← 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

Pixar/Disney 3D Cartoon Character with Knitted Name

game-asset

A comprehensive image generation prompt for creating a full-body 3D cartoon girl character rendered in the style of Pixar or Disney. The prompt focuses on specific clothing details, including an oversized knitted sweater with the name 'NOOR' woven into the fabric, emphasizing yarn knit realism and a warm color palette against a solid yellow background.

展开提示词全文
A full-body 3D cartoon girl character in a Pixar/Disney-style render, standing confidently against a solid bright {argument name="background color" default="yellow"} background. She has big expressive brown eyes, a cute smiling face, and light brown curly hair tied in a messy high bun, with white round goggles resting on her head. She is wearing an oversized knitted sweater in cream and mustard yellow stripes, with the name “{argument name="name on sweater" default="NOOR"}” clearly knitted into the fabric across the chest (woven yarn texture, not printed). Loose knitted beige cargo pants with side pockets, white chunky sneakers with subtle yellow accents. Soft studio lighting, smooth textures, high detail yarn knit realism, warm color palette, playful pose with arms slightly spread, ultra-high quality, 4K, sharp focus, clean background, character centered.

Transformer Robot to Tank Transition Prompt

game-asset

A prompt for generating a 6-step transitional process image, showing a Transformer robot transforming into a tank. It specifies a 3x2 layout and requires maintaining the same style without outlines.

展开提示词全文
Show the transitional process of this Transformer robot transforming into a tank in 6 (3 x 2) step-by-step process. Use same style without outlines

Hyper-Realistic Studio Portrait with Floating Ring Prop Prompt

game-asset

A template prompt for Nano Banana Pro to generate a hyper-realistic, full-body studio portrait featuring a character surrounded by a floating, diagonally tilted ring. The prompt allows customization of the character, outfit, ring material, and studio background gradient, emphasizing cinematic lighting and sharp focus on the subject and the ring.

展开提示词全文
A hyper-realistic studio full-body portrait of {argument name="character" default="[CHARACTER]"} with {argument name="outfit description" default="[OUTFIT DESCRIPTION]"} in a [POSE]. His/Her full body is fully visible from head to toe, standing on a [FLOOR TYPE] reflective studio floor, with both feet clearly visible in frame. Camera is positioned at full-body height, straight-on, ensuring clean composition and strong symmetry.

Surrounding the subject, [RING TYPE] arranged precisely around the mid-torso area. [RING CONTENT] (repeat seamlessly if text-based). The ring is tilted diagonally in perspective and floats naturally around the body with a clear gap, without touching the clothing/skin. Ring Rendering: {argument name="ring material" default="[MATERIAL/STYLE: metallic / chrome / dot-matrix LED / anime ink]"} with [EXTRUSION or GLOW], deep shadows, and glossy highlights.

Background: a clean studio gradient from [COLOR 1] to [COLOR 2], evenly lit and minimal. Lighting: soft cinematic studio lighting, [KEY LIGHT direction/quality] creating smooth dramatic shadows across [materials]. A subtle backlight / rim light enhances depth and separation from the background, while gentle specular highlights emphasize contours, texture, and premium realism. Mood: [FINAL MOOD LINE] [STYLE INTERPRETATION]. Ultra-detailed, cinematic composition, sharp focus

Dark Sci-Fi Action Scene with Venom-like Symbiote

game-asset

A highly detailed JSON prompt for generating an ultra-realistic, 16K cinematic action scene in a dark industrial warehouse. The prompt focuses on a young woman (with identity lock enabled) in a dynamic action pose, from whose back a violent, glossy black, Venom-like alien symbiote is bursting, emphasizing high contrast, warm rim lighting, and dramatic low-angle framing.

展开提示词全文
{
  "identity_lock": {
    "reference_image": "uploaded_reference_image",
    "face_editing": "disabled",
    "preserve_facial_features": true,
    "preserve_proportions": true
  },
  "scene": {
    "description": "Ultra-realistic cinematic action scene",
    "resolution": "16K",
    "style": "Hollywood action-movie poster",
    "genre": "dark sci-fi action"
  },
  "subject": {
    "person": "same young woman from reference",
    "pose": {
      "stance": "dynamic action",
      "body_position": "slightly crouched forward",
      "legs": "one knee bent",
      "hands": {
        "left_hand": "pressed against the ground",
        "right_hand": "reaching outward"
      }
    },
    "expression": "focused and intense",
    "motion": "mid-action, about to leap or attack"
  },
  "symbiote": {
    "type": "{argument name="symbiote type" default="Venom-like alien symbiote"}",
    "origin": "bursting from her back",
    "features": [
      "large menacing tendrils",
      "aggressive snarling face above shoulder"
    ],
    "material": "glossy black organic texture",
    "behavior": "violent expansion and movement"
  },
  "environment": {
    "location": "dark industrial warehouse",
    "atmosphere": [
      "misty",
      "smoke-filled",
      "floating dust particles"
    ],
    "lighting": {
      "primary": "sharp cinematic light beams cutting through fog",
      "highlights": "warm rim lighting on subject and symbiote"
    }
  },
  "camera": {
    "angle": "low angle",
    "tilt": "slightly tilted",
    "lens": "cinematic wide lens",
    "depth_of_field": "shallow",
    "motion_blur": "subtle directional blur"
  },
  "post_processing": {
    "effects": [
      "lens flares",
      "warm highlights",
      "cinematic color grading",
      "subtle film grain"
    ],
    "contrast": "high",
    "sharpness": "ultra-detailed"
  },
  "mood": {
    "energy": "high intensity",
    "tone": "dark, powerful, aggressive",
    "cinematic_feel": "epic and dramatic"
  }
}

Ultra-Detailed 3D Stylized Character Design Prompt

game-asset

A detailed prompt for generating a Pixar/Disney-inspired 3D stylized character, focusing on soft features, expressive eyes, cozy-chic modern outfit, and high-quality rendering specifications like Octane/Arnold style and 8K resolution.

展开提示词全文
Use Reference figuire1 Create Ultra-detailed 3D stylized character design of a cute with a Pixar/Disney-inspired look, soft rounded facial features, big expressive eyes, smooth porcelain skin, and playful proportions.
Outfit is cozy-chic and modern: oversized knitted sweaters, fluffy jackets, cropped tops, skirts or wide-leg jeans, textured fabrics like wool, fleece, and knit, paired with chunky sneakers or plush boots. Warm color palette with pastel and vibrant tones ({argument name="Color Palette" default="orange, teal, purple, yellow"}).
Accessories include a small backpack or sling bag, headphones or goggles, and a cute animal companion (like a {argument name="Animal Companion" default="tiny owl"}) resting on person shoulder. Confident yet relaxed pose, fashion-model stance or playful walking motion.
Rendered in ultra-high-quality 3D, soft studio lighting, smooth gradients, clean solid background colors, shallow depth of field, cinematic composition, highly detailed fabric textures, realistic subsurface scattering, polished toy-like finish, adorable and wholesome aesthetic, premium character art, 8K resolution, Octane/Arnold style render.

Nano Banana Pro prompt for Cross Dimensions style

game-asset

This is a prompt shared for the Nano Banana Pro model, specifically utilizing a 'Cross Dimensions' style, suitable for generating complex, multi-dimensional imagery.

展开提示词全文
Cross dimensions, a {argument name="subject" default="cybernetic samurai"} standing on a floating island, surrounded by glowing neon runes and ancient Japanese architecture, volumetric fog, cinematic lighting, highly detailed, 8k, made with Nano Banana Pro

Cinematic fantasy silhouette art with metallic skin prompt

game-asset

A highly structured JSON prompt for generating an epic, ultra-detailed cinematic fantasy silhouette. It specifies a regal feminine figure with metallic silver-gold skin fused with crystalline structures and gems, emerging from a dense luminous mist, emphasizing identity preservation and high contrast lighting.

展开提示词全文
{
  "meta": {
    "aspect_ratio": "9:16",
    "style": "cinematic fantasy silhouette art",
    "render_quality": "ultra-detailed, high fidelity, epic scale"
  },

  "identity_lock": {
    "rule": "Preserve exactly the facial structure, proportions, silhouette, and overall likeness from the reference image provided by the user",
    "skin_rule": "Allow material transformation while keeping facial identity intact",
    "strict": true
  },

  "subject": {
    "description": "Regal feminine figure emerging through ethereal mist, standing with quiet authority",
    "presence": "otherworldly, majestic, timeless",
    "silhouette": "elegant balance of flowing curves and refined sharp edges"
  },

  "body_materials": {
    "skin_tone": "polychromatic silver-gold metallic skin",
    "surface": "organic metal fused with crystalline structures",
    "details": [
      "precious gems organically growing across the body",
      "gem plating covering the entire form",
      "crystal hues blended into marbled silver and gold textures",
      "delicate swirling patterns mixed with large wind-swept marbling"
    ]
  },

  "aesthetic_influences": {
    "design_language": "golden Celtic-inspired ornamental forms",
    "style": "mythic elegance with sacred geometry undertones"
  },
  "environment": {
    "atmosphere": "dense luminous mist",
    "effects": [
      "soft volumetric fog",
      "subtle light rays piercing through the haze"
    ],
    "background": "abstract, undefined space to enhance silhouette focus"
  },

  "lighting": {
    "type": "otherworldly glow",
    "key_light": "soft internal luminescence from within the figure",
    "accent": "gentle rim light outlining the silhouette",
    "contrast": "high contrast between glowing form and misty surroundings"
  },

  "camera": {
    "framing": "full-body cinematic composition",
    "angle": "slightly low angle to enhance regality",
    "focus": "sharp on form and material textures, soft falloff into mist"
  },

  "mood": {
    "emotion": "mystical, powerful, serene",
    "tone": "epic fantasy, sacred presence"
  },

  "negative_prompt": [
    "explicit nudity",
    "sexualized anatomy",
    "cartoon",
    "anime",
    "low detail",
    "flat lighting",
    "plastic look",
    "identity change",
    "distorted face",
    "extra limbs",
    "text",
    "logo",
    "watermark"
  ]
}

Pixar-style 3D avatar generation prompt

game-asset

A prompt for creating a high-quality 3D avatar based on an uploaded image. It specifies a cheerful, expressive face with a warm smile and soft features, rendered in a Pixar-style aesthetic with smooth textures, exaggerated proportions, and soft, even studio lighting.

展开提示词全文
Create a high-quality 3D avatar of the person in the uploaded image with a cheerful, expressive face. The character should have a warm smile, bright eyes, and soft facial features that feel friendly and approachable. Render in a Pixar-style aesthetic with smooth textures, subtle skin shading, and slightly exaggerated proportions for a cute, animated look. Lighting should be soft and even, creating a clean studio look with gentle shadows for depth.

LINE Sticker Generation Prompt (3D Clay Style)

game-asset

A detailed Japanese prompt designed to generate a 3x3 grid of nine different LINE stickers featuring a 3D character in a blind box/Pop Mart style. It specifies a clay texture, matte finish, soft lighting, and nine distinct expressions, each with a cute Japanese text label and white outline.

展开提示词全文
3D character design, blind box style, Pop Mart style design, C4D, Octane rendering, clay texture, matte finish, soft lighting, sticker sheet layout, 3x3 grid view {argument name="expressions and text" default="9 types of expressions: joy making a heart, sadness with tears, anger exhaling steam, sleepy yawning expression, surprised expression with open mouth, shy blushing expression, cheering expression with raised fist, confused thinking expression, celebrating with confetti"}, each with a cute Japanese text label, white outline, die-cut, white background, high quality, 8k --ar 3:4

8K 3D Illustration of Anthropomorphic Bees (Gym and Relaxing)

game-asset

A complex prompt structured into two modules for generating 8K, high-end AI-generated 3D illustrations of anthropomorphic bees. The first module depicts a bee lifting weights in a natural setting, and the second shows a relaxed bee in sunglasses holding a Pepsi can on a lounge chair, emphasizing physically based rendering and extreme detail clarity.

展开提示词全文
{
  "master_prompt": {
    "global_settings": {
      "resolution": "8K",
      "aspect_ratio": "3:4",
      "render_style": "high-end AI-generated 3D illustration",
      "image_quality": "ultra-sharp, cinematic depth, physically based rendering",
      "lighting_quality": "soft global illumination with realistic shadows",
      "focus": "extreme detail clarity, shallow depth of field where applicable"
    },

    "module_1": {
      "scene_identity": "Bee lifting weights in nature",
      "subject": {
        "type": "anthropomorphic bee",
        "body": "fuzzy yellow and black striped body",
        "eyes": "large glossy black eyes",
        "antennae": "two thin black curved antennae",
        "wings": "semi-transparent wings with visible vein patterns",
        "expression": "neutral to slightly cheerful"
      },
      "pose_action": {
        "stance": "standing upright on two legs",
        "arms": "both arms raised holding a barbell",
        "object_interaction": "holding a metal barbell with circular weight plates on both ends"
      },
      "environment": {
        "setting": "outdoor natural environment",
        "ground": "small dirt path or rock surface",
        "surroundings": "flowers on both sides",
        "background": "blurred trees and foliage"
      },
      "lighting": {
        "type": "soft natural daylight",
        "direction": "top-center glow",
        "effects": "light haze and floating particles"
      },
      "color_palette": {
        "dominant_colors": ["yellow", "black", "green", "orange"],
        "accent_colors": ["soft pink", "warm brown"]
      },
      "camera": {
        "angle": "eye-level",
        "framing": "full body centered",
        "depth_of_field": "foreground sharp, background softly blurred"
      }
    },

    "module_2": {
      "scene_identity": "Relaxed bee on chair with soda can",
      "subject": {
        "type": "anthropomorphic bee",
        "body": "dense fuzzy yellow and black stripes",
        "eyes": "hidden behind oversized black sunglasses",
        "antennae": "two black antennae extending upward"
      },
      "pose_action": {
        "posture": "reclining",
        "legs": "one leg crossed over the other",
        "arms": "one arm resting on chair, other holding a can"
      },
      "objects": {
        "chair": "wooden lounge chair with yellow fabric seat and backrest",
        "drink_can": "blue soda can with visible {argument name="drink brand" default="Pepsi"} logo",
        "sunglasses": "large glossy black frames"
      },
      "environment": {
        "setting": "studio-style minimal background",
        "background_color": "light neutral gray",
        "surface": "smooth floor"
      },
      "lighting": {
        "type": "soft studio lighting",
        "shadow": "subtle shadow beneath chair"
      },
      "color_palette": {
        "dominant_colors": ["yellow", "blue", "black", "wood brown"]

Cinematic Noblewoman and Dragon Prompt

game-asset

A prompt for generating a cinematic, hyper-realistic, high-fantasy image of a noblewoman in a medieval gown standing next to a massive grey dragon in a rocky, desolate volcanic landscape under a moody sky.

展开提示词全文
Cinematic full-body shot of a young noblewoman with an intricate braided hairstyle, wearing a highly detailed, silver-grey embroidered medieval gown with puff sleeves. She is standing next to a massive, realistic grey dragon with detailed scales and horns. She gently places her hand on the dragon's snout.

The setting is a rocky, desolate volcanic landscape under a moody, overcast sky. Desaturated colors,

film grain, 8k resolution, hyper-realistic, {argument name="style" default="high fantasy"} Style."

Early 2000s Video Game Render Style Transfer

game-asset

A text prompt designed to transform a given image into the aesthetic of an early 2000s video game render, specifically mimicking the look of Maya 4.0 rendering. It focuses on low-poly geometry, low-resolution textures, and atmospheric effects like fogging distant objects, while explicitly avoiding pixel art or voxel styles.

展开提示词全文
Low poly, low res textures
- Distant objects get simplified and fogged out
- Avoids gotchas like pixel art and voxels
- Based on Maya 4.0 rendering

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。