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
Luxury minimalist product photography based on a reference image
product-marketingA prompt for generating high-end, minimalist commercial product photography in the style of luxury brand ads, using an uploaded reference image of the core product as the base.
展开提示词全文
Using my uploaded reference image as the base, generate a minimalist, high-quality commercial still life photograph with the aesthetic of a luxury brand advertisement. Preserve the general shape, proportions, and main color scheme of the core product in the reference so that it is instantly recognizable as the same product, but upgrade the overall texture and atmosphere of the image, making it look like an ad for a top-tier international fragrance, skincare item, or high-end electronic product. Use a vertical 4:5 composition. The background should be a large area of clean, neutral negative space, such as soft off-white, cool gray, or light beige, creating a quiet, restrained, and expensive studio environment. Apart from the core product and a minimal number of necessary supports, do not add any extra decorations. No clutter, no elaborate scene setup—only keep very simple geometric supports (such as a plain white cube, a cylinder, or a thin transparent panel). The supports must be simple and low-profile, existing only to hold and accentuate the product. Strongly emphasize the material details of the product, and let the lighting fully serve those materials: Show frosted glass with a fine, soft matte texture, ceramics with a matte or slightly glazed feel, and polished metal with clean, sharp specular highlights. Liquids should have clearly visible viscosity and volume. Avoid any cheap plastic feel, complex patterns, or gaudy stickers; the overall material quality must feel cool, restrained, and luxurious. Use professional studio lighting: mainly soft, diffused light from softboxes, plus precise rim light outlining the product’s shape. The contours should be crisp and layered, and the shadows should be soft and clean, with no noise or dirty shadow patches. You may use a near-macro viewpoint, moving in closer to the product to highlight materials and details, while preserving ample negative space around the frame so the product can "speak for itself" in the emptiness. Keep the overall color scheme neutral and calm. The product’s own color can be slightly more saturated, making it the single visual focal point in the scene. Do not use exaggerated gradient backgrounds, flashy colored lighting, or e-commerce promo aesthetics. No large-price text, labels, or cartoon graphics. The final result must be a high-resolution commercial key visual that looks ready for a magazine back cover or a high-end brand announcement poster: minimalist, quiet, high-end, with the core product confidently centered, surrounded by clean negative space and precisely controlled lighting.
3D paper cut light box illustration framework
product-marketingA detailed prompt template for generating dreamy, multi-layered 3D paper cut light box artworks, where you can swap in any theme and the model handles layers, lighting, color logic, and material realism.
展开提示词全文
Generate an art photograph of a highly dreamy and three-dimensional 3D paper cut light box.
The paper cut theme is: {argument name="theme" default="a deer in a forest under the moonlight"}.
Layering structure and composition:
Design the image as a real, physical paper cut light box composed of 5–7 layers of paper stacked together. Each layer must have its own depth of field and clear silhouette, and you should be able to see the thickness of the paper and the shadows between layers.
Core structure:
- The image should clearly present a multi-layered silhouette effect, with visible physical spacing between the paper layers.
- Overall composition is vertical 3:4, with the light box centered, leaving a bit of space at the edges, like a glowing art object placed on a table.
Depth layout:
- Foreground (layers 1–2): use dark, intricate silhouettes that form a frame around the edges of the image, with elements matching the current theme, such as branches and vines for forest themes, windows and arches for city or castle themes, or rocks and coral for underwater or fantasy themes.
- Midground (layers 3–4): this holds the core subject of the theme, slightly central in the composition and taking up the main visual weight. The subject’s silhouette must be complete and not overly blocked by the foreground.
- Background (layers 5–6): use more simplified, lower-contrast silhouettes to show distant environment and structures, adding depth to the scene.
Three-dimensionality:
- There must be obvious physical spacing and shadows between layers. Light should pass between the paper layers to create soft gradations of light and dark, emphasizing the paper thickness and 3D depth, so it looks like a real paper cut light box, not a flat illustration.
Light and atmosphere (backlighting):
Backlighting:
- The light source must come from the very back of the scene, shining forward through all the paper layers.
- Light passing through the cutouts in each layer should form soft volumetric light and gradually decreasing brightness and contrast from back to front.
Color gradients (auto-adapting to the theme):
If no specific color scheme is given, automatically choose a main palette and gradient that fit the theme, while keeping a soft, night-light-friendly look. For example, warm gold to cool blue-green for forest themes, teal to deep blue for underwater themes, icy blue to deep blue for winter scenes, amber to electric blue for cyber cities, candlelight gold to deep indigo for castles, or deep blue to purple with golden glows for space themes.
If the user clearly specifies a color direction or mood (such as “cool sci-fi” or “pink-blue dreamy”), follow that as the top priority while maintaining the soft backlit, soothing feeling of a night light.
Overall feel:
The image should feel quiet, healing, and storybook-like, like a softly glowing bedtime story lamp, not a noisy neon poster or infographic.
Materials and details:
Paper texture:
- Emphasize the reality of heavy art paper: fine texture, slight visible fibers, clean sharp cut edges with visible thickness, and light that diffuses softly through the paper like a real fibrous material, not plastic or metal.
Physical light box photography feel:
- Present the image as a photograph of a real light box, not a flat illustration or vector graphic. You can faintly show the light box frame (simple white or light wood) and a slightly blurred tabletop or environment.
- The lighting should feel natural, with real-lens depth of field: slightly blurred foreground, sharp midground subject, and soft background.
Detail decorations:
- You may add a modest amount of tiny floating elements between paper layers to enhance space, such as tiny glowing dots, dust motes, snowflakes, bubbles, or other small particles relevant to the theme. Their number must be restrained so they only enhance atmosphere and depth without cluttering or disrupting the silhouette structure.
Technical parameters: vertical 3:4 ratio, high-resolution output.
JSON selfie-in-car mirror prompt for Nano Banana Pro
product-marketingA detailed JSON-formatted prompt for generating an ultra-realistic selfie of a young woman reflected in a car’s side mirror, including subject, clothing, props, environment, lighting, style, and a negative prompt.
展开提示词全文
{
"image_generation_prompt": {
"subject": {
"description": "Young woman with long brown hair",
"pose": "Leaning gently on car window, resting head on one hand, relaxed and confident",
"action": "Taking a selfie in the side mirror reflection"
},
"clothing": {
"top": "Simple red turtleneck long-sleeve top",
"accessories": "Minimalist stud earrings"
},
"props": {
"item": "{argument name=\"phone model\" default=\"iPhone 17 Pro Max\"}",
"details": "Realistic proportions, accurate lens design, held in hand"
},
"environment": {
"location": "Outdoors, reflected in the side mirror of a {argument name=\"car model\" default=\"black Toyota Land Cruiser\"}",
"background": "Trees and orange-blue evening sky",
"depth_of_field": "Subtly blurred background for depth (bokeh)"
},
"lighting": {
"type": "Golden hour",
"characteristics": "Warm sunlight, soft natural glow, evening light, realistic shadows"
},
"style": {
"aesthetic": "Natural, ultra-realistic, minimalist, Instagram style",
"quality": "8k resolution, highly detailed, sharp focus, cinematic photography"
},
"technical_constraints": {
"perspective": "Accurate mirror reflection, correct optical orientation",
"distortion_control": "No exaggeration or distortion of features or phone"
}
},
"negative_prompt": "cartoon, illustration, painting, drawing, bad anatomy, disfigured, deformed, blurry face, low quality, pixelated, unnatural lighting, distorted phone, wrong reflection angle, extra fingers, messy hair, heavy makeup, text, watermark"
}
Ad replacement and brand adaptation prompt for Nano Banana Pro
product-marketingA structured Nano Banana Pro prompt for recreating a provided advertisement concept while replacing the original product with the user’s own brand product, matching mood and composition while removing competitor branding.
展开提示词全文
Recreate the provided advertisement concept, but substitute the original product with {argument name="my product in English" default="my product"}.
Requirements:
Visual continuity
Match the source ad’s mood, lighting, camera angle, composition, and overall atmosphere.
Do not replicate or keep any competitor logos, text, or brand marks.
Product replacement
Insert the product from {argument name="uploaded image in English" default="my uploaded image"} in place of the original item.
Ensure the replacement appears naturally integrated with accurate scale, proportions, reflections, and shadows.
Scene adaptation
Adjust all background elements, props, surfaces, and textures so they reflect {argument name="brand style in English" default="my brand’s visual style"}, flavor or aesthetic cues, and thematic identity.
Remove or redesign any elements tied to the competitor’s brand.
Output quality
Maintain photorealistic rendering throughout.
Ensure the final composition feels authentic to the original ad concept but clearly represents my brand.
3D chibi concept store brand prompt
product-marketingA simple Nano Banana prompt for generating a 3D chibi-style miniature concept store themed around a specific brand name.
展开提示词全文
3D chibi-style miniature concept store of {argument name="brand name in English" default="{Brand Name}"}
Highly detailed 8K morning still life desk scene prompt
product-marketingAn extremely detailed Nano Banana Pro prompt describing an 8K, golden-hour still life on an old wooden desk with food, notebook, wine spill, fountain pen, dust particles, and strong texture emphasis, including aspect ratio and stylization hints.
展开提示词全文
Extreme close-up 8K morning still life on an old wooden desk bathed in golden sunlight through a dusty window:
- Half-eaten glazed {argument name="dessert in English" default="strawberry"} on a fine bone china plate, sticky syrup dripping
- Antique silver fork with food residue and tiny scratches
- Open Moleskine notebook with real leather cover, worn edges, and textured paper showing fibers
- Spilled red wine creating rings on the wood, absorbing into the grain
- Brass fountain pen leaking dark blue ink, pooling and reflecting light
- Crumpled silk handkerchief with subtle embroidery threads
- Dust particles floating in sunbeams, landing on a matte black camera body with micro-scratches
- Small puddle of water with floating dust and lens flare
- Tiny spiderweb strand catching light between objects
- Visible wood grain, knots, and 100-year-old cracks on the desk
Maximum texture detail, subsurface scattering, caustics, sharp specular highlights where needed, photorealistic, shot on medium format Phase One, --ar 4:5 --v 3 --stylize 350
Cinematic lakeside hanging chair concept prompt with space object theme
product-marketingA long-form Nano Banana Pro prompt for a cinematic night scene at a lakeshore with a large hanging chair whose shape, surface, and lighting are derived from a specific space object placeholder.
展开提示词全文
Cinematic night scene of a cozy outdoor retreat by a calm lakeshore. In the center, a large hanging chair inspired by {argument name="space object in English" default="[SPACE_OBJECT]"} floats just above the ground, suspended by sturdy metal chains from a thick, low tree branch on the left. The chair’s overall silhouette, proportions, color palette, and surface detailing are clearly derived from this celestial body, so its characteristic outline, light and dark regions, subtle bands, patches, and recognizable markings from astronomy images are faithfully translated into the design of the outer shell. The material looks like a refined, slightly weathered fusion of stone and metal with finely sculpted relief matching those distinctive patterns, while the interior forms a smooth, comfortable hollow lined with warm woven fibers and cushions that softly echo the same hues. A plush pillow rests inside, illuminated by a gentle glow from within the chair, casting a soft pool of light onto the surrounding earth and grass. Tall wild grasses and small plants encircle the base
Simple grapes-in-a-basket image prompt
product-marketingA concise Nano Banana Pro image prompt for generating grapes in a basket made from grape vines, used to compare model quality.
展开提示词全文
{argument name="subject in English" default="grapes in a basket made from grape vines"}
Snow globe character illustration prompt for Nano Banana Pro
product-marketingA detailed Japanese prompt for Nano Banana Pro to create a chibi anime-style character inside a realistic snow globe with specific props, lighting, and restrictions.
展开提示词全文
Maintain the characteristics of the character from the attached reference image, and depict them as a default chibi character in anime style striking an uncool pose. Place a small raccoon dog on their head. The character is placed inside a realistically rendered snow globe, where fantastical powdery snow is falling and piling up in a dramatic night scene. The base of the globe is decorated with LED illumination. The snow globe is displayed on a warm wooden desk, with a candle a little farther back. On the fogged window, only the part where the phrase "(ᐢ⓿ᴥ⓿ᐢ) たぬ参上" is traced in a handwritten-looking font allows a view of the snowy Japanese landscape outside. Do not show any human fingers. Do not make the raccoon dog’s tail striped.
Japanese izakaya entrance sign image prompt for Nano Banana Pro
product-marketingA Nano Banana Pro image prompt to generate a photorealistic Japanese restaurant (izakaya) entrance sign with specific text, atmosphere, and lighting.
展开提示词全文
A beautiful Japanese restaurant entrance sign
with the text "{argument name="sign text" default="Izakaya Sakura"}" written in a traditional calligraphy style,
a warm wooden background,
soft lantern lighting,
photorealistic quality
3D chibi miniature brand concept store prompt
product-marketingA reusable prompt to generate 3D chibi-style miniature concept stores for any brand, focusing on their signature product, colors, and cozy interior with tiny figures.
展开提示词全文
A 3D chibi-style miniature concept store for {argument name="brand name" default="Starbucks"}, creatively designed with an exterior inspired by the brand’s most iconic products or packaging (for example, a giant {argument name="core product of the brand" default="chicken bucket/hamburger/donut/roast duck"}). The store is two stories tall with large glass windows that clearly showcase a cozy, richly decorated interior: decorations themed around {argument name="primary color of the brand" default="primary color of the brand"}, warm lighting, and busy staff wearing outfits that match the brand. Cute tiny figures walk and sit along the street, surrounded by benches, streetlights, and potted plants, creating a charming urban scene. It is rendered in a miniature cityscape style using Cinema 4D, with the aesthetic of blind-box toys, abundant detail, and realistic yet soft lighting that evokes a relaxed afternoon atmosphere. Please include the mini characters by referring to the attached character sheet. --ar 2:3
3D chibi miniature travel spot concept prompt
product-marketingAn English prompt for generating a 3D chibi-style miniature travel concept scene centered on an iconic local landmark and themed structure, easily reusable by swapping the place name and key elements.
展开提示词全文
A 3D chibi-style miniature travel concept themed around {argument name="travel location name" default="Mount Fuji"}. At the center is a creatively designed two-story observation deck and tourist information center, built around a giant iconic {argument name="symbol of the travel location" default="symbol of the travel location"} object. Through the large glass windows, you can see the intricately detailed interior, with warm lighting and decorations based on {argument name="theme color of the travel location" default="theme color of the travel location"}. Miniature characters wearing tour guide uniforms are working inside, while visiting mini characters are taking photos and relaxing. Around the building are benches, streetlights, stone-paved walkways, and {argument name="local natural elements or plants" default="local natural elements or plants"}, expressing the unique atmosphere of the destination. It is rendered in a miniature cityscape style using Cinema 4D, with the aesthetic of a blind-box toy, rich details, and soft lighting that evokes the feeling of a relaxing travel afternoon. Please place the mini characters by referring to the attached character sheet. --ar 2:3
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。