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License information is collected from official sources and may be outdated or missing.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.
1099 matches
F-14D in the Style of a Western Religious Painting
othersA prompt used with Nano Banana Pro via Google Gemini 3.1 to generate an image of an F-14D fighter jet rendered in the style of a Western religious painting.
Show full prompt
an F-14D in the style of a Western religious painting
Whimsical Cyberpunk Alley Network
othersA prompt for Nano Banana Pro to generate a whimsical miniature world depiction of a rain-soaked alley network in a cyberpunk style.
Show full prompt
Whimsical miniature world depiction of a rain-soaked alley network in cyberpunk style.
Tactile Embroidered Tapestry of a Ship in Nebulae
othersA descriptive prompt for Nano Banana Pro to generate an image of a tactile embroidered tapestry fragment. The tapestry depicts a wooden sailing ship navigating a sea of swirling nebulae, emphasizing visible stitch textures, layered thread, and a warm romantic twilight glow on the textile surface.
Show full prompt
Tactile embroidered tapestry fragment showing a lone wooden sailing ship navigating a sea of swirling nebulae, visible stitch textures and layered thread in deep navy, gold, and starlit silver, trailing mist like loose floss caught in wind, warm romantic twilight glow on the textile surface.
Cinematic Macro Toy Photography of a Charging Army
othersA highly detailed prompt for generating a cinematic macro toy-photography scene using Nano Banana, depicting dozens of identical bean-sized characters charging forward in a military formation through a violent rainstorm, led by a commanding figure on a fantastic mount. The prompt includes extensive constraints on likeness integrity, scene structure, motion dynamics, camera perspective, and lighting doctrine.
Show full prompt
A cinematic macro toy-photography scene of dozens of identical bean-sized instances of the uploaded reference character charging forward through a violent rainstorm in a partially broken military formation, led by a commanding figure riding a fantastic mount deeper in the frame. ar 16:9 🧬 Likeness Integrity (CRITICAL) All instances must preserve exactly: • proportions • eye shape, spacing, stylization • silhouette • material identity No redesign. No added features. No facial changes. All soldiers are identical instances of the same character. ⚔️ Scene Concept & Motion Structure The army transitions from formation into full charge: • front rows breaking into aggressive motion • mid rows reacting milliseconds later • deeper rows still partially aligned Motion spreads like a wave through the army Each unit runs with controlled variation: • different stride timing and body angles • no identical poses • all movement directed forward Weapons: • each unit carries an oversized medieval-style weapon • designs vary but follow a unified visual language • subtle controlled glow, never overpowering • must not obscure character identity 🐉 Leader & Mount (COMMAND LAYER) A commanding leader appears deeper in the frame, elevated above the formation: • positioned off-center along a rule-of-thirds axis • partially silhouetted through rain and haze • clearly distinct from the soldiers through scale and placement Mount Design Logic (CRITICAL): • derived from the character’s material and world language • no literal cloning or costume mimicry • subtle harmony in form, texture, and accents Pose: • mount in forward surge, cutting through rain • leader stable and controlled, not exaggerated • presence communicates authority, not motion chaos The leader has already moved. The army is catching up. 🪂 Foreground Hero (IMPACT ANCHOR) The closest instance dominates the foreground: • captured mid-air in a dynamic jumping attack pose • limbs extended with directional force • weapon leading the motion This figure acts as the visual entry point into the scene 🎥 Camera & Perspective (PRESSURE SHOT) Ultra-low ground-level camera, almost touching wet terrain 18–24mm close-lens perspective • foreground character enlarged by proximity • army recedes diagonally into depth • leader visible in mid/deep plane • slight horizon tilt for instability • some units cropped at frame edges Viewer feels inside the charge 🔍 Depth of Field (MANDATORY) Extremely shallow depth of field • foreground hero = razor sharp • nearby units slightly softened • leader readable but partially diffused • distant army dissolves into rain and haze No full-frame clarity 💡 Lighting Doctrine (STORM LIGHT) Hard directional back/side light cutting through rain • strong rim light outlining silhouettes • rain streaks illuminated as sharp lines • deep shadow poc
Neanderthal image generation based on expert knowledge
othersA discussion about generating historically accurate images of Neanderthals using AI, specifically mentioning the need to include 'based on expert knowledge of Neanderthal behavior' in the prompt for the Nano Banana model.
Show full prompt
image of Neanderthals “based on expert knowledge of Neanderthal behavior”
Intricate Paper Cut Silhouette of a Library
othersA detailed prompt for Nano Banana Pro describing an intricate, multi-layer paper cut silhouette of a crumbling ancient library floating above storm clouds, emphasizing texture, color palette, and folk art style.
Show full prompt
Intricate multi-layer paper cut silhouette of a crumbling ancient library floating above storm clouds, heavy handmade paper with visible fibers and rough cut edges casting subtle shadows between layers, muted indigo, sepia, and silver tones, soft backlighting creating depth, traditional folk art silhouette feel with surreal scale.
4K Photo Restoration Prompt
othersA simple prompt instructing the model to restore an old uploaded photo to 4K resolution while strictly preserving all original details and authenticity.
Show full prompt
Restore this old photo to 4K without changing any details
Hyper-Detailed Anatomical Portrait of Sadie Sink in Minimalist Attire
othersAn extremely technical and detailed JSON prompt for Nano Banana Pro, focusing on generating an image of Sadie Sink. It includes forensic parameters for identity mapping, highly specific anatomical geometry (emphasizing exaggerated volume and curvature), detailed wardrobe physics (high-tension fabric), and a scene set on a highly reflective industrial stainless steel surface with cinematic studio lighting.
Show full prompt
{
"subject": {
"identity": {
"biometric_reference": "{argument name="subject name" default="Sadie Sink"}",
"forensic_parameters": "1:1 craniofacial mapping, distinct auburn hair (#8B4513), #5D9B9B iris stroma texture, specialized dental occlusion pattern."
},
"anatomy_geometry": {
"torso_volumetrics": {
"anterior_upper_torso": {
"volume_distribution": "Exaggerated volumetric mass in the anterior upper torso region, significant forward projection",
"surface_tension": "Defined anterior thoracic curvature geometry, high skin-tension simulation, pronounced midline depression topographic definition"
},
"posterior_pelvic": {
"curvature_geometry": "Pronounced hip curvature geometry (#0.68), significant volume-to-waist ratio definition"
}
},
"extremities": {
"proximal_femoral_exposure": "Significant femoral and gluteal-femoral boundary visibility due to truncated textile geometry limits",
"pedal_morphology": "Anatomically correct phalanges, high-resolution dermal ridges",
"ungual_pigmentation": "Total saturation of distal phalangeal plates with black pigment (#000000)"
}
}
},
"wardrobe_physics": {
"upper_layer": {
"material": "High-elasticity white ribbed cotton (#FFFFFF)",
"textile_physics": "Extreme fabric tension vectors due to hyper-volumetric mass wrapping, emphasized minimal geometric footprint across the midline, visible textile stretch limits"
},
"lower_layer": {
"material": "Minimalist black synthetic weave (#000000)",
"fit_geometry": "Ultra-truncated hemline, micro-inseam length defined by minimum surface area coverage, high-tension elastic structure terminating prior to the major pelvic joinery boundary"
}
},
"pose_action": {
"description": "Seated posture on a horizontal specular plane, symmetric pelvic tilt, ankles in adduction position.",
"manual_interaction": "Bilateral hand engagement with a metallic communication device, neutral facial affect."
},
"scene": {
"surface_science": {
"substrate": "Polished industrial stainless steel surface",
"reflectivity": "High-fidelity ray-traced specular reflections of the subject's morphology and environment",
"reflection_integrity_rules": "1:1 parity between physical subject and mirrored projection on the metallic plane"
},
"background_elements": [
"Low-frequency focus on dressing room apparatus",
"Neutral-toned vertical drapes",
"Organized cosmetic canisters with realistic material shaders"
]
},
"lighting": {
"architecture": "High-key cinematic studio illumination",
"focal_highlights": "Sharp specular glints on the metallic surface and iris coronas",
"shadow_mapping": "Soft ambient occlusion at skin-to-surface contact points"
},
"camera": {
"optics": "85mm focal length, f/1.8 aperture, 9:16 vertical aspect ratio",
Seamless Pattern of Cartoonish Fancy Goldfish
othersA simple prompt for generating a seamless pattern suitable for textiles or wallpaper, featuring cute, cartoonish fancy goldfish with large eyes on a cream background.
Show full prompt
A seamless pattern of cute, cartoonish fancy goldfish with large bulging eyes on a cream-colored background. The goldfish are round and orange with large black eyes and delicate, wispy fins and tails. The pattern is dense, with fish scattered randomly across the frame, creating a playful and whimsical feel.
Ultra-Photorealistic Katyayani Warrior Goddess Prompt
othersA highly detailed, narrative prompt for Gemini Nano Banana Pro to generate an ultra-cinematic, hyper-realistic depiction of the Hindu goddess Katyayani, emphasizing natural human skin texture, fierce yet calm expression, divine attributes (four arms, sword, lotus), and dramatic mythological battlefield lighting and composition.
Show full prompt
“Ultra-cinematic, hyper-realistic depiction of Katyayani, the fierce warrior form of Durga created to defeat Mahishasura. She appears as a powerful divine warrior woman with natural human skin texture, realistic lighting, visible pores, and authentic facial details—avoiding any plastic or artificial AI look. She is seated majestically while riding a powerful lion, her posture confident and commanding. The lion moves forward with strength and intensity, muscles visible beneath detailed fur, symbolizing courage and dominance over evil forces. Her expression is calm yet fierce, reflecting both compassion and unstoppable divine power. She has four arms: • One hand holding a radiant divine sword, symbolizing the destruction of evil • One hand holding a lotus flower, representing purity and spiritual wisdom • One hand raised in Abhaya Mudra, granting protection and fearlessness • One hand in Varada Mudra, blessing devotees with success and fulfillment She wears a deep red warrior-style saree with golden accents, flowing dynamically in the wind. Her royal golden crown is elegant yet strong, emphasizing her divine warrior identity. A subtle indigo glow shines from her forehead, representing the Ajna chakra, symbolizing spiritual insight and divine awareness. Behind her radiates a powerful fiery red and golden aura, like sacred flames mixed with divine sunlight. The background shows a dramatic mythological battlefield sky with swirling storm clouds and powerful sun rays breaking through, symbolizing the victory of divine power over darkness. Wind moves her hair and garments while sparks of golden energy and dust particles float in the air, creating motion and intensity. Camera angle: low cinematic hero angle, looking upward at the goddess riding the lion to emphasize her divine authority and warrior strength. Lighting: dramatic cinematic lighting with volumetric god rays, fiery highlights, and deep shadows. Mood: fearless, protective, powerful warrior goddess energy. Style: ultra-photorealistic mythological cinematic realism, HDR lighting, extremely detailed fabrics, metals, and lion fur, natural human skin tones, epic fantasy realism, vertical 9:16 composition”
Bubbly Cheeseburger Still Life Prompt
othersA detailed prompt for generating a meticulously composed still life image of a cheeseburger, wine, and fries, where all objects are made of vibrant, translucent, colorful bubbles with intense glossy and iridescent shine, set against a dark baroque background. The image is generated using Nano Banana Pro.
Show full prompt
a meticulously composed still life of a cheeseburger, a tall glass of wine, and a heap of french fries, where the entire scene and every object is made out of vibrant, translucent colorful bubbles with even more intense glossy surfaces, clustered highlights and multi-layered holographic iridescent shine, set against a softly blurred yet visually rich dark baroque-inspired background with ornate swirling decor and subtle gilded patterns that make the glowing bubbles pop, dramatic studio lighting from the side to emphasize extreme reflections and refractions across every bubble, ultra high detail, hyper-polished surfaces, no legible text, logos, or signatures anywhere in the image
Hogwarts Great Hall during a thunderstorm
othersA descriptive prompt for generating a dramatic scene of the Hogwarts Great Hall during a thunderstorm. The prompt specifies the enchanted ceiling showing violent lightning, thousands of flickering floating candles, and rain evaporating just above the students, emphasizing the gothic architecture and foggy darkness. This prompt is listed for Nano Banana Pro, Midjourney v8, and Uni -1.
Show full prompt
The Great Hall of Hogwarts during a thunderstorm, the enchanted ceiling showing violent lightning striking directly overhead, thousands of floating candles flickering wildly, rain phasing through the magical ceiling and evaporating inches before touching the students, long tables stretching into foggy darkness, gothic architecture dripping with atmosphere
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。
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。
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。
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
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.