← Back to home
Skill

Ai Image Prompts

tencent_skillhub · 1.0.9 · Downloads 2.1K · Heat 56.5

Introduction

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。

Resource Information

Author:dophinl
Category:Multimedia
Version:1.0.9
Auth: No auth
Pricing: Not specified

License information is collected from official sources and may be outdated or missing. Refer to the LICENSE file in the original repository before commercial use.

Tags
图片生成

Prompt Library · 22.8K

Source: community prompt library (MIT, synced daily)

15141 distinct prompts across 11 use cases; one prompt may serve several, so category counts add up to more than the deduplicated total.

5717 matches

Japanese gyaru magazine spread on school uniforms

product-marketing

A prompt to generate a Japanese gyaru-style magazine feature page focusing on school uniform styling.

Show full prompt
A Japanese gyaru magazine feature page about styling school uniforms.

Paint scheme comparison image

product-marketing

A Japanese prompt that asks Nano Banana Pro to generate a single image containing multiple paint simulation patterns for easy comparison.

Show full prompt
So that I can do a paint simulation, make a single image that lets me compare several different patterns.

Hand-drawn style header image prompt from photo

product-marketing

Prompt for a hand-drawn style header image of a person introducing Nano Banana Pro

Show full prompt
Completely recreate the uploaded person.
Make it a header image for a note article where that person introduces “Nano Banana Pro”.
Aspect ratio: horizontal 16:9.
Style and colors: simple, hand-drawn style, italic, with a blue and green gradient.
Title text: “In-depth explanation of Google’s new AI ‘Nano Banana Pro’”.

Shoe pattern pieces layout

product-marketing

An English prompt to create an image of all individual shoe pattern pieces separated and laid out on a neutral background.

Show full prompt
Create an image showing the individual pattern pieces of this shoe, each separated and placed on a neutral background.

Photorealistic naan bread pun image

product-marketing

A Japanese prompt that generates a 1:1 photorealistic close-up of freshly baked naan with a pun text seared into it and curry on the side.

Show full prompt
A 1:1 aspect ratio photorealistic close‑up image of freshly baked naan. On the surface of the fluffy, puffed‑up naan, the words "{argument name="message_en" default="You can do naan-thing"}" appear in char marks. A bowl of curry is placed beside it.

Recipe breakdown and food photoshoot

product-marketing

An English prompt that analyzes a dish image to produce a detailed recipe with ingredients, while making the output look like a professional photo shoot.

Show full prompt
Make a detailed recipe for this dish with all the ingredient names and their raw ingredients. Make it look like a real photo shoot.

Cinematic 3D logo with auto-assigned texture

product-marketing

A prompt for generating a cinematic 3D logo where the AI chooses a realistic texture based on the brand style, with dramatic lighting and a product-ad feel.

Show full prompt
Create a cinematic 3D logo for {argument name="brand_en" default="[BRAND]"}.
Automatically assign a realistic texture (glass, fire, neon, chrome, liquid, ice, lava, wood, or cloud) based on the brand style.
Use dramatic lighting, depth of field, and a soft glowing background.
Style: product ad / reveal shot, cinematic tone, ultra HD.

High-angle fairy grunge idol in cluttered closet

product-marketing

A long, highly detailed image-generation specification describing a high-angle shot of an East Asian idol lying upside down in a cluttered closet, with fairy grunge styling, tattoos, and specific wardrobe and environment details. Best used when working with a reference pose image.

Show full prompt
High-angle bird's-eye view shot of a female East Asian idol subject lying on the floor of a cluttered closet, strictly following the upside-down pose and anatomical structure shown in {argument name="reference_image_en" default="image_0.png"}. She is wearing a rich blue lace-overlay mini dress with a milkmaid bodice, sweetheart neckline, cap sleeves, and a lettuce hem. She wears heavy, knee-high red leather boots with a vertical front seam. Visible tattoos include a barbed wire band on the thigh and small stick-and-poke heart and key motifs on the chest. The floor is covered in piles of mixed textiles, tulle, and clothing. The background walls are painted yellow, featuring white wire shelving, semi-transparent plastic storage drawers, and a packed clothing rack. Lighting is overhead tungsten, creating a warm sepia, vintage 90s disposable camera filter look. The mood is exhausted, messy, and romantically grunge.

Fairy grunge aesthetic, girl in a rich blue dress and red leather boots lying upside down in a cluttered closet with yellow walls, pose from {argument name="reference_image_short_en" default="image_0.png"}, sepia tone, high-angle shot.

Negative prompt: minimalism, clean floor, bright daylight, cold lighting, organized, empty space, modern furniture, neon colors, HD digital look, glossy finish, wide angle, fisheye, distorted limbs, missing tattoos, incorrect pose.

Turn a social bio into a NES cartridge cover

product-marketing

A prompt that analyzes your social media bio and turns it into a NES game cartridge close-up, styled like a product photo with a teenager’s room in the background and your name on the label.

Show full prompt
Analyze my bio and come up with a video game that would represent me if I were a video game. Create a NES cartridge close-up with a blurred background, showing a teenager's room behind it. Make it look like a product photo, and make sure to include my name.

Squatty Potty whiteboard instructions

product-marketing

A humorous instructional prompt to create a detailed whiteboard-style illustration explaining how to properly use a Squatty Potty.

Show full prompt
A detailed whiteboard illustration and instructions on how to properly use the Squatty Potty.

Grid of four camera angles from reference image

product-marketing

A prompt to create a grid of four different camera angles of a reference image, matching its style and color palette while keeping each shot unique.

Show full prompt
Create a grid of four different camera angles of {argument name="reference_en" default="your reference image"}, with {argument name="camera_angle_en" default="your chosen camera angles"}, that follow the same style and color palette as {argument name="reference_repeat_en" default="the reference image"}. Make the new shots unique.

Clothing separated on the bed

product-marketing

An edit-style prompt that takes a reference person and lays out each piece of her clothing separately on a bed.

Show full prompt
Lay out each piece of her clothing separately on the bed.
Prev 474 / 477 Next

Prompts are model-agnostic and work with Midjourney / DALL-E / Flux / Stable Diffusion.

Information boundary

Information on this page is collected from official documents for technical presentation only and does not imply our endorsement. Pricing, quotas and availability are subject to the latest official statements. We make no commitment regarding any action you take after leaving this site.

Similar skills

视频短视频图片音乐音频配音口播数字人全能创作

Marked paid

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

Marked paid

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

Not specified

【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。

自动化克隆数字人口播混剪视频

FreemiumAPI key required

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

海报设计工作室

FreemiumAPI key required

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。

MiniMax H3 AI视频创作

Not specified

用 MiniMax H3 这款 AI视频生成器创作高质感 2K AI 视频。从文字创意出发完成文生视频,让静态图片自然动起来,用首尾画面做首尾帧视频的完整转场,也可以结合图片、视频和音频参考,以多模态视频生成塑造统一场景。适合 AI 广告视频、电商产品视频、品牌宣传视频、动态海报、游戏 UI、电影片头和社交短视频创作,形成电影感画面与同步的原生立体声。使用 Beatra 账号即可开始,创作进度与成片集中管理。

What is a Skill

A Skill is a packaged single capability, such as text recognition, document summarization, or keyword extraction. Developers wrap the calling logic and prompts into a plugin-like unit, so users can load it without understanding the underlying model. StackPilot indexes a large number of skills that can be tried instantly or assembled into a plan.