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
Pose transfer for fitness shots
othersA reference-guided prompt that recreates a man in the same fitness poses as in another image, rendered realistically.
展开提示词全文
Show this man in the same fitness poses as in the first image, in a realistic style.
Hyperreal winter park walk portrait
othersA structured, parameterized prompt for a hyperrealistic Ultra HD portrait of a man walking in a cold winter city park with shallow depth of field and cinematic lighting.
展开提示词全文
Subject: {argument name="subject_identity_en" default="same man as reference"}
Focus: 100% on subject (sharp), background = 0% focus (heavy Gaussian blur).
Environment:
- Location: {argument name="location_en" default="city park"}
- Time: {argument name="time_of_day_en" default="early cold winter morning"}
- Elements: misty air, frosty grass, long soft shadows, pale sunlight.
Appearance:
- Outfit: insulated winter jacket, layered innerwear, scarf wrapped neatly, warm trousers, subtle accessories.
- Vibe: calm, composed, natural morning-walk posture.
Camera:
- Depth of field: very shallow.
- Lens: 85mm cinematic portrait lens.
- Color tone: cold blue-white, high dynamic range.
- Framing: center-weighted, portrait orientation.
Output:
- Hyperrealistic.
- Ultra HD.
- Detailed texture on clothes and skin.
- Blurred park-goers in background.
Peaceful anime hillside landscape
othersA lush hand-painted anime scene of a cottage on a green hillside under massive clouds, ideal for calm, nostalgic backgrounds.
展开提示词全文
A lush, hand-painted anime landscape of a rolling green hillside with a small cottage. Fluffy, massive cumulus clouds in a bright blue sky. Vibrant greens and soft shadows. A gentle breeze blowing the grass. Detailed, peaceful, and nostalgic style.
Alien-human hybrid sorrow portrait
othersA detailed ultra-close portrait prompt of a human–alien hybrid face with intricate textures, nebula-reflecting eyes, and tiny embedded text.
展开提示词全文
Ultra-close-up of a human–alien hybrid face expressing quiet sorrow: detailed hybrid features like scaled skin blending into human pores, heterochromatic eyes with reflective pupils showing a starry nebula, and tears with realistic refraction. Embed tiny text on the scales in alien script and English ("{argument name="embedded_text_en" default="Emotion Transcends Species"}"). Push for no blurring in fine details like eyelashes or vein networks, under dramatic side lighting.
Watercolor US map with state abbreviations
othersA prompt for a full watercolor-style map of the United States, labeling each state with its abbreviation and adding creative illustrations.
展开提示词全文
A full map of the US with all states labeled with their abbreviations, in watercolor style with creative illustrations.
Multi-panel cytokine signaling pathways
othersA scientific prompt to generate multi-panel diagrams of IL-2, IL-4, IL-12, and IL-6 signaling pathways, useful for immunology figures.
展开提示词全文
In multiple panels, create {argument name="pathways_en" default="IL-2, IL-4, IL-12, and IL-6 signaling pathways"}.
Foggy pine forest cinematic portrait
othersA JSON-structured, ultra-photorealistic prompt of a person walking through a dense pine forest with fog, cinematic lighting, and detailed wardrobe and camera settings.
展开提示词全文
{
"scene": "Solitary person walking through a dense pine forest",
"description": "Ultra-photorealistic 4K cinematic portrait of a person surrounded by thick rolling fog, captured in a three-quarter turn, mid-step, with a calm and slightly curious expression.",
"subjects": [
{
"type": "human",
"description": "A person wearing a dark moss-green wool overcoat that flows slightly with movement, a charcoal turtleneck, and a vintage leather satchel strap across the chest. Heavy boots show traces of wet soil and pine needles. Fine moisture beads on fabric and hair, droplets visible on eyelashes and brows.",
"position": "Center frame, slightly off to the left",
"pose": "Walking slowly, one hand gently parting the fog or brushing a low pine branch in the foreground."
}
],
"environment": {
"location": "Dense pine forest",
"props": ["low pine branches", "thick rolling fog"],
"background": "Tall pine trees fading into layers of mist."
},
"visual_style": {
"style": "hyper-real cinematic photography",
"mood": "calm, alert, slightly curious",
"color_palette": ["cool green", "blue"],
"lighting": "Natural daylight filtering through the canopy, forming realistic volumetric god-rays."
},
"camera": {
"angle": "85mm lens with f/1.8 aperture, shallow depth of field",
"distance": "Close-up on the subject, sharp focus on face and hand with background dissolving into soft bokeh."
},
"technical": {
"resolution": "3840 × 5760",
"quality": "HDR lighting with global illumination, realistic volumetric fog scattering, and subtle analog film grain."
}
}
Ronaldo selfie with Musk and Putin
othersA humorous speculative prompt where Cristiano Ronaldo takes a selfie with Elon Musk and Vladimir Putin in front of the White House, all wearing suits.
展开提示词全文
Cristiano Ronaldo taking a selfie with Elon Musk and Vladimir Putin, all three wearing suits and standing in front of the White House. The image should capture a friendly and relaxed atmosphere, with good lighting on their faces and the White House clearly visible in the background.
Lego-style self transformation
othersA quick edit prompt that turns a person in a photo into a Lego-style version while keeping everything else unchanged.
展开提示词全文
Make me Lego, keep everything else the same.
Live-action video game BTS scene
othersA flexible prompt template that generates behind-the-scenes shots of filming a live action adaptation of a chosen video game.
展开提示词全文
Behind-the-scenes shot of them making a live-action {argument name="video_game_en" default="[video game]"}.
Celebrity face replacement trio
othersAn editing prompt that replaces people in a photo with specific celebrities, suitable for playful composites.
展开提示词全文
Replace the blonde with {argument name="person_1_en" default="Sydney Sweeney"} and the other two with {argument name="person_2_en" default="Kendall Jenner"} and {argument name="person_3_en" default="Kylie Jenner"}.
Restored pyramids and Sphinx
othersA historical reconstruction prompt showing the pyramids and Sphinx as they might have looked when newly built, with the Sphinx’s face intact.
展开提示词全文
A photo of the pyramids and Sphinx, but showing how they looked when they were originally built, with the Sphinx's face perfect.
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。