude and Nano Banana Pro to automatically generate cooking manga. It defines parameters for the scene, characters, dialogue, and specific prompts for both the manga panel and the real-life cooking image.
展开提示词全文
Page, Panel, Panel Size, Scene Description, Character, Dialogue, Manga Part Prompt, Live-Action Cooking Prompt, Notes 1, 1, Large, Yuta plates Japanese food in a Western style, Yu...
Nano Banana Pro 4-Panel Comic Explanation
comic-storyboardA prompt instructing an AI to create a four-panel comic strip explaining the 'Nano Banana Pro' product, utilizing a specified character for the illustration.
展开提示词全文
Use this character to explain the {argument name="product name" default="Nano Banana Pro"} in a 4-panel comic!
Hyper-realistic crossover image of Zenitsu Agatsuma from Demon Slayer
comic-storyboardA detailed, hyper-realistic prompt for Nano Banana Pro that generates an image of Zenitsu Agatsuma from the anime 'Demon Slayer' stepping out of a giant physical manga book, blending the 8K photo-realistic world with the black-and-white manga panel style.
展开提示词全文
An astonishing hyper-realistic 8K photograph capturing the moment {argument name="character name" default="Zenitsu Agatsuma"} from "{argument name="manga name" default="Demon Slayer"}" steps out of a giant physical manga book.
Zenitsu in the real world:
Zenitsu's image is photorealistic, with messy gold and orange hair, wearing a realistically textured Demon Slayer Corps uniform and his iconic yellow haori with white triangle patterns. His expression is determined, his eyes sharp, full of resolve, tightly gripping his Nichirin blade in its sheath. Half of his body has stepped onto the wooden bedroom floor, while the other half remains within the manga pages.
The giant manga book and interaction:
A giant, thick Japanese edition of "Demon Slayer" manga book is spread open on a slightly worn wooden floor. Zenitsu breaks the boundary of the paper, and the pages are violently torn, curled, and burst where he steps out, with paper scraps and toner flying in the air.
Details within the manga page (picture-in-picture):
The pages display an extremely authentic black-and-white Japanese manga style.
Style: Rough black ink lines, rich screentone textures for shading, exaggerated speed lines.
Layout: Strict Japanese right-to-left reading order, a surreal four-panel manga (yonkoma) spread.
Content: Inside the broken panel, a trapped, manga-style Zenitsu can be seen. He is wearing the same clothes, shedding noodle tears in the panel, frantically knocking on the borders of the manga panel, accompanied by large Japanese onomatopoeia like "出られない!" (Can't get out!), "えええ!?", and "ドンドンドン" (Knocking sound). The manga version of him is watching the real-world version of himself tear the frame in terror.
Environment and lighting:
The bedroom background is soft-focused, with domestic items like bed legs and bookshelves. Natural afternoon light streams in from the side window, illuminating the edges of the torn paper and the fabric texture of Zenitsu's clothes, emphasizing the strong contrast between reality and the two-dimensional world.
Ink Noir Portrait Generation Prompt
comic-storyboardA detailed image generation prompt designed for a high-contrast ink noir portrait. It specifies the use of expressive black ink strokes and controlled splatter, emphasizing heavy shadows and selective highlights created through negative space. The goal is to achieve a moody, cinematic, graphic novel aesthetic.
展开提示词全文
A high-contrast ink noir portrait of {argument name="subject" default="[SUBJECT]"}, illustrated entirely with expressive black ink strokes and controlled splatter. Heavy shadows dominate the composition while selective highlights emerge through negative space. Subtle paper grain is visible. Atmosphere is moody, cinematic, and intense, like a graphic novel frozen at its most dramatic panel.
Nano Banana Pro Storyboard Prompt Pattern
comic-storyboardThis is a prompt pattern designed for Nano Banana Pro to generate storyboards. The user is instructed to use this pattern and only change the scene description for each panel to maintain consistency across the storyboard.
展开提示词全文
A storyboard panel, depicting a scene of {argument name="scene description" default="a young woman sitting alone in a dimly lit cafe, rain streaks down the window, her expression is melancholic"}. The style is clean, cinematic, and black and white, with strong contrast and deep shadows. The composition is a medium close-up, focusing on the character's face and the atmosphere of the cafe. Aspect ratio 16:9.
Style Transfer for Cinematic Live-Action Keyframes
comic-storyboardA straightforward prompt used for style transfer, instructing the model to convert a set of keyframes (presumably from a movie clip) into a realistic live-action cinematic style. The key instruction is to maintain the exact grid layout and cell positions from the input image.
展开提示词全文
“This is a set of keyframes from a movie clip. Convert each cell into a realistic live-action cinematic style. Keep the final output in the exact same grid layout, and do not change the position of any cell.”
Generating Rich 4-Panel Manga with NanoBanana Pro
comic-storyboardA simple prompt for NanoBanana Pro to quickly create a rich, 4-panel manga strip based on a provided text. The prompt specifies a cute, pop art style, characters, and panel layout, making it useful for generating content like manga advertisements or landing page comics.
展开提示词全文
"Using the following text, please create a rich 4-panel manga. The design tone and manner should be a cute, pop art style with characters and panel division."
Documentary Style Image Generation with Nano Banana Pro
comic-storyboardThis prompt template is designed for Nano Banana Pro to generate images in the style of a documentary TV program, complete with split-screen scenes (2x2 grid), superimposed text (telop), and picture-in-picture (wipe). Users upload a person's photo and then use this prompt, customizing the documentary's theme to create different scenarios, such as a '24-hour ramen shop' or 'former idol working in a local factory.'
展开提示词全文
Generate differential images based on the attached image, in the style of the documentary program "{argument name="program theme" default="24-Hour Ramen Shop, Beautiful Solo Female Staff"}". The image is composed of four scenes divided into a 2x2 grid. Generate superimposed text (telop) and a picture-in-picture (wipe) as if it were a TV program.
Four-Panel Manga Creation Prompt (Version 2 with Formatting)
comic-storyboardAn updated version of the manga generation prompt, adding specific formatting requirements: all dialogue must be in vertical Japanese text, speech bubbles must progress from right to left, and clarifying that 'gibasa' is a dialectal name for 'akamoku'.
展开提示词全文
The attached pink-haired woman is "Nagisa no Yosei Gibasa-chan" (Gibasa-chan the Fairy of the Shore). Please create a four-panel manga where this character introduces herself. The four panels should follow the Kishōtenketsu structure and include a punchline. - Nagisa no Yosei Gibasa-chan is a fairy of the seaweed called akamoku. - The attached image of seaweed in the sea is akamoku. Please include an image that conveys the image of akamoku. - All dialogue must be written vertically in Japanese. - Speech bubbles should progress from right to left. - "Gibasa" is a dialectal name for "akamoku." - The attached image of food topped with something is akamoku rice. Akamoku rice is a typical way to eat akamoku, so please include a panel where Gibasa-chan is eating akamoku rice.
Behind-the-Scenes Selfie Identity Swap Prompt
comic-storyboardA prompt for generating a photorealistic image where the subject's identity and outfit are preserved from a reference image, but the background is replaced with a chaotic, real behind-the-scenes set from the movie 'Léon: The Professional'. The subject, Léon, and Mathilda are taking a selfie together amid crew members and filming equipment.
展开提示词全文
Keep the subject’s facial features and outfit from the reference image unchanged. Replace the background with a real behind-the-scenes set photo from Léon: The Professional. In the foreground, Léon, young Mathilda, and the woman from the reference image are taking a selfie together. The background shows the film’s shooting location, with crew members, filming props, and multiple camera setups visible. Aspect ratio 9:16, with a subtle cinematic film grain.
1-Minute Challenge: Setsubun Manga
comic-storyboardA user completed the 'Nano Banana Pro 1-Minute Challenge' by generating a short manga about Setsubun (Bean-Throwing Festival), suggesting that SNS-bound manga can now be created in just one minute.
展开提示词全文
I'll draw it again next month, but it's a manga about Setsubun.
Character Breaking Out of a Comic Book
comic-storyboardA prompt for an ultra-realistic cinematic scene where a real human character bursts dynamically out of a giant open comic book lying on the floor. The prompt specifies preserving only the facial identity from a reference image while detailing the character's outfit, the messy aesthetic room environment, and the blend of comic art and reality.
展开提示词全文
{
"type": "image_generation_prompt",
"output_goal": "Ultra-realistic cinematic scene where a real human character bursts out of a giant open comic book, blending comic art and reality while preserving only the facial identity from the reference image.",
"reference_image": {
"use_uploaded_image": true,
"identity_lock": "face_only",
"preserve": [
"facial bone structure",
"nose shape",
"eye spacing",
"jawline",
"beard pattern"
]
},
"subject": {
"identity": "same person as reference face",
"expression": "intense, focused",
"outfit": "white t-shirt, {argument name="hoodie color" default="red"} hoodie, blue jeans, Air Jordan 1 sneakers",
"pose": "dynamic forward motion, breaking through torn comic pages"
},
"environment": {
"scene": "giant open comic book on the floor of a detailed aesthetic room",
"comic_pages": "illustrated versions of the same character inside panels",
"room": "messy floor with clothes, books, random objects, wooden furniture",
"walls": "comic art blending into real textures",
"effects": [
"floating paper fragments",
"subtle dimensional cracks",
"multiverse shimmer"
]
},
"lighting": {
"type": "natural daytime",
"mood": "rich cinematic realism"
},
"camera": {
"shot": "medium-wide",
"lens": "35mm",
"focus": "sharp subject, balanced depth"
},
"style": {
"resolution": "8K",
"detail": "realistic fabric, torn paper fibers, dust",
"tone": "surreal yet grounded"
}
}
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。