← Back to home
Skill

Ai Image Prompts

tencent_skillhub · 1.0.9 · Downloads 2.1K · Heat 56.5

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

Author:dophinl
Category:Multimedia
Version:1.0.9
Auth: No auth
Pricing: Not specified

License information is collected from official sources and may be outdated or missing.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.

Tags
图片生成

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.

5717 matches

Hyperrealistic Mayan Pyramid Coffee Bean Miniature Prompt

product-marketing

A detailed prompt for generating a hyperrealistic miniature scene of an ancient Mayan pyramid complex constructed entirely from different roasts of coffee beans, set on a rustic wooden tray with specific lighting and atmospheric details.

Show full prompt
Hyperrealistic miniature ancient Mayan pyramid complex built entirely from coffee beans of different roasts, set on a rustic wooden coffee tray. Dark roast beans form the pyramid steps, medium roast creates the plaza, light roast beans scattered as sand. Tiny figures conducting a coffee ceremony. Steam rising artistically. Warm café lighting, shallow depth of field, 8K detail.

Nano Banana Pro Chibi Snow Globe Prompt

product-marketing

A detailed prompt for Nano Banana Pro that converts an uploaded image (either a real photo or an existing character) into a 2-head-tall super-deformed chibi character, renders it as a small 3D figure, and places it inside a glass snow globe with a miniature snowy town and Christmas lighting bokeh background.

Show full prompt
Use the uploaded image as the only character reference.
CONDITION
If the uploaded image is a real-life photo (live-action, not chibi/cartoon):
First convert the person into a 2-head-tall super-deformed chibi character.
Then render that chibi as a small cute 3D figure.
Keep the character’s key identity (face shape, hairstyle, hair color, outfit colors, accessories) clearly recognizable, just stylized in chibi form.
If the uploaded image is already a chibi / super-deformed / cartoon-style character:
Do not change the character’s face, facial expression, hairstyle, colors, or overall design.
Directly convert this exact design into a small cute 3D figure.
[SUBJECT]
small cute 3D figure style character based on the uploaded image,
big head, short body (2-head-tall chibi proportions),
toy-like look with realistic plastic texture,
single full-body character, centered in the frame
[SCENE]
place the character inside a glass snow globe,
miniature snowy town inside the dome,
tiny houses, street lights, Christmas decorations
[BACKGROUND]
Christmas night light bokeh,
dark blue night background with glowing lights
[STYLE]
realistic miniature photography,
macro lens look,
shallow depth of field,
soft warm lighting,
high detail, clean render
[EFFECT]
snow falling inside the globe,
light reflections on the glass surface,
natural shadows and highlights,
slightly whimsical, cozy Christmas mood
[POSE]
random cute pose that fits the character’s personality
[QUALITY]
sharp focus, high resolution, photorealistic background,
no text, no watermark, no extra characters

Nano Banana Pro 3D Digital Signage Prompt (Shinjuku)

product-marketing

A detailed prompt for Nano Banana Pro to generate a photorealistic image of a massive L-shaped glasses-free 3D LED screen in a bustling Tokyo intersection, like Shinjuku. The prompt specifies the urban environment, the dynamic 3D animation effect (objects breaking the screen boundary), and realistic lighting and shadow details.

Show full prompt
A majestic L-shaped glasses-free 3D LED screen stands prominently in a bustling Tokyo intersection, such as Shinjuku. It is designed to integrate with the iconic and futuristic urban architecture, reminiscent of the streetscape of Shinjuku East Exit and Kabukicho landmarks. The screen displays captivating glasses-free 3D animation. Characters and objects possess astonishing depth and three-dimensionality, appearing to break through the screen's boundary and leap forward, or vividly float in the air. Under realistic daytime lighting conditions, these elements cast vivid shadows on the screen surface and surrounding buildings, harmonizing with the urban space. The animation, featuring complex details and vibrant colors, perfectly blends with the energetic atmosphere unique to Shinjuku and the bright sky overhead.

Cyber-Grunge Surveillance Fashion Editorial Prompt (Japanese Woman)

product-marketing

An extremely detailed, multi-part prompt for Nano Banana Pro to generate a cyber-grunge surveillance-style fashion editorial collage. It specifies the subject (a young Japanese woman with K-pop inspired makeup and Y2K street fashion), the scene (late-afternoon plaza with dramatic shadows), technical style (Hyper-real 8K, cinematic contrast), and complex UI overlay elements (bounding boxes, telemetry, timecode).

Show full prompt
A cyber-grunge surveillance-style fashion editorial featuring a young, beautiful, cute Japanese woman in her early 20s, with large expressive eyes and K-pop idol–inspired makeup. Her makeup highlights flawless radiant skin, soft shimmer around the eyelids, sharp eyeliner, and glossy lips, giving a refined feminine glow.

She has long, sleek black hair with perfectly trimmed bangs, smooth texture, and soft highlights, flowing naturally behind her as she walks.

Her outfit consists of a fitted rib-texture turtle-neck knit top and denim short pants with visible stitching details, slightly low-rise styling, giving a modern Japanese Y2K street flavor. She wears long sleek boots—clean, structured, and stylish—adding elegance and contrast to her exposed legs. Accessorized with a small gold pendant necklace. She holds an iced chocolate/coffee cup with a straw in her left hand and a half-eaten pastry in her right hand.

Her body posture is mid-stride, full-body captured, facing slightly off-center, head angled down slightly with a cool, indifferent expression—visually as if caught candidly by a high-end surveillance system monitoring an urban location.

Scene environment:
A bright late-afternoon plaza with paved concrete tiles. Highly directional sunlight creates long diagonal shadows, deep blacks under the boots, and warm atmospheric highlights. The tone feels cinematic but raw, like real street documentation.

Technical image style:
Hyper-real 8K Ultra-HD clarity, deep focus across full frame, dramatic daylight contrast, color palette composed of urban greys, pure whites, deep blacks, and striking crimson UI overlay accents. 1440 × 1920 resolution, 4:5 editorial framing.

Layout structure:
Editorial collage combining:
● one large main full-body walking shot
+
● three cropped secondary frames:
— close-up of face + makeup styling + drink hand
— torso crop featuring turtle-neck knit texture
— boot-and-legs detail with pavement shadows

These cropped windows connect visually via red surveillance-style vector lines.

UI Overlay Components:
· thin red bounding rectangles
· telemetry-like ID codes
· crosshair alignment marks
· vector targeting lines
· timecode print
· numeric encryption motifs

Example printed graphics:
“TR521”
“CCWW”
“18/02”
“#25747//”
“#83575//”
“19 5 3 21 18 9 20 25”

Atmospheric concept:
Modern cyber-grunge × candid street-watching × dystopian fashion documentation.
Feels like a digital observation archive rather than posed photography.
A stylish mystery aura, privacy-invasion chic, cinematic realism.

Camera Specifications:
Shot from a slightly high-angle perspective, around 35–50mm focal length, long daylight-cast shadows visible, crisp texture on concrete paving, deep-focus realism.

Nano Banana Pro 2x2 Grid Phone Screen Replacement JSON Prompt

product-marketing

A complex JSON prompt structure for Nano Banana Pro to create a 2x2 grid image sequence where a person is holding a smartphone, and the content displayed on the phone screen is replaced with a second uploaded image. It maintains identity consistency and defines specific poses and camera effects for each panel.

Show full prompt
{
  "layout": {
    "type": "grid_2x2"
  },

  "global": {
    "edit_type": "phone_motion_edit",

    "source": {
      "mode": "EDIT",
      "reference_images": {
        "first": "base_photo_person_and_environment",
        "second": "screen_content_for_phone"
      },
      "preserve_from_first": {
        "same_person_or_group": true,
        "same_faces": true,
        "same_hairstyles": true,
        "same_outfits": true,
        "same_environment_style": true
      }
    },

    "identity": {
      "keep_identity_consistent": true,
      "expression": "bright_natural_smile"
    },

    "phone": {
      "allowed": true,
      "holding_styles": [
        "one_handed",
        "two_handed",
        "near_chest",
        "near_hip",
        "tilted",
        "sideways",
        "partially_toward_lens"
      ],
      "rules": {
        "each_person_may_hold_one_phone": true,
        "screen_should_be_naturally_visible": true,
        "do_not_force_phone_directly_toward_camera": true
      }
    },

    "screen_replacement": {
      "use_second_reference_image_as_content": true,
      "fit_without_distortion": true,
      "no_ui": true
    },

    "environment": {
      "preserve_environment_style_from_reference": true,
      "lighting_consistent_with_reference": true
    },

    "constraints": {
      "no_new_characters": true,
      "no_costume_change": true,
      "no_change_to_reference_location_type": true
    }
  },

  "panels": [
    {
      "id": "panel_1",
      "role": "soft_intro",
      "edit": true,
      "pose": {
        "pose_can_change": true,
        "style_tags": ["walk", "soft_motion", "side_by_side"],
        "focus_on_expressive_hands": true
      }
    },

    {
      "id": "panel_2",
      "role": "phone_view_soft",
      "edit": true,
      "pose": {
        "pose_can_change": true,
        "style_tags": ["looking_at_phone", "face_close", "natural_pose"],
        "focus_on_expressive_hands": true
      }
    },

    {
      "id": "panel_3",
      "role": "phone_forward",
      "edit": true,
      "pose": {
        "pose_can_change": true,
        "style_tags": ["hand_forward", "phone_front_soft", "arm_extended"],
        "focus_on_expressive_hands": true
      },
      "camera_effect": {
        "perspective": "wide_angle",
        "near_objects_appear_large": true
      }
    },

    {
      "id": "panel_4",
      "role": "jump_cut",
      "edit": true,
      "use_preset": "jump_frame"
    }
  ],

  "pose_presets": {
    "jump_frame": {
      "pose": {
        "pose_can_change": true,
        "style_tags": ["jump", "lively", "mid_air"],
        "focus_on_expressive_hands": true
      },
      "camera_effect": {
        "perspective": "wide_angle",
        "allow_view_from_below": true
      }
    }
  }
}

Generating Starbucks Pop-up Style Image

product-marketing

The user generated an image in the style of a Starbucks pop-up advertisement by feeding content into Nano Banana Pro, suggesting a style transfer or visual formatting prompt.

Show full prompt
I loaded something and tried to output it like a Starbucks pop-up.

Developing a Nano Banana Pro Manga Creation Tool

product-marketing

An announcement about developing a simple tool that uses Nano Banana Pro to create original manga in three minutes. The user only needs to send a 'start generation' command and answer a few simple questions.

Show full prompt
Just send 'Start Generation' to this independently developed tool and quickly answer a few simple questions.

AI-Generated Web Page Summary and Message

product-marketing

The user used Nano Banana Pro to summarize a web page and generate a promotional message for a book, demonstrating its LLM and design capabilities for marketing content.

Show full prompt
Your book, to more readers. A new form of advertising expanded by book reviews.

1x3 Grid Phone Motion Edit JSON Prompt

product-marketing

A highly detailed JSON prompt structure for Nano Banana Pro designed to generate a 1x3 grid of images. The primary function is 'phone motion edit,' where a person's photo is uploaded along with content for the phone screen, ensuring identity consistency and specific poses like looking at the phone, holding it forward, and a jump cut.

Show full prompt
{
  "layout": {
    "type": "grid_1x3"
  },

  "global": {
    "edit_type": "phone_motion_edit",

    "source": {
      "mode": "EDIT",
      "reference_images": {
        "first": "base_photo_person_and_environment",
        "second": "screen_content_for_phone"
      },
      "preserve_from_first": {
        "same_person_or_group": true,
        "same_faces": true,
        "same_hairstyles": true,
        "same_outfits": true,
        "same_environment_style": true
      }
    },

    "identity": {
      "keep_identity_consistent": true,
      "expression": "bright_natural_smile"
    },

    "phone": {
      "allowed": true,
      "holding_styles": [
        "one_handed",
        "two_handed",
        "near_chest",
        "near_hip",
        "tilted",
        "sideways",
        "partially_toward_lens"
      ],
      "rules": {
        "each_person_may_hold_one_phone": true,
        "screen_should_be_naturally_visible": true,
        "do_not_force_phone_directly_toward_camera": true
      }
    },

    "screen_replacement": {
      "use_second_reference_image_as_content": true,
      "fit_without_distortion": true,
      "no_ui": true
    },

    "environment": {
      "preserve_environment_style_from_reference": true,
      "lighting_consistent_with_reference": true
    },

    "constraints": {
      "no_new_characters": true,
      "no_costume_change": true,
      "no_change_to_reference_location_type": true
    }
  },

  "panels": [
    {
      "id": "panel_2",
      "role": "phone_view_soft",
      "edit": true,
      "pose": {
        "pose_can_change": true,
        "style_tags": ["looking_at_phone", "face_close", "natural_pose"],
        "focus_on_expressive_hands": true
      }
    },

    {
      "id": "panel_3",
      "role": "phone_forward",
      "edit": true,
      "pose": {
        "pose_can_change": true,
        "style_tags": ["hand_forward", "phone_front_soft", "arm_extended"],
        "focus_on_expressive_hands": true
      },
      "camera_effect": {
        "perspective": "wide_angle",
        "near_objects_appear_large": true
      }
    },

    {
      "id": "panel_4",
      "role": "jump_cut",
      "edit": true,
      "use_preset": "jump_frame"
    }
  ],

  "pose_presets": {
    "jump_frame": {
      "pose": {
        "pose_can_change": true,
        "style_tags": ["jump", "lively", "mid_air"],
        "focus_on_expressive_hands": true
      },
      "camera_effect": {
        "perspective": "wide_angle",
        "allow_view_from_below": true
      }
    }
  }
}

Studio Still Life of Coffee and Croissant

product-marketing

A detailed still life prompt for image generation, describing a white studio setting with an oak table, featuring a ZARA paper bag, a ceramic plate with a chocolate croissant, and a Starbucks takeaway latte, emphasizing a clean, photographic style.

Show full prompt
White background, photography studio, with an oak table, white paper bag with the ZARA logo on the table. White blue-ceramic plate with a paper napkin on top, and a chocolate croissant placed on the plate. Fork and knife placed neatly beside the plate. Starbucks takeaway hot late coffee with chocolate shavings, smoke.

Dramatic Neon Portrait with Wet Hair and Color Contrast

product-marketing

An extensive, highly detailed prompt for Gemini Nano Banana 3.0 Pro, focusing on a high-resolution studio portrait of a woman with wet hair, featuring extreme color contrast lighting (orange-red on one side, blue/green on the other) for a high-fashion, enigmatic aesthetic. It also specifies using an uploaded image as a face reference.

Show full prompt
A mesmerizing, high-resolution studio portrait of a woman [image uploaded, no face alterations] with an ethereal and slightly enigmatic expression. Her medium-dark, straight hair is visibly wet, clinging in strands and creating a glistening texture, with some longer pieces cascading over her shoulders and down her back, while others frame her face. Her right hand (viewer's left) is raised, fingers splayed and gently intertwined within her wet hair, pushing it back from her forehead and crown, emphasizing the dampness and natural movement. Water droplets glisten on her skin, most noticeably on her forehead, cheekbones, and jawline, adding a tactile, lifelike quality to the scene.

The lighting is a sophisticated interplay of extreme color contrast. A vibrant, intense orange-red light illuminates the entire right side of her face (viewer's left), from her forehead down to her cheek, jawline, and neck, creating striking highlights on her skin and hair. This warm light also strongly catches the bridge of her nose, her right eye, and the contours of her lips. Conversely, the left side of her face (viewer's right) and shoulder are bathed in cooler, almost electric blue and green light, creating sharp shadows and further emphasizing the dramatic color separation. The interplay of these colors creates a strong visual division down the center of her face.

Her skin is impeccably smooth and dewy, with subtle sheen and natural texture visible, especially on her forehead, cheekbones, and lips, where the light reflects most intensely. Water droplets are strategically placed on her skin to amplify the tactile realism, glistening across the surface in contrast to the intense lighting. Her eyes are a prominent feature, dark brown or hazel, wide-set, and intensely focused on the camera, conveying a sense of directness and depth. The pupils are dilated, and the irises catch subtle reflections of the colorful lights, further adding to the realism. A small, bright catchlight appears in her eyes, adding a touch of life and sparkle. Her eyebrows are well-groomed and naturally arched.

Her lips are full and appear slightly parted, revealing just a hint of shadow between them, and are painted with a soft, natural reddish-pink hue that glows under the warm light. A single, small, silver stud earring is visible in her left earlobe (viewer's right). Her shoulders and upper chest are minimally visible, suggesting she might be wearing a simple, light-colored garment, possibly white or off-white, which peeks out subtly on her left side (viewer's right) as a soft, blurred shape.

The background is a smoothly transitioned, out-of-focus gradient of teal at the top left, shifting to a darker emerald green towards the bottom right, providing a minimalist yet impactful backdrop that complements the cool tones on her face and further isolates the subject.

The overall aesthetic is one of high fashion, artist

Urban Street Fashion Portrait with a Bugatti

product-marketing

A structured JSON prompt for Nano Banana Pro, requesting a portrait of a young woman in urban street fashion (T-shirt, miniskirt, Jordans) leaning against an orange Bugatti Chiron, set in Rome near the Colosseum at night with neon lighting and soft bokeh.

Show full prompt
{
  "image_request": {
    "resolution": "1200x1200px",
    "subject": {
      "type": "Portrait of a young woman",
      "hair": "Long golden straight",
      "face": "Natural, no heavy makeup",
      "expression": "Relaxed, confident, honest energy",
      "pose": "Leaning lightly against the car, casual",
      "clothing": {
        "top": "Tight, low-cut white T-shirt with deep necklace",
        "bottom": "Salted red checked pleated miniskirt",
        "shoes": "Pink and white high-top Jordan sneakers"
      },
      "accessories": [
        "Dark sunglasses"
      ]
    },
    "vehicle": {
      "make": "{argument name="car make" default="Bugatti"}",
      "model": "{argument name="car model" default="Chiron"}",
      "color": "Orange with black alloy wheels"
    },
    "background": {
      "visibility": "Dark with minimal noise",
      "bokeh": "Soft bokeh",
      "ambient_elements": "Rome near Coliseum",
        "Blurred and slightly halated streetlights",
        "Car headlights",
        "Neon signs"
      ]
    },
    "style": {
      "type": "Portrait photography",
      "lighting": "Natural light, soft shadows",
      "realism": "High-detail realism",
      "aesthetic": "Urban street fashion"
    }
  }
}
Prev 463 / 477 Next

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。一节课的讲解也能做成课程口播。

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。

自动化克隆数字人口播混剪视频

FreemiumAPI key required

抖音短视频双路径生产体系(单 Skill 版)。Path A[付费·高质量]:策略大脑→(可选:素材混剪/AI高光提取)→脚本优化→AI生图/素材准备→配音渲染(百炼/GPT-SoVITS/CosyVoice/VoxCPM2+剪映/Remotion/ffmpeg/数字人)。Path B[免费·动画风]:采集热点→脚本→edge-tts免费配音+HyperFrames开源渲染→MP4,零云费开箱快。触发词分层:①"抖音短视频/选题规划/合规闸门/运营策略" ②"口播脚本/AI生图/AI配音/视频渲染/Remotion渲染" ③"蹭热点/快速出片/免费做视频" ④"混剪/高光提取/素材粗剪/autoclip

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,在海报排版上搭配清晰视觉层级、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。

MiniMax H3 AI视频创作

Not specified

用 MiniMax H3 这款 AI视频生成器创作高质感 2K AI 视频。从文字创意出发完成文生视频,让静态图片自然动起来,用首尾画面做首尾帧视频的完整转场,也可以结合图片、视频和音频参考,以多模态视频生成塑造统一场景。适合 AI 广告视频、电商产品视频、品牌宣传视频、动态海报、游戏 UI、电影片头和社交短视频创作,形成电影感画面与同步的原生立体声。使用 Beatra 账号即可开始,创作进度与成片集中管理。

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.