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 725 条
Panoramic Character Concept Sheet for 17-Year-Old Japanese JK
game-assetA complex prompt designed to generate a panoramic character concept decomposition sheet for a Japanese high school student (JK). It requires strict face preservation from a reference image and includes detailed sections for clothing layers, expressions, and related school items, suitable for character design workflows.
展开提示词全文
{
"Objective": "Create a panoramic character concept decomposition sheet for a Japanese high school student. Center: Full-body illustration of female student in JK uniform. Surrounding: Layered clothing showing school uniform layers and casual wear, Expression sheet with cheerful smile, studious concentration, surprised excitement, and shy embarrassment, Texture zoom on uniform fabric and school accessories",
"FaceReference": {
"Mode": "Strict face preservation",
"Instruction": "Use uploaded reference image for exact facial features, bone structure, and proportions",
"Consistency": "Face must remain identical across all frames"
},
"CharacterDetails": {
"Subject": { "Type": "Japanese high school student", "Age": "17" },
"ClothingLayers": [
"School blazer with emblem",
"White button-down shirt",
"Pleated skirt",
"Casual underwear set",
"Loafers and socks"
]
},
"RelatedItems": {
"Bag": "School satchel with textbooks, notebooks, pencil case, lunch box",
"SchoolTools": "Student ID card, club activity items, study materials",
"Personal": "Smartphone, headphones, cute accessories, manga, snacks"
}
}
3D Isometric Urban Transit Stop Diorama Prompt
game-assetA template prompt for generating a clean, minimal 3D isometric diorama of an urban transit stop, allowing customization of the transport type, vehicle, platform, and shelter, emphasizing realistic materials and a miniature architectural model style.
展开提示词全文
A clean, minimal 3D isometric diorama of a {argument name="city transport type" default="[CITY TRANSPORT TYPE]"} stop, featuring a {argument name="vehicle type" default="[VEHICLE]"} paused at a [PLATFORM TYPE], simple [SHELTER / CANOPY], subtle wayfinding signs, smooth concrete surfaces, soft studio lighting, realistic materials, rounded edges, miniature architectural model style, high detail, neutral background.
Stylized 3D Glass Skeleton Render Prompt
game-assetA detailed text prompt for Nano Banana Pro to create a high-quality, stylized 3D render. The scene features a translucent glass skeleton wearing glasses, sitting at a wooden desk and highlighting text in an open textbook, illuminated by a warm gold desk lamp. The prompt specifies the background, clutter, and aesthetic mood.
展开提示词全文
Create a high-quality stylized 3D render of a clear, translucent glass skeleton wearing black-rimmed glasses sitting at a wooden desk. The skeleton MUST be looking down at an open textbook and holding a yellow highlighter, actively highlighting a line of text. The scene MUST feature a warm gold desk lamp on the right side casting a cozy, yellow light that creates glossy reflections on the skeleton's surface. The desk is cluttered with a white coffee mug, a stack of hardcover books on the right, and scattered pens and pastel pink and yellow highlighters. The background MUST be a solid, soft pink wall. The overall aesthetic should be warm, studious, and visually soft. Do not include any text overlays or watermarks.
Four-View Character Reference Sheet for 3D Modeling
game-assetA highly specific prompt designed to create a four-view reference sheet (front, left profile, right profile, back) of a young adult woman for character design or 3D modeling purposes. It mandates a plain white background and minimal attire to clearly display detailed body proportions and muscle definition.
展开提示词全文
Create a detailed and realistic full-body reference image on a plain white background, showing four views of the young adult woman in the attached image, follow this description: "body_description": "ethnicity": "caucasian with fair skin tone" "hair": brown with blonde highlights, long, wavy", "build": "athletic hourglass, fit and toned", "torso": "narrow, high-waisted, plain stomach", "bust": "proportional, firm", "waist": "taut, slim, high-definition transition to hips", "hips": "wide, curvy, pronounced shelf-like curve at the iliac crest", "legs": "toned, athletic thighs with smooth skin transition", Arrange the views horizontally from left to right: front view, left side profile view, right side profile view, and back view. In each pose, she stands straight with arms relaxed at her sides, feet slightly apart, wearing a simple black sports bra and black thong underwear to clearly display body proportions, muscle definition, facial details, hair, and posture. Ensure a 4:4 aspect ratio, high resolution, realistic rendering, no shadows, no additional elements, and equal spacing between views for easy reference.
Character Emerging from Smartphone Screen (Forced Perspective)
game-assetTwo related prompts (A and B) for generating ultra-realistic images of a character emerging dynamically from a smartphone placed on a table. Both use extreme wide-angle and forced perspective to exaggerate the size of the hands and face closest to the camera, creating a 3D pop-out effect.
展开提示词全文
🍌 Prompt A Ultra-realistic photo. The moment this character emerges three-dimensionally from a smartphone placed on a table. One hand is reaching towards the viewer, the other hand is on the smartphone frame, the lower body is inside the smartphone, and the feet are cropped out. The character is looking at the viewer. Due to strong exaggerated perspective (extreme wide-angle, forced perspective), the hands and face appear extremely large, being very close to the camera, and the lower body appears smaller in the back, creating a three-dimensional depth composition. 🍌 Prompt B Ultra-realistic photo. The moment this character emerges three-dimensionally from a smartphone placed on a table. One hand is reaching towards the viewer, one foot is on the smartphone frame, and the lower body is inside the smartphone. Exaggerated perspective makes the nearby face and hands look large. Motifs associated with the atmosphere of the reference image also pop out. The character is leaping out vigorously while looking at the viewer, and motion blur is occurring.
Full-Body Reference Sheet for Athletic Hourglass Figure
game-assetA prompt requesting a detailed, realistic full-body reference image of a woman with an athletic hourglass figure. It specifies the creation of a four-view arrangement (front, left profile, right profile, back) on a plain white background, with the subject wearing minimal black sports attire to clearly display body proportions and muscle definition.
展开提示词全文
Create a detailed and realistic full-body reference image on a plain white background, showing four views of the young adult woman in the attached image, follow this description:
"body_description":
"ethnicity": "caucasian with fair skin tone"
"hair": "{argument name="hair description" default="brown with blonde highlights, long, wavy"}",
"build": "athletic hourglass, fit and toned",
"torso": "narrow, high-waisted, plain stomach",
"bust": "proportional, firm",
"waist": "taut, slim, high-definition transition to hips",
"hips": "wide, curvy, pronounced shelf-like curve at the iliac crest",
"legs": "toned, athletic thighs with smooth skin transition",
Arrange the views horizontally from left to right: front view, left side profile view, right side profile view, and back view. In each pose, she stands straight with arms relaxed at her sides, feet slightly apart, wearing a simple black sports bra and black thong underwear to clearly display body proportions, muscle definition, facial details, hair, and posture. Ensure a 4:4 aspect ratio, high resolution, realistic rendering, no shadows, no additional elements, and equal spacing between views for easy reference.
Hyper-Realistic Caricature of a Bald Man in a Jersey
game-assetA highly specific prompt for generating an 8K, hyper-realistic, stylized caricature figure with extremely exaggerated proportions (large head/torso, short limbs). The subject is bald, glossy-skinned, and wearing a tight white sports jersey, standing on a polished wooden table.
展开提示词全文
{
"resolution": "8K ultra high resolution",
"style": {
"visual_style": "hyper-realistic, stylized caricature realism",
"render_quality": "extreme detail, sharp focus on subject, shallow depth of field",
"lighting_style": "cinematic warm indoor lighting with soft highlights and smooth shadows",
"color_grading": "warm tones, golden highlights, natural skin tones with glossy reflections"
},
"subject": {
"type": "human-like caricature figure",
"pose": "standing upright with legs slightly apart",
"proportions": "extremely exaggerated proportions, very large head and torso, very short limbs",
"scale": "small, table-height figure",
"expression": {
"mouth": "slightly open",
"eyes": "looking slightly to the side",
"emotion": "neutral to mildly surprised"
}
},
"head_and_face": {
"head_shape": "very large, rounded head",
"hair": "completely bald",
"skin_texture": "smooth, glossy, reflective with visible moisture",
"skin_tone": "light to medium skin tone with noticeable red flush on cheeks",
"facial_features": {
"cheeks": "very large, swollen appearance with strong redness",
"chin": "multiple visible folds",
"eyebrows": "dark, defined eyebrows",
"eyes": "small relative to head size, natural reflections visible",
"nose": "small and rounded",
"lips": "slightly parted, natural color"
}
},
"body": {
"torso": "extremely large, rounded belly protruding forward",
"arms": "short and thick arms hanging down",
"hands": "small hands with short fingers",
"legs": "short, thick legs",
"feet": "bare feet, small toes visible",
"skin_detail": "glossy surface with visible highlights, subtle texture, reflective sheen"
},
"clothing": {
"top": {
"type": "short-sleeve sports jersey",
"color": "{argument name="jersey color" default="white"}",
"fit": "very tight, stretched over torso",
"logos": [
{
"placement": "center chest",
"description": "sports brand logo in blue"
},
{
"placement": "left chest",
"description": "gold shield-shaped emblem"
},
{
"placement": "right chest",
"description": "circular crest with crown and letters"
}
],
"details": "blue accent stripes on shoulders"
},
"bottom": "no visible pants or shorts"
},
"environment": {
"setting": "indoor room",
"surface": {
"type": "wooden table",
"texture": "polished wood grain with reflections"
},
"background": {
"focus": "heavily blurred",
"elements": [
"warm glowing lights",
"candle-like light sources",
"dark interior shapes"
],
"bokeh": "large circular light bokeh"
}
},
"props": {
"left_side": {
"object": "transparent glass"
Isometric figurine generation prompt for Nano Banana Pro
game-assetA template prompt for generating a miniature, full-body, isometric, realistic figurine of a person based on an uploaded selfie. It allows customization of the figure's attire and action.
展开提示词全文
"Make a miniature, full-body, isometric, realistic figurine of this person, wearing {argument name="attire" default="ABC"}, doing {argument name="action" default="XYZ"}, on a white background, minimal, 4K resolution."
Isometric Miniature Figurine of a Character in a Japanese Flower Shop
game-assetA prompt designed to transform an uploaded image of a person into a realistic miniature figurine. The figurine should be full-body, isometric, and perfectly match the features of the reference image. The scene is a cute Japanese flower shop with a white background and minimal style, rendered in 4K resolution.
展开提示词全文
Create a miniature, full-body, isometric, realistic doll. The features of the doll must perfectly match the uploaded image. The doll is currently strolling through a {argument name="location theme" default="cute Japanese flower shop"} with a {argument name="background location" default="white background"}, minimal style, and 4K resolution.
Kaiju Kitten Destroying Sydney Waterfront
game-assetA simple, creative prompt structure for generating an image of a massive kaiju kitten destroying a specific urban landmark, viewed from a ground-level perspective under bright daylight.
展开提示词全文
Massive kaiju kitten destroying Sydney's urban waterfront, destroying the {argument name="landmark name" default="[place landmark name here]"}. Ground-level view. Bright, daytime, blue skies. No glowing eyes.
Character Expression Sheet Generation (Anime Style)
game-assetA highly detailed, structured prompt for Nano Banana Pro designed to generate a 2x3 grid expression sheet (6 panels) of a character from a reference image. It strictly controls layout, aspect ratio, background, and ensures all elements (hair, clothing, lighting) remain identical across panels, changing only the expression.
展开提示词全文
Create an expression variation sheet as a single image based on the character in the attached reference image.
Format:
- 2 rows x 3 columns grid (6 panels of the same size)
- Overall aspect ratio 3:2
- Background is pure white (#FFFFFF)
- Panel borders should be thin and subtle (light gray) is acceptable
- Place small numbers in the top left of each panel: "1. {argument name="expression 1" default="Neutral"}" "2. Happy" "3. Ecstatic" "4. Sad" "5. Angry" "6. Surprised" (Black, easy to read)
Common Conditions (Must be completely identical across all 6 panels):
- Hairstyle, hair color, eye color, face contour, clothing, accessories
- Face direction (front), bust-up angle, head size, position
- Lighting, shadow placement, coloring (anime-style soft shading)
Only the "expression" can be changed. Do not change the pose or angle.
Arrangement (Fixed order: Left -> Right, Upper -> Lower):
1 (Top Left): Neutral expression. Calm, relaxed face. Mouth closed.
2 (Top Center): Happy. Gentle smile. Soft eyes.
3 (Top Right): Ecstatic. Full smile. Mouth open laughing. Strong highlight in the pupils making them shine (excessive effects unnecessary).
4 (Bottom Left): Sad. Eyes well up. Downcast gaze. Corners of the mouth turn down.
5 (Bottom Center): Angry. Frowning eyebrows with wrinkles between them. Teeth clenched (or lips tightly sealed).
6 (Bottom Right): Surprised. Eyes wide open. Eyebrows raised. Mouth open.
Do Not Include:
- Background objects, text (other than numbers 1-6), effect lines, sweat marks, different outfits, different accessories
Isometric Figurine from Photo Prompt
game-assetA prompt template designed for image-to-image generation, instructing the AI to transform an uploaded person's image into a miniature, full-body, isometric, realistic figurine. It requires specifying the clothing and action of the figurine, set against a minimal white background in 4K resolution.
展开提示词全文
Make a miniature, full-body, isometric, realistic figurine of this person, wearing {argument name="clothing" default="ABC"}, doing {argument name="action" default="XYZ"}, on a white background, minimal, 4K resolution
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。
架构图一键生成
官方标注收费需申请 Key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
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,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。
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。