Ai Image Prompts
Introduction
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。
Resource Information
License information is collected from official sources and may be outdated or missing. Refer to the LICENSE file in the original repository before commercial use.
Prompt Library · 22.8K
Source: community prompt library (MIT, synced daily)15141 distinct prompts across 11 use cases; one prompt may serve several, so category counts add up to more than the deduplicated total.
242 matches
Infographic for Minato-ku Women's Fashion Magazine
app-web-designA prompt to generate an infographic or feature page design for a fashion magazine targeting 'Minato-ku women' (implying a sophisticated, high-end audience). The content should be systematic and easy to understand, utilizing icons, photos, graphs, diagrams, and handwritten pop-ups.
Show full prompt
Design a feature page for a fashion magazine read by beautiful Minato-ku women. The content should be systematic, constructive, and easy to understand. Include icons, photos, graphs, diagrams, and handwritten pop-ups if necessary.
Hyper-Realistic Mixed Reality Fanta Ad Concept
app-web-designA detailed prompt for generating a hyper-realistic, first-person perspective image of a hand holding a bottle of Fanta in a brightly lit supermarket aisle. The image features a complex, futuristic holographic augmented reality interface displaying nutritional data, recipes, and a dynamic shopping list, showcasing next-generation retail technology.
Show full prompt
First-person perspective, standing in a brightly lit supermarket aisle. A realistic human hand is holding a bottle of {argument name="drink brand" default="Fanta soda"}, close to the camera.
This brightly colored orange drink in its iconic branded bottle is surrounded by a multi-layered holographic augmented reality interface, which displays nutritional data including calories, sugar content, caffeine content, freshness, shelf life, and refreshing recipes and cocktails recommended based on {argument name="drink brand" default="Fanta"}.
The user interface elements smoothly move and rearrange according to the viewer's line of sight, dynamically responding to the user's focus of attention.
On the edge of the left field of view, a vertical, semi-transparent shopping list is visible, listing checked items, with {argument name="drink brand" default="Fanta"} highlighted as the currently selected item.
Hyper-realistic mixed reality, minimalist futuristic augmented reality design, glass-textured user interface panels, soft ambient light, realistic light and shadow effects, natural depth of field, immersive first-person interface, showcasing next-generation retail technology.
Recreating Airbnb UI with Image-to-Text and Nano Banana Pro
app-web-designA demonstration of using an Image-to-Text model to convert a screenshot of the Airbnb UI into a prompt, which is then used by Nano Banana Pro to recreate the design. The user notes the high accuracy and potential for converting design prompts into web implementations using React and Tailwind.
Show full prompt
Recreating a copy of Airbnb using a self-made Image-to-Text model to generate a prompt for Nano Banana Pro.
Minimalist Continuous Line Art Illustration
app-web-designA prompt for generating minimalist illustrations using thin, continuous black line art. It specifies a soft off-white background, fluid and minimal lines with no shading or fill, except for one subtle accent color used sparingly, ideal for elegant design work.
Show full prompt
Illustrate {argument name="subject" default="[SUBJECT]"} using thin, continuous black line art on a soft off-white background. The lines should be fluid, confident, and minimal, with no shading or fill except for one subtle accent color used sparingly.
High-End E-Commerce Portrait with UI Overlay Prompt
app-web-designA complex prompt structure designed to generate a high-end, full-body e-commerce studio portrait overlaid with a simulated mobile phone browser interface (UI layer), emphasizing volumetric lighting on the subject and flat, clean digital graphics for the overlay.
Show full prompt
"Subject Reference: A full-body portrait of \[INSERT SUBJECT NAME\]. Scene Description: A full-body, centered portrait of the subject \[INSERT POSE DESCRIPTION\]. The subject has \[INSERT EXPRESSION\], staring directly at the camera. The immediate background behind the subject is a \[INSERT BACKGROUND TYPE, e.g., seamless, pure high-key white studio backdrop\]. Crucially, the subject is lit with volumetric studio lighting that creates deep definitions, realistic shadows, and a strong 3D quality on her body and the folds of the outfit, distinguishing her sharply from the flat background without casting shadows on the floor. CRITICAL DETAIL (UI Layer): The entire photographic image is digitally layered beneath a simulated mobile phone browser interface overlay. Four distinct, clean, white, rectangular browser window elements are stacked vertically and angled slightly, segmenting the subject. Each window bar contains the sharp text '{argument name="browser text" default="[INSERT LINK OR TEXT HERE]"}'. The area outside the active white browser windows is a solid, uniform, dark charcoal gray/black matte UI frame, with absolutely no light bleed or color gradients. Style: Hybrid Composition: A highly realistic, three-dimensional studio photograph with deep color depth, overlaid with flat, clean digital graphics. Lighting Quality: Specific volumetric studio lighting focused ONLY on the subject. Soft, directional light from slightly off-center to sculpt the body and the rich texture of the fabric, creating depth. The background must remain completely flat. Color Palette: High contrast. \[INSERT OUTFIT COLOR\] outfit against \[INSERT BACKGROUND COLOR\] backdrop, framed by the dark matte gray UI. Texture and Mood: Realistic skin and rich fabric texture contrasting with the smooth digital elements of the UI. Intentional inclusion of subtle digital noise/grain to mimic a screen capture. Full body, centered portrait. Ensure the head and feet are fully within the frame before segmentation. Angle: Straight eye-level view, perpendicular to the subject. Framing Elements: Four overlapping, white browser windows/tabs. The pose is elegant and fluid. The bottom interface elements (e.g., 'Private', 'Done') must be clean and visible. Focal Length: Standard portrait lens (approx. 50mm equivalent) for realistic proportions. Camera Type: Simulated high-quality smartphone screen capture of a professional photo. Depth of Field: Shallow enough to focus sharply on the subject, allowi
Designer-Grade Brand Moodboard Generation Prompt
app-web-designA simple, high-level prompt for Nano Banana Pro designed to generate a sophisticated, designer-grade brand moodboard. It focuses on abstract concepts like grid layout, tactile textures, editorial photography, and a muted premium color palette, aiming for a professional internal deck aesthetic.
Show full prompt
Curated brand moodboard for a modern tech brand. Balanced grid layout, tactile textures, editorial photography references, muted premium color palette, typography-forward composition, crafted like a senior brand designer’s internal deck.
Promo Effect v2.0 Prompt for Profile Screenshot Composition
app-web-designA technical prompt structure for Nano Banana Pro's 'Promo Effect v2.0' feature, designed to composite a character image onto a user's profile screenshot. The prompt enforces specific rules, such as ensuring the 'Follow' button text is present, maintaining background structure, and defining the character's pose (sitting, pointing to the account name and the 'Follow' button). This prompt is highly specialized for UI manipulation and image composition.
Show full prompt
{
"edit_type": "precise_composite_overlay_dual_interaction_english_ui",
"source": {
"_hint": "Base Logic: Character sitting on Background. Background is fixed EXCEPT for the specific text on the button.",
"mode": "IMAGE_COMPOSITION",
"reference_images": {
"foreground": "character_ref_image",
"background_canvas": "profile_page_screenshot"
},
"consistency": {
"character_fidelity": "high",
"background_structure": "rigid_layout_preservation"
}
},
"ui_text_enforcement": {
"_hint": "CRITICAL: Ensure the button text reads 'Follow' in English, regardless of the text in the original screenshot.",
"target_element": "action_button_top_right",
"mandatory_text": "Follow",
"language": "English",
"font_style": "sans_serif_bold_legible",
"correction_policy": "overwrite_original_text_if_not_follow"
},
"background_preservation": {
"_hint": "Background is a rigid floor. Only allow changes to shadows and the button text.",
"policy": "strict_pixel_retention_mostly",
"allowed_modifications": [
"realistic_contact_shadows_under_character",
"replacement_of_button_text_to_Follow"
]
},
"camera_and_lighting": {
"_hint": "Character sitting ON the interface.",
"perspective": "high_angle_looking_down",
"grounding_effect": {
"technique": "contact_shadows_under_legs",
"placement": "on_background_surface"
}
},
"pose": {
"_hint": "Dual pointing: Left Hand -> Name, Right Hand -> 'Follow' Button.",
"pose_style": "sitting_cross-legged_or_kneeling",
"head_position": "tilted_back_looking_at_camera",
"hands_configuration": {
"s
Multi-Step Design Generation Prompts for 'Lovart' Brand
app-web-designA comprehensive, multi-step workflow using design agent 'Lovart' (likely integrated with Nano Banana Pro) to generate a complete brand identity, starting from a logo and extending to design guidelines, UI, website, exhibition booth, and merchandise. This demonstrates a structured approach to design generation.
Show full prompt
A logo mark for a company named "{argument name="company name" default="Lovart"}" with a base color gradient of vibrant {argument name="color 1" default="emerald green"} and vibrant {argument name="color 2" default="blue"}
Generate a color palette and font design guidelines from this logo mark
Generate the application UI design for this service. PC version and smartphone version
Design a website to introduce this service. PC version and smartphone version
Design image of an exhibition booth for this service
Merchandise design for this service. T-shirt, hoodie, cap, notebook, sticker
Video Game Wiki Style Image Generation
app-web-designA prompt for testing Google Gemini's image generation capabilities, specifically requesting a combination of a sloth, a tuna, and an F-15J fighter jet rendered in the distinct style of a video game wiki website's page.
Show full prompt
a sloth, a tuna, an F-15J in the style of a video game wiki website's page
3D Icon Collection Grid Generator
app-web-designA prompt template for Nano Banana Pro designed to generate a collection of 3D icons arranged in a 3x3 grid. The icons are colorful and three-dimensional, centered around a specific theme, and generated on a white background without any text.
Show full prompt
Prompt: Create a collection of icons representing [Theme]. They are unified as a single theme. Please arrange them in a 3x3 grid. The background is white. The icons should be created in a colorful, three-dimensional 3D style. No text is required.
- {argument name="Theme 1" default="90s Gadgets"}
- {argument name="Theme 2" default="February"}
- {argument name="Theme 3" default="Emotional Fruits"}
- The Darkness of Remote Work
Conceptual brand storytelling visual prompt
app-web-designA concise prompt for generating a conceptual visual that communicates a brand narrative focused on journey and growth. It specifies abstract progression elements, a sense of movement, soft cinematic lighting, and an optimistic, forward-moving tone.
Show full prompt
Conceptual storytelling visual for a modern brand narrative. Abstract progression elements, sense of movement and flow, soft cinematic lighting, optimistic, forward-moving tone, crafted to communicate journey and growth.
LinkedIn Banner Design Prompt
app-web-designA simple prompt for generating a professional and modern LinkedIn banner image for a 'Creative Director,' featuring abstract 3D shapes floating in a gradient space with a high-quality render.
Show full prompt
LinkedIn banner for a '{argument name="job title" default="Creative Director"}.' Abstract 3D shapes (spheres, cubes) floating in a gradient space. Professional, modern, high-quality render.
Prompts are model-agnostic and work with Midjourney / DALL-E / Flux / Stable Diffusion.
Information boundary
Information on this page is collected from official documents for technical presentation only and does not imply our endorsement. Pricing, quotas and availability are subject to the latest official statements. We make no commitment regarding any action you take after leaving this site.
Similar skills
视频短视频图片音乐音频配音口播数字人全能创作
Marked paid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
Marked paid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。
罗斯蒙德可视化图形生成
Not specified【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。
架构图一键生成
Marked paidAPI key required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。
AI Image Prompts · 绘画提示词库
Marked freeRecommend 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
架构图一键生成
Marked paidAPI key required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。
What is a Skill
A Skill is a packaged single capability, such as text recognition, document summarization, or keyword extraction. Developers wrap the calling logic and prompts into a plugin-like unit, so users can load it without understanding the underlying model. StackPilot indexes a large number of skills that can be tried instantly or assembled into a plan.