← Back to home
Skill

Ai Image Prompts

tencent_skillhub · 1.0.9 · Downloads 2K · Heat 56.3

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License information is collected from official sources and may be outdated or missing.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

2105 matches

Hyperrealistic Caricature Portrait

profile-avatar

A structured JSON prompt for generating a hyperrealistic caricature portrait of an older man. It specifies exaggerated features (large cheeks, deep frown lines, voluminous hair), a serious/dramatic mood, soft studio lighting, and a shallow depth of field against a plain dark background.

Show full prompt
{
  "style": {
    "type": "hyperrealistic caricature",
    "lighting": "soft studio lighting",
    "mood": "serious, dramatic",
    "details": "exaggerated facial proportions, smooth skin texture, painterly realism"
  },
  "subject": {
    "type": "older man",
    "features": {
      "hair": "light blond, voluminous, swept to the side with dramatic flow",
      "face": "large exaggerated cheeks and chin, deep frown lines, pronounced brows, slightly drooping eyelids",
      "expression": "stern, pouting, serious"
    },
    "clothing": {
      "outfit": "dark formal suit",
      "shirt": "light-colored dress shirt",
      "tie": "light blue textured tie"
    },
    "pose": "straight posture, facing forward"
  },
  "background": {
    "type": "plain dark gradient",
    "atmosphere": "studio portrait, minimalistic"
  },
  "camera": {
    "angle": "straight-on",
    "depth_of_field": "shallow, soft background",
    "focus": "sharp on"
  }
}

Image Overlay for 'Roast Scribble' Effect (Confirmation)

profile-avatar

A simple prompt instructing the AI to take an image and overlay it with aggressive, humorous, and chaotic annotations, including red ink, doodles, remarks, and comments, simulating a 'roast' effect.

Show full prompt
Overlay this with insane roast scribble, red ink, doodles, remarks, comments.

Luxury Golden Hour Architectural Portrait

profile-avatar

A structured JSON prompt for generating a hyper-realistic, high-status portrait of a Middle Eastern man in a grand architectural setting. It requires maintaining the subject's identity from a reference image, dressing him in tailored luxury attire (navy blazer, cream trousers), and setting the scene on a marble staircase at golden hour with dramatic long shadows.

Show full prompt
{
  "Objective": "Generate a hyper-realistic luxury portrait of the subject in a grand architectural setting.",
  
  "Identity_Safety": "Maintain facial features, hairstyle, beard, and overall appearance consistent with the provided reference image.",

  "Subject": {
    "Description": "Handsome Middle Eastern man in his late 30s",
    "Appearance": {
      "Hair": "Black hair, styled neatly",
      "Beard": "Black, well-groomed",
      "Eyewear": "Round dark sunglasses",
      "Expression": "Confident, composed"
    },
    "Wardrobe": {
      "Blazer": "Tailored {argument name="blazer color" default="navy"} blazer with peak lapels",
      "Shirt": "Open white dress shirt showing some chest",
      "Trousers": "Cream high-waisted tailored trousers",
      "Accessories": "Luxury silver wristwatch"
    },
    "Pose": {
      "Body_Position": "Standing confidently on a grand staircase",
      "Posture": "Relaxed but assertive",
      "Vibe": "Elegant, masculine, high-status presence"
    }
  },

  "Scene_Description": {
    "Setting": "Exterior of a luxurious mansion",
    "Architecture": {
      "Location": "Grand ornate marble staircase",
      "Elements": [
        "Classical balustrades",
        "Decorative stone lamps",
        "High-end architectural detailing"
      ]
    },
    "Lighting": {
      "Time": "Golden hour",
      "Effects": [
        "Warm sunlight",
        "Dramatic long shadows",
        "Highlighting facial structure and outfit textures"
      ]
    },
    "Atmosphere": "Cinematic, elegant, luxurious, refined"
  },

  "Visual_Style": {
    "Resolution": "Ultra-realistic 8K",
    "Aesthetic": "Gemini-style high-end cinematic realism",
    "Color_Palette": [
    ]
  }
}

Lifestyle Fitness Portrait on Gym Machine

profile-avatar

A detailed JSON prompt for generating a clean, high-resolution lifestyle fitness portrait. It specifies the subject (young woman, dark brown hair, black sports bra and leggings) sitting confidently on a chest-press machine in a modern gym with mirrored walls, emphasizing a soft confident smile and warm ambient lighting.

Show full prompt
{
  "image_prompt": {
    "subject": {
      "description": "young woman sitting on a gym machine inside a modern fitness center",
      "face_preservation": true,

      "pose": {
        "body_position": "seated comfortably on chest-press machine",
        "hands": "right hand bent with fingers resting near her lips, left arm relaxed on machine handle",
        "expression": "soft confident smile with slightly playful gaze into camera",
        "posture": "relaxed upright posture, legs resting naturally"
      },

      "appearance": {
        "hair": {
          "color": "dark brown",
          "style": "long, voluminous waves flowing over right shoulder"
        },

        "clothing": {
          "top": {
            "type": "black sports bra",
            "fit": "snug athletic fit showing midriff"
          },
          "bottom": {
            "type": "black high-waisted leggings",
            "fit": "form-fitting athletic material"
          }
        },

        "accessories": {
          "bracelet": "simple gold bracelet on right wrist"
        }
      }
    },

    "environment": {
      "setting": "modern indoor gym with mirrored walls",
      "details": {
        "equipment": [
          "chest press machine",
          "various gym machines in background"
        ],
        "flooring": "wood-textured gym flooring",
        "walls": "full-height mirrors reflecting gym interior",
        "lighting": "soft overhead LED lighting with warm ambient accents"
      }
    },

    "photography": {
      "style": "clean lifestyle fitness portrait",
      "framing": "mid-body shot centered on subject with gym environment included",
      "camera_angle": "slightly eye-level frontal angle",
      "quality": "high-resolution, clear indoor lighting",
      "color_tone": "neutral, modern, slightly warm highlights"
    },

    "composition": {
      "focus": "subject sitting confidently on the gym machine",
      "background_depth": "reflections in mirrors add visual depth",
      "negative_prompt": [
        "altered face",
        "incorrect hair color",
        "missing gym equipment",
        "distorted mirrors",
        "extra people",
        "watermarks",
        "incorrect lighting"
      ]
    }
  }
}

Image Overlay for 'Roast Scribble' Effect (Short)

profile-avatar

A very short, direct prompt instructing the AI to overlay a provided image (a profile snapshot) with chaotic, humorous annotations, including red ink, doodles, remarks, and comments, simulating a 'roast' effect.

Show full prompt
Overlay this with insane roast scribble, red ink, doodles, remarks, comments.

Photorealistic Dressing Room Mirror Selfie

profile-avatar

A natural language prompt for generating a photorealistic mirror selfie, focusing on replicating the subject's facial identity from a reference image. It specifies a stylish pose (low squat), detailed outfit (white satin midi dress, nude block heels), accessories (pearl hair clip, silver jewelry), and a modern indoor setting with soft, warm lighting to achieve an elegant, high-quality mirror selfie aesthetic.

Show full prompt
A young female subject whose face must exactly match the reference image, preserving the face shape, eyebrows, eye structure, natural makeup style, lip shape and tone, hairline, and hairstyle, is taking a mirror selfie while squatting stylishly in a low squat with one knee bent forward, torso leaning slightly toward the mirror, head angled slightly downward, and eyes toward the phone screen. She holds a vertical smartphone with a clear transparent case in her right hand near her face for the mirror capture, while her left hand rests casually on her thigh, maintaining a neutral calm look with subtle softness. Her hair is styled in a half-up ponytail secured with a {argument name="hair clip type" default="pearl hair clip"}, smooth with a slight wave, and she wears an elegant {argument name="dress color" default="white"} satin midi dress with a side slit, featuring a glossy highlight texture, paired with nude block heels, silver earrings, a necklace, and rings. The scene is set indoors in a modern room with a glossy wooden laminate floor and a background of white curtains casting soft shadows, illuminated by warm soft indoor light providing even illumination that enhances the skin tone. The final output is an 8K photorealistic image captured in a mirror selfie aesthetic with soft neutral tones, high but natural sharpness, and an elegant, calm, feminine mood, framed full body centered in the 4:5 aspect ratio, using an eye-level reflection angle, with sharp focus on the face and soft room depth.

Image Overlay for 'Roast Scribble' Effect (Variant)

profile-avatar

A simple prompt instructing the AI to take an image and overlay it with aggressive, humorous, and chaotic annotations, including red ink, doodles, remarks, and comments, simulating a 'roast' effect.

Show full prompt
Overlay this with insane roast scribble, red ink, doodles, remarks, comments.

Image Overlay for 'Roast Scribble' Effect

profile-avatar

A simple prompt instructing the AI to take an image and overlay it with aggressive, humorous, and chaotic annotations, including red ink, doodles, remarks, and comments, simulating a 'roast' effect.

Show full prompt
Overlay this with insane roast scribble, red ink, doodles, remarks, comments.

Casual Gamer Selfie Portrait

profile-avatar

A highly detailed JSON prompt for generating a realistic, casual selfie portrait of a young woman in a gaming context. It specifies natural details like visible freckles, messy blonde hair, and loungewear (oversized hoodie), focusing on the accessories (large gaming headset, PS5 controller held close to the face) and simulating realistic indoor low-light photography with soft bokeh and grain.

Show full prompt
{
  "image_prompt": {
    "subject": {
      "description": "Young woman with a casual, authentic appearance",
      "hair": "Messy blonde hair tied back in a loose bun or ponytail with stray strands framing the face",
      "face": "Natural skin texture with visible freckles, hazel-green eyes, soft pink lips, neutral to slightly pouty expression",
      "gaze": "Direct eye contact with the camera"
    },
    "clothing": {
      "top": "Oversized charcoal grey hoodie",
      "style": "Casual loungewear / gaming attire"
    },
    "accessories": {
      "headwear": "Large black over-ear gaming headset with an attached boom microphone positioned near the cheek",
      "jewelry": "Layered gold necklaces, including a shorter chain and a longer chain with a round coin pendant",
      "hands": "White manicured nails"
    },
    "props": {
      "primary": "White PlayStation 5 DualSense controller held up close to the face, partially covering the chin and cheek"
    },
    "background": {
      "setting": "Modern interior room",
      "ceiling": "Tray ceiling architecture with warm recessed LED strip lighting and two visible pot lights",
      "walls": "Plain beige or cream-colored walls",
      "ambience": "Cozy, domestic evening setting"
    },
    "lighting": {
      "type": "Warm artificial indoor lighting",
      "source": "Overhead recessed ceiling lights creating a soft glow",
      "shadows": "Soft shadows under the chin and around the eyes due to overhead lighting"
    },
    "camera_style": {
      "shot_type": "Selfie-style portrait, medium close-up",
      "lens_details": "35mm prime lens with natural perspective",
      "aperture": "f/2.0 for shallow depth of field and soft background bokeh",
      "iso": "ISO 800 for realistic indoor low-light grain",
      "shutter_speed": "1/60s to capture natural movement",
      "file_format": "RAW, with subtle film simulation processing",
      "focus": "Sharp focus on the eyes and freckles, with soft blur on the background"
    }
  }
}

Influencer-Style Hard Flash Car Selfie

profile-avatar

A highly specific JSON prompt designed to replicate the aesthetic of a high-end influencer's car selfie taken at night with a hard flash. It details the subject's appearance (glass skin, beach waves, glossy lips, seductive squint), fashion (sequin tube top, 90s rimless sunglasses, chunky gold jewelry), and technical parameters (hard direct flash, high contrast, wide-angle lens simulation, and night city bokeh background).

Show full prompt
{
  "subject": {
    "type": "Young woman",
    "appearance": {
      "hair": "Golden blonde, long layered cut with curtain bangs, textured beach waves, slightly messy 'bedhead' volume",
      "skin": "White, hyper-glowy finish, intense specular highlights on cheekbones and tip of nose (glass skin effect)",
      "eyes": "Hazel-green, looking over sunglasses frame, seductive squint",
      "lips": "Plump, glossy nude-pink lip gloss, slightly parted, tongue playfully pressed against teeth/lip"
    }
  },
  "fashion": {
    "apparel": {
      "item": "Sequin tube top or dress",
      "color": "{argument name="sequin color" default="Champagne gold / Silver mix"}",
      "texture": "High-reflectivity sequins creating distinct glitter/sparkle points"
    },
    "accessories": {
      "eyewear": "90s style rectangle rimless sunglasses, brown gradient lenses, gold bridge, positioned low on nose",
      "jewelry": [
        "Stacked chunky gold dome rings on multiple fingers",
        "Cartier-style gold love bangles on wrist"
      ]
    }
  },
  "pose": {
    "type": "Car selfie / Candid close-up",
    "angle": "Slight high angle, tilted frame (Dutch angle)",
    "gesture": "Right hand adjusting sunglasses frame, left hand splayed on chest showcasing jewelry"
  },
  "environment": {
    "location": "Luxury car interior (black leather visible)",
    "lighting_context": "Nighttime city driving",
    "background_details": "Out-of-focus city lights (bokeh) through rear window, dark moody cabin atmosphere"
  },
  "technical_parameters": {
    "lighting_style": "Hard direct flash (on-camera), high contrast, minimal diffusion",
    "color_grading": "Warm golden tones, saturated skin tones, deep blacks in shadows",
    "camera_simulation": {
      "camera_type": "High-end compact digital (e.g., Canon G7X Mark II) or iPhone 15 Pro with Flash",
      "lens_characteristics": "24mm or 28mm wide angle, slight lens distortion on edges",
      "aperture": "f/2.8 (sharp subject, creamy bokeh background)",
      "iso": "ISO 400 (clean but with slight digital texture)",
      "shutter": "Fast shutter to freeze flash action"
    },
    "visual_fidelity": "Hyper-realistic, sharp focus on eyes and jewelry, 'influencer' aesthetic"
  }
}

AI Restoration of Heavily Damaged Vintage Photo

profile-avatar

A complex JSON prompt detailing the requirements for restoring a heavily damaged vintage photograph of a young girl. It explicitly lists the types of damage to fix (cracks, tears across face, faded colors) and sets specific restoration goals, such as reconstructing missing areas naturally, correcting color without oversaturation, and enhancing sharpness while avoiding the 'plastic skin' effect, aiming for an authentic restored vintage look.

Show full prompt
{
  "task": "old_photo_restoration",
  "description": "Restore a heavily damaged vintage photograph of a young girl",
  
  "input_photo_condition": {
    "damage_types": [
      "deep cracks",
      "fold lines",
      "tears across face",
      "scratches",
      "faded colors",
      "paper texture damage",
      "missing parts along crack lines"
    ],
    "age_effects": [
      "yellowish tint",
      "low contrast",
      "washed-out tones",
      "grain/noise"
    ]
  },

  "restoration_goals": {
    "fix_cracks": "remove all cracks and fold marks cleanly",
    "reconstruct_missing_areas": "restore face details naturally where torn",
    "color_correction": "restore natural skin tones without over-saturation",
    "sharpness": "enhance facial details smoothly, maintain softness appropriate for child's portrait",
    "noise_reduction": "remove grain while keeping natural texture",
    "background_cleanup": "smooth restoration of vintage background",
    "preserve_identity": "do NOT alter facial structure or change the person's identity"
  },

  "subject_details": {
    "type": "young girl (approx. 5–7 years old)",
    "hair": "dark brown, two ponytails with small flower hairpins",
    "expression": "smiling, bright eyes",
    "clothing": "vintage floral dress with white collar",
    "pose": "front-facing school-style portrait"
  },

  "output_style": {
    "look": "authentic restored vintage photo",
    "finish": "clean, high-resolution, natural colors",
    "texture": "remove paper wrinkles but preserve slight vintage softness",
    "lighting": "even, soft retro portrait lighting"
  },

  "quality": {
    "resolution": "Ultra HD 4K restoration",
    "clarity": "high but natural (no plastic skin effect)"
  }
}

Dramatic Golden Hour Chiaroscuro Portrait

profile-avatar

A structured JSON prompt for generating a moody, high-contrast portrait of a young woman. It specifies a cinematic, chiaroscuro aesthetic using strong directional golden hour light from the left to create a dramatic shadow that splits the face, emphasizing the hair and illuminated side against a deeply shadowed background.

Show full prompt
{
  "type": "photorealistic image prompt",
  "description": "A close-up, low-key portrait of a young woman with long, straight, medium-brown hair and natural makeup. She is wearing a dark, simple top. She looks directly at the camera with a serious, intense, and self-assured expression.",
  "style": {
    "aesthetic": "Golden hour portraiture, cinematic, moody, high-contrast, chiaroscuro lighting.",
    "lighting": "Strong directional natural light (possibly golden hour) coming from the left, creating a dramatic, harsh shadow that splits the face and illuminates the hair and the left side of the face. The background wall is cast in deep shadow.",
    "camera_details": {
      "lens": "85mm or 50mm prime lens",
      "aperture": "f/1.8 to f/2.5 (shallow depth of field)",
      "film_type": "Digital, high-resolution",
      "composition": "Close-up headshot/bust shot, centered subject, eye-level angle."
    }
  },
  "subject_details": {
    "person": "Young woman, appearing to be in her early 20s.",
    "hair": "Long, straight, rich medium-brown hair, styled with natural movement.",
    "expression": "Serious, steady, direct gaze, confident.",
    "attire": "Black or dark navy simple crewneck or t-shirt.",
    "skin_tone": "Warm, natural tone."
  },
  "background": {
    "setting": "Plain, simple wall or indoor setting, strongly shadowed.",
    "color_palette": "Dominantly warm browns and creams on the illuminated side, contrasted with deep, dark shadows and blacks."
  }
}
Prev 162 / 176 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。

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。

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。

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.