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
Cards, Shakespeare, and Nabokov scenes
othersThree short prompts: recolor trading cards to black, depict Shakespeare writing a famous line, and show Nabokov writing about aurochs and angels with butterflies around.
展开提示词全文
Convert all these cards to black. Create a picture of Shakespeare writing the famous opening line from Mark Antony’s speech at Caesar’s funeral. Create a picture of Nabokov writing the famous line about aurochs and angels.
Sci-fi cinematic triptych and expansions
othersA pair of prompts to create a cinematic sci-fi triptych in a 4:5 composition and then expand each panel into full 4:5 scenes, inspired by Roger Deakins and IMAX framing.
展开提示词全文
Create a triptych of three 2.39:1 shots within a 4:5 composition. Make them cinematic, science-fiction shots with an atmospheric feel, as if shot by Roger Deakins in IMAX, with high contrast and desaturated blue and gray color grading. Then expand the three images one by one into three separate 4:5 scenes.
High-angle fashion portrait prompt for Gemini 3 Pro
othersReply contains a detailed prompt for a high-angle fashion portrait of a young Asian man on marble stairs.
展开提示词全文
High-angle fashion portrait of a 25-year-old Asian man, with the same facial features as the man in the reference photo, messy hairstyle framed on his face, leaning casually on a white marble staircase
Photoreal K-pop selfie on rooftop
othersA very detailed JSON prompt for an 8K photoreal rooftop selfie of a K-pop idol named LUNA, including micro facial details, lighting, environment, and camera metadata.
展开提示词全文
{
"subject": {
"identity": "K-pop girl-group lead vocalist, stage name: LUNA",
"age": 21,
"ethnicity": "Korean",
"hair": {
"style": "high ponytail, bubble-gum pink with a 3 cm ash-rose root fade",
"texture": "glass-shine, with 2 mm fly-aways lit by neon",
"accessory": "heart-shaped rhinestone hair tie with 5 mm stones catching the flash"
},
"makeup": {
"skin": "luminous cushion foundation, with 0.1 mm pores visible on the cheek",
"eyes": "foiled rose-gold shadow up to the brow bone, 4 mm silver glitter under the tear duct, and 12 mm outer-flare false lashes",
"liner": "sharp 45° wing with a 0.5 mm gap filled with white",
"lips": "gradient cherry color inside, blurred to a petal effect outside, with 1 mm thick gloss in the center",
"blush": "cool pink swept high on the cheekbone, reflecting the phone flash"
},
"pose": {
"head": "tilted 15° to the right, chin down to emphasize a V-line",
"eyes": "looking up at the phone lens, with a 2 mm highlighted aegyo-sal",
"mouth": "tiny heart-shaped pout with a 3 mm gap between the lips",
"hand": {
"device": "iPhone 15 Pro in a glittery lilac case, with three rhinestones missing from the lens ring",
"grip": "three fingers behind the phone, pinky extended, nails almond-shaped in nude with micro-sequins",
"angle": "camera held 30 cm above eye level, arm elongated"
}
},
"attire": {
"top": "cropped pastel-lavender hoodie with a raw hem and a 1 cm sweat bead at the collar",
"neck": "layered silver chains, with the shortest choker 1 cm above the collarbone",
"earrings": "asymmetrical star and moon earrings, 8 mm, swinging with the head tilt"
},
"lighting": {
"key": "built-in phone flash at 6500 K, slightly overexposing the tip of the nose",
"fill": "LED ring light clipped to the phone at 5600 K, creating circular catchlights in the eyes",
"background_bokeh": "city-night hexagonal bokeh, 2 stops underexposed"
}
},
"background": {
"location": "Seoul rooftop café on the 23rd floor at 21:17",
"depth": "out-of-focus neon signs reading purple ‘카페’ and pink ‘OPEN’, with 3 cm blur",
"sky": "clear indigo sky with 2% of the sunset orange remaining on the horizon",
"props": "frosted glass railing and a fairy-light string 5 cm in the foreground, with one bulb blown"
},
"camera": {
"mode": "portrait mode, 3× zoom, f/1.78, 1/120 s, ISO 250",
"filter": "built-in ‘Bright’ at +10, with skin smoothing turned off",
"artifacts": "slight purple fringing on the earring edge—keep this effect"
},
"output": "photoreal, 8K resolution, keep the flash glare on the cheek, retain the vertical phone ratio of 9:16, no watermark"
}
Hyper-realistic environmental portrait of stylish woman prompt (partial)
othersJSON-styled prompt describing a hyper-realistic environmental portrait of a stylish young woman in a dense tropical bamboo forest with detailed clothing and pose instructions, but truncated.
展开提示词全文
{
"prompt": "Hyper-realistic environmental portrait of a stylish young woman standing in a dense tropical bamboo forest. She is wearing a wide-brimmed black fedora hat, round dark sunglasses with thin metal frames, a plain black crew-neck t-shirt tucked in, and dark grey high-waisted trousers. She stands with a confident posture, leaning slightly forward, with her right
Convert scene to low-res pixel art
othersA brief prompt instructing the model to recreate an entire scene, including water splashes and background, as low resolution pixel art.
展开提示词全文
From scratch, recreate the entire scene, including the water splashes and the background, as low-resolution pixel art.
Group image from multiple character references
othersA simple prompt that asks Nano Banana Pro to combine multiple individual character reference images into one group shot.
展开提示词全文
make a group image of all the characters
Infographic from pasted text
othersThis prompt turns a block of text, such as a summary, into a clean infographic layout.
展开提示词全文
Make me an infographic for: {argument name="source text" default="[paste your text here]"}
Storyboard-style action-following frame
othersThis prompt generates a new frame that follows the sketched annotations, continuing a stampede scene toward the camera.
展开提示词全文
Follow annotations. The stampede continues to run towards the camera
Two-layer neural network diagram in Stephen Biesty style
othersGenerates a diagram of a two-layer neural network illustrated in the detailed, cutaway style of Stephen Biesty.
展开提示词全文
Generate a diagram of a two-layer neural network in the style of Stephen Biesty
Hieronymus Bosch-style AI future painting
othersCreates a surreal painting about the state of AI in 2025 in the style of Hieronymus Bosch.
展开提示词全文
generate a Hieronymus Bosch–style painting of the state of AI in 2025
Cat drinking cola illustration
othersA playful prompt that makes a cat drinking Coca-Cola, suitable for fun posts or memes.
展开提示词全文
Generate an image of a cat drinking Coca-Cola
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。