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License information is collected from official sources and may be outdated or missing.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.
725 matches
Using Nano Banana Pro as a Shading Tool for MMD Output
game-assetA user experimented with using Nano Banana Pro as a shading tool to add texture, decals, and glow effects to MMD (MikuMikuDance) output. They found that adding a croquis effect to emphasize edges worked well.
Show full prompt
I used nanobanana pro as a shading tool to add texture, decals, and glow to MMD output. I wanted to emphasize the edges, so I added lines with a croquis effect.
Live-action Lara Croft fantasy casting prompt
game-assetThis prompt is designed for image generation models like Nano Banana Pro to create a live-action fantasy casting image of Lara Croft, focusing on a specific actress, setting, and cinematic style.
Show full prompt
Live-action fantasy casting of Lara Croft, starring {argument name="actress name" default="Ana de Armas"}, in a jungle temple, cinematic lighting, ultra-realistic, photorealistic, 8k, high detail, high quality, professional photography, action pose, full body shot, wide shot
Complex Image Generation Test Prompt for Model Coherence
game-assetThis is a highly detailed, complex image generation prompt used to test the coherence, accuracy, and photorealism capabilities of models like Nano Banana Pro. It demands the generator accurately render numerous specific elements, precise counts (like 3 missing puzzle pieces, 23 rocks, 5 diagram panels), physics (liquid levels, centrifugal force), specific text/labels (DVORAK keyboard, presidential seal), and complex scene arrangements (people forming letters, Olympic rings, chess checkmate).
Show full prompt
A large, highly detailed, photorealistic image of a spacious, crowded house party room with dozens of diverse people mingling naturally. In the foreground, a table holds: a nearly finished jigsaw puzzle of a medieval castle with exactly three missing pieces placed next to it (holes clearly visible in the puzzle), exactly 23 randomly arranged rocks scattered nearby, a very wide glass and a very thin tall glass each filled with exactly the same volume of red wine (correct liquid levels accounting for glass shapes), a split before-and-after view of a Lego sunflower (left half showing all individual disassembled pieces, right half fully assembled with matching parts), an accurate standard DVORAK keyboard but with the V and K keys precisely swapped, and a 5-panel instructional diagram on how to make toast (exactly 5 panels, consistent toaster). On a central chess table, a top-down view of a full chessboard in a legal midgame position where a white bishop is directly checking the black king (all pieces positioned validly). In the background: a group of about a dozen people lying on the floor forming the letters 'OPEC' clearly with their bodies, five people standing on the ground each holding one correctly colored and interlocked hula hoop to precisely form the Olympic rings symbol, a man sitting on a woman's shoulders while both expertly spin glowing sock poi in circular motion (poi extended straight by centrifugal force), a detailed Where's Wally-style crowded scene on one wall with Wally hidden, a Secret Service agent mid-backflip off a presidential podium (with accurate presidential seal and text), and a man performing poi spins. Dramatic natural lighting, sharp focus everywhere, no artifacts, perfect anatomy and physics, all text and labels fully legible and accurate, highly coherent composition.
Sci-Fi Cinematic Image: Man in Cryo-Chamber
game-assetA structured prompt for generating a high-quality, hyper-realistic cinematic image depicting a young man preserved inside a futuristic glass ice box or cryo-chamber, emphasizing cold blue lighting, frost details, and a sci-fi/cyberpunk aesthetic.
Show full prompt
{
"Objective": "Generate a high-quality cinematic image of a young man preserved inside a futuristic glass ice box or cryo-chamber.",
"Subject": {
"Gender": "Male",
"Age_Group": "Young Adult",
"Appearance": {
"Eyes": "Closed, peaceful",
"Skin": {
"Texture": "Smooth, pale",
"Details": "Subtle frost on the skin and eyebrows",
"Makeup": "None"
},
"Hair": {
"Style": "Short, modern cut",
"Details": "Slightly frosted and damp"
},
"Expression": "Serene, in deep sleep"
}
},
"Wardrobe": {
"Clothing": "Futuristic minimal bodysuit",
"Style": "Sleek and tech-oriented"
},
"Lighting": {
"Type": "Cold neon and ambient technological glow",
"Quality": [
"Soft blue light from within the ice",
"Cinematic highlights on the glass edges"
]
},
"Camera_and_Technical": {
"Camera_Style": "Cinematic Film",
"Lens": "35mm",
"Aperture": "f/2.8",
"Focus": "Sharp on the subject through the cracked ice",
"Depth_of_Field": "Medium, showing a futuristic laboratory background"
},
"Visual_Style": {
"Aesthetic": "Sci-fi, Cyberpunk, Cold",
"Resolution": "8K Ultra-HD",
"Color_Grading": {
"Palette": [
"Deep Cyan",
"Electric Blue"
],
"Style": "High contrast, cold atmosphere"
}
},
"Text_Instruction": "A metallic nameplate at the base of the chamber clearly displays the single letter '{argument name="nameplate letter" default="A"}'."
}
Freepik prompt for a futuristic nano banana
game-assetThis is an image generation prompt for Freepik, designed to create a hyper-realistic, futuristic image of a nano banana. The prompt specifies a detailed, high-quality render with a focus on metallic textures, neon lighting, and a dark, sci-fi environment, emphasizing cinematic quality and extreme detail.
Show full prompt
A hyper-realistic, futuristic nano banana, metallic texture, neon light, dark background, sci-fi, cinematic, 8k, extremely detailed, photorealistic, high quality, {argument name="style" default="cyberpunk"}
Medium Shot of Character Interacting with Floating Interface
game-assetAn image generation prompt capturing a medium shot of a 3D character gently turning off a transparent floating interface panel. The scene transitions from cool to warm lighting, emphasizing a calm, focused expression and emotional realism within a modern minimal environment.
Show full prompt
{argument name="Character Name" default="Mia"} Medium shot of the 3D character gently reaching out to turn off a transparent floating interface panel, other panels fading softly, warm light slowly replacing cool tones, calm, focused expression, modern minimal environment, emotional realism, clean composition
Character Sheet for Deep-Sea Creature with Bioluminescent Skeleton
game-assetA creative prompt instructing the AI to invent a new animation style and character, specifically a deep-sea creature. The prompt details the creature's appearance, featuring an iridescent oil-slick surface and a pulsing bioluminescent skeletal structure.
Show full prompt
Character sheet showing Front, Back, and Side views of a deep-sea creature. The surface is a swirling, iridescent oil-slick with rainbow fuel-tints. Underneath the oily surface, a pulsing bioluminescent skeletal structure glows {argument name="skeleton color" default="soft blue"}. Wet, viscous texture, dark underwater studio lighting.
Zootopia Style Snowman Building Scene
game-assetAn image generation prompt for a 3D animated scene in the style of Disney/Pixar's Zootopia, featuring a rabbit and a fox building a snowman in a festive, magically lit winter holiday environment.
Show full prompt
{
"subject": "{argument name="characters" default="Animated rabbit and fox"} building a snowman (Zootopia style)",
"clothing": "Rabbit in blue vest and red scarf; Fox in green sweater and tie",
"action": "Rabbit rolling snow, Fox placing carrot nose",
"accessories": "Snowman with stick arms and coal buttons",
"environment": "Winter holiday scene, decorated Christmas tree, colorful string lights, falling snowflakes",
"lighting": "Magical twilight blue background with warm holiday light glow",
"camera": "Medium shot, eye-level, central composition",
"style": "3D animation style, Disney/Pixar aesthetic, festive, vibrant colors, high detail"
}
3D Isometric Atlas Scene in Firefly Style
game-assetA prompt for generating an epic 3D isometric atlas scene, where a massive ancient map erupts from a scroll, transforming into a living landscape with stacked civilizations and dramatic golden-hour lighting, rendered in an 8K Unreal Engine 5 style.
Show full prompt
Epic 3D isometric atlas scene: a massive ancient map of {argument name="subject" default="[SUBJECT]"} erupts from an unfurled parchment scroll, filling nearly the entire frame. Ink lines ignite into living terrain: mountain ranges push upward, cities rise in vertical layers, rivers glow and flow, borders burn softly in gold. Multiple civilizations {argument name="civilization layers" default="[CIVILIZATION LAYERS]"} coexist in stacked time, their architectures phasing through one another as if time is folding. A carved timeline spirals across the map with engraved dates. All text in {argument name="language" default="[LANGUAGE]"}. Extreme scale contrast, dense micro-detail everywhere, dramatic golden-hour light, volumetric dust, cinematic depth, 8K, UE5.
Glitch Storm Dragon Prompt
game-assetA prompt used to generate an image of a legendary dragon emerging from a glitch storm, utilizing pixel sorting, RGB color split, and fragmented wings to create an epic cinematic atmosphere. This prompt was tested on both Nano Banana Pro and ChatGPT.
Show full prompt
legendary dragon emerging from glitch storm, pixel sorting distortion, RGB color split, fragmented wings, epic cinematic atmosphere, highly detailed
Nano Banana Prompt for Heroic Low-Angle Pose with Beam Weapon
game-assetA detailed image generation prompt focusing on recreating a specific heroic pose using Nano Banana. The prompt specifies a dramatic low-angle shot, strong foreshortening of the legs, a powerful silhouette, and the inclusion of a beam weapon.
Show full prompt
Key Pose: Heroic stance from an extreme low angle, legs spread wide, feet strongly foreshortened towards the camera, torso slightly tilted back, one arm fully extended pointing a weapon towards the sky, the other arm down by the side (relaxed but ready), powerful silhouette. I want to emphasize the beam weapon feel more.
Eraser Gun Style Prompt for Nano Banana Pro (Fighting Pose Stage)
game-assetA multi-stage prompt designed to generate a character performing an 'Eraser Gun' style energy wave attack, similar to Dragon Ball techniques. This is the first stage prompt, which changes the character's pose to a fighting stance while strictly preserving the original art style from a reference image.
Show full prompt
subject: > The character exactly as shown in the reference image, preserving the original art style, proportions, line quality, coloring, texture, and overall visual appearance without alteration. composition: > Bust-up shot, frontal view, framing from the upper chest to the top of the head, balanced composition consistent with the reference image style. Aspect ratio is 16:9. action: > The character performs a clear pre-attack pose, crossing both arms above the head with clenched fists, slightly lowering the hips (implied through posture and shoulder angle), while shouting loudly with mouth wide open. The posture conveys physical tension and preparation. No additional visual effects. location: > Same environment as the reference image, unchanged background and setting. style: > Identical to the reference image. Do not modify or reinterpret the art style in any way. camera_lighting: > Same camera angle, lighting direction, and shading as the reference image, without enhancement or dramatization. colors: > Preserve the original color palette exactly as in the reference image. text: > None. edit_instructions: > Change only the character’s pose: bust-up framing, arms crossed above the head, shouting facial expression. Lowered hips are implied through upper-body posture only. Do not add effects, glow, motion lines, or stylistic changes. references: > Reference Image A: character identity, art style, and environment. extras: > High fidelity reproduction of the reference image style, no stylization, no reinterpretation.
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。
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。
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。
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.