← 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 1099 条

Replace clothing while keeping identity and pose

others

A detailed editing prompt that keeps the user’s face, pose, and environment while changing clothing to match a reference dress.

展开提示词全文
Keep my exact face, pose, body, and environment from my original photo. Change ONLY the clothing and accessories so they match the dress and accessories from the second reference image with full accuracy. Do not alter my hairstyle, makeup, body proportions, or camera angle.

Add baseball hat with embroidered text

others

A follow-up editing prompt to add a baseball cap with specific lettering to an existing generated image.

展开提示词全文
Give me a baseball hat with the word "{argument name="hat text_en" default="create"}" embroidered on it.

Blackboard solving Pythagoras theorem

others

Generates an image of a classroom blackboard where the Pythagorean theorem is being solved step by step, great for educational visuals.

展开提示词全文
Generate an image of a classroom blackboard with the {argument name="topic_en" default="Pythagorean theorem"} being solved step by step.

1915 Bengali newspaper page reconstruction

others

A rich, historically detailed prompt to recreate an authentic 1915 Bengali newspaper page with accurate typography, illustrations, and paper texture.

展开提示词全文
A meticulously reconstructed {argument name="year_en" default="1915"} Bengali newspaper page designed in authentic early‑twentieth‑century typesetting. The layout uses narrow, perfectly aligned vertical columns with period‑accurate fonts, uneven metal‑type spacing, and slight misregistration between lines. The ink appears imperfect, showing faint smudges, minor over‑inking at the edges of letters, and occasional broken glyphs consistent with hand‑set printing presses of the era. The page includes multiple woodcut‑style illustrations: small portraits, political cartoons, and simple scene sketches carved with visible hatch marks and rough contour lines. All Bengali text must be fully legible, grammatically consistent with the period, and arranged in structured headlines, subheads, and body paragraphs. The paper texture should resemble aged newsprint with subtle yellowing, gentle creases, and soft fiber patterns under angled lighting. The final image should feel like a genuine archival artifact preserved from {argument name="year again_en" default="1915"}, precise in typography, layout, ink behavior, and cultural context.

Extract frame and modify expression and weather

others

A prompt pattern for extracting one frame from a multi-frame image and changing the character’s expression and background conditions.

展开提示词全文
Extract frame {argument name="frame number_en" default="2"}, but change her expression to scared and add rain in the background.

Glossy magazine article with full text

others

Generates a photo of a glossy magazine article laid on a desk, containing the entire supplied text with designed typography, photos, and pull quotes.

展开提示词全文
Put this whole text, verbatim, into a photo of a glossy magazine article on a desk, with photos, beautiful typography design, pull quotes, and bold formatting. The text: {argument name="article text_en" default="[...the unformatted article]"}.

Einstein teaching at MIT with Hindi joke text

others

A detailed prompt for a realistic classroom scene of Einstein at an MIT chalkboard, with a playful Devanagari sentence written clearly on the board.

展开提示词全文
A realistic, slightly cinematic scene of Albert Einstein teaching a class at MIT in the early 20th century. Show him at a large chalkboard covered with equations, chalk in hand, mid‑explanation. The classroom has wooden desks, warm natural light from tall windows, and attentive students. On the chalkboard, clearly written in Devanagari, include the sentence: "मैं आपसे रिलेट नहीं कर पा रहा, क्योंकि रिलेटिविटी अभी तक डिस्कवर नहीं हुई है". Capture Einstein’s characteristic hair, suit, and expressive posture. Blend historical accuracy with playful anachronism, maintaining a high‑detail, academic visual style.

Low-angle man with hood scarf and cat on head

others

A cinematic 9:16 portrait prompt of a young man wearing a specific hooded scarf with a Maine Coon cat sitting on top.

展开提示词全文
Ultra-detailed, hyper-realistic, cinematic image, aspect ratio 9:16. A low-angle camera shot, slightly looking upward, capturing a young man (face and hair 100% from a photo reference) wearing an earthy red coat and an olive-yellow knitted hood scarf that clearly wraps around his head and neck unchanged. A bright-furred Maine Coon cat sits on top of the hood, looking toward the light coming from behind. Pose: the man stands upright, turning his head slightly to the side.

Annotate photo with hot-or-not console ratings

others

A prompt to overlay console-style text, pointers, and loading bars over a portrait to rate attractiveness and facial features.

展开提示词全文
Annotate this photo with console-style text and pointers that rate the attractiveness of the person and their facial features, with loading bars across categories, and include an overall rating.

Cartoon-to-realistic transformation

others

A meta-prompt pattern suggesting you first create a cartoon of something, then ask for its realistic version.

展开提示词全文
Create a cartoon of something and then ask for the realistic version of it.

Realistic human skeletal system infographic

others

Generates a realistic infographic showing the human skeletal system with labels, ideal for educational content.

展开提示词全文
Make a realistic infographic of the {argument name="subject_en" default="human skeletal system"} with labels.

Monochrome cinematic portrait of young woman

others

A structured JSON-style prompt describing an ultra-realistic monochrome portrait of a young woman with minimalist background and cinematic lighting.

展开提示词全文
A cinematic, ultra-realistic monochrome portrait of a young woman with expressive eyes and a calm, intense gaze. She has short, dark, neatly styled hair; striking eyes with reflective highlights and a highly expressive look; a fair complexion with subtle freckles and realistic texture; and softly defined, naturally shaped lips. Her expression is calm and intense, with a direct gaze. She wears black clothing with a white textured collar that creates strong contrast. The background is a smooth monochrome gradient, minimalist and drawing focus to her face. Use soft but high-contrast monochrome lighting, with gentle highlights on facial features and subtle shadow depth, creating a cinematic, clean, refined effect. Frame it as a close-up portrait, ultra-realistic and high-resolution with a fine tonal range, sharp focus on the eyes and facial details, and a smooth background gradient. The overall aesthetic is minimalist, artistic, and elegant, with high texture detail, crisp monochrome rendering, and premium realism.

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。