← 返回首页
技能

Ai Image Prompts

tencent_skillhub · 1.0.9 · 下载量 1,827 · 热度分 55.6

产品介绍

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。

资源信息

作者:dophinl
分类:图文音视频多模态生成
版本:1.0.9
认证方式: 无需认证
是否付费: 官方未说明

许可证信息摘自官方源,可能过时或缺失。商用前请以原仓库的 LICENSE 文件为准。

标签
图片生成

提示词库 · 2.3万

数据源:社区提示词库(MIT 许可,每日同步)

共 15141 条提示词,按 11 个用途归类;同一条可归入多个用途,因此分类条数相加会大于去重后的总数。

命中 725 条

Ultra-Realistic 3D Inflatable Object Render

game-asset

A prompt designed to generate ultra-realistic 3D renders of an object (Valentine themed in this case) with a glossy, inflated plastic material, focusing on smooth contours, high specular highlights, and a designer collectible toy aesthetic against a plain studio background.

展开提示词全文
"{argument name="subject" default="SUBJECT"}, ultra realistic 3D render, smooth inflated glossy plastic material, soft pillowy balloon like contours, subtle stitched panel seams and paneling, high specular highlights, clean reflections, soft contact shadows, designer collectible toy aesthetic, cute proportions, premium polished finish, floating centered, plain light gray studio background, soft diffused studio lighting, sharp focus, high resolution, 8k, 1:1, no text, no logo, no watermark.”

Fisheye Product Photo with Forced Perspective

game-asset

A prompt designed to create a high-impact, cartoonish yet realistic product photo using a fisheye lens effect, emphasizing warped forced perspective where the character's head is immense in the foreground and limbs taper into blur.

展开提示词全文
A high impact fisheye product photo of the character, shown full-body in warped forced perspective. The head is immense in the foreground, limbs taper into blur, cartoonish yet grounded in realistic detail. Pose: The character leans slightly forward, stepping into the viewer’s space. The oversized head pushes closest to the lens, eyes sharp and engaging, while the arms hang loosely at its sides. Shoes recede into deep blur, vanishing into the background. Camera: Fisheye macro, 15–20mm lens, tilted slightly upward to exaggerate the forward lean. Lighting: Strong frontal light reveals fine surface textures, with soft fill shadow along the torso and a faint rim halo separating the figure from the backdrop. Eyes: Eyes are emphasized with dimensional lighting subtle gradients across the surface, crisp specular highlights, and surrounding contrast shadows to add depth and expression without altering their shape. Background: Neutral infinite fade in soft grey/white, with no visible floor or horizon. Material Focus: Extreme emphasis on surface qualities textures, finishes, and subtle reflections are captured with high fidelity, whether matte, soft, or powdery. Gloves appear simple and soft, shoes trail into blur with faint sheen. Emotion: Direct and intimate the figure feels like it’s leaning out of the photo toward you, demanding presence. Negative prompt: No props, no clutter, no flat neutral standing pose

Cinematic Action Video Prompt: Banana Fairy vs. Zombies

game-asset

A detailed video generation prompt for Vidu AI, creating a cinematic action scene where a banana fairy girl fights off zombies using only bananas as weapons in a fantastical indoor space filled with banana decorations. The prompt includes specific instructions for character, setting, action, camera work, lighting, and style.

展开提示词全文
Use the woman in the attached image as the main character.
The setting is a fantastical indoor space surrounded by bananas, identical to the attached image.
Zombies attack one after another in a space lined with banana trees and giant banana objects.
The banana fairy girl quickly grabs bananas around her and throws them in rapid succession.
The only weapon is bananas.
The bananas fly straight while spinning at high speed, hitting the zombies' heads.
The moment of impact is in slow motion.
Strong shockwave effects, light trails, dynamic motion blur.
The hit zombies are blown away, collapsing while shaking the surrounding banana decorations.
The girl jumps onto a giant banana and throws bananas accurately while spinning.
Emphasize the impact with a low-angle hero shot.
Dynamic tracking camera following the flying bananas.

Camera Direction:
・High-speed dolly-in towards the girl
・Intense handheld-style shake when zombies approach
・Slow motion upon banana impact
・Smooth tracking shot following the flying bananas
・Tense low angle

Lighting:
Strong contrast
Rim light emphasizing contours
Contrast with the fantastical gold interior light

Style:
Anime Cinematic Action
High definition
Smooth animation
Strong motion blur
Dynamic composition
Depth of field

Atmosphere:
Tension
Thrilling
Heroic

No text
No subtitles

Cinematic Portrait of Sydney Sweeney as Wanda Maximoff

game-asset

A highly detailed JSON prompt for generating a cinematic, realistic portrait of actress Sydney Sweeney as Wanda Maximoff (Scarlet Witch). The prompt specifies a dramatic visual tone, deep crimson costume details (satin dress, angular crown), and focuses heavily on facial expression (determined, conflicted) and realistic skin texture.

展开提示词全文
{
  "style": {
    "genre": "cinematic realistic portrait",
    "visual_tone": "dramatic, intense, slightly surreal realism",
    "color_palette": "deep reds, warm skin tones, muted background colors",
    "overall_mood": "controlled chaos, emotional tension, restrained power"
  },

  "character": {
    "subject_reference": "Sydney Sweeney",
    "gender_presentation": "female",
    "age_range": "mid 20s to early 30s",
    "expression": "lips pressed together, slightly pursed, holding back emotion",
    "emotion": "determined, conflicted, restrained anger",
    "gaze": {
      "direction": "directly into camera",
      "intensity": "wide-eyed, intense, unblinking",
      "feeling": "alert, emotionally charged, on edge"
    }
  },

  "face": {
    "face_shape": "soft oval with defined cheekbones",
    "skin": {
      "texture": "natural skin texture, subtle pores visible",
      "finish": "soft matte with slight natural sheen"
    },
    "eyes": {
      "size": "large",
      "shape": "round with sharp focus",
      "eye_color": "light green to hazel",
      "eyelashes": "defined but not exaggerated"
    },
    "eyebrows": {
      "shape": "natural, slightly arched",
      "thickness": "medium, realistic"
    },
    "lips": {
      "shape": "medium fullness",
      "expression_detail": "pressed inward, tension visible",
      "lip_color": "natural pink-red"
    }
  },

  "makeup": {
    "foundation": "light coverage, natural skin visible",
    "eyes": {
      "eyeshadow": "neutral warm tones, very subtle",
      "eyeliner": "thin, close to lash line",
      "mascara": "natural definition"
    },
    "cheeks": "very subtle blush",
    "lips": "soft red or rose tint, satin finish"
  },

  "hair": {
    "color": "warm light brown to dark blonde",
    "length": "shoulder length",
    "style": "loose, softly waved",
    "parting": "slightly off-center",
    "movement": "natural, slight motion as if caught mid-step"
  },

  "costume": {
    "outfit_type": "superhero-inspired elegant costume",
    "primary_color": "deep crimson red",
    "fabric": "smooth satin-like material with soft sheen",
    "dress": {
      "cut": "sleeveless, fitted bodice",
      "neckline": "structured with ribbon tie at collarbone",
      "fit": "form-fitting but elegant"
    },
    "gloves": {
      "length": "elbow-length",
      "material": "matching satin fabric",
      "color": "same deep red"
    }
  },

  "accessories": {
    "headpiece": {
      "type": "stylized crown / headband",
      "color": "dark red",
      "shape": "sharp angular points rising upward",
      "material": "matte or semi-gloss hard surface"
    },
    "jewelry": "none visible"
  },

  "pose": {
    "body_position": "standing upright",
    "hands": "hands close together near chest level",
    "gesture": "subtle tension in fingers"
  },

  "framing": {
    "shot_type": "medium close-up portrait",
    "crop": "head to mid-torso",

Cinematic Concept Art of Sadie Sink as Jean Grey

game-asset

A structured JSON prompt for generating a cinematic 3D render or concept art of actress Sadie Sink portraying the Marvel character Jean Grey, detailing three distinct costume variants, specific physical features, and technical rendering parameters like 4K resolution and Unreal Engine 5 style.

展开提示词全文
{
  "subject": {
    "actor_likeness": "Sadie Sink",
    "character": "Jean Grey (Marvel Comics)",
    "physical_features": {
      "hair": "Long, voluminous, wavy ginger-red hair, natural texture",
      "eyes": "Pale blue/grey",
      "expression": "Stoic, determined, heroic neutral",
      "build": "Athletic, slender"
    }
  },
  "costume_variants": {
    "variant_1_phoenix": {
      "base_color": "Metallic emerald green",
      "accents": "Gold chrome gloves, boots, and waist sash",
      "insignia": "Large white Phoenix force emblem on chest",
      "style": "Sleek spandex-metallic hybrid"
    },
    "variant_2_classic_xmen": {
      "base_color": "Dark forest green leather",
      "accents": "Yellow 'X' symbols on belt and boot straps",
      "armor": "Metallic green sculpted breastplate and abdominal plating",
      "headwear": "V-shaped green metallic tiara/circlet"
    },
    "variant_3_tactical_armor": {
      "base_color": "Deep crimson/burgundy textured fabric",
      "armor_plating": "Iridescent cobalt blue metallic plating on chest, shoulders, forearms, and shins",
      "insignia": "Red and black 'X' logo on belt",
      "headwear": "Integrated blue metallic combat headset/tiara"
    }
  },
  "artistic_style": {
    "type": "Cinematic 3D render / Concept art",
    "lighting": "Studio rim lighting, volumetric glow, subtle golden aura or smoke",
    "background": "Solid studio backdrop (Slate blue or Charcoal) with atmospheric haze",
    "framing": "Full-body shot, centered composition, eye-level camera angle",
    "texture_quality": "High-fidelity fabric weave, metallic reflections, realistic skin pores"
  },
  "technical_parameters": {
    "aspect_ratio": "2:3",
    "resolution": "4K",
    "rendering_engine": "Unreal Engine 5 / Octane Render style"
  }
}

Whimsical 3D Clay Sculpture of Stacked Children Prompt

game-asset

A detailed prompt for generating a highly detailed 3D cartoon sculpture of three whimsical children stacked on top of each other on a rustic house, emphasizing exaggerated features, expressive poses, and realistic clay texture.

展开提示词全文
A highly detailed 3D cartoon sculpture of three whimsical children stacked on top of each other on a small rustic house. The children have exaggerated features: large round eyes, big ears, small noses, and rosy cheeks. The top child has wild, messy hair, wearing a blue checkered dress, looking excited with mouth open showing teeth. The middle child has short hair, a brown sweater, gray pants, a gray cap, looking surprised. The bottom child has wavy hair, wearing a muted patterned dress, looking worried and nervous. Each child has oversized shoes and expressive poses. The tiny house at the bottom is textured with stone walls, wooden windows, and a blue door, slightly crooked. Realistic shading and textures, ultra-detailed, cinematic lighting, depth of field, hyper-realistic clay sculpture style.

Optional style tags:
 hyper-detailed, cinematic lighting, whimsical, clay sculpture, 3D cartoon, expressive characters, ultra-realistic textures, soft shadows

Caricature Bobblehead Figurine Prompt

game-asset

A detailed prompt for generating a highly detailed caricature figurine in a bobblehead style, emphasizing exaggerated features, intense expression, and professional product photography aesthetics.

展开提示词全文
Highly detailed caricature figurine of {argument name="subject" default="[SUBJECT]"} as a cute but intense bobblehead-style collectible statue, exaggerated oversized head with hyper-realistic facial features, deep wrinkles, fierce intense expression, slightly open mouth showing teeth, sitting relaxed in a vintage armchair, wearing {argument name="outfit" default="[OUTFIT]"}, dramatic colorful studio lighting, {argument name="background" default="[BACKGROUND]"}, modern collectible toy photography style, sharp focus, cinematic depth of field, extremely intricate sculpting details, realistic skin texture, professional product photography, 8k quality

Maze Generation Failure in Nano Banana

game-asset

The user attempted to generate a maze using Nano Banana, concluding that the model's underlying mechanism prevents it from successfully creating functional mazes.

展开提示词全文
I tried generating a maze, but I see that this kind of thing isn't possible due to the mechanism...

Character Generation from Google Slides Shapes

game-asset

This tweet expresses surprise at the high quality of a cute character generated by Nano Banana Pro using simple shapes from Google Slides as input, implying an image-to-image or style transfer process.

展开提示词全文
Such a cute character was created from Google Slides shapes!!

Nano Banana's Understanding of Fallout Terminology

game-asset

This tweet notes that Nano Banana (likely Pro) has a high understanding of specific proper nouns and terminology from the Fallout universe, such as 'Nuka-Launcher' and 'Ghoul,' suggesting these terms were used in a prompt.

展开提示词全文
Proper nouns like Nuka-Launcher and Ghoul are understood.

Billie Eilish Fortnite-Style 3D Character Render

game-asset

A structured JSON prompt for generating a high-fidelity 3D character render of Billie Eilish in a Fortnite/Unreal Engine aesthetic. The prompt specifies her iconic neon green and black outfit (oversized t-shirt and shorts with graffiti print), space buns, dynamic mid-air pose, and dramatic volumetric neon green stage lighting, aiming for a stylized, action-oriented look.

展开提示词全文
{
  "subject": {
    "name": "Billie Eilish",
    "style": "Fortnite stylized 3D character model",
    "pose": "Dynamic mid-air jump, forward-leaning, action-oriented",
    "features": {
      "hair": "Two high space buns, black hair with vibrant neon green roots/highlights",
      "eyes": "Light blue/grey, calm and focused expression",
      "skin": "Smooth, stylized porcelain complexion"
    }
  },
  "outfit": {
    "top": "Oversized neon lime green short-sleeved t-shirt",
    "bottom": "Matching neon lime green oversized shorts",
    "pattern": "All-over black graffiti print featuring 'Billie Eilish' text and 'Blohsh' stick-figure logos",
    "accessories": [
      "Stacked chunky silver chrome chain necklaces",
      "Silver Blohsh pendant"
    ]
  },
  "footwear": {
    "shoes": "Monochromatic neon green high-top sneakers (Air Jordan 1 style)",
    "socks": "Mid-calf neon green ribbed socks"
  },
  "environment": {
    "setting": "Futuristic concert stage / Festival mainstage",
    "lighting": "Dramatic neon green volumetric lighting, laser beams, glowing floor panels",
    "atmosphere": "Vibrant green haze and digital energy effects",
    "background_elements": "Silhouetted guitarist on a raised platform in the distance"
  },
  "technical_specs": {
    "art_style": "High-fidelity 3D render, Unreal Engine 5 aesthetic",
    "color_palette": ["#39FF14 (Neon Green)", "#000000 (Black)", "#C0C0C0 (Silver)"],
    "composition": "Low angle, vertical aspect ratio, dynamic motion blur"
  }
}

1/7 Scale Collectible Figure Product Shot

game-asset

A prompt for generating a high-resolution commercial product photograph of a detailed 1/7 scale collectible figure, emphasizing realistic textures, specific base details, and a background featuring a computer monitor displaying the figure's 3D wireframe mesh and collector's box.

展开提示词全文
A high-resolution commercial product photograph of an incredibly detailed {argument name="scale" default="1/7"} scale collectible figure. The figure features intricate clothing textures and realistic skin, standing on a pristine, transparent circular acrylic base on a modern artist's desk surface. Eye-level close-up. In the soft-focus background, a computer monitor displays the complex 3D wireframe mesh of the same figure, next to a premium matte collector's box with vibrant 2D character art. Lighting is a mix of professional soft studio light and the subtle blue glow from the monitor screen creating rim lighting. Highly detailed, photorealistic, shallow depth of field.

提示词模型无关,可直接用于 Midjourney / DALL·E / Flux / Stable Diffusion 等任意文生图模型。

信息边界说明

本页信息摘自官方文档,仅作技术信息呈现,不代表本站的判断或推荐。价格、配额、可用性以官方最新说明为准。你离开本站后的任何行为(申请 Key、付费、部署、商用),本站不做任何承诺与担保。

同类推荐

视频短视频图片音乐音频配音口播数字人全能创作

官方标注收费

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

官方标注收费

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

官方未说明

【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

官方标注收费需申请 Key

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

官方标注免费

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

官方标注收费需申请 Key

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。

什么是技能

技能(Skill)是封装好的单项能力,比如文字识别、文档摘要、关键词提取。开发者把调用逻辑和提示词打包,使用者像用插件一样加载即可,无需了解底层模型。启枢技能 收录大量技能,可直接试跑或编入方案。