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 5717 条
3D Caricature Style Transfer Prompt
product-marketingA prompt found in the image ALT text (as indicated by the tweet) for transforming a subject into a 3D caricature style. This is an image-to-image prompt.
展开提示词全文
Turn the subject into a 3D caricature. The style should be highly detailed, glossy, and resemble a collectible vinyl toy figure. The background should be a simple, vibrant color.
Interactive Billboard Selfie Prompt (Jim Carrey Style)
product-marketingA complex, structured JSON prompt template for Nano Banana Pro designed to generate an image where the user (based on an uploaded photo) interacts playfully with a giant billboard featuring a celebrity. The prompt specifies the spatial logic, subject pose (pointing, laughing), background details (realistic vinyl texture), and negative constraints to ensure a high-quality, lifestyle-oriented street snap.
展开提示词全文
{
"project_name": "{argument name="project name" default="Pro_Billboard_Interactive_Lifestyle_v9"}",
"usage_guide": "1. Fill in STAR_NAME, STAR_EXPRESSION, USER_POSE. 2. Set Aspect Ratio (e.g., 3:4). 3. Upload FULL BODY reference. 4. This version creates a casual, fun interaction between you and the giant poster.",
"prompts": {
"positive_prompt": "A high-end editorial fashion shot, full body, captured in {argument name="aspect ratio" default="3:4"} format.\n\n[Spatial Logic – Perfect Depth]\nA real person stands in the foreground, positioned about {argument name="distance" default="50cm"} (a few dozen centimeters) away from the background wall. Not touching the wall. There is a visible, natural depth. Soft shadows are cast on the wall behind, proving the physical separation.\n\n[Subject – Casual & Interactive]\nSubject's outfit, gender, and age perfectly match the uploaded reference image. Full body visible from head to toe, including shoes.\nPOSE & VIBE: The person is {argument name="user pose" default="pointing at the billboard, laughing loudly, excited"}. The pose is casual, unposed, and lifestyle-oriented (NOT a stiff passport photo). It feels like a fun street snap where the person is interacting with the background celebrity.\n\n[Background – Giant Expressive Poster]\nBehind the person is a massive, building-sized commercial advertisement. It features a gigantic portrait of {argument name="star name" default="Thomas Stanley Holland"} with a {argument name="star expression" default="seductive charming smile"} expression. Visible from the shoulders up, looking huge and imposing.\n\n[Texture & Material Reality]\nThe billboard has a realistic heavy-duty vinyl or canvas texture. Visible details: slight surface ripples, tension wrinkles, uneven lighting reflection, and micro-folds. It looks like a real physical object, not a smooth screen.\n\n[Lighting]\nSoft overcast natural light, 8k resolution, raw photo quality, sharp focus.",
"negative_prompt": "stiff pose, military stance, passport photo, bored expression, touching the wall, zero distance, flat digital image, perfectly smooth texture, glossy screen, fake poster, floating feet, missing shoes, cropped, lowres, bad anatomy, changing outfit, cartoon, 3d render"
}
}
Floor Plan Visualization with Family Life
product-marketingA prompt for Nano Banana Pro to visualize a floor plan (間取り) as a realistic, miniature-style, high-angle bird's-eye view, incorporating a specific family living within the space, based on the provided floor plan and family photos.
展开提示词全文
Convert this floor plan into a realistic interior of a {argument name="house builder" default="Ichijo Komuten (i-smart 2)"}, rendered as a bird's-eye view seen from a 45-degree angle. Then, actually place the scene of this family living inside the bird's-eye view. Use a viewing angle where the entire floor plan is visible. Make it look like a miniature.
Capsule Product Packaging Design Prompt
product-marketingA prompt for Nano Banana Pro to generate a product packaging design in the shape of a capsule. It specifies material, texture, logo placement, background, lighting, and aspect ratio, using Coca-Cola as an example brand and Coke as the product.
展开提示词全文
A capsule-shaped container designed for the brand "{argument name="Brand" default="Coca-Cola"}". The upper part is made of the brand's color frosted material, featuring a 3D embossed "{argument name="Brand" default="Coca-Cola"}" Logo, highlighting the brand essence. The transparent lower part is filled with realistic, textured "{argument name="Product" default="Coke"}". The transparent area also features the "{argument name="Brand" default="Coca-Cola"}" Logo. The background is a minimalist solid color, with soft, even lighting and subtle shadows to emphasize the texture and form of the "{argument name="Product" default="Coke"}". The brand logo is printed in the upper left corner. Aspect ratio 1080x1080. Vertical design.
Streetwear Algorithm AI: Object-to-Wearable Conversion
product-marketingA complex, multi-step system prompt that instructs the AI to act as a 'Streetwear Algorithm' to convert any random input object into a corresponding 'Hypebeast' fashion item (Puffer Jacket, Sneaker, Backpack, or Sunglasses) based on the object's physical properties (Texture, Structure, Shape). The prompt then requires generating a studio product shot of the resulting wearable, ensuring it looks manufactured from the input object's parts/materials.
展开提示词全文
<instruction>Act as the "Streetwear Algorithm" AI.</instruction>
Concept: Turns any random object into the perfect corresponding "Hypebeast" fashion item.
1. ANALYZE INPUT (Form & Physics):
Look at the attached image. Determine:
Texture: ({argument name="texture options" default="Soft/Hard/Liquid/Glass"})
Structure: ({argument name="structure options" default="Rigid/Flexible/Mechanical"})
Shape: ({argument name="shape options" default="Boxy/Round/Aerodynamic/Flat"})
2. AUTO-SELECT MODEL (Run this Logic Tree):
IF Input is Soft, Volumetric, or Tangled (Noodles, Clouds, Moss, Bubblewrap)
-> GENERATE: Oversized Puffer Jacket
IF Input is Rigid, Aerodynamic, or Mechanical (Stapler, Car, Power Tool, Robot)
-> GENERATE: Chunky Conceptual Sneaker
IF Input is Boxy, Container-like, or Heavy Metal (Safe, Trash Can, Speaker, Computer Case)
-> GENERATE: Hard-Shell Tech Backpack
IF Input is Transparent, Glassy, or Thin/Wire-like (Neon Sign, Circuit Board, Stained Glass, Ice)
-> GENERATE: Futuristic Wrap-Around Sunglasses (Visor)
IF Input is Textile, Flat, or Pattern-Heavy** ({argument name="pattern input examples" default="Persian Rug, Painting, Cardboard"})
-> GENERATE: Oversized Hoodie or Tactical Vest
3. EXECUTE DESIGN:
Create a studio product shot of the "selected item".
Design Rule: The item must look like it was manufactured "using the parts/materials of the input object".
Details: Keep original branding/logos if present.
Setting: Floating pedestal, Cinematic Lighting, 8k Resolution.
Liquid Gloss Logo Generation
product-marketingA prompt template for generating a logo formed from thick, flowing liquid gloss, emphasizing high-shine, viscous texture, and a luxury cosmetic-brand aesthetic against a minimal background.
展开提示词全文
Create a {argument name="brand name" default="Brand Name"} logo formed from thick, flowing liquid gloss. High-shine surface, smooth curves, reflective highlights. Viscous, slightly dripping appearance frozen in motion. Minimal background, luxury cosmetic-brand aesthetic, studio lighting.
Cloud Silhouette Drop-in Prompt Template
product-marketingA description of a reusable prompt template for Nano Banana Pro designed to create ultra-realistic cloud formations that silhouette a subject, grounded by a landscape and featuring clean daylight lighting.
展开提示词全文
Using image as reference, reinterpret the scene as a small-scale realistic high quality diorama • Convert the scene into a handcrafted miniature display mounted on a solid rectangular base with realistic terrain textures. • The diorama is held in a human hand to clearly show scale. • Soft natural lighting, macro photography, shallow depth of field. • Photorealistic, ultra-detailed, clean composition. • No text, no UI, no motion blur. • ar 1:1
Empire In Miniature Diorama
product-marketingA prompt template for generating a miniature diorama of a business leader inside a symbolic workspace that represents their vision, featuring elements like a tiny desk, screens, city models, and warm ambient lighting.
展开提示词全文
A miniature diorama of {argument name="business leader" default="BUSINESS LEADER"} inside a symbolic workspace representing their vision. Tiny desk, screens, city models, warm ambient lighting.
Cinematic Female Fighter Pilot Portrait at Sunset
product-marketingA detailed JSON prompt for generating an ultra-realistic, cinematic portrait of a female fighter pilot in a cockpit at sunset. It emphasizes dramatic golden hour lighting, strong lens flare, high contrast, and authentic film grain to achieve a heroic and empowering mood.
展开提示词全文
{
"type": "image_generation_prompt",
"style": "cinematic, ultra-realistic, aviation portrait",
"composition": {
"aspect_ratio": "3:4",
"framing": "medium close-up inside cockpit",
"camera_effects": [
"cinematic lens flare",
"heat distortion waves",
"35mm film grain"
]
},
"subject": {
"gender": "female",
"role": "fighter pilot",
"pose": {
"position": "sitting in the cockpit on a runway",
"gesture": "giving a thumbs-up to the ground crew",
"expression": "confident, charismatic smile",
"headgear": {
"oxygen_mask": "off",
"visor": "up"
}
}
},
"environment": {
"location": "runway at sunset",
"cockpit": {
"interior_lighting": "deep shadow with visible technical details"
},
"background": {
"sun_position": "low on the horizon",
"lighting_effect": "golden hour sun blasting directly into the camera lens",
"atmosphere": "haze of warm golden light washing over the left side of the frame"
}
},
"lighting": {
"type": "golden hour natural light",
"effects": [
"strong lens flare",
"warm haze",
"high contrast between exterior light and cockpit shadows"
]
},
"mood": {
"tone": [
"heroic",
"empowering",
"cinematic",
"inspiring"
]
},
"quality": {
"realism": "highly photorealistic",
"detail_level": "high detail in facial features, cockpit instruments, and lighting",
"texture": "authentic film grain and heat shimmer"
},
"output_goal": "Create a stunning cinematic portrait of a female fighter pilot at sunset, conveying confidence, heroism, and cinematic intensity through dramatic golden-hour lighting and realistic cockpit detail."
6-Panel Brand Identity Grid Mockup
product-marketingA structured prompt for generating a professional 6-panel grid layout displaying a complete brand identity suite, including business cards, a pamphlet, a flyer, a shopping bag, and a calendar, for a customizable brand concept, ideal for design mockups and portfolio pieces.
展开提示词全文
A professional 6-panel grid layout photograph displaying a complete brand identity suite for the concept: "{argument name="content" default="beauty"}". The image is divided into two rows and three columns, each cell framed with a clean white border. The overall style is a clean, modern studio mockup with uniform lighting.
Top Row (Left to Right):
Cell 1 (Business Card - Original): Two stacks of business cards showing front and back, featuring the primary logo, color palette, and typography of "{argument name="content" default="beauty"}". Clean white or light background paper stock.
Cell 2 (Business Card - Inverted): Two stacks of business cards showing front and back, featuring the same design as Cell 1 but with inverted colors (e.g., dark background with light logo/text).
Cell 3 (Pamphlet): An open tri-fold brochure showcasing detailed information, images, and branding elements related to "{argument name="content" default="beauty"}".
Bottom Row (Left to Right):
Cell 4 (Flyer): A single-page promotional flyer design for "{argument name="content" default="beauty"}", with a strong headline, imagery, and call to action.
Cell 5 (Shopping Bag): A premium paper shopping bag with handles, featuring a large version of the "{argument name="content" default="beauty"}" logo and brand pattern.
Cell 6 (Calendar): A desk calendar showing a monthly view with themed illustrations or photos related to "{argument name="content" default="beauty"}" and brand branding on each page.
All items across all six cells consistently apply the logo, color scheme, typography, and graphic elements of the "{argument name="content" default="beauty"}" brand identity. The background behind the grid is a clean, neutral grey studio wall. 4k resolution, highly detailed texture.
A minimal and chic handwritten signature 'Willy' is in the bottom-right corner.
content: {argument name="input" default="beauty"}
Composite Racing Car Shot with Vintage Film Branding
product-marketingA prompt for generating a composite medium shot of three racing cars (branded with Kodak, Polaroid, and Sony logos) on a rain-soaked street. It specifies a slightly elevated angle, harsh direct flash lighting, motion-blurred background elements, and a disposable camera aesthetic with grain and uneven exposure.
展开提示词全文
Medium Shot (MS): Central mass of these exact three racing cars captured from a slightly elevated angle, showcasing their distinctive branding liveries, sponsor logos (Polaroid, Sony, Kodak), and detailed body modifications. Harsh direct flash illuminates their wet surfaces, creating dramatic reflections on the rain-soaked Canggu street. Motion-blurred scooters and pedestrians frame the edges. Cropped composition with intentional cut-off at edges. High contrast between illuminated car bodies and pitch-black background. Disposable camera aesthetic with slightly grainy texture and uneven exposure.
Cartoon Character Paper Sculpture Museum Display
product-marketingA prompt for transforming a cartoon character into a hyper-detailed paper sculpture displayed inside a minimalist museum box. It specifies using layered premium paper with visible folds, soft gallery lighting, and a photorealistic finish to create a high-end collectible art style.
展开提示词全文
A hyper-detailed paper sculpture of {argument name="character name" default="[CHARACTER]"}, mounted inside a minimalist museum display box. The figure is crafted from layered premium paper with visible folds, edges, and textures. Soft gallery lighting, glass reflections, subtle depth-of-field. High-end collectible art style, photorealistic finish, sharp focus. 1:1 square 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。一节课的讲解也能做成课程口播。
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。
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,在海报排版上搭配清晰视觉层级、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。
自动化克隆数字人口播混剪视频
免费增值需申请 Key抖音短视频双路径生产体系(单 Skill 版)。Path A[付费·高质量]:策略大脑→(可选:素材混剪/AI高光提取)→脚本优化→AI生图/素材准备→配音渲染(百炼/GPT-SoVITS/CosyVoice/VoxCPM2+剪映/Remotion/ffmpeg/数字人)。Path B[免费·动画风]:采集热点→脚本→edge-tts免费配音+HyperFrames开源渲染→MP4,零云费开箱快。触发词分层:①"抖音短视频/选题规划/合规闸门/运营策略" ②"口播脚本/AI生图/AI配音/视频渲染/Remotion渲染" ③"蹭热点/快速出片/免费做视频" ④"混剪/高光提取/素材粗剪/autoclip
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。