← 返回首页
技能

Ai Image Prompts

tencent_skillhub · 1.0.9 · 下载量 1,921 · 热度分 56.0

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 702 条

Action scene from reference photos and sketch

comic-storyboard

Uses uploaded photos and a sketch to compose a 1990s-style NYC action shot of a man slipping off a building edge and a woman reaching out, matching the sketch’s pose and composition.

展开提示词全文
Use the man photo as if he is slipping off the building edge, the woman is reaching out, match the sketch pose and composition precisely, use {argument name="city_style_en" default="NYC"} as the style reference for the scene. High-quality action shot from the 1990s.

Four-panel anime manga with panda-girl character

comic-storyboard

Generates a vertical four-panel manga in typical Japanese anime style featuring a silver twin-tailed panda-human girl named Rookie, great for character-based comic strips.

展开提示词全文
Generate a four-panel manga in a typical Japanese anime style. The image is a vertically long rectangle with four panels arranged from top to bottom.

[Character settings]
* Name: {argument name="character_name_en" default="Rookie"}
* Race: {argument name="race_en" default="Panda-human (a human girl with round panda ears on her head)"}
* Hair: {argument name="hairstyle_en" default="Silver twin-tails"}

Ben 10 meets TMNT full comic page

comic-storyboard

An English prompt for creating a full comic page where Ben 10 crosses over into the Teenage Mutant Ninja Turtles universe, with expressive panels, clean linework, and vibrant, official-looking colors.

展开提示词全文
A full comic page bringing {argument name="character_1_en" default="Ben 10"} into the {argument name="universe_en" default="TMNT"} universe, with expressive panels, clean linework, and vibrant colors that feel straight out of an official crossover issue.

Four-panel manga about Bitcoin from cypherpunk view

comic-storyboard

Generates a Japanese four-panel manga where a reference character explains the origins of Bitcoin from a cypherpunk perspective.

展开提示词全文
Create a Japanese four-panel manga in which the character from the reference image explains the origins of Bitcoin from a cypherpunk perspective.

4-panel Japanese gag manga about Nanami eating ramen

comic-storyboard

A detailed prompt for creating a vertical 4-panel Japanese gag manga featuring a young woman named Nanami eating Jiro-style ramen, with proper Japanese layout and speech direction.

展开提示词全文
Create a Japanese 4-panel gag manga showing this young Japanese woman, “{argument name="character_name" default="Nanami"},” eating {argument name="dish" default="Jiro-style ramen"}. Design the composition so it doesn’t become just a face-focused comic. Arrange four panels vertically. Place the dialogue as vertical text, readable from right to left.

Visual story cartoon for a Moroccan Arabic joke

comic-storyboard

A prompt to create a visual story cartoon illustrating a Moroccan Arabic joke about a stoner misunderstanding the word “model.”

展开提示词全文
I want you to create a visual story cartoon for this joke:
A stoned guy saw a very slim girl.
He asked her: “What do you work as?”
She said: “I’m a model (عارضة).”
He replied: “For which stadium?” (playing on the word meaning “stadium presenter”).

Moody cinematic Paris car scene

comic-storyboard

A rich English prompt describing a moody late-night movie still in rainy Paris, viewed from inside a retro Citroën with cinematic mixed lighting.

展开提示词全文
A moody, atmospheric movie still. Late night in Paris, rain pouring. Inside a retro Citroën, a man in a wet trench coat looks calmly at the viewer. The lighting is a mix of cold blue with the warm amber and neon glow of a cafe outside the windshield. Introspective mood.

4-panel RPG manga of original character Anna

comic-storyboard

A Japanese prompt to create a vertical 4-panel manga featuring the user's original female warrior character Anna in an RPG-style world, with Japanese dialogue.

展开提示词全文
This girl is my original character, "{argument name="character_name_en" default="Anna"}." She is the female warrior holding a sword in the second image. Please create a 4-panel manga with an RPG game-style world. The panels are arranged vertically. The dialogue should be in Japanese.

Vertical 4-panel gekiga-style manga YAML prompt

comic-storyboard

A long English YAML prompt specifying layout, art style, manga elements, and panel-by-panel content for a 1:3 vertical 4-panel gekiga-style manga page featuring Knight Alex working at a convenience store.

展开提示词全文
---
generation_parameters:
  aspect_ratio: "1:3"

manga_page_generation_prompt:
  layout_structure:
    type: Full page vertical 4-panel comic strip (yon-koma layout).
    arrangement: Four roughly square panels stacked perfectly vertically from top to bottom.
    spacing: Clear white gutters separating each of the four panels.
    title_area: (Optional) A small space at the very top for a title.
    overall_aesthetic: A printed comic magazine page look with slightly textured paper.

  art_style:
    description: {argument name="style_desc_en" default="1970s–80s Japanese Gekiga style: gritty, heavy shadows, serious tone."}
    color_palette: Desaturated, heavy oil-painting colors, sepia tones, dark atmosphere.
    texture: Rough ink lines, analog brushwork, dramatic cross-hatching shadows, and ink bleed effects.

  manga_elements:
    speech_bubbles:
      - Presence: Multiple hand-drawn speech bubbles (fukidashi) within panel boundaries.
        Style: Rough, organic outlines containing placeholder Japanese marks.
    sound_effects:
      - Presence: Bold Katakana sound effects integrated into the art.
        Style: Rough calligraphy (e.g., "ドォォォン", "ゴゴゴゴ").

  panel_content_sequence:
    panel_1_top (Intro):
      - Scene: [Wide angle] Knight Alex (grim face, full armor) standing stiffly behind a modern convenience store counter.
      - Text/FX: Speech bubble with formal greeting. Small "ウィーン" (door sound).
    panel_2_upper_mid (Development):
      - Scene: A scared salaryman customer shrinking away, Alex glaring intensely and leaning forward over the counter.
      - Text/FX: Customer's scared bubble. Large "ゴゴゴゴ" (menacing FX) around Alex.
    panel_3_lower_mid (Twist):
      - Scene: [Dramatic close-up] Alex pulling out his giant claymore sword just to point at a bento box.
      - Text/FX: Spiky shout bubble "貴様の糧はこれか!!" and intense "ジャキィィン!" (sword FX).
    panel_4_bottom (Conclusion):
      - Scene: The exhausted store manager (looser art style) smacking Alex's head with a rolled magazine. Alex looks comically dejected.
      - Text/FX: Manager's angry bubble "剣をしまうんだよ!" and sharp "スパン!" (slap FX).

negative_prompt:
  - Single illustration, square image, landscape orientation
  - Panels arranged horizontally in a 2x2 grid
  - Modern clean digital art, anime style
  - Bright cheerful colors, no shadows

Neon-girl manga page 1 setup

comic-storyboard

A Japanese prompt for page 1 of a manga about the girl Neon, specifying vertical Japanese text bubbles, right-to-left reading order, and 9:16 aspect ratio.

展开提示词全文
Please create the image for page 1 of the following manga featuring the girl in the picture, "{argument name="character_name_en" default="Neon"}."

Speech bubbles should be vertical.
Panels are read from right to left, top to bottom.
Make it a manga image with an {argument name="aspect_ratio_en" default="9:16"} size.

Title: "{argument name="title_en" default="Sparkling Boot-Up! It’s Neon!"}"

Page 1

Manga-style Japanese onomatopoeia overlay

comic-storyboard

An English prompt to overlay large, bold Japanese onomatopoeia text in classic manga style onto a photo without altering the subject or background.

展开提示词全文
Add large Japanese onomatopoeia text in classic manga style.

Insert ONLY bold, dynamic text:
「{argument name="sfx_text_en" default="ゴゴゴゴーッ!!!"}」

Style requirements:
- Heavy black ink manga typography
- Thick strokes with a white outline
- Slightly rough, hand-drawn texture like shonen manga sound effects
- Diagonal placement from lower left toward upper right
- Strong perspective distortion for impact
- Add subtle speed lines and impact rays around the text
- Slight drop shadow for depth

Do NOT change the woman, the lighting, or the background.
Keep photo realism intact.
Only overlay manga-style sound effect text.

Comprehensive manga one-page scene creation system prompt

comic-storyboard

A long, system-style prompt for Nano Banana Pro that defines roles, objectives, stylistic guidelines, and constraints to create a Japanese manga/anime one-page scene with natural Japanese speech bubbles and micro-emotional expression.

展开提示词全文
Act as a “comprehensive creative” who simultaneously holds the following three perspectives:
Author’s perspective
 → Naturally capture nuances of the character’s emotions, atmosphere, and movement
Editor’s perspective
 → Manage composition, natural flow of text, and consistency of information density
Reader’s perspective
 → Prioritize the kind of emotion that instantly draws the viewer in and maximizes appeal
Make sure these three perspectives are fused without contradiction in your output.
■ Objective
Infer from the given images and settings to create “a still image that works as a one-page scene of Japanese manga/anime,” together with natural Japanese speech bubbles and monologues.
Make “micro-emotion” and “the pull of texture” the core of the scene.
■ Basic policy (axes for the AI’s free inference)
Place focus on depictions that embed emotion in subtle motions and textures, such as the character’s gestures, fingertips, gaze, and the sway of their hair.
Use the three personas to simultaneously achieve “visually strong × natural to read × compelling to look at.”
Do not treat it as a single panel, but give it the structural strength of “a one-page scene.”
Arrange backgrounds and small props so that they complement the character’s inner world.
Leave a rhythmic sense of empty space in the frame where speech bubbles can be placed.
Create a “pulling pause” through distance, light direction, and shadows.
Treat it not as a magazine cover, but as “a frozen decisive moment in the story.”
■ Lines to keep (coherence and aesthetic guidelines)
Natural Japanese (no typos, no AI-ish phrasing).
Physical consistency of hands, joints, light sources, shadows, and posture.
Avoid excessive information density; respect empty space and pauses.
Real URLs, QR codes, and JAN codes are prohibited.
Avoid AI noise and visual breakage.
Do not damage the character’s dignity or psychological realism.
Do not lean toward sexual expression; keep “the charm of micro-emotion” as the core.
Treat “micro-emotion” as texture description that touches the psyche and do not use specific fetishistic terms.
■ Areas you may infer (creative freedom)
Fluctuations in the character’s emotions and inner movements.
The relationship between light direction and psychology.
“Touchable” textures of hair, clothing, and materials.
Angles of hands, wavering gaze, and body tilt.
Narrative meaning of the background.
Temperature of the air (silence/humidity/tension).
The visual focal point of attraction.
Strength of the composition as a one-page layout.
Add small props when needed (within the bounds of consistency).
■ Output style (manga one-page spec)
A readable flow as a single page:
 → empty space → character → text → background support.
Speech bubbles should be in natural Japanese, placed in a way that captures the character’s breath and edges of emotion.
Treat monologue as words sinking inside the character (not explanatory text but a shadow of feeling).
Make the still image feel like it contains a drift of time.
From gestures and textures, depict the “peak of micro-emotion.”
■ One-sentence summary
“Integrate the three perspectives (author, editor, reader) and, focusing on micro-emotion and the pull of texture, infer and finish a one-page Japanese-language scene that captivates.”

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。一节课的讲解也能做成课程口播。

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。

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

海报设计工作室

免费增值需申请 Key

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。

自动化克隆数字人口播混剪视频

免费增值需申请 Key

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

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。