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License information is collected from official sources and may be outdated or missing.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
Character Stepping Out of a Sketchbook (Surreal Photo)
comic-storyboardA highly detailed JSON prompt for generating a realistic photograph of a hand-drawn character physically stepping out of an open, spiral-bound notebook onto a rustic wooden desk. The prompt emphasizes soft natural lighting, realistic textures, and requires an uploaded photo for facial features and placeholder details for the character and props.
Show full prompt
{
"image_prompt": {
"style": "Highly detailed, realistic photograph",
"lighting": "Soft, natural light",
"setting": {
"surface": "Rustic wooden workshop bench",
"background": "Blurred bookshelf and window"
},
"focal_point": {
"object": "Open, spiral-bound notebook",
"paper_type": "Lined paper",
"page_content": "Detailed hand-drawn pencil sketch of a character"
},
"character": {
"action": "Physically stepping off the page and out onto the desk",
"appearance": "Dynamic, fully-realized figure matching the pose and form of the sketch",
"character_details": "{argument name=\"character details\" default=\"[Placeholder: insert character details replacing 'or or']\"}",
"facial_features": "[Instruction: use facial description from the uploaded photo]"
},
"text_elements": {
"style": "Handwritten pencil notes",
"top_left": "PROJECT:",
"top_right": "Date:",
"body": "Idea: Create a character with her own mind."
},
"props": {
"placement": "Scattered realistically across the wooden desk",
"items": "{argument name=\"craft tools and props\" default=\"[Placeholder: various craft tools and props specific to the character and project (e.g., for the artist, sculptor, or architect)]\"}"
},
"raw_prompt": "A highly detailed, realistic photograph of an open, spiral-bound notebook resting on a rustic wooden workshop bench, with a blurred bookshelf and window in the background, all illuminated by soft, natural light. On the lined paper page, a detailed hand-drawn pencil sketch of a character is visible, matching the pose and form of a dynamic, fully-realized figure that is physically stepping off the page and out onto the desk. The figure is [insert character description]. The open notebook page contains handwritten pencil notes, including the title: 'PROJECT:' (top-left) and 'Date:' (top-right), with the recurring sentence: 'Idea: Create a character with her own mind.' written below it. Scattered realistically across the wooden desk are various craft tools and props specific to the character and project, such as [insert specific tools]. Note: use facial description from the uploaded photo."
}
}
Nano Banana Pro Image Generation Prompt: Currency Issuance and Infinite Balance
comic-storyboardA creative, abstract prompt designed for Nano Banana Pro (Gemini 3 Pro Image) to generate images related to complex, philosophical concepts like currency issuance rights, infinite balance, and global financial themes, presented in a four-panel manga format.
Show full prompt
Currency issuance rights, my favorite (lol) ~Melody of infinite balance~ The “Truth” of NOBU, President of the Space Bank “The illusion of ‘trillions’ crushed by a tank” “The Hermit’s Smile: Japan’s Exemption Plan” 4-panel manga
Uzumaki Naruto Pop-Up Book Prompt
comic-storyboardA structured prompt using a spatial map to generate a 3D 'Pop-Up Book' aesthetic image based on the manga 'Uzumaki Naruto', featuring a 3D character jumping out of a vertical manga panel art background, rendered in 'Toy Photography' style.
Show full prompt
manga <Uzumaki Naruto>
[ OUT OF FOCUS LIBRARY BACKGROUND ]
[ VERTICAL MANGA PANEL ART ] <--- Backplate
|
[ 3D [CHARACTER] JUMPING OUTWARD ] <--- Hero Object
[ (Mid-Air Pose, Dynamic Action) ]
|
[ OPEN BOOK / GRASS / DEBRIS BASE ] <--- Ground
[ (Infer based on [SERIES_NAME]) ]
[ TABLE SURFACE ]
</spatial_map>
INSTRUCTION:
1. Render as a high-end "Pop-Up Book" aesthetic.
2. The Background is flat paper. The Character is full 3D plastic/resin.
3. Lighting: "Toy Photography" style (Softbox, vibrant colors).
Classic Animation Light Table Prompt
comic-storyboardA template prompt for generating a photorealistic, top-down close-up view of a professional animation light table in a dimly lit studio, featuring a detailed pencil sketch of a customizable subject on the glowing paper.
Show full prompt
photorealistic top-down close-up view of a professional animation light table in a dimly lit studio, bright soft white glow coming from underneath through the glass surface, a crisp white sheet of animation paper centered on the light table, detailed pencil sketch of **{argument name="subject" default="a character portrait"}** drawn in clean confident animator lines on the paper, visible rough construction lines, light guidelines, subtle eraser marks and graphite texture, soft rim lighting highlighting the paper edges and pencil strokes, realistic light diffusion and subtle bloom from the table, warm wooden table frame, scattered animation pegs and a few loose pencils nearby, focused cinematic atmosphere, ultra detailed, high-end animation production still
Emotion Grid with Gradient Backgrounds
comic-storyboardA prompt for generating a multi-panel grid (7 panels) showing different emotions (Joyful, Shocked, Serious, Affectionate, Confident, Friendly, Sad) against corresponding colored gradient backgrounds, with specific instructions for layout and visual details for each panel.
Show full prompt
Panels are NOT edge-to-edge Visible thin white spacing between panels Subtle outer white margin around the entire grid clean modern UI-style layout Slight rounded corners on each tile Panel 1 — Joyful / Celebratory (Yellow) Bright yellow gradient background Arms raised Eyes closed Big open laugh Energetic posture Panel 2 — Shocked (Blue) Blue gradient background Hands on cheeks Wide eyes Open mouth Raised brows Panel 3 — Serious / Stern (Red) Red background Arms crossed Furrowed brows Neutral tight lips Wearing dark hoodie Panel 4 — Affectionate (Pink) Soft pink gradient Holding small brown puppy Gentle smile Cozy knit sweater Panel 5 — Confident / Sassy (Purple) Purple gradient background One hand on hip Slight smirk Graphic t-shirt Relaxed stance Panel 6 — Friendly / Casual Approval (Green) Green gradient background Wearing cap + denim jacket Thumbs-up Relaxed smile Panel 7 — Sad / Emotional (Gray) Gray gradient background Slight downward gaze Eyebrows slightly raised in center Lips slightly curved downward
Six-Panel Cinematic Storyboard Sketch
comic-storyboardA reusable prompt template for generating a six-panel movie storyboard sketch based on a provided subject. It specifies pencil sketch style with tonal shading, cinematic camera angles, and inclusion of shot type labels and director's notes in the margins.
Show full prompt
[Image reference/object/person] as a [movie/TV show genre] movie storyboard, six sequential panels, pencil sketch with tonal shading, cinematic camera angles, shot type labels, director's notes in margins, 4K storyboard sheet.
4-Panel Manga Prompt: A Day's Meals
comic-storyboardA detailed prompt for generating a 4-panel manga illustrating the user's meals throughout a day, including tuna can for breakfast, Big Mac set for lunch, gyoza for an afternoon snack, and curry for dinner.
Show full prompt
Today's events Morning Tuna can Noon Big Mac set at McDonald's Fries and chocolate shake Afternoon Gyoza no Ohsho, 2 servings of grilled gyoza to go Night Curry 4-panel manga
Nano Banana Pro Comic Prompt: Eiji Kotoge as Harry Potter
comic-storyboardA prompt for Nano Banana Pro (Gemini 3 Pro Image) to generate a 4-panel, 4-row (16-frame) comic strip featuring Eiji Kotoge as Harry Potter and Voldemort as 'Kotogemort' (Kotoge + Voldemort), representing the Ministry of Finance, titled 'The Reversal of Finance'.
Show full prompt
Eiji Kotoge = Harry Potter Voldemort = Kotogemort = Ministry of Finance 4 vertical panels 4 horizontal rows 16 frames 4-panel comic strip The Reversal of Finance
Lego Explorer Chased by Polar Bear (Video Prompt)
comic-storyboardA prompt for generating a dynamic, action-packed video using Gemini Nano Banana Pro and Kling 3.0. It describes a Lego explorer minifigure driving a snowmobile, chased by a polar bear, emphasizing cinematic effects, motion, and the crisp texture of Lego plastic.
Show full prompt
lego explorer minifigure driving a mini snowmobile across icy terrain chased by a massive roaring polar bear, snow spraying dramatically behind, frozen mist in the air, intense cinematic backlight, dynamic tilted camera shot, blockbuster action style, exaggerated comic motion, crisp lego plastic texture, dramatic cold color grading
Galdodon Comic Strip Prompt
comic-storyboardA prompt for generating a 4-panel comic strip using Nano Banana Pro (Gemini 3 Pro Image) featuring Galdodon from Dragon Quest, where Galdodon encounters and defeats a demon.
Show full prompt
Galdodon discovers a demon Galdodon says, "What? A demon?" Galdodon fires Jigodein Beating up the demon... 4 vertical panels 4-panel comic strip
Kamen Rider Armor Transformation Sequence Prompt
comic-storyboardA detailed prompt for generating a dynamic video sequence of a subject inserting a glowing Ridewatch into a Ziku-Driver, triggering a 'mechanical reveal' transformation into armored form, concluding with a combat stance. Designed for video generation tools like Veo 3.1 or Nano Banana 2.
Show full prompt
Subject inserts a glowing Ridewatch into the Ziku-Driver and spins it 360 degrees. A 'mechanical reveal' begins as white and gold armor plates materialize piece-by-piece, snapping onto the torso, shoulders, and legs with robotic precision. Rapidly rotating golden clock hands and glowing orange pixelated data streams wrap around her body against a giant glowing crescent moon background. The sequence concludes with the helmet visor flashing pink katakana eyes as she shifts into a powerful combat stance, executing a sharp martial arts strike with her white cape flowing majestically.
Cinematic Night Drive Filmstrip Prompt
comic-storyboardA highly structured prompt for generating a 3-frame vertical filmstrip showing a woman leaning out of a car window during a night drive. It requires preserving the identity from a reference image and focuses on cinematic night lighting (warm tungsten streetlights, bokeh headlights), subtle film grain, and micro facial expression changes across the three frames (dreamy, peaceful, melancholic).
Show full prompt
{
"generation_request": {
"meta_data": {
"tool": "NanoBanana Pro",
"task_type": "night_drive_filmstrip_3frame_micro_expression",
"language": "en",
"priority": "highest",
"version": "v1.0_NIGHT_CAR_WINDOW_FILMSTRIP_3FRAME_WARM_BOKEH"
},
"input": {
"mode": "image_to_image",
"reference_image_usage": "maximum",
"preserve_identity": true,
"preserve_facial_features": true,
"preserve_hairstyle": true,
"notes": "Use the reference as the primary anchor. Create a 3-frame horizontal film strip (three stacked widescreen frames). Same adult woman identity, same car window composition, same night street background. Only micro facial expression changes per frame. Warm tungsten streetlights, soft film grain, bokeh headlights, subtle lens flare. No text, no logos, no watermark."
},
"output_settings": {
"aspect_ratio": "9:16",
"orientation": "portrait",
"resolution_target": "ultra_high_res",
"num_images": 1,
"layout": {
"type": "filmstrip",
"frames": 3,
"direction": "vertical_stack",
"gutter": "thin_black",
"outer_border": "none",
"panel_consistency": "maximum"
},
"sharpness": "soft_film",
"grain": "true_film",
"render_style": "cinematic_night_film"
},
"scene": {
"concept": "night drive cinematic filmstrip",
"environment": "moving car at night, city street, distant headlights, streetlamp bokeh",
"lighting": {
"style": "warm night street lighting",
"key_light": "tungsten streetlights + soft bounce from car body",
"highlights": "gentle specular highlights on skin and car paint",
"avoid": "flash, daylight, HDR"
},
"camera": {
"lens": "50mm cinematic",
"look": "shallow depth of field, creamy bokeh, subtle anamorphic flare",
"focus": "eyes and face sharp enough, background very soft"
}
},
"subject": {
"type": "adult woman",
"pose": "leaning out of the car window with forearms resting on the window frame, head resting on arms",
"hair": "long dark hair loose, softly moving",
"makeup": "natural warm makeup, soft lips",
"anatomy_rules": "correct facial proportions, realistic arms and hands, no warped skin"
},
"frame_directions": {
"frame_01": "soft direct eye contact, calm dreamy expression",
"frame_02": "eyes gently closed or half-closed, peaceful sleepy moment",
"frame_03": "eyes open again, slightly more melancholic gaze, subtle micro-smile fade"
},
"style": {
"color_palette": "warm amber streetlights + deep teal night shadows",
"contrast": "low-medium",
"finish": "cinematic film scan: soft halation, grain, mild vignette"
},
"quality_control": {
"identity_lock": "strict",
"composition_lock": "maximum",
"avoid": [
"changin
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.