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License information is collected from official sources and may be outdated or missing.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
Image Overlay Text Removal Test
othersA before/after comparison testing Nano Banana Pro's ability to remove overlaid text from an image, concluding that the attempt was unsuccessful or pointless.
Show full prompt
“Please remove the overlaid text from the image”
Multi-Step Prompt Generation Workflow for Product Posters
othersA detailed workflow instruction for generating complete, system-level prompts for product posters using LLMs (GPT, Claude, Gemini) and then executing them on Nano Banana Pro. The process involves the LLM extracting selling points, determining style, and layout, followed by the image model generating the final poster, with specific constraints on logo consistency and product appearance.
Show full prompt
Input this instruction, allowing the AI to complete the entire process step-by-step: extracting selling points, determining style, determining layout, and finally generating a complete, system-wide prompt. Finally, give the AI-generated prompt to the Nano Banana Pro model (it must be Pro). You can first provide some overall style prompts separately as general constraints. Then, whether generating images individually or in batches using third-party tools, it is possible.
Reference Image Prompt for Facial Expression and Angle Variations
othersA simple instruction prompt intended to be used after uploading a reference portrait. The goal is to generate multiple close-up shots of the subject while varying their facial expressions and camera angles, maintaining the core identity from the uploaded image.
Show full prompt
Change her facial expressions, various angles of close up shots
Fantasy Christmas Portrait with Magical Glow
othersA structured prompt for generating a fantasy, hyper-realistic Christmas portrait of a woman in an elf-like festive dress, set in a snowy enchanted village with soft, magical cinematic lighting.
Show full prompt
{
"render_goal": "Fantasy hyper-realistic Christmas portrait with magical vibe",
"subject": {
"gender": "female",
"age_range": "mid-20s",
"pose": "holding a gift with glowing light",
"expression": "cheerful and playful"
},
"wardrobe": {
"outfit": "{argument name="outfit color" default="red and white"} festive dress with elf-like details"
},
"environment": {
"location": "snowy enchanted village",
"background": {
"decor": "twinkling lights, candy canes, snow-covered rooftops",
"atmosphere": "magical winter glow"
}
},
"lighting_and_color": {
"lighting_style": "soft magical cinematic lighting",
"color_palette": "reds, whites, soft warm glow"
}
}
Surreal Double Exposure Portrait with Transparent Torso
othersA structured JSON prompt for generating a surreal, artistic portrait using a double exposure style, where the subject's torso is transparent and overlaid with a hand-drawn doodle outline, revealing a majestic alpine landscape background.
Show full prompt
{
"photo": {
"type": "surreal_artistic_portrait",
"quality": "8k photorealistic, high fidelity, masterpiece, double exposure style, mixed media aesthetic",
"lens": "35mm wide angle lens, sharp focus"
},
"face": {
"preserve_original": false,
"reference_match": false,
"description": "Young woman with shoulder-length straight blonde hair, eyes cast down or closed in a serene expression, soft natural lighting on face, dreamlike mood"
},
"model_pose": {
"position": "standing center frame on a road",
"legs": "standing naturally, hips slightly tilted",
"hands": "both arms raised high above head, stretching upwards, hands touching or overlapping",
"expression": "relaxed, meditative, immersive"
},
"wardrobe": {
"special_effect_top": {
"type": "surreal transparency",
"texture": "invisible/transparent body",
"style": "white hand-drawn doodle outline of an oversized t-shirt superimposed over the landscape",
"note": "The torso is transparent, revealing the mountain background through the body shape"
},
"bottom": {
"type": "denim jeans",
"style": "light wash, classic fit, cropped at waist",
"color": "faded light blue"
},
"accessories": {
"belt": "black leather belt with simple buckle",
"hair": "straight blonde bob, naturally falling back",
"other": "exposed naval/midriff area with realistic skin texture"
}
},
"textures": {
"emphasis": [
"rough denim fabric",
"smooth skin on midriff",
"grainy asphalt road",
"rugged mountain rock",
"white sketch lines"
]
},
"environment": {
"backdrop": "Majestic alpine landscape, straight paved road leading towards mountains, steep rocky cliffs, overcast dramatic sky, green grassy fields on roadsides",
"lighting": {
"style": "natural overcast daylight",
"key_light": "soft diffused skylight",
"fill_light": "cool ambient environmental light",
"shadows": "soft shadows, moody atmosphere"
}
},
"color_grade": {
"type": "cinematic moody",
"balance": "desaturated cool tones, muted greens and greys, matte finish, low contrast, melancholic aesthetic"
}
}
Watercolor and Ink Portrait with Identity Lock
othersA prompt designed to create a high-detail watercolor and ink portrait that precisely matches an existing face, blending soft pastel watercolor washes with expressive black ink linework and visible paper texture.
Show full prompt
"Create a high-detail watercolor and ink portrait of the exact same face (100% match). Preserve the facial features precisely. The artwork should blend soft flowing watercolor washes in pastel blues and warm pinks with expressive black ink linework defining contours and hair strands. The colors should bleed naturally into each other with visible paper texture and delicate brush splatter. Use light transparency layers to convey emotion, depth, and a sense of calm movement. Place the subject in front of a textured wall (e.g., brick, stucco, or painted surface) instead of a plain background, keeping the wall subtle so it complements the portrait without distracting. Maintain a soft, artistic feel with the wall integrated naturally behind the figure."
Abstract Scene Description Prompt
othersA short, evocative text prompt describing an abstract scene involving a sphere, a sleeping city beneath clouds, and a sailing boat. This is a simple, non-structured prompt for image generation.
Show full prompt
The sphere calls. The city sleeps beneath clouds. The boat sails on.
Image-to-Image 'Carbonite' Effect Prompt
othersA conceptual prompt for Nano Banana Pro that describes an image transformation effect called 'Carbonite', where characters from an uploaded image are placed into a deep freeze state. This is an instruction for an image-to-image process.
Show full prompt
"Carbonite" Upload an image and all the characters get put into a deep freeze.
Fierce Elven Warrior Princess Cinematic Portrait (Duplicate)
othersA highly descriptive, single-line prompt designed for an ultra-detailed cinematic portrait of a fierce elven warrior princess. It details her appearance, including pale skin with freckles, intricately braided platinum-blonde hair, ice-blue eyes with dark eyeliner, black runic tattoos, and her outfit of a grey-white fur cloak and twisted silver armor, while she wields a massive dark steel greatsword.
Show full prompt
An ultra-detailed cinematic portrait of a fierce elven warrior princess. Her pale, almost white skin is dotted with delicate freckles, making her striking appearance even more captivating. Long, intricately braided platinum-blonde hair flows gracefully over one shoulder, showcasing her pointed elven ears adorned with ornate silver cuffs. Intense ice-blue eyes, framed by dark eyeliner, convey determination, enhanced by black runic tattoos resembling ancient Nordic scripts on her face and neck. Draped in a luxurious grey-white fur cloak and twisted silver armor with thorny vine motifs, she wields a massive ornate dark steel greatsword with a raven.
Fierce Elven Warrior Princess Cinematic Portrait
othersA highly descriptive, single-line prompt designed for an ultra-detailed cinematic portrait of a fierce elven warrior princess. It details her appearance, including pale skin with freckles, intricately braided platinum-blonde hair, ice-blue eyes with dark eyeliner, black runic tattoos, and her outfit of a grey-white fur cloak and twisted silver armor, while she wields a massive dark steel greatsword.
Show full prompt
An ultra-detailed cinematic portrait of a fierce elven warrior princess. Her pale, almost white skin is dotted with delicate freckles, making her striking appearance even more captivating. Long, intricately braided platinum-blonde hair flows gracefully over one shoulder, showcasing her pointed elven ears adorned with ornate silver cuffs. Intense ice-blue eyes, framed by dark eyeliner, convey determination, enhanced by black runic tattoos resembling ancient Nordic scripts on her face and neck. Draped in a luxurious grey-white fur cloak and twisted silver armor with thorny vine motifs, she wields a massive ornate dark steel greatsword with a raven.
Nano Banana Pro Image Upscaler Prompt
othersA prompt for Nano Banana Pro to perform x4 upscaling on a cropped image area, specifically focusing on sharpening details and removing blur. The key feature is its ability to intelligently distinguish between actual blur (like bokeh) and image degradation, only sharpening the degraded parts.
Show full prompt
Sharpen this image (remove blur and draw details)
Ultra-Photorealistic Macro Shot of a Red Hibiscus
othersA highly technical and detailed prompt for generating an ultra-photorealistic macro photograph of a red hibiscus flower, specifying camera settings (100mm macro lens, f/2.8), lighting (golden hour), and texture details (water droplets, velvety petals) to achieve extreme realism and creamy bokeh.
Show full prompt
{
"type": "image_generation",
"style": "ultra_photorealistic_dslr",
"aspect_ratio": "3:4",
"resolution": "8K",
"quality": "extreme_detail_realism",
"subject": {
"category": "flower",
"species": "red hibiscus",
"details": {
"petal_color": "deep crimson red",
"petal_texture": "soft, velvety with visible veins",
"center": "prominent stamen with pollen detail",
"surface": "fresh water droplets on petals"
}
},
"environment": {
"location": "tropical garden",
"background": "softly blurred palm trees and greenery",
"season": "summer"
},
"lighting": {
"type": "golden hour sunlight",
"direction": "side and back lighting",
"quality": "warm, natural, cinematic glow",
"highlights": "sunlit water droplets sparkling naturally",
"shadows": "soft and realistic"
},
"camera": {
"device": "DSLR",
"lens": "100mm macro lens",
"aperture": "f/2.8",
"shutter_speed": "1/250",
"iso": 100,
"focus": "sharp focus on flower center",
"depth_of_field": "very shallow, creamy bokeh background"
},
"composition": {
"framing": "close-up macro shot",
"angle": "eye-level with slight side tilt",
"rule_of_thirds": true
},
"rendering_details": {
"color_grading": "natural warm tones",
"sharpness": "crisp micro-details on petals",
"dynamic_range": "high, DSLR-quality",
"noise": "none",
"artifacts": "none"
},
"negative_prompt": [
"cartoon",
"anime",
"illustration",
"painting",
"cgi",
"plastic texture",
"oversaturated",
"flat lighting",
"blurred details",
"low resolution",
"fake bokeh"
]
}
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.