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License information is collected from official sources and may be outdated or missing.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

224 matches

Multi-Concept AI Evolution Prompt

youtube-thumbnail

A complex, multi-part JSON prompt designed to generate three distinct images: a mythic 'ImagineArt Goddess' in cosmic armor, a futuristic 'ChatGPT Orb Library,' and 'Dual Cyborg Knowledge Entities' in space, showcasing different AI art concepts.

Show full prompt
[
  {
    "title": "ImagineArt Goddess",
    "subject": "Divine celestial female figure",
    "appearance": {
      "gender": "female",
      "skin": "pale",
      "hair": "long black, flowing",
      "face": "calm expression, eyes closed",
      "body": "slender, elegant posture"
    },
    "clothing": {
      "style": "ornate royal robes",
      "color": ["black", "gold"],
      "details": "elaborate gold armor-like patterns on chest, shoulders, and waist"
    },
    "accessories": {
      "headpiece": "large golden ornate crown with rays",
      "bracelets": "gold arm cuffs",
      "hand_effects": "glowing cosmic energy, colorful light streaks"
    },
    "environment": {
      "type": "cosmic galaxy backdrop",
      "elements": [
        "nebula clouds",
        "stars",
        "colorful cosmic dust",
        "electric lightning-like streaks"
      ],
      "color_palette": ["purple", "blue", "pink", "green", "gold"]
    },
    "foreground": {
      "text": "{argument name="text overlay 1" default="ImagineArt"}",
      "style": "ornate golden script typography",
      "subtitle": "ImagineArt — Dreamline Generative Muse"
    },
    "mood": "mythic, divine, majestic, surreal",
    "lighting": "dramatic glowing lighting",
    "camera": {
      "framing": "full body, centered",
      "angle": "straight on"
    }
  },
  {
    "title": "ChatGPT Orb Library",
    "subject": "Glowing AI orb in futuristic library",
    "objects": {
      "main": "large floating white orb",
      "floating_docs": "papers and data sheets with code and text"
    },
    "text": {
      "main_label": "{argument name="text overlay 2" default="ChatGPT"}",
      "style": "bright neon teal glow"
    },
    "environment": {
      "location": "circular modern library",
      "surroundings": "bookshelves, open books, papers suspended in mid-air"
    },
    "color_palette": ["white", "light teal", "mint", "gray"],
    "lighting": "soft ambient, glowing highlights",
    "mood": "clean, futuristic, intelligent, serene",
    "camera": {
      "framing": "medium-wide",
      "angle": "slightly low angle"
    },
    "style": "futuristic, minimal, high-tech"
  },
  {
    "title": "Dual Cyborg Knowledge Entities",
    "subjects": [
      {
        "type": "futuristic cyborg",
        "color_scheme": "blue",
        "pose": "standing back to back"
      },
      {
        "type": "futuristic cyborg",
        "color_scheme": "gold",
        "pose": "standing back to back"
      }
    ],
    "appearance": {
      "build": "humanoid, detailed cybernetic body structure",
      "material": "metallic with glowing circuits"
    },
    "environment": {
      "background": "outer space with stars and warm clouds",
      "floating_elements": "holographic data cards with symbols and equations"
    }

Mahira Khan 2x2 Collage Podcast Interview Prompt

youtube-thumbnail

A simple JSON prompt to create a 2x2 collage of Mahira Khan based on a podcast interview reference image. The prompt specifies candid shots, a sleeveless outfit, and captures the subject speaking with her mouth open in an 'O' expression, using iPhone 13 Pro Max camera settings.

Show full prompt
{ task: 2x2 collage with multiple angles of her in this podcast interview, but her outfit is sleeveless, candid shots, not looking at the camera, speaking and mouth open in an “O” expression resolution: 1080p aspect_ratio: 4:5 Sharpness: medium camera: iPhone 13 pro max 12MP CMOS camera }

Creative Composite for 'Follow' Button Promo

youtube-thumbnail

A complex JSON prompt designed for a creative composite edit, superimposing a character (from a reference image) onto a background image (a screenshot of a profile page). The character is posed lying down and actively pointing their finger towards the upper right corner, mimicking pressing a 'Follow' or 'Subscribe' button for social media promotion.

Show full prompt
{
  "edit_type": "creative_composite_layering",

  "source": {
    "_hint": "Base logic: Character (Ref 1) superimposed ON TOP OF the Background Image (Ref 2).",
    "mode": "EDIT",
    "reference_images": {
      "first": "foreground_character_person",
      "second": "background_scenery_or_pattern"
    },
    "preserve_from_first": {
      "same_person_or_group": true,
      "same_faces": true,
      "same_hairstyles": true,
      "same_outfits": true
    }
  },

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

  "camera_effect": {
    "_hint": "High-angle selfie style, creating a sense of depth between the hand and face.",
    "perspective": "high_angle_shot_looking_down",
    "style": "social_media_call_to_action",
    "depth_of_field": "focus_on_face_and_pointing_finger",
    "framing": "character_centered_with_space_at_top_right"
  },

  "pose": {
    "_hint": "Key action: Lying down but actively pointing to the 'Follow' button area (Top Right).",
    "pose_style": "lying_down_or_reclining_on_back",
    "face_direction": "looking_directly_up_into_lens",
    "hand_gestures": {
      "right_hand_action": "pointing_index_finger",
      "target_direction": "upper_right_corner_45_degrees",
      "purpose": "mimicking_pressing_subscribe_button",
      "arm_position": "extended_towards_camera_top_right"
    },
    "body_language": "inviting_and_energetic",
    "style_tags": [
      "kpop_idol_fan_service",
      "influencer_promo_style",
      "dynamic_perspective"
    ]
  },

  "background_integration": {
    "_hint": "The second reference image is the background/floor.",
    "method": "full_background_replacement",
    "target_area": "entire_canvas_behind_character",
    "content_source": "reference_image_second",
    "perspective_match": "flat_lay_style",
    "rules": {
      "character_must_be_top_layer": true,
      "leave_space_in_upper_right_for_ui": true
    }
  },

  "composition": {
    "_hint": "Ensure the pointing finger leads the viewer's eye to the top right corner.",
    "visual_flow": "diagonal_line_from_face_to_top_right_corner",
    "focal_points": [
      "character_eyes",
      "pointing_finger_tip"
    ],
    "negative_space": "clear_area_at_top_right_45_degrees"
  },

  "constraints": {
    "no_holding_phone_device": true,

Social Media Call-to-Action Composite with Pointing Character

youtube-thumbnail

A Nano Banana Pro prompt designed for creating a composite image where a character, strictly based on a reference image, is superimposed onto a background (like a profile page screenshot) and is actively pointing to the 'Follow' button area (upper right corner). This is used for promotional content and influencer-style fan service, utilizing a high-angle selfie perspective.

Show full prompt
{
  "edit_type": "creative_composite_layering",

  "source": {
    "_hint": "Base logic: Character (Ref 1) superimposed ON TOP OF the Background Image (Ref 2).",
    "mode": "EDIT",
    "reference_images": {
      "first": "foreground_character_person",
      "second": "background_scenery_or_pattern"
    },
    "preserve_from_first": {
      "same_person_or_group": true,
      "same_faces": true,
      "same_hairstyles": true,
      "same_outfits": true
    }
  },

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

  "camera_effect": {
    "_hint": "High-angle selfie style, creating a sense of depth between the hand and face.",
    "perspective": "high_angle_shot_looking_down",
    "style": "social_media_call_to_action",
    "depth_of_field": "focus_on_face_and_pointing_finger",
    "framing": "character_centered_with_space_at_top_right"
  },

  "pose": {
    "_hint": "Key action: Lying down but actively pointing to the 'Follow' button area (Top Right).",
    "pose_style": "lying_down_or_reclining_on_back",
    "face_direction": "looking_directly_up_into_lens",
    "hand_gestures": {
      "right_hand_action": "pointing_index_finger",
      "target_direction": "upper_right_corner_45_degrees",
      "purpose": "mimicking_pressing_subscribe_button",
      "arm_position": "extended_towards_camera_top_right"
    },
    "body_language": "inviting_and_energetic",
    "style_tags": [
      "kpop_idol_fan_service",
      "influencer_promo_style",
      "dynamic_perspective"
    ]
  },

  "background_integration": {
    "_hint": "The second reference image is the background/floor.",
    "method": "full_background_replacement",
    "target_area": "entire_canvas_behind_character",
    "content_source": "reference_image_second",
    "perspective_match": "flat_lay_style",
    "rules": {
      "character_must_be_top_layer": true,
      "leave_space_in_upper_right_for_ui": true
    }
  },

  "composition": {
    "_hi"

Dan-Style Cover Image Prompt

youtube-thumbnail

A prompt designed to create cover images in the style of 'Dan' (likely a popular creator or style), shared for use with Youmind, which integrates Nano Banana Pro, allowing users to create visually striking cover art.

Show full prompt
A highly detailed, professional, and visually striking cover image for a blog post about {argument name="topic" default="AI tools"}. The image should feature a clean, modern design with bold typography and a minimalist color palette, emphasizing {argument name="visual focus" default="technology and innovation"}. Use dramatic, high-contrast lighting and a shallow depth of field to draw attention to the central subject. The style should be photorealistic and cinematic, similar to high-end tech editorial photography. Aspect ratio 16:9.

Master Prompt for NBA Finals Arena Promos

youtube-thumbnail

A user-developed 'Master Prompt' for the Nano Banana PRO model, designed to create elite-tier, highly realistic NBA arena promotional images that capture the electric pre-game energy of any franchise, going beyond simple logo placement.

Show full prompt
Master Prompt" using the Nano Banana PRO model that creates elite-tier arena promos. 
It doesn't just put a logo on a court; it captures the electric pre-game energy of any franchise.

Ana de Armas Red Carpet Portrait Prompts (Yellow and Red Dress)

youtube-thumbnail

Two highly detailed JSON prompts for generating ultra-realistic, 8K resolution portraits of Ana de Armas on a red carpet. The prompts specify celebrity identity, pose, intricate couture outfit details (yellow or red minidress with black geometric patterns), cinematic lighting (soft professional flash), and technical camera settings (85mm lens, f/1.8 aperture, bokeh background), along with a comprehensive negative prompt list.

Show full prompt
{
  "image_prompt": {
    "subject": {
      "name": "{argument name="celebrity name" default="Ana de Armas"}",
      "description": "young woman with shoulder-length layered blonde ponytail hair, soft waves, blue eyes, soft natural makeup with nude pink lipstick, glowing skin complexion, pearl necklace",
      "pose": "looking directly at camera, slight smile, confident red carpet stance, head and shoulders portrait",
    },
    "outfit": {
      "item": "{argument name="outfit color" default="Yellow"} dress",
      "details": "black beaded geometric web pattern over nude sheer illusion fabric, sweetheart neckline, intricate black sequin embroidery, sleeveless, structured fit",
      "style": "glamorous, high fashion, couture"
    },
    "environment": {
      "setting": "movie premiere red carpet event",
      "background": "dark blurred media wall with unrecognizable white and red logos, professional event backdrop",
      "atmosphere": "exclusive, cinematic, celebrity sighting"
    },
    "technical_specs": {
      "lighting": "soft professional flash photography, rim lighting on hair, even facial illumination, no harsh shadows",
      "camera": "85mm lens, f/1.8 aperture, sharp focus on eyes, bokeh background",
      "quality": "8k resolution, ultra-realistic, highly detailed texture, raw photo, photorealism, masterpiece",
      "aspect_ratio": "9:16"
    }
  },
  "negative_prompt": "cartoon, illustration, painting, drawing, bad anatomy, blurry, low quality, distorted eyes, text, watermark, logo, oversaturated, messy hair, wrong face",
  "parameters": {
    "size": "highest_resolution",
    "orientation": "vertical",
    "style_preset": "photographic" Ratio 3.4
  }

{
  "image_prompt": {
    "subject": {
      "name": "Ana de Armas",
      "description": "young woman with shoulder-length layered long black, soft waves, blue eyes, soft natural makeup with nude pink lipstick, glowing skin complexion, pearl necklace",
      "pose": "looking directly at camera, slight smile, confident red carpet stance, full body",
    },
    "outfit": {
      "item": "Red minidress",
      "details": "black beaded geometric web pattern over nude sheer illusion fabric, sweetheart neckline, intricate black sequin embroidery, sleeveless, structured fit, red high heels sandals",
      "style": "glamorous, high fashion, couture"
    },
    "environment": {
      "setting": "movie premiere red carpet event",
      "background": "cremisi blurred media wall with unrecognizable white and red logos, professional event backdrop",
      "atmosphere": "exclusive, cinematic, celebrity sighting"
    },
    "technical_specs": {
      "lighting": "soft professional flash photography, rim lighting on hair, even facial illumination, no harsh shadows",
      "camera": "85mm lens, f/1.8 aperture, sharp focus on eyes, bokeh background",
      "quality": "8k resolution, ultra-realistic, highly detailed texture, raw photo, photorealism, masterpiece",
      "aspect_ratio": "9:16"

Talk-Show Style Celebrity Interview Photo

youtube-thumbnail

A detailed prompt for generating an ultra-realistic, cinematic talk-show style photo featuring a host and a specified celebrity. It focuses on precise composition, lighting, and facial accuracy to achieve a premium 'Netflix documentary interview' aesthetic.

Show full prompt
Create an ultra-realistic cinematic shot of both individuals seated in a modern studio lounge setup, angled slightly toward each other.
The host (use the attached face reference) is interviewing {argument name="celebrity name" default="[Celebrity Name]"} in a warm, soft-glow studio lit with overhead spotlights.
Place them on a cozy couch setup with a low coffee table between them—no podcast mics in frame, just natural conversation energy.
Maintain 100% facial accuracy, lifelike skin texture, and crisp depth of field. Use 8K resolution, 9:16 format, and give it a premium “Netflix documentary interview” aesthetic with shallow focus and rich shadows.

Image Conversion to Berry Tart Dress Style

youtube-thumbnail

A prompt used with Nano Banana Pro to convert an existing image into a 'Berry Tart' style. The prompt describes a gorgeous dress covered in lots of strawberries, suggesting a sweet and sour love flavor. This is an image-to-image conversion prompt.

Show full prompt
The taste of sweet and sour love? 💕
The dress full of strawberries is gorgeous! ✨

Image Conversion to Berserker Style

youtube-thumbnail

A prompt used with Nano Banana Pro to convert an existing image into a 'Berserker' style. The prompt describes a fierce warrior, a red flash speeding across the battlefield, wielding an axe that cuts through everything. This is an image-to-image conversion prompt.

Show full prompt
A red flash speeding across the battlefield! ⚡️
That axe cuts through everything...!

Nano Banana Pro Prompt for X Article Header Image Generation

youtube-thumbnail

A comprehensive prompt template for Nano Banana Pro designed to generate visually appealing header images for X (Twitter) articles or blog posts. It instructs the AI to use reference images effectively, avoid duplication, and incorporate the article title and optional subtitle/dialogue, while specifying a 5:2 aspect ratio and 4K quality.

Show full prompt
Please create a visually appealing header image for a blog post by arranging the reference images well.
However, use each image only once.
Do not duplicate.
Ensure the elements in the reference images do not blend together.
There should be a slight margin above and below the image.
Be creative with the background.
The title may be overlaid on the image.
5:2 4K quality
Title: {argument name="title" default="[Enter article title]"}

Cricketer Composite Portrait and Stats Graphic

youtube-thumbnail

A prompt for generating a dynamic composite portrait of an Indian cricketer (Shreyas Iyer) in his Royal Challengers Bangalore jersey. The composition includes a large close-up portrait, a smaller action shot (celebration), and a third inset (batting), all set against a bold red background with a golden lion emblem. The prompt also requires the inclusion of specific IPL 2025 statistics via typography.

Show full prompt
A dynamic composite portrait of Indian cricketer {argument name="cricketer name" default="you neme"} in his Royal Challengers Bangalore jersey, set against a bold red background with a stylized golden lion emblem. The composition features a large, close-up portrait of Iyer in the foreground, looking directly at the viewer with a serious expression, short dark hair, and a trimmed beard. Behind him, a smaller, action-oriented image shows him mid-celebration, mouth open in triumph, wearing the same red jersey with "DREAM11" and "KINGS" logos. A third, smaller inset depicts him batting in full gear, mid-swing. He wears a red long-sleeved jersey with gold accents, blue pants, and cricket pads. The lighting is dramatic and studio-like, highlighting his features and the vibrant red of his uniform. The background is a deep red with a glowing golden lion logo, evoking team identity. Text elements on the left display his IPL 2025 stats: {argument name="innings" default="13"} innings, {argument name="runs" default="604"} runs, 50.33 average, 175.07 strike rate, and 6 fifties. The overall style is a high-impact sports graphic, combining realistic photography with bold typography and graphic design elements.
Prev 10 / 19 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.