← 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

3D Rendered Barista Character in Pixar Style

game-asset

A JSON prompt for Nano Banana Pro on Gemini to create a high-quality 3D rendered character of a young, friendly barista. The prompt specifies clothing, setting (cozy coffee shop), lighting (soft studio), and style (clay render texture, Pixar/Disney animation style, 4k resolution).

展开提示词全文
{
  "prompt": "A high-quality 3D rendered character of a young, friendly barista with big expressive eyes and styled brown hair. He is wearing a green apron over a plaid flannel shirt. The setting is a cozy coffee shop with wooden counters, espresso machines, and shelves of coffee beans in the background. The image features soft studio lighting, a clay render texture with cute and appealing shape language, reminiscent of Pixar or Disney animation styles, in 4k resolution."
}

Cartoon Character Design Sheet with Personality

game-asset

A prompt for creating a cartoon character design sheet based on an uploaded image, specifying a complex personality trait: a man who projects confidence but is inwardly insecure.

展开提示词全文
create a cartoon character design sheet from this image

a man who performs confidence louder than he feels it. Chest forward, jaw up but something in the eyes gives him away. He's used to being watched, terrified of being seen

3D Chibi Sticker Set with Customizable Jacket Color

game-asset

A prompt for generating a set of 3D chibi-style cartoon stickers featuring the same character in various emotions and poses. It specifies a Pixar/Disney 3D render style, soft lighting, and a clean white sticker outline, requiring a reference image for the character's face.

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

Full Armor Mecha Girl model kit concept prompt

game-asset

A prompt used with Nano Banana Pro to generate an image concept for a 1/7 scale plastic model kit of a 'Full Armor Mecha Girl' (FAMG-001 Aurelith). The design incorporates a 'Jingasa' (samurai hat) image for the head, derived from 'Warrior Mecha Girl' and 'Knight Mecha Girl' concepts.

展开提示词全文
Full Armor Mecha Girl
FAMG-001 Aurelith
⠀
1/7 scale plastic model
⠀
The head is inspired by a "Jingasa" (samurai hat).
It was created using a derived prompt from 'Warrior Mecha Girl' → 'Knight Mecha Girl'.

Bat Cowl Protocol Character Prompt

game-asset

A complex prompt for Nano Banana (or Gemini Nano Banana) to generate a high-quality 3D render of a designer toy character, integrating a custom 'Bat Cowl' from a reference image onto the character while strictly maintaining the character's original outfit, likeness, and lighting conditions.

展开提示词全文
A high-quality 3D render of the designer toy from [Reference Image 1]. Requirement: The character must retain its exact original outfit . The Mask: Tightly fit a custom "Bat Cowl" ([Reference Image 2]) over the head.

The Cowl: Must match the exact color, material, and design, with size adjusted as needed to fit the reference character’s head.
Scaling: Tailored, bespoke fit with a shortened chin guard precisely following the character's jawline. Cowl size is adjusted to match the reference character exactly. The cowl fits seamlessly, with no gap between the head and the chin guard.
Ears: Only the sharp bat ears are visible; hide original ears, headwears, horn, accessories, hat, helmet entirely.
The Cutout: The cowl features a cutout area; through this opening, the underlying part of the reference character must be visible exactly as it is, with no additions, removals, or alterations.
Eyes: Use the exact glowing eye effect from the reference cowl image.
Constraint: No nose or eyes should be rendered on the cowl or the character's face.
8k, studio lighting, Background must match the reference character’s background exactly.
Lighting
Lighting should match the reference character’s original light behavior, and the cowl must follow and respond to the same lighting conditions.
Character Likeness Integrity (CRITICAL)

Maintain the exact eye shape, spacing, stylization, patterns, silhouette, and original color palette from the reference.

Do not humanize.

Do not alter anatomy.

Do not modify facial structure.

Identity must remain instantly recognizable.

If the character wears a balaclava, mask, helmet, or covered face, don't invent facial anatomy.
No added nose.

No added mouth.

No visible skin where the reference does not show it.

Ghibli x Game of Thrones Character Prompts

game-asset

Two prompts for Nano Banana 2 to create images combining the Ghibli art style with Game of Thrones characters. The first prompt uses a reference image for character turnaround, and the second creates a scene with the characters.

展开提示词全文
use the character turnaround format from [img1] to create {argument name="character name" default="[character name]"} in the same style

prompt: show them in a scene together, ghibli style

Ghibli Nezha Character Turnaround

game-asset

A prompt specifically designed for Nano Banana 2 to create a character turnaround sheet for Nezha in the style of Studio Ghibli, referencing an external image for the format.

展开提示词全文
use the character turnaround format from [img1] to create {argument name="character name" default="Nezha"} in the same style

Pixelated Cartoon Animal Image

game-asset

A simple template prompt for Nano Banana 2 to generate a pixelated image of a cartoon animal, allowing the user to specify the animal name.

展开提示词全文
A cartoonish ({argument name="animal name" default="Animal Name"}) in pixelated image format

Ghibli-Inspired Character Turnaround

game-asset

A prompt for Nano Banana 2 requesting the generation of Ghibli-inspired anime characters using a character turnaround format based on a provided reference image.

展开提示词全文
use the character turnaround format from [img1] to create {argument name="character description" default="[character name / image]"} in the same style

Nano Banana Pro Prompt: 8-bit Chicken in T-Rex Costume

game-asset

A prompt used with Nano Banana Pro (Gemini 3.1 image generator) to create an 8-bit style image of a chicken wearing a T-Rex costume on its way home.

展开提示词全文
a chicken in a T-Rex costume's on the way of homecoming in the style of an 8-bits #11

LMGT3-Class Car Inspired Sea Iguana

game-asset

A prompt for Nano Banana Pro (Gemini 3.1 image generator) to create an image of a sea iguana inspired by an LMGT3-class race car.

展开提示词全文
a sea iguana that is inspired by a LMGT3-class car

Cinematic Macro Toy-Photography of Mini Beasts

game-asset

A complex, multi-section prompt for generating a cinematic macro toy-photography scene. The concept involves dozens of miniature identical character instances working on a giant open comic book that tells their story. The prompt strictly enforces likeness integrity, specific camera perspective (low-angle macro, 90-100mm lens), shallow depth of field, and hard directional lighting.

展开提示词全文
A cinematic macro toy-photography scene of the uploaded reference character multiplied into dozens of miniature identical instances, each actively working on a giant open comic book that tells the story of the same character.
Likeness Integrity (CRITICAL)

All miniature instances must preserve the exact identity of the reference character:

• identical proportions

• exact eye shape, spacing, stylization

• same silhouette and material behavior

• no added features, no face changes, no stylization drift
The comic book artwork must depict the exact same character design language, translated into printed comic style without altering anatomy or facial structure.
Scene Concept & Action
The giant comic book lies open like a construction site of narrative.
Mini characters are scattered across the pages, each performing a specific task:
• some are drawing panels with tiny tools (pens, brushes, stylus-like tools)

• some are painting color into panels

• some are climbing panel borders like scaffolding

• some are inspecting scenes, pointing, directing

• some are physically interacting with the comic world ( lifting panels, stepping into frames)
The scene must feel like they are building their own story in real-time.
Perspective & Composition (MANDATORY)
Camera & Perspective (Corrected)
Low-angle macro shot, camera positioned close to the comic page
Lens: 90–100mm macro (compression, NOT distortion)
• Perspective compression must preserve consistent object scale

• Foreground character appears larger only due to proximity to lens

• No exaggerated wide-angle distortion

• Spatial depth created through distance falloff + focus, not scaling

• The open comic book stretches diagonally into depth

• Panels form strong leading lines across the frame

• Composition is intentionally off-balance, not centered

• Some characters partially cropped by frame edges
Foreground includes blurred ink tools, paper edges, or panel borders creating depth layering
Depth of Field (CRITICAL)
Extremely shallow depth of field
• Primary focal plane: one or two mini characters in the foreground actively working

• Mid-ground characters slightly softer

• Background characters and panels fall into creamy blur
No full-frame sharpness
Focus must guide the viewer toward the “main worker” character
Lighting Doctrine
Hard directional cinematic light from top-left
• sharp shadows cast across comic panels

• subtle rim light separating characters from page

• ink reflections create small specular highlights

• shadows from panel edges create natural depth
No flat lighting
Environment & Surface Detail
Macro-level realism of the comic book:
• visible paper fibers

• ink texture and slight gloss

• subtle imperfections in print

• panel borders slightly raised or embossed
Tiny tools leave micro mar

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。