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License information is collected from official sources and may be outdated or missing.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

Old Photo Restoration Prompt for Nano Banana Pro

others

A detailed prompt designed for Nano Banana Pro to restore old, damaged photographs. It focuses on fixing facial and body details, removing noise, sharpening, reconstructing missing backgrounds based on context, and ensuring the final image is natural, modern, fully colored, and emotionally resonant while preserving the original identity and composition.

Show full prompt
Fixing damaged facial details and body parts with natural reconstruction Removing visual noise and sharpening the image Reconstructing missing background elements based on context Matching textures and lighting seamlessly Final image must look natural, modern, fully colored, and emotionally resonant. Preserve all facial structure and identity from the original. Composition and proportions must remain intact. Use soft ambient lighting with high-definition clarity.

Surreal Conceptual Portrait Submerged Under Ice (JSON Format)

others

A detailed JSON prompt for generating a cinematic, surreal, and moody conceptual photograph of a young woman submerged beneath a frozen surface. The prompt specifies the subject's pose (looking up, hand pressed against the ice), cool lighting tones filtering through the ice, and the texture details of crushed ice, frost, and trapped air bubbles to create a hauntingly beautiful, isolated aesthetic.

Show full prompt
{
  "subject": {
    "description": "Young woman submerged beneath a frozen surface",
    "pose": "Looking upward through the ice, right hand pressed flat against the underside of the surface",
    "expression": "Calm, slightly melancholic, direct gaze",
    "visible_parts": "Face and right hand clearly visible, body obscured by ice texture"
  },
  "face": {
    "skin_tone": "Pale, porcelain-like",
    "eyes": "Blue-grey, sharp focus, looking directly at viewer",
    "lips": "Soft reddish-pink, natural finish",
    "makeup": "Minimal or natural, slight emphasis on eyelashes"
  },
  "hair": {
    "color": "Dark brown or black",
    "style": "Long, flowing loosely around the head",
    "interaction": "Spreading out in the water/ice, intermingling with frost and bubbles"
  },
  "clothing": {
    "type": "Dark, textured garment",
    "material": "Possibly wool or heavy fabric",
    "visibility": "Mostly obscured by the white frost and ice layer surrounding the subject"
  },
  "accessories": {
    "visible": "None"
  },
  "environment": {
    "setting": "Underneath a frozen layer of water or ice",
    "elements": [
      "Crushed ice",
      "Slushy texture",
      "Frost patterns",
      "Trapped air bubbles",
      "Water droplets"
    ],
    "atmosphere": "Cold, claustrophobic, ethereal, wintery"
  },
  "lighting": {
    "type": "Diffuse, soft ambient light",
    "direction": "Top-down, filtering through the ice",
    "tone": "Cool tones, cyan, white, and deep grey shadows",
    "quality": "Soft glow on the face, no harsh shadows"
  },
  "camera": {
    "angle": "Top-down view (bird's-eye view looking straight down at the subject)",
    "focus": "Sharp focus on the face and hand",
    "depth_of_field": "Slight blur on the peripheral ice textures",
    "shot_type": "Close-up portrait"
  },
  "style": {
    "aesthetic": "Cinematic, surreal, moody, conceptual photography",
    "genre": "Fine art portraiture",
    "vibe": "Hauntingly beautiful, isolation, frozen in time"
  },
  "details": {
    "textures": "Grainy ice, smooth skin, refraction of water",
    "visual_effects": "Distortion caused by the ice layer, contrast between the dark hair and white snow/ice",
    "composition": "Subject centered, framed by a vignette of white frost"
  }
}

Horror Cinematic Image with Identity Consistency

others

A detailed prompt for generating a horror-themed, photorealistic image of an adult woman sitting in a canoe on a dark lake at dusk. The prompt heavily emphasizes identity consistency, requiring the generated face, bone structure, and features to closely match an uploaded reference photo, creating an unsettling mood with mist and moonlight.

Show full prompt
Create an image of an adult woman based directly on the uploaded photo sits alone in a small wooden canoe in the middle of a dark, still lake at dusk. His face, bone structure, facial proportions, skin tone and hairstyle closely and unmistakably match the person in the uploaded image, with a high degree of facial fidelity and accurate likeness. He looks frightened and vulnerable, scanning the water nervously. Mist rolls across the lake, the distant tree line silhouetted by moonlight, creating an eerie atmosphere with soft ripples in the water. Cinematic realism, horror movie tone, unsettling mood, photorealistic lighting, natural skin texture, realistic facial expression, identity consistency with the uploaded photo.

Photorealistic Ultra-Wide Desert Scene with Inverted Pyramid

others

A highly detailed, photorealistic prompt for generating an ultra-wide desert scene in Egypt featuring a colossal, inverted pyramid near the Giza plateau. The prompt specifies extreme HDR realism, crisp micro-textures, natural color grading, and includes tiny scale cues like tourists and a camel caravan to emphasize the pyramid's unimaginable scale.

Show full prompt
Photorealistic ultra-wide desert scene in Egypt near the Giza plateau at golden hour. A colossal inverted pyramid, point-down, dominates the landscape at an unimaginable scale, dwarfing the horizon. Its vast upper rim stretches for multiple kilometers, while the sloping faces plunge inward toward a needle-like apex that hovers just above the sand, leaving a gigantic shadowed void beneath. The surface reads as ancient limestone blocks with dark granite inlays: mega-sized courses, eroded edges, wind-sanded wear, and long, faint bands of hieroglyphs that only appear where the sun grazes the stone. Include tiny scale cues in the distance: a thin line of tourists like ants, a few small buses and 4x4s parked far away, a camel caravan crossing the flats, and scattered survey flags. Heat haze and dust plumes soften the far edges. Sand dunes climb the lower planes where stone meets desert, with drifting sand spilling down seams like a slow waterfall. Pale sky, low sun, strong raking light, extreme HDR realism, crisp micro-textures, natural color grading, no glow or energy effects.

Diorama Reinterpretation Prompt

others

A prompt for Nano Banana Pro instructing the model to use an uploaded image as a reference and reinterpret the scene as a small-scale, realistic, high-quality diorama held in a human hand, emphasizing macro photography, shallow depth of field, and ultra-detailed textures.

Show full prompt
Using image as reference, reinterpret the scene as a small-scale realistic high quality diorama  • Convert the scene into a handcrafted miniature display mounted on a solid rectangular base with realistic terrain textures.    • The diorama is held in a human hand to clearly show scale.   • Soft natural lighting, macro photography, shallow depth of field.   • Photorealistic, ultra-detailed, clean composition.   • No text, no UI, no motion blur.  • ar 1:1

Head in Styrofoam Meat Tray Prompt

others

A simple, surreal prompt for Nano Banana Pro requesting an image of a head placed inside a teal blue styrofoam supermarket meat tray.

Show full prompt
head placed inside a teal blue styrofoam supermarket meat tray.

Childhood Photo Recolorization and Restoration Prompt

others

A prompt template for Nano Banana Pro designed to recolorize and restore an uploaded childhood picture into a modern, high-resolution digital photograph, strictly preserving the subject's facial structure and features while enhancing details, lighting, and composition.

Show full prompt
Recolonize this image into a modern digital
photography. Do not change the facial structure and features of the subject. Keep the background the same. The composition should be photorealistic, with sharp details in their clothes, skin textures, The lighting should highlight her expressions. The image should have a 9:16 aspect ratio.","size": "16k".

Negative_prompt: 
"low resolution, CGI, cartoon style, plastic skin, over-smoothed face, distorted anatomy, extra fingers, bad hands, harsh lighting, flat lighting, blown highlights, motion blur, noise, grain, watermark, logo, text, oversharpening",
  "style": "photorealistic, cinematic realism, documentary-style",
  "resolution": "15360x8640",
  "aspect_ratio": "16:9",
  "camera": {
    "lens": "50mm prime",
    "aperture": "f/1.8",
    "iso": 100,
    "shutter_speed": "1/125"
  },
  "lighting": {
    "type": "soft natural daylight",
    "direction": "side-lit from windows",
    "contrast": "balanced"
  },
  "composition": {
    "framing": "medium shot",
    "angle": "eye-level",
    "depth_of_field": "shallow"
  },
  "quality_tags": [
    "16K",
    "ultra-realistic",
    "hyper-detailed",
    "cinematic",
    "education portrait",
    "full-frame look",
    "16:9 composition"
  ]

Cyberpunk City Night Scene

others

A simple prompt for generating an image of a young woman standing in the middle of a four-way intersection in a cyberpunk city at night, emphasizing the wet asphalt texture.

Show full prompt
Woman age 20 in a cyberpunk city at night standing in the middle of a four-way intersection, wet asphalt

Majestic Bald Eagle Wildlife Portrait

others

A detailed JSON prompt for generating a majestic wildlife portrait of a Bald Eagle perched on a moss-covered branch in a forest canopy under overcast conditions. The prompt emphasizes a shallow depth of field, moody natural light, and high detail on the eagle's features.

Show full prompt
{
  "subject_identification": {
    "species": "Bald Eagle (Haliaeetus leucocephalus)",
    "type": "Bird of Prey / Raptor",
    "pose": "Perched upright, facing forward with head turned slightly left"
  },
  "visual_attributes": {
    "plumage": {
      "head": "Distinctive bright white",
      "body": "Dark brown/black feathers",
      "tail": "White feathers visible at the bottom"
    },
    "beak": "Large, hooked, yellow",
    "eyes": "Piercing, pale yellow iris",
    "talons": "Bright yellow feet with sharp black claws gripping the branch"
  },
  "setting_and_environment": {
    "location": "Forest canopy",
    "perch": "Thick, dark, moss-covered tree branch",
    "vegetation": "Pine needles visible in the top corners and bottom right",
    "weather_conditions": "Overcast, likely damp or rainy (visible water droplets on upper branches)"
  },
  "composition_and_lighting": {
    "framing": "Natural framing by overhanging pine branches",
    "depth_of_field": "Shallow; sharp focus on the eagle with a heavily blurred background (bokeh)",
    "color_palette": [
      "Deep Forest Green",
      "Charcoal Grey",
      "Stark White",
      "Golden Yellow",
      "Dark Brown"
    ],
    "lighting": "Soft, diffuse, moody natural light"
  },
  "mood": "Majestic, Stoic, Solitary, Serene"
}

Ethereal Cosmic Library

others

A prompt for generating a hyper-detailed, cinematic wide shot of a surreal cosmic library. The scene features glowing nebulae drifting between endless floating bookshelves, and a transparent, holographic woman reaching for a book made of pure light, emphasizing deep indigo/violet colors and breathtaking lighting.

Show full prompt
A hyper-detailed, cinematic wide shot of an ethereal cosmic library where glowing nebulae drift between endless floating bookshelves. A transparent, holographic figure of a woman is seen reaching for a book made of pure light. Shimmering stardust particles, deep indigo and violet color palette, soft glowing bokeh, intricate architectural details, sense of infinite knowledge, high-resolution digital art, masterpiece, breathtaking lighting, 8K.

Grand Baroque Celestial Woman Oil Painting

others

A highly detailed JSON prompt for generating an image of a celestial woman, personifying the universe, in the style of a Grand Baroque oil painting. It specifies techniques like Chiaroscuro and Sfumato, material textures (oil impasto, craquelure), and dramatic internal lighting from a 'star-thread' she is weaving.

Show full prompt
{
  "art_medium": "A high-fidelity Grand Baroque Oil Painting with heavy Symbolist influence. The technique utilizes masterful 'Chiaroscuro' to create extreme contrast and 'Sfumato' for the soft, nebulous transitions of the skin into the cosmos. The surface features visible, energetic brushwork, rich oil impasto on the starlight highlights, and a classic museum-quality finish with subtle craquelure and a deep, aged varnish.",
  "subject": "A breathtaking celestial woman, a personification of the universe, captured in the act of weaving light. She is seen from a three-quarter angle, her body elongated and graceful. Her skin has a pearlescent, translucent quality, shimmering with faint, glowing nebulae patterns beneath the surface. Between her slender, elegant fingers, she holds a strand of pure, blinding white stellar light that illuminates her face and torso. Her gown is not made of fabric, but of the deep night sky, flowing into a vast 3:2 horizontal expanse of star clusters and cosmic dust.",
  "environment": "The edge of a vibrant nebula. The background is a breathtaking depth of deep indigo, royal purple, and charcoal black, filled with swirling clouds of interstellar gas and distant, twinkling galaxies. Tiny 'stardust' motes float in the air around her like glowing embers.",
  "lighting_and_color": "Spectacular internal lighting. The primary light source is the 'star-thread' in her hands, casting a dramatic, warm glow on her features while her back fades into the cold, deep blue shadows of space. The palette is a rich contrast of deep cosmic violets and blues against the brilliant, warm gold and white of the newborn stars.",
  "technical_specs": {
    "composition": "Cinematic wide-angle composition, utilizing the Golden Ratio. The figure's movement creates a leading line across the 3:2 horizontal frame.",
    "aspect_ratio": "3:2 horizontal",
    "texture_details": "Highly tactile textures: the smoothness of celestial skin, the grainy 'sand-like' texture of cosmic dust, and the thick, raised paint of the brightest stars.",
    "finish": "Aged, varnished masterpiece, evocative and awe-inspiring."
  },
  "negative_prompt": "photograph, photorealistic, 3D render, digital art, modern technology, casual clothing, bright flat lighting, messy background, text, signature, watermark, frame, blurry, low resolution, distorted anatomy, plastic skin, anime style, cartoon."
}

Image Editing: Change Hair Color to Black

others

A prompt used to test the image editing capabilities of various models (ChatGPT Image 1.5, Nano Banana Pro, Seedream 4.5), specifically instructing the model to change the hair color to black while maintaining the composition, clothing, expression, skin tone, and aspect ratio of the original image.

Show full prompt
Keep the composition, clothing, expression, skin tone, hairstyle, and aspect ratio as they are, and only change the hair color to black.
Prev 62 / 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。

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 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

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.