← Back to home
Skill

Ai Image Prompts

tencent_skillhub · 1.0.9 · Downloads 1.8K · Heat 55.6

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License information is collected from official sources and may be outdated or missing.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

1099 matches

Urban Lifestyle Portrait Prompt (Street Art Background)

others

A highly detailed, structured prompt for generating an urban lifestyle portrait photograph using the Gemini Nano Banana Pro model. It specifies composition, subject details (clothing, expression, pose), lighting, color palette, and a specific background featuring a large monochrome mural, aiming for a social media-ready, contemporary aesthetic captured with a smartphone camera style.

Show full prompt
{ "image_type": "photograph", "genre": "urban lifestyle portrait", "composition": { "framing": "three-quarter body portrait", "angle": "eye-level, straight-on", "orientation": "portrait", "subject_placement": "subject positioned slightly right of center", "background_balance": "large-scale mural occupying left background", "visual_hierarchy": "foreground subject emphasized against graphic mural backdrop" }, "subject": { "count": 1, "gender_presentation": "female-presenting", "age_range": "young adult", "facial_features": { "skin_tone": "light, neutral", "complexion": "smooth with natural texture", "eyes": "light-colored", "eyebrows": "full, softly shaped", "nose": "straight, proportional", "lips": "natural pink, smiling with teeth slightly visible" }, "hair": { "color": "medium brown", "length": "shoulder-length", "style": "loose waves", "part": "center part" }, "expression": "playful, cheerful", "gaze": "directed toward camera", "pose": { "stance": "relaxed, casual", "hands": "one hand holding a drink cup, other supporting straw" }, "accessories": [ "clear plastic cup with lid and straw" ], "clothing": { "top": "oversized t-shirt", "color": "White", "bottom": "black lounge pants", "fit": "loose, relaxed streetwear", "style": "casual, modern" } }, "lighting": { "type": "natural daylight", "direction": "diffuse frontal light", "quality": "soft, even", "shadows": "minimal, low contrast", "highlights": "subtle highlights on face and hair" }, "color_palette": { "dominant_colors": [ "white", "gray", "yellow" ], "accent_colors": [ "cherry beverage", "black mural outlines" ], "overall_tone": "urban, contemporary, playful" }, "background": { "setting": "outdoor urban space", "environment": "city courtyard or alley", "elements": [ "large monochrome mural portrait of Elon Musk with yellow graphic accents", "modern building facades", "metal railing", "stone or concrete pavement" ], "style": "street art–influenced", "depth_of_field": "deep, background clearly visible" }, "technical_details": { "camera_type": "smartphone camera", "focal_length_equivalent": "standard wide lens", "sharpness": "high overall sharpness", "noise": "low", "dynamic_range": "balanced highlights and shadows", "white_balance": "neutral" }, "artistic_style": { "aesthetic": "urban lifestyle, social media–ready", "retouching": "minimal, natural appearance", "mood": "fun, relaxed, youthful", "contrast": "moderate with strong graphic background" }, "typography": { "presence": false } }

Kawaii Jūnihitoe Outfit Modification Prompt for NanoBananaPro

others

A prompt for the NanoBananaPro image generation tool to modify a character's clothing. It specifies changing the outfit to a pastel-colored, kawaii-style Jūnihitoe (traditional Japanese ceremonial robe), arranging the hair ornaments, setting the length to a stylish mini-skirt style, and posing energetically.

Show full prompt
Change the clothing to a {argument name="clothing style" default="pastel-colored kawaii"} Jūnihitoe
Arrange the hair ornaments as well
Wearing a stylish Jūnihitoe with a mini-skirt length, and taking an {argument name="pose" default="energetic pose"}

Preserve Original Photo in YouTube Thumbnail Prompt

others

A specific instruction used in Nanobanana Pro prompts for YouTube thumbnail generation, designed to increase the probability that the AI will use the provided human photo/image without altering or processing it, which is crucial for maintaining personal branding.

Show full prompt
Please use the image or photo of the person as is without making any changes.

Optimal Taste Selection Prompt

others

A simple, high-level prompt instructing the AI (Nano Banana Pro or Grok) to select the most appropriate artistic style or 'taste' to represent the given content, useful for quick style adaptation.

Show full prompt
Please select the optimal taste (style) to represent the following content and create an image.

Fidelity-Locked Edit Base Pose Variation

others

This appears to be a description of a feature or base prompt within the Nano Banana Pro tool, focusing on generating pose variations for an image edit base, specifically set for a night-time scene.

Show full prompt
Fidelity-Locked Edit Base
Pose Variation Edition (night time)

Novel Generation Prompt: Earth Floating in the Sky

others

This is a creative writing prompt used with GPT-5.2 Pro (referred to as 'Nano Banana Pro' in the image context) to generate a novel starting with the surreal premise of seeing the Earth floating in the sky instead of the moon. The resulting text is a detailed, atmospheric narrative exploring the sudden appearance of the Earth and the subsequent societal reaction and mystery.

Show full prompt
Write a novel that begins with the line: "When I looked up at the blue sky, the Earth was floating there instead of the white moon."

Image-to-3D Conversion Prompt for nano banana pro

others

This is a simple Japanese prompt designed for the nano banana pro AI tool, which converts an existing 2D image (like a hand-drawn illustration or icon) into a sophisticated, high-quality 3D image. The user shared this prompt after updating their profile icon to a 3D version, demonstrating its effectiveness for quick visual upgrades.

Show full prompt
Please convert this image into a sophisticated, high-quality 3D image.

Nano Banana Pro Pencil Sketch Generation

others

A user is experimenting with an AI generator, possibly Nano Banana Pro, to create an image based on a pencil sketch. The goal is to generate a front and side view from a pencil draft, although the user notes the resulting AI image is too clean and different from the original sketch.

Show full prompt
nano banana pro! Trying to generate front and side views from a pencil sketch.

Image-to-Image Instruction for Clothing Swap

others

The user describes a powerful image-to-image capability of Nano Banana Pro for photorealistic generation, specifically mentioning a prompt instruction to swap the clothing between two people in an uploaded image.

Show full prompt
Swap all the clothes worn by the two people in this image

Reality Glitch Documentary Image Prompt: Low-Poly Deer in Headlights

others

An image generation prompt designed to create a surreal, glitch-art documentary scene. It features a low-poly, flat-shaded gray deer (a geometric mesh) that has failed to load its textures, caught in the blinding headlights of a vehicle. The scene is set in a hyper-realistic forest at night, emphasizing the contrast between the sterile mathematical perfection of the glitch and the gritty natural environment, captured with a trail cam aesthetic and digital imperfections.

Show full prompt
{
  "meta": {
    "stylization": "{argument name="stylization" default="reality_glitch_documentary"}",
    "virality_factor": "ontological_proof"
  },
  "subject": {
    "primary": "{argument name="primary subject" default="a wild deer caught in headlights"}",
    "mutation": "the deer has failed to load its textures",
    "details": "the animal is a flat-shaded, low-poly gray geometric mesh, but it casts a hyper-realistic shadow",
    "eyes": "glowing white spheres (default unreal engine assets)"
  },
  "visual_fidelity": {
    "camera": "trail cam or dashcam",
    "lighting": "blindingly bright headlights cutting through darkness",
    "imperfections": [
      "motion blur on the background trees",
      "digital compression artifacts",
      "lens flare",
      "date/time stamp in corner: 'ERR:NULL'"
    ]
  },
  "context": {
    "background": "dense, hyper-realistic forest at night",
    "juxtaposition": "the perfect contrast between the gritty, dirty nature and the sterile, mathematical perfection of the glitch"
  }
}

Photorealistic Portrait Prompt for Gemini Nano Banana Pro

others

A highly detailed, structured JSON prompt designed for the Gemini Nano Banana Pro model, specifying the visual parameters for generating a photorealistic, intimate portrait of a young woman leaning in a doorway. The prompt meticulously defines the subject's appearance, environment, lighting, camera settings, and color grading to achieve a cinematic, moody atmosphere.

Show full prompt
{
  "subject": "A young fair-skinned woman leaning in a doorway",
  "description": {
    "woman": {
      "age": "{argument name="age" default="early twenties"}",
      "skin": "fair complexion with natural texture and soft highlights",
      "pose": "leaning against the doorframe with left hand, right hand resting on her head",
      "hands": "ring visible on left hand, natural finger positioning",
      "outfit": {
        "top": "{argument name="top color and fabric" default="long-sleeved pale green fabric top with visible weave and soft folds"}",
        "skirt": "patterned reddish skirt with detailed textile texture"
      },
      "hair": "long wavy blonde hair cascading over shoulders, individual strands visible",
      "expression": "calm, contemplative, slightly upward gaze",
      "emotion": "intimate, introspective"
    }
  },
  "environment": {
    "setting": "interior space near an open doorway",
    "background": "mostly dark, softly blurred interior",
    "elements": "out-of-focus lamp glow and faint window view suggesting exterior beyond",
    "contrast": "bright foreground against shadowed background"
  },
  "lighting": {
    "type": "warm, low-light interior illumination",
    "source": "soft directional light from the doorway and nearby lamp",
    "effects": "gentle highlights on face and doorframe, smooth shadow falloff",
    "mood": "intimate, cinematic, slightly mysterious"
  },
  "camera": {
    "angle": "slightly low angle",
    "framing": "subject positioned on the left side of the frame",
    "lens": "cinematic portrait lens",
    "depth_of_field": "shallow depth of field with background blur",
    "focus": "sharp facial focus with soft environmental bokeh"
  },
  "color_and_mood": {
    "palette": "warm amber highlights, muted greens, soft reds, deep shadows",
    "grading": "cinematic color grading",
    "atmosphere": "moody, intimate, emotionally subtle",
    "film_grain": "very subtle natural grain"
  },
  "quality": {
    "style": "photorealistic",
    "resolution": "ultra-high resolution",
    "detail_level": "HDR, sharp textures, realistic skin pores, fabric fibers, high pixel fidelity"
  }
}

Field Expansion Prompt: Lost Love Girls

others

Part of a 'Tennen's Prompt Festival' series for Nano Banana Pro, this prompt is labeled as a 'Field Expansion Prompt' and is titled 'Lost Love Girls,' suggesting a scene-setting or world-building instruction.

Show full prompt
[Field Expansion Prompt]

Lost Love Girls

Field fully deployed!
Prev 53 / 92 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。

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 free

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

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.