Ai Image Prompts
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
License information is collected from official sources and may be outdated or missing.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.
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.
2105 matches
Selfie of multiple random female celebrities
profile-avatarA simple prompt that asks the model to generate a selfie containing ten random female celebrities, useful for stress-testing face generation and multi-subject composition (though may conflict with platform policies).
Show full prompt
a selfie of 10 random female celebrities
Detailed mirror-selfie otaku room scene
profile-avatarA very detailed Nano Banana prompt describing a female mirror selfie in a blue-toned otaku computer corner, with full specifications for character, environment, lighting, camera, and negative prompts.
Show full prompt
### Scene
Mirror selfie in an otaku-style computer corner, blue color tone.
### Subject
* Gender expression: female
* Age: around 25
* Ethnicity: East Asian
* Body type: slim, with a defined waist; natural body proportions
* Skin tone: light neutral tone
* Hairstyle:
* Length: waist-length hair
* Style: straight with slightly curled ends
* Color: medium brown
* Pose:
* Stance: standing in a slight contrapposto pose
* Right hand: holding a smartphone in front of her face (identity hidden)
* Left arm: naturally hanging down alongside the torso
* Torso: body leaning slightly back; waist and abdomen exposed
* Clothing:
* Top: light blue cropped knit cardigan, top two buttons fastened; a blue French-style bra faintly visible
* Bottom: denim ultra-short shorts, with a blue satin ribbon bow on each side of the hips
* Socks: blue and white horizontal striped over-the-knee socks
* Accessory: a blue cute mascot phone case
### Environment
* Description: bedroom computer corner seen through a wall-mounted mirror
* Furnishings:
* White desk
* Single monitor showing a soft blue wallpaper (no readable text)
* Mechanical keyboard with white keycaps on a blue desk mat
* Mouse on a small blue mouse pad
* PC tower on the right side with blue case lighting
* Three anime figures on or near the PC tower
* A poster of a pagoda on the wall
* Cat-shaped desk lamp with blue accents
* A transparent glass of water
* A tall green leafy plant by the window (on the left side of the frame)
* Color replacement: replace all originally pink elements (clothes and room decor) with blue tones (baby blue to sky blue/periwinkle blue).
### Lighting
* Light source: daylight coming from a large window on the left side of the camera, through sheer curtains
* Light quality: soft, diffused light
* White balance (K): 5200
### Camera
* Mode: smartphone rear camera shooting via the mirror (no portrait/bokeh mode)
* Equivalent focal length (mm): 26
* Distances (m):
* Subject to mirror: 0.6
* Camera to mirror: 0.5
* Exposure:
* Aperture (f): 1.8
* ISO: 100
* Shutter speed (s): 0.01
* Exposure compensation (EV): -0.3
* Focus: focus on the torso and shorts in the mirror image
* Depth of field: natural smartphone deep depth of field; background clearly visible with no artificial blur
* Composition:
* Aspect ratio: 1:1
* Crop: from the top of the head to mid-thigh; include the desk, monitor, PC tower, and plant in the frame
* Angle: slightly high angle from the mirror’s point of view
* Composition note: keep the subject centered; to avoid wide-angle edge distortion, have her stand a bit further away and crop to a square later.
### Negative prompts
* Any appearance of pink/magenta anywhere
* Beauty filters/over-smoothed skin; poreless skin look
* Exaggerated or distorted anatomy
* NSFW, see-through fabrics, wardrobe malfunctions
* Logos, brand names, or readable user interface text
* Fake portrait-mode blur, CGI/illustration feel
Anthropomorphized apple and banana couple
profile-avatarA very short Japanese prompt that asks for a couple made of anthropomorphized apple and banana rather than humans.
Show full prompt
A married couple not as humans, but as an anthropomorphized apple and banana.
Goth makeover variant of existing photo
profile-avatarAn English natural-language prompt used to reimagine a person’s photo as if they were into goth music at the time, letting the model infer what to change.
Show full prompt
Redo this as though this person was into goth music at the time.
Levi’s shopping mirror selfie edit
profile-avatarAn English prompt that edits a person’s photo to look like they are shopping at Levi’s, holding bags and taking a mirror selfie with a specific phone model.
Show full prompt
Make it look like I am shopping at Levi’s holding bags, taking a picture in the store mirror, covering my face with my phone. Make the phone a {argument name="phone_model_en" default="Samsung S25 Plus"}.
ID verification character with visible passport
profile-avatarA prompt for creating a character image where the subject clearly displays their passport to the camera for identity verification, with customizable name, affiliation, and birthday on the ID.
Show full prompt
Make the character in the image hold their passport while sitting in front of a computer, showing the ID clearly to the camera to prove they are a real person. The ID information should be clearly visible, with the name {argument name="name_en" default="[NAME]"}, the affiliation {argument name="affiliation_en" default="[YOUR DATA]"}, and the birthday {argument name="birthday_en" default="[YOUR DATE]"}. All other details can be random and fictional.
Ultra-realistic Roronoa Zoro portrait
profile-avatarA concise prompt for generating a hyper-realistic portrait of the One Piece character Roronoa Zoro.
Show full prompt
Ultra-realistic Roronoa Zoro portrait.
Swimsuit to bikini pose-edit prompt (reply)
profile-avatarA pose-edit and wardrobe-change prompt from the replies, asking to change a one-piece swimsuit to a bikini and add high heels while keeping style and background.
Show full prompt
Change the one-piece swimsuit to a bikini and add high heels while keeping the same style and background.
Cute handwritten notes over a photo
profile-avatarAsks Nano Banana Pro to overlay lots of cute handwritten annotations onto a photo, ideal for playful social posts or decorated snapshots.
Show full prompt
Write as many cute handwritten notes and highlights as possible on the photo!
Edit moon position and change painting style
profile-avatarAn editing prompt that moves the painted moon to the left of a woman and switches the art style to transparent watercolor.
Show full prompt
Move the moon that is painted in the background of the woman to the left side from the viewer’s perspective. Change the painting style to transparent watercolor.
Age progression of a woman into an old lady
profile-avatarA Japanese prompt that transforms the adult woman from the first image into an elderly close-up with older-style clothing and a home background, used for visualizing growth or aging.
Show full prompt
Generate an image of the adult woman from the first picture as an old lady. Make it a close-up. Make her clothing look like that of an older woman, and set the background as a house.
Depth of field shift to focus on man’s face
profile-avatarAn edit prompt that pulls focus onto a man’s face while blurring his hand, great for creating a more dramatic, storytelling portrait look.
Show full prompt
Focus on man's face, blur his hand
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。
架构图一键生成
Marked paidAPI key required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。
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。
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。
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
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.