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License information is collected from official sources and may be outdated or missing.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.
702 matches
Dramatic Cinematic Train Rescue Scene Prompt
comic-storyboardA structured prompt for generating an ultra-realistic, dramatic cinematic rescue scene involving a police officer pulling a civilian to safety on top of a moving or halted train. It specifies a low-angle dynamic shot, 35mm lens perspective, foggy daylight, and detailed subject descriptions to convey an urgent, heroic moment.
Show full prompt
{
"style": "Dramatic cinematic rescue scene, ultra-realistic, 4K",
"camera": {
"angle": "Low-angle dynamic shot from the side of the train",
"lens": "35mm action perspective",
"motion": "Slight action blur for intensity",
"lighting": "Foggy daylight, soft diffused light"
},
"scene": {
"location": "Railway station platform with overhead wires and metal structures",
"environment": "Light fog, high tension wires above, station bridge with people watching",
"vibe": "Urgent rescue moment, high-risk situation"
},
"subjects": [
{
"role": "Police officer",
"pose": "Climbing on top of a moving or halted train, pulling a person to safety",
"expression": "Focused, determined",
"outfit": "Brown uniform, tactical gloves, utility belt"
},
{
"role": "Civilian in distress",
"pose": "Lying on the train roof, about to slip, being lifted by the officer",
"expression": "Weak, struggling"
}
],
"details": {
"background_action": "Crowd watching from overhead bridge, some filming with phones",
"elements": "Realistic textures of train roof, high-tension cables, metal frames",
"tone": "Heroic, intense, life-saving moment",
"composition": "Wide frame capturing both subjects, overhead wires and bridge visible"
}
}
Image Overlay for 'Conspiracy Scribbles' Effect
comic-storyboardA prompt instructing the AI to overlay a provided image with chaotic, intense annotations, specifically 'insane schizophrenic conspiracy scribbles,' red ink, doodles, remarks, and comments, creating a highly distressed and annotated visual.
Show full prompt
overlay this with insane schizophrenic conspiracy scribbles, red ink, doodles, remarks, comments.
Cinematic Last of Us Campfire Scene
comic-storyboardA detailed prompt for generating a cinematic, hyper-realistic image of Ellie and Joel from The Last of Us. It specifies the setting (ruined forest clearing, dying campfire, overgrown cars), the characters' actions (Joel leaning, Ellie tuning guitar), and the lighting/atmosphere (firelight mixing with cold blue twilight, gritty, moody shadows, 8K realism).
Show full prompt
Ellie and Joel from The Last of Us web series sit by a dying campfire in a ruined forest clearing at dusk. Joel leans back against a broken tree trunk, rifle resting beside him, watching Ellie tune her worn-out guitar. Firelight flickers across their tired faces, mixing with the cold blue twilight. Overgrown cars and collapsed highway signs fade into the background. Atmosphere is gritty, emotional, cinematic. Soft drifting ash, subtle lens flare, sharp textures, moody shadows, 8K realism.
Generate Scene Five Minutes Earlier
comic-storyboardA creative prompt used for image-to-image generation, asking the AI to analyze a provided image and generate a new image depicting the scene exactly five minutes before the original moment, specifically to explain the current emotional state of a subject.
Show full prompt
Show me 5 minutes earlier so I can see why he’s upset.
High-Fashion Streetwear Editorial with Forced Perspective
comic-storyboardA highly technical and structured JSON prompt for generating a multi-panel, high-fashion streetwear editorial image. It focuses on technical execution, including multi-panel consistency, identity locking (strict enforcement of facial features from a reference), extreme wide-angle perspective study, and detailed descriptions of the model's appearance, wardrobe (neon orange bomber, tactical pants), and material fidelity.
Show full prompt
{
"meta_control": {
"generation_mode": "multi_panel_consistent",
"priority_stack": ["identity_lock", "perspective_physics", "material_fidelity", "environmental_coherence"],
"quality_target": "editorial_print_ready"
},
"intent": {
"primary": "High-fashion streetwear editorial with extreme wide-angle perspective study",
"secondary": "Technical demonstration of foreshortening and forced perspective",
"publication_context": "Double-page spread, fashion magazine collage layout"
},
"frame": {
"aspect_ratio": "3:4",
"layout": {
"type": "2x2 grid collage",
"gutter_width": "2px white or seamless",
"panel_uniformity": "identical dimensions per panel"
}
},
"subject": {
"type": "Human female fashion model",
"identity_lock": {
"enforcement_level": "strict",
"anchor_features": ["face_geometry", "skin_tone", "body_proportions", "hair_style"]
},
"biometrics": {
"age_presentation": "22-26",
"height_cm": 175,
"build": "Slender athletic, model proportions",
"ethnicity_presentation": "Northern European features"
},
"facial_signature": {
"structure": "Angular diamond face, high cheekbones, defined jawline",
"eyes": "Sharp almond, steel grey, graphic black winged liner extending 8mm",
"nose": "Refined, straight, small silver hoop piercing on left nostril",
"lips": "Natural shape, matte nude-pink",
"skin": "Fair, visible pores and natural texture, subtle peach fuzz, tiny freckle cluster left cheekbone",
"expression_default": "Cool confidence, intense direct eye contact, composed"
},
"hair": {
"style": "Platinum blonde straight bob, blunt bangs ending at eyebrows",
"texture": "Silky, light-catching, individual strand definition",
"behavior": "Natural movement responding to pose changes"
},
"wardrobe": {
"jacket": {
"item": "Oversized bomber jacket",
"material": "Ripstop nylon, high gloss",
"color": "Neon orange (vivid, saturated)",
"state": "Unzipped, hanging open",
"light_behavior": "Sharp specular highlights, visible weave texture"
},
"top": {
"item": "Crop top",
"material": "Black synthetic mesh, diamond pattern",
"fit": "Tight, stretched across torso",
"transparency": "Semi-sheer, skin visible through weave"
},
"pants": {
"item": "Tactical cargo pants",
"material": "Heavy cotton twill, matte",
"color": "Charcoal grey",
"details": "Multiple pockets, silver buckles, black nylon straps, baggy fit"
},
"footwear": {
"item": "Platform sneakers",
"color": "W"
}
}
}
}
Overlay Image with Funny Comments
comic-storyboardA simple prompt instructing the model to overlay an image (implied, as this is a modification prompt) with funny comments, doodles, and remarks using red ink, with the option to specify the language of the comments.
Show full prompt
Overlay this with funny comments, red ink, doodles, remarks, comments in {argument name="language" default="[language]"}
Messed Up Psycho Image with Speech Bubble
comic-storyboardA prompt instructing the AI to generate an extremely detailed, messed up, and weird image of a 'crazy psycho' character, including a speech bubble that says 'heading out?'. It requires a reference photo for the character.
Show full prompt
Create an image of a crazy psycho with speech bubble that says “heading out?” Make the entire image extremely detailed but make it really messed up and weird af.
Overlay Image with Conspiracy Scribbles
comic-storyboardA simple prompt instructing the model to overlay an existing image (implied, as this is a modification prompt) with chaotic, handwritten elements like schizophrenic conspiracy scribbles, doodles, remarks, and comments using red ink.
Show full prompt
overlay this with insane schizophrenic conspiracy scribbles, red ink, doodles, remarks, comments.
Gritty Western Gunslinger Scene Prompt
comic-storyboardA highly descriptive prompt for generating an ultra-realistic, cinematic western scene. It focuses on a lone gunslinger riding through a dusty frontier town at golden hour, detailing the lighting, textures (cracked leather, rough wood), and the tense, gritty mood before a gunfight.
Show full prompt
A lone gunslinger on horseback rides through a dusty frontier town at golden hour. Sunlight cuts across the street, casting long shadows from wooden saloons, broken fences, and old telegraph poles. The gunslinger wears a weathered leather coat, a tilted cowboy hat, and a holstered revolver glinting in the sun. His face is rugged with dirt, sweat, and subtle scars. Dust swirls around the horse’s hooves as wind rolls through the town, lifting loose papers and dry hay. In the background: mountains fading into haze, a saloon door swinging, crows circling overhead. Hyper-detailed textures — cracked leather, rough wood grain, dust particles shining in sunlight. The mood is tense, cinematic, and quiet: the calm before a gunfight. Ultra-realistic 8K western aesthetic, gritty tone, deep contrast, golden lighting.
Cinematic Noir Portrait Prompt
comic-storyboardA prompt for generating a high-contrast, black and white cinematic portrait in the noir style. It specifies chiaroscuro lighting, deep shadows, strong film grain, and a dramatic mood, suitable for subjects like a detective.
Show full prompt
High-contrast black and white portrait of {argument name="subject" default="[a detective in a trench coat]"}, cinematic style, deeply shadowed eyes, chiaroscuro lighting, strong single light source from the left, heavy film grain texture, analog photo, moody and dramatic, 35mm lens, 8K, ultra-detailed.
Hyper-Realistic Flash Selfie Crime Scene Prompt (JSON format)
comic-storyboardAn intense, highly detailed JSON prompt for generating a hyper-realistic, cinematic crime-scene style flash selfie. It specifies extreme camera settings, a dramatic subject (runaway bride meets cyber-thriller), a trashed penthouse environment, and dramatic lighting effects like blinding flash and deep red emergency light.
Show full prompt
{
"my_prompt": {
"core_style": "insane hyper-realistic flash selfie, cinematic crime-scene energy",
"target_quality": "16K raw photorealism, zero beauty filters",
"main_rule": "face locked exactly to reference, no softening or reshaping",
"shot_setup": {
"type": "mirror selfie in abandoned luxury hotel suite",
"camera": "iPhone 16 Pro Max, flash cranked to maximum",
"lens": "24 mm, slight barrel distortion on edges",
"angle": "phone held high above head, shooting downward (dutch tilt 15°)",
"framing": "full body + massive cracked mirror reflection, phone dominating foreground"
},
"subject": {
"age": "24-27",
"vibe": "high-fashion runaway bride meets cyber-thriller",
"pose": "perched on the edge of a shattered glass coffee table, knees wide, one stiletto dangling off toe, leaning forward aggressively toward mirror, one hand gripping a half-empty champagne bottle by the neck, the other holding phone like a weapon",
"hair": "long blood-red hair, wet and slicked back on top, loose chaotic waves below, strands stuck to face and neck",
"outfit": "ripped white silk wedding dress torn to mini length, smeared with real blood and red wine stains, black leather harness over torso, thigh-high patent black boots with broken heel on one side"
},
"accessories": [
"smudged black eyeliner running down cheeks",
"diamond choker + torn veil hanging from it",
"bloody fingerprints on champagne bottle",
"silver ring flash reflecting in eyes"
],
"environment": {
"location": "trashed penthouse suite at 4 AM",
"background": "floor-to-ceiling windows showing city skyline at dawn, overturned furniture, shattered mirror wall, rose petals and broken glass everywhere, police caution tape visible through open door",
"lighting": "only source is dying red EMERGENCY EXIT sign + iPhone flash cutting white-hot through crimson haze"
},
"lighting": {
"main_source": "blinding white flash creating nuclear highlights and pitch-black shadows",
"ambient": "deep blood-red emergency lighting + faint blue pre-dawn glow from windows",
"effect": "face lit like an interrogation, red rim light bleeding into hair, reflections in blood puddles"
},
"render_details": {
"skin": "sweat, wine, and blood droplets with real refraction",
"glass": "microscopic shards catching flash individually",
"motion": "slight hand shake blur on phone, subject frozen by flash",
"sensor": "heavy noise, lens flare streaks, crushed blacks"
},
"negative": [
"cute, soft, clean",
"smiling",
"studio lighting",
"anime/cartoon",
"perfect skin",
"intact dress",
"daylight"
]
}
}
Split-Screen Cinematic Time Travel Prompt
comic-storyboardA complex, structured prompt for generating a horizontal split-screen cinematic image that seamlessly merges two different eras, creating a dynamic time-travel interaction where elements and people from the past and present visually overlap and react to each other.
Show full prompt
A horizontal split-screen cinematic shot of {argument name="scene" default="{Scene}"}, seamlessly blending two different eras: {argument name="era A" default="{Era_A}"} on the left and {argument name="era B" default="{Era_B}"} on the right (default: about 100 years ago vs. present day).
On the left side ({argument name="era A" default="{Era_A}"}): show era-appropriate architecture, interior or environment design, materials, vehicles, and props that clearly belong to that historical period. People wear authentic clothing from {argument name="era A" default="{Era_A}"}, including hairstyles, accessories, and typical items in their hands (such as books, umbrellas, instruments, letters, newspapers, etc.). The overall mood feels nostalgic and historically accurate.
On the right side ({argument name="era B" default="{Era_B}"}): show the same {argument name="scene" default="{Scene}"} in the modern era, with updated architecture or renovated structures, contemporary materials (glass, steel, LED screens, modern furniture), modern vehicles or equipment, and current technology (smartphones, laptops, cameras, etc.). People wear contemporary fashion that matches today’s style in this setting.
In the center: the two eras merge and overlap organically, without a hard dividing line. Elements from {argument name="era A" default="{Era_A}"} and {argument name="era B" default="{Era_B}"} visually interact: people from different times look at each other, walk through each other’s space, or seem surprised by the other era’s technology and objects. Architecture and environment smoothly morph from old to new (for example, stone gates turning into modern campus gates, classical concert hall décor fading into a futuristic stage, old street shops transforming into neon-lit storefronts).
Make sure the scene is not just a simple left/right comparison but a dynamic time-travel interaction where buildings, clothing, props, and human gestures clearly emphasize the contrast and fusion between the two eras. Photorealistic, 8k resolution, cinematic lighting, wide angle, highly detailed textures, rich sense of time-travel storytelling.
SCENE: {argument name="scene example" default="Times Square, New York"}
Era Comparison: {argument name="era comparison example" default="1920s and present day"}
Aspect Ratio: {argument name="aspect ratio" default="4:3"}
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。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
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。
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
海报设计工作室
FreemiumAPI key required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,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。
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.