← 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

Cinematic Hamster Deadlift Video Prompt

game-asset

A detailed video generation prompt for creating an ultra-realistic, cinematic scene of a small hamster performing a deadlift in a gym, focusing on slow, dramatic buildup, hyper-realistic style, and low-angle perspective to exaggerate the scale and power.

展开提示词全文
Ultra-realistic cinematic gym scene featuring a small tan-and-white hamster wearing a beige baseball cap, silver over-ear headphones, and a white lifting belt.
Scene opens with the barbell resting fully on the ground on a worn wooden lifting platform. The hamster is in a proper deadlift stance — feet planted wide, paws gripping the bar, back straight, head slightly lifted forward.
0–4 seconds:
Slow, dramatic buildup. The hamster struggles to initiate the lift — muscles tense, fur slightly trembling, paws tightening on the bar. Subtle body shake, controlled strain, deep focus. No camera shake. No text. No flashy effects.
4–8 seconds:
The hamster successfully deadlifts the barbell in one smooth, powerful motion, lifting it from the floor to full standing lockout. Chest up, shoulders back, bar held firmly at hip level. The effort turns into quiet triumph.
Cinematic low front angle throughout to exaggerate scale and power.
Shallow depth of field with a modern gym environment softly blurred in the background.
Cool neutral gym lighting with realistic reflections on metal plates and soft shadows on the floor.
Style:
Hyper-realistic, premium movie realism, high contrast, clean motion, no distortion, no surreal physics, no bar intersecting the body, no camera jumps, no visual noise.
Emotional tone: determination → victory.

3D Anthropomorphic Bunny Character Prompt

game-asset

A structured prompt for generating a 3D animated, stylized-realistic image of a cheerful, chubby anthropomorphic white bunny wearing yellow overalls, focusing on fluffy fur detail, large glossy eyes, and soft studio lighting against a solid color background.

展开提示词全文
{
  "subject": {
    "type": "anthropomorphic bunny",
    "species": "rabbit",
    "gender": "not specified",
    "age_representation": "childlike / cartoon-styled",
    "pose": "standing on hind legs with one leg lifted forward, one arm raised upward, the other arm slightly bent outward",
    "expression": "happy, joyful, open-mouthed smile",
    "emotion": "cheerful, playful"
  },
  "head_and_face": {
    "head_shape": "round and fluffy",
    "fur_color": "pure white",
    "fur_texture": "very soft, dense, fluffy, fine strands visible",
    "eyes": {
      "size": "very large",
      "shape": "round",
      "color": "blue with darker outer ring",
      "pupils": "large black pupils",
      "eye_style": "glossy, reflective, cartoon-like"
    },
    "nose": {
      "size": "small",
      "shape": "rounded",
      "color": "soft pink"
    },
    "mouth": {
      "state": "open",
      "shape": "small rounded opening",
      "inner_color": "dark pink",
      "teeth": "not visible"
    },
    "cheeks": {
      "shape": "puffy",
      "tint": "light pink blush"
    }
  },
  "ears": {
    "count": 2,
    "position": "upright",
    "shape": "long and slightly curved",
    "outer_fur": "white and fluffy",
    "inner_ear_color": "light pink",
    "accessory": {
      "type": "small hair band",
      "color": "red",
      "placement": "wrapped around one ear"
    }
  },
  "body": {
    "proportions": "chubby, small torso with oversized head",
    "fur_color": "white",
    "fur_texture": "plush, soft, evenly groomed"
  },
  "clothing": {
    "outfit_type": "overalls",
    "material_appearance": "soft fabric with visible texture",
    "color": "{argument name="overalls color" default="yellow"}",
    "design": {
      "straps": 2,
      "buttons": {
        "count": 2,
        "shape": "round",
        "color": "pink",
        "decoration": "flower-shaped"
      }
    },
    "fit": "loose and rounded around the belly"
  },
  "limbs": {
    "arms": {
      "count": 2,
      "fur_color": "white",
      "pose": {
        "left_arm": "raised upward in a waving gesture",
        "right_arm": "slightly bent outward"
      },
      "paws": {
        "shape": "small and rounded",
        "pads_color": "light pink"
      }
    },
    "legs": {
      "count": 2,
      "pose": {
        "support_leg": "standing firmly on ground",
        "raised_leg": "lifted forward in playful motion"
      },
      "feet": {
        "shape": "rounded",
        "pads_color": "light pink"
      }
    }
  },
  "background": {
    "type": "solid color",
    "color": "{argument name="background color" default="coral / warm reddish-pink"}",
    "texture": "smooth, gradient-free"
  },
  "lighting": {
    "type": "soft studio lighting",
    "direction": "even frontal lighting",
    "shadows": "soft and subtle beneath the feet",
    "highlights": "gentle highlights on fur and eyes"
  },
  "render_style": {
    "style": "3D animated character",
    "realism_level": "stylized realism",
    "fur_detail": "high strand"

3D Chibi Cartoon Sticker Set Generation Prompt

game-asset

A prompt for generating a set of 3D chibi-style cartoon stickers based on a reference face. It specifies the aesthetic (Pixar/Disney-inspired, glossy eyes, rounded face), character details (red leather jacket), multiple emotional poses, and technical requirements (smooth plastic texture, white outline, high resolution).

展开提示词全文
A cute 3D chibi-style cartoon sticker set, featuring the same character in multiple emotions and poses(using an uploaded face as a reference). Big expressive glossy eyes, soft rounded face, slightly oversized head, small body proportions.  Wearing a {argument name="jacket color" default="red"} leather jacket over a white top. Each pose shows different expressions: surprised, sad, confused, happy, thinking, winking, peace sign, shrugging. Pixar/Disney-inspired 3D render, smooth plastic-like texture, soft lighting, pastel beige background. Sticker-style white outline around each character, clean and minimal aesthetic, high detail, ultra cute, emoji-like expressions, high resolution, studio quality.

RPG Status Screen Overlay

game-asset

A Japanese prompt for generating an image where a realistic RPG status screen appears behind the subject.

展开提示词全文
A realistic RPG status screen appears in the background.

Hyper-Realistic Military Squad Portrait

game-asset

A prompt designed to generate a hyper-realistic, cinematic portrait of an elite three-person military squad in tactical gear. The scene is set in a gritty warzone with smoke and sparks, aiming for a game-poster aesthetic with high detail and 8K resolution.

展开提示词全文
A hyper-realistic, cinematic 9:16 portrait of a modern military squad lineup. In the middle stands, wearing tactical combat gear with a vest, headset, gloves, and a futuristic assault rifle. On the left: a rugged soldier with a beard and boonie hat, wearing heavy tactical armor. On the right: a mysterious masked operative with a skull-patterned mask and combat uniform. The three stand side by side as an elite special forces unit, set in a gritty warzone environment with sparks, smoke, and cinematic lighting. Ultra-detailed, realistic textures, game-poster style, 8K

Short Prompt for POV Fisheye Pokemon Wildlife

game-asset

A very short, stylistic prompt combining POV, Raw, Fisheye lens effects with the subject matter of Pokemon Wildlife.

展开提示词全文
POV Raw Fisheye Pokemon Wildlife

Ultra-Realistic Cinematic Scene of Floating in Mid-Air

game-asset

An ultra-realistic cinematic prompt for generating a dynamic scene of a character floating upside down above the clouds. The prompt emphasizes motion blur, realistic physics, epic scale, and the presence of two futuristic stealth fighter jets flying close to the subject.

展开提示词全文
Ultra realistic cinematic scene of my floating and falling in mid air above the clouds, dynamic upside down pose with legs bent and arms slightly raised, wearing black hoodie black pants black cap sunglasses and {argument name="shoe color" default="red"} sports shoes, dramatic sense of motion, two futuristic stealth fighter jets flying very close above and below the character with motion blur and heat trails, high altitude sky with soft clouds far below, daylight cinematic lighting, sharp focus on character, wide angle shot, epic scale, realistic physics, dramatic composition, 4k quality, no text, no logo, no watermark

High-End 3D Render of Segmented Object

game-asset

A detailed prompt for creating an ultra-clean, high-end 3D render of an object with clearly segmented parts, utilizing bold, high-contrast colors and a playful, premium collectible-toy aesthetic, rendered with Octane or Redshift-style quality.

展开提示词全文
Ultra-clean high-end 3D render of {argument name="object" default="OBJECT"}, designed with clearly segmented parts in bold, vibrant, high-contrast colors, each component using a different saturated pop color (electric blue, neon pink, bright yellow, mint green, cyan, purple, glossy white accents), smooth matte and semi-gloss plastic materials with subtle rubberized elements, rounded edges, playful industrial toy-like proportions, premium collectible-toy aesthetic, the object floating in mid-air with slightly separated components to emphasize individual parts, no motion blur, perfectly balanced composition, studio lighting with soft diffused key light and controlled rim light to enhance color separation, minimal clean shadows, smooth gradient background transitioning from deep blue to purple, ultra-polished Apple-level cleanliness, no textures, no scratches, no dirt, no realism noise, no muted tones, no desaturation, no monochrome dominance, perfect global illumination, ray-traced reflections, soft contact shadows, shallow depth while remaining razor sharp, cinematic framing, centered composition, minimalistic, modern, playful yet premium, rendered in ultra-high resolution with Octane or Redshift-style quality, Behance-feature-level output, no text, no logos, no branding, no extra elements, no people, no environment clutter, no watermark, no typography, aspect ratio 4:5.

Massive Ancient Abandoned Alien Mining Machine Prompt

game-asset

A simple, high-concept prompt for generating an image of a massive, ancient, abandoned alien mining machine shaped like a worm, using specific Midjourney parameters for style and reference.

展开提示词全文
Massive ancient abandoned alien mining machine in the shape of a worm --ar 16:9 --raw --sref 213005887 --sw 100 --stylize 300 --v 6.1

Minimal Character Illustration Template

game-asset

A simple template prompt for generating minimal character illustrations with simplified features, flat colors, and soft curves, suitable for clean, visually calm designs.

展开提示词全文
Illustrate a minimal character of {argument name="character type" default="[CHARACTER TYPE]"} with simplified facial features (dots and lines only). Use flat colors, soft curves, and no textures. Neutral pose, centered, on a plain background. Cute, calm, and visually clean.

Cinematic 3D World Emergence from Object

game-asset

A template prompt for generating a cinematic 3D composition where a small object releases an entire world or reality far bigger than itself, with the object's shapes transforming into the terrain and architecture of the emerging world.

展开提示词全文
Cinematic 3D composition centered on a {argument name="object" default="[OBJECT]"}, frozen at the instant it releases something far bigger than itself.

From within it, an entire {argument name="world style" default="[WORLD STYLE / THEME]"} reality unfolds, spilling outward into sweeping environments, towering forms, and dynamic motion that suggests this world was hidden there all along.

The object doesn’t just contain the world — it becomes part of it, with its shapes transforming into terrain, architecture, and symbolic landmarks.

Small figures, machines, or creatures navigate the scene, adding life, scale, and narrative.
The moment balances between dream and physics, where visual logic holds even as reality stretches.

The scene is charged with [ATMOSPHERE: glow, fog, particles, smoke, energy], amplifying the sense of rupture and emergence.

A subtle hint of the real world remains visible around the edges, anchoring the spectacle in realism.

Hyper-detailed textures, dramatic lighting, cinematic depth, ultra-realistic, 8K, concept art finish.

Pixar-style 3D character of a cheerful girl in yellow

game-asset

A prompt for generating a high-quality, Pixar/Disney-inspired 3D cartoon character of a cheerful young girl. It details her appearance, attire (yellow and white outfit, chunky sneakers), pose (energetic/surprised), and technical specifications like clay-like textures and cinematic depth of field.

展开提示词全文
A high-quality 3D cartoon-style character of a cheerful young girl with expressive oversized eyes and soft facial features, rendered in a Pixar/Disney-inspired aesthetic. She has long, wavy blonde hair with detailed strands, wearing round oversized glasses and a cozy yellow-and-white outfit. The character is dressed in a yellow hoodie layered with a textured jacket, white cargo pants, and chunky sneakers Accessories include a beanie hat and playful glasses matching the warm color palette.The pose is energetic and expressive-either mid-jump with arms raised in excitement or standing confidently with crossed arms and a surprised, curious expression. Clean monochrome {argument name="background color" default="yellow"} background, soft studio lighting, smooth clay-like textures, ultra-detailed clothing fabric, vibrant colors, joyful mood, cinematic depth of field, 4K resolution, modern stylized 3D illustration.

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。