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 1099 条
Dream diary with Kirby blowing bubbles
othersA cute prompt for a dreamy diary-style illustration of a pink Kirby sleeping on a star, blowing rainbow bubbles amid pastel clouds and candy.
展开提示词全文
Dream diary. A pink Kirby lying asleep on a star, blowing rainbow-colored bubbles from its mouth. Soft macaron color palette, cloud and candy stickers, glittery crayon-like details, dreamy and sweet.
Nano Banana Pro brand hero image (with later edit request)
othersThe main prompt asks for a Nano Banana Pro hero image in Google’s brand style; replies mention editing chopsticks to hold a condom, suggesting a possible humorous variant.
展开提示词全文
Draw a hero/header image for Nano Banana Pro that matches Google Nano Banana’s brand tone and design elements.
Glassmorphism personal branding mockup
othersA long English/Chinese hybrid prompt (in the replies) for a modern glassmorphism-style visual mockup featuring a rounded glass panel with specific text layout, used for personal branding designs.
展开提示词全文
Generate a highly modern glassmorphism-style visual design mockup. 3:4 aspect ratio. In the right one-third of the center, there is a semi-transparent, glass-textured rounded rectangular panel with soft edges, a blurred background, and gradient light and shadow effects. The panel contains the following text: • Top left: Zho • Bottom left: Architect Artist Ai explorer • Small text on the right: Founder of https://t.co/s6eXbY9EAY
Nano Banana Pro brand hero image (variant tweet)
othersAnother tweet repeating the same Nano Banana Pro header image prompt, aiming for consistency with Google’s brand design.
展开提示词全文
Draw a hero/header image for Nano Banana Pro that matches Google Nano Banana’s brand tone and design elements.
Three advanced abstract reasoning image tests
othersThis tweet contains three separate detailed prompts: a chalkboard quadratic formula derivation, a hyper-real Penrose triangle in gold, and an ambigram-like LIFE/DEATH design, each testing different aspects of visual reasoning.
展开提示词全文
A close-up photo of a green chalkboard. The correct derivation steps of the quadratic formula are written in white chalk. First line: ax^2 + bx + c = 0. Second line: x^2 + (b/a)x = -c/a. Third line: completing the square. Final line: x = \frac{-b \pm \sqrt{b^2 - 4ac}}{2a}. The handwriting is neat and clear. No garbled symbols.
An ultra-realistic photo of a Penrose triangle made of polished gold, placed on a marble table. This object forms a continuous, impossible triangular optical illusion. The geometric structure has no breaks. Studio lighting.
A flat graphic design of an ambigram. Viewed normally, the word reads 'LIFE'; when rotated 180 degrees upside down, it reads 'DEATH'. Black ink on white paper, Gothic calligraphy style.
Nano Banana Pro brand hero image (another duplicate)
othersAgain repeats the prompt to generate a Nano Banana Pro header image that aligns with Google Nano Banana’s brand tone and visual elements.
展开提示词全文
Draw a hero/header image for Nano Banana Pro that matches Google Nano Banana’s brand tone and design elements.
Three English Nano Banana 2 test prompts
othersFrom the replies: three English prompts testing invisible text via light, knitted Ferrari material transformation, and a miniature forest inside a vintage lightbulb.
展开提示词全文
A cyberpunk street at night in heavy rain. A bright neon sign in the window reflects on the wet pavement. A full-scale Ferrari sports car made entirely of fluffy pink knitted wool. It is parked on a race track. The tires are made of yarn balls. High A vintage lightbulb. Inside the glass bulb, there is a tiny, detailed magical forest with a glowing wooden cabin and a miniature waterfall. Cinematic lighting, macro
Cinematic rainy street, underwater cathedral, and design-to-photo
othersReplies contain multiple Chinese prompts: a rainy old street with neon reflections, a submerged cathedral with volumetric light and diver, and a request to turn a design draft into a real object image.
展开提示词全文
An old street in pouring rain, with dim yellow streetlights, distorted neon signs reflected on the wet ground, and a person holding a transparent umbrella standing at the center of the frame, face not visible, shallow depth of field, cinematic composition, 8K, grainy texture, with a slightly blue-green cool tone. An ancient cathedral completely submerged underwater. Sunlight penetrates the water surface, with volumetric rays filled with floating particles. Stained glass windows cast colorful patterns onto the stone floor, tens of thousands of tiny bubbles rise up, and a diver wears a sleek suit. Turn the design draft into a realistic product photo.
Moody cinematic portrait from a photo
othersA Chinese prompt for generating a high-end, atmospheric black-and-white photo from an input image, focusing on controlled lighting and emotional mood.
展开提示词全文
For the person in the input image, generate: Atmospheric tone. The overall photo is cold and restrained, with a dramatic black-and-white texture. There is no cluttered background or distracting elements; a single beam of light becomes the only narrative focus. The frame looks like a movie still: quiet, deep, carrying loneliness yet containing strength. Wherever the light falls, that’s where the viewer’s gaze is drawn.
Weekend photo dump grid for Instagram
othersAn English prompt that generates a 9-image ‘photo dump’ grid showing a person’s weekend in various lifestyle shots, perfect for social media content automation.
展开提示词全文
Generate a 9-image ‘photo dump’ grid of this person’s weekend: a mirror selfie, a café shot, friends at dinner, a blurry party photo, a walking shot, a laptop/coffee work shot, a pet moment, a sunset, and a candid laugh.
Taiwan 10,000 NTD distribution infographic
othersA Traditional Chinese prompt asking the model to create an illustrated chart explaining how to claim a recent 10,000 NTD payout in Taiwan.
展开提示词全文
The methods for claiming the recent 10,000 NTD universal payout in Taiwan, in Traditional Chinese, as an illustrated infographic chart.
Baroque genre painting of a merry company in a park
othersAn English prompt in the replies asking for a Dutch/Flemish Golden Age baroque genre painting with a wide, highly detailed festive park scene and no typography.
展开提示词全文
Baroque genre painting, Dutch / Flemish Golden Age, a classic “merry company in a park” festive group scene, as a single highly detailed oil painting, not a poster, with no typography and no graphic design elements. Ultra-wide horizontal composition, inspired by 17th-century baroque painting.
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,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。