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 Giant Cat Chasing Tiny Woman
comic-storyboardA structured JSON prompt for a cinematic 3D photorealistic scene set in a kitchen, featuring a size disparity. A tiny woman (with a face reference) is running across the floor holding a scared German Shepherd, while being chased by a giant fluffy gray cat. It specifies warm dramatic lighting, shallow depth of field, and Pixar-level realism.
展开提示词全文
{
"scene": {
"type": "cinematic 3D photorealistic",
"setting": "kitchen",
"lighting": "warm dramatic",
"camera": {
"depth_of_field": "shallow",
"motion_blur": true,
"focus": "sharp"
},
"props": "scattered"
},
"subjects": [
{
"identity": "woman",
"size": "tiny",
"action": "running across wooden floor",
"holding": "scared German shepherd",
"face_reference": "use same face as reference image without changes"
},
{
"identity": "cat",
"size": "giant",
"appearance": {
"fur": "fluffy gray",
"eyes": "yellow"
},
"action": "chasing the woman and dog"
}
],
"style": {
"realism": "Pixar-level",
"detail": "ultra-detailed",
"resolution": "8K"
}
}
Nanobanana Prompt Engineering Workflow
comic-storyboardA user describes their workflow for creating high-quality Nanobanana prompts using a custom tool. The process involves defining the subject (e.g., polar bear and panda on skates), generating the initial image, performing detailed annotation (labeling parts like pose, background, face, clothing) based on file names, and finally adding compositional and color information for the final generation. This highlights the importance of detailed language specification for effective prompting.
展开提示词全文
① Create a "{argument name="character 1" default="Polar Bear"}" and a "{argument name="character 2" default="Panda"}" wearing ice skates, and the background location. Normal chat-based input is also OK. Whether you generate it all at once or separately, the process is the same.
② Perform annotation on the image.
This is the most troublesome part, so I made it a tool.
Based on the file name, I create a prompt that organizes "which part of which image to reference."
(Pose / BG / Face / Clothing, etc.)
③ Add supplementary information such as composition and color scheme for the final generation.
Photorealistic Ana de Armas as Spider-Woman in a Domestic Bathroom
comic-storyboardA highly detailed, photorealistic prompt designed to generate a medium shot of Ana de Armas in a form-fitting, black Spider-Man inspired bodysuit within a domestic bathroom setting. The prompt specifies technical details like 8k resolution, 35mm lens, and soft indoor lighting to achieve a celebrity photography style.
展开提示词全文
{
"prompt_data": {
"positive_prompt": "Photorealistic medium shot of {argument name="character" default="Ana de Armas"} standing in a domestic bathroom, wearing a form-fitting black sleeveless Spider-Man inspired bodysuit. The suit features a high neck, a dark grey spiderweb pattern, and a large spider emblem on the chest. She has dark brown hair tied back in a high messy ponytail with loose tendrils framing her face. She is leaning one hand on a red and black speckled granite countertop. In the background, there is a wooden door with a frosted glass panel and a framed vintage Avengers comic book poster hanging on a white wall. Soft, natural indoor lighting, 8k resolution, highly detailed skin texture, shot on 35mm lens.",
"negative_prompt": "cartoon, illustration, 3d render, anime, sketch, painting, low quality, jpeg artifacts, blur, bad anatomy, extra fingers, deformed hands, cross-eyed, text, watermark, signature, ugly, distorted face",
"subject_details": {
"character": "Ana de Armas",
"outfit": "Black Spider-Woman bodysuit, high-neck, sleeveless, spiderweb texture, chest logo, black thigh-high stockings visible",
"hair_style": "Dark brown, high ponytail, messy waves",
"pose": "Standing, facing forward, hand resting on counter, direct eye contact"
},
"environment_details": {
"setting": "Bathroom",
"elements": [
"Red granite countertop",
"Wooden door with vertical frosted glass insert",
"Framed Avengers comic book poster (Captain America cover)",
"Silver towel bar",
"White walls"
]
},
"technical_settings": {
"style": "Realism, Celebrity Photography",
"lighting": "Soft diffuse indoor lighting",
"aspect_ratio": "9:16",
"camera_angle": "Eye level"
}
}
}
Converting Video to 4-Panel Manga
comic-storyboardA description of a workflow where a story is built with GPTs, refined with GenSpark, and then a video from Kling is converted into a 4-panel manga using Nano Banana Pro.
展开提示词全文
From Kling video footage to 4-panel manga using Nano Banana Pro
Manga Generation Prompt Template for Nano Banana Pro
comic-storyboardA template for generating manga panels (ratio 2:3) in Nano Banana Pro, where the user inputs the desired content and the previously generated style tags (Style, Negative-Style, Color) to maintain a consistent aesthetic.
展开提示词全文
Manga Generation (Ratio: 2:3)
Content:
<{argument name="content" default="Insert content here"}>
<{argument name="style tags" default="Insert style tags (Style, Negative-Style, Color) here"}>
Nano Banana Prompt for Consistent Character Jumpshots
comic-storyboardAn instruction for using Nano Banana to maintain facial and clothing consistency across multiple shots (jump cuts) by uploading source images for the face and the scene (like a staircase shot). This is a workflow instruction that functions as a prompt.
展开提示词全文
To maintain consistency in face and clothing, use Nano Banana to create additional jump cuts.
Upload the source image of the face, and the {argument name="scene type" default="staircase shot"}:
Comic Book Poster Illustration Template
comic-storyboardA structured JSON prompt template for Nano Banana Pro, designed to generate a dynamic, modern comic book poster illustration (16:9 aspect ratio) with a collage of comic panels, halftone effects, and dramatic lighting. It includes placeholders for the main character, title, and specific panel content, and requires strict identity preservation from a reference image.
展开提示词全文
{
"meta": {
"purpose": "Comic book poster illustration for viral sci-fi storytelling or graphic novels",
"style": "Modern comic/graphic novel with halftone and dynamic effects, 4K resolution"
},
"reference_image": {
"use": true,
"identity_preservation": "strict",
"face_similarity": "high"
},
"canvas": {
"aspect_ratio": "16:9",
"orientation": "horizontal poster"
},
"title_text": {
"text": "{argument name="title text" default="ZOOM!!! OR Your Title"}",
"position": "top_center",
"style": "bold comic lettering, thick hand-drawn font",
"color": "cream white with black outline",
"effects": ["3D emboss", "ink shadow", "halftone texture"]
},
"main_character": {
"subject": "{argument name="main character" default="Space pilot with metallic implant OR Your hero"}",
"pose": "[e.g., Angry heroic OR Dynamic action]",
"lighting": "dramatic rim lighting",
"render_style": "Japanese Anime comic illustration"
},
"comic_panels": [
{
"position": "top_left",
"subject": "[e.g., Extreme close-up behind cracked glass]",
"expression": "[e.g., Angry]",
"panel_effect": "[e.g., Burst explosion, sound effect CRAAACK]"
},
{
"position": "top_right",
"subject": "[e.g., Pilot mouth open]",
"expression": "[e.g., Worried]",
"speech_text": "[e.g., NOOO!]"
},
{
"position": "bottom_left",
"subject": "[e.g., Spacecraft profile]",
"speech_text": "[e.g., WHAAA?!]",
"motion_lines": true
},
{
"position": "bottom_right",
"subject": "[e.g., Pilot scared]",
"speech_text": "[e.g., LAZARUS!]",
"panel_effect": "[e.g., Starburst]"
}
],
"background": {
"style": "comic panels collage",
"colors": ["orange", "yellow", "blue", "teal"],
"elements": ["halftone dots", "ink splashes", "action lines", "explosion shapes"],
"bottom_scene": "[e.g., Asteroid field with gold veins]"
},
"art_style": {
"genre": "modern comic book",
"influences": ["Marvel covers", "DC posters", "Pop-art"],
"line_work": "clean bold outlines",
"shading": "soft painterly with halftone"
},
"render_quality": {
"detail_level": "high",
"sharpness": "crisp",
"color_grading": "vibrant cinematic"
},
"constraints": {
"no_blur": true,
"no_extra_faces": true,
"no_watermark": true
},
"negative_prompt": ["low quality", "blurry", "extra limbs", "distorted face", "bad anatomy", "realistic photo"]
}
4-Panel Manga Generation from a Scene Description
comic-storyboardA two-step prompt sequence for Nano Banana Pro (Gemini 3 Pro Image) aimed at creating a 4-panel manga. The first instruction converts a specific scene (a Dragon Quest X monster zone special move) into a 4-panel format, and the second instruction adds speech bubbles and dialogue to the generated panels.
展开提示词全文
Turn this (the Dragon Quest X Superstar special move Monster Zone) into a 4-panel manga! Next Add speech bubbles and dialogue!
12-Panel Sticker/Emoji Grid Generation Prompt
comic-storyboardA structured prompt for generating a set of 12 emoji/sticker images in a 4:3 vertical format, where each panel depicts a different emotion or action (e.g., working hard, lying flat, working overtime) with corresponding large overlay text. The user needs to specify the main character/subject using the {argument name="subject" default="protagonist"} placeholder.
展开提示词全文
Generate 4 images based on the prompt, maintaining consistency in style with the original image. Each image should have 12 panels, and the prompt for each panel is as follows. Image aspect ratio: Vertical 4:3:
1 Full of energy Go! {argument name="subject" default="protagonist"} in a running and sprinting pose, limbs spread powerfully, speed lines behind, determined expression, large text "Go!" at the top of the screen.
2 Completely lying flat Lie Flat {argument name="subject" default="protagonist"} lying on their back with all four limbs up, eyes drawn as horizontal lines, soul floating out of the body, blank expression, large text "Lie Flat" at the top of the screen.
3 Received confirmation Okay! {argument name="subject" default="protagonist"} standing at attention and saluting, serious and solemn expression, straight body, large text "Okay!" at the top of the screen.
4 Slacking off Give up {argument name="subject" default="protagonist"} slumped on the sofa, holding snacks, vacant eyes, lazy posture, large text "Give up" at the top of the screen.
5 Super happy Yay! {argument name="subject" default="protagonist"} raising both fists in celebration, mouth wide open smiling, stars sparkling around, large text "Yay!" at the top of the screen.
6 Feeling wronged Sob {argument name="subject" default="protagonist"} eyes watery, mouth pouting, ears drooping, wronged expression, large text "Sob" at the top of the screen.
7 Smirking Hehe {argument name="subject" default="protagonist"} tilting head sideways, squinting and smirking, rubbing hands together, sly demeanor, large text "Hehe" at the top of the screen.
8 Work fatigue Overtime {argument name="subject" default="protagonist"} slumped over the computer, obvious eye bags, coffee cup nearby, tired expression, large text "Overtime" at the top of the screen.
9 Watching the drama Eating melon {argument name="subject" default="protagonist"} holding and eating a watermelon, eyes wide and curious, looking forward, large text "Eating melon" at the top of the screen.
10 Sudden wealth Rich! {argument name="subject" default="protagonist"} wearing sunglasses and a gold chain, banknotes and gold ingots floating around, smug expression, large text "Rich!" at the top of the screen.
11 Blushing Shy {argument name="subject" default="protagonist"} covering face with hands but peeking through fingers, cheeks blushing, shy expression, large text "Shy" at the top of the screen.
12 Good night Sleep {argument name="subject" default="protagonist"} curled up under a small blanket, eyes closed sleeping soundly, "zzz" symbol nearby, large text "Sleep" at the top of the screen.
Dramatic Historical Scene Generation with Emotional Dialogue
comic-storyboardA text prompt designed for an LLM or video generation model (like Seedance 2.0/Sora 2) to create a highly dramatic historical scene featuring intense dialogue, emotional conflict, and character revelation. The scene focuses on two characters, Xiao Jingheng and Shen Qingtang, discussing their shared history of reincarnation and failure.
展开提示词全文
Xiao Jingheng, his face covered in blood, draws his sword and points it at Shen Qingtang, shouting hysterically: "I have accompanied you through ninety-nine reincarnations, yet you still haven't defeated him! My intolerance for stupidity is about to flare up!" The woman in front of Xiao Jingheng, Shen Qingtang, sits on the ground, gently stroking Cheng Jingchuan, who is barely alive, in her arms. Upon hearing this, she suddenly looks up in surprise and says, "You, you are also a reincarnator?" Xiao Jingheng is instantly deflated by the shock. "Useless! You big idiot! I've accompanied you through ninety-nine reincarnations."
Image-to-Image Action Generation Template
comic-storyboardA template prompt for image-to-image generation in Nano Banana Pro, instructing the AI to take a person from the first uploaded image and generate a new image where that person performs a specified action within the context of the second uploaded image.
展开提示词全文
Please generate an image where the person in the first image {argument name="action" default="does XXX"} within the second image.
Dual Superhero Variant Scene (Ana de Armas and Sydney Sweeney Likeness)
comic-storyboardA complex, multi-part prompt written in Urdu/Hindi (Romanized) describing two separate superhero variants (Spider-Girl) resembling Ana de Armas and Sydney Sweeney, detailing their unique costumes, poses, and distinct New York City environments under golden hour or backlit conditions.
展开提示词全文
[
{
"image_no": 1,
"person_details": {
"name": "{argument name="person 1 name" default="Ana de Armas (Likeness)"}",
"pose": "Confident pose, sitting on a rooftop wall",
"hair": "Brown, slightly wavy hair"
},
"attire_and_appearance": {
"title": "Spider-Girl Variant",
"suit_color": "Deep orange and medium purple",
"vibe": "Cinematic superhero suit",
"shoes": "Heeled superhero boots that appear to be part of the suit"
},
"background_environment": {
"view": "New York Skyline",
"prominent_building": "One World Trade Center (Freedom Tower)",
"lighting": "Soft golden light of the evening (Golden hour lighting)",
"weather": "Clear sky with light clouds"
},
"items_and_objects": {
"bag": "Large white leather tote bag",
"clothing": "Yellow cardigan or scarf",
"shoes": "Separate brown leather boots placed aside"
}
},
{
"image_no": 2,
"person_details": {
"name": "{argument name="person 2 name" default="Sydney Sweeney (Likeness)"}",
"pose": "Sitting on the ground, legs crossed",
"hair": "Golden (Blonde) and loose"
},
"attire_and_appearance": {
"title": "Yellow Spider-Suit",
"suit_color": "{argument name="suit color" default="Bright yellow (yellow)"} with black stripes",
"design": "Large black spider mark on the chest",
"lower_half": "Black bodysuit style"
},
"background_environment": {
"view": "Modern city buildings (Skyscrapers)",
"sun": "Sun shining from behind the buildings (Backlit effect)",
"setting": "Modern rooftop balcony with a glass railing"
},
"items_and_objects": {
"fabric": "Shiny electric blue fabric lying on the ground",
"shoes": "Black pointed high heels taken off to the side",
"feet": "Barefoot pose"
}
}
]
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。