← Back to home
Skill

Ai Image Prompts

tencent_skillhub · 1.0.9 · Downloads 1.8K · Heat 55.6

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License information is collected from official sources and may be outdated or missing.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.

1099 matches

3D Gorilla Emerging from 2D Charcoal Sketch

others

A highly creative, macro-scale prompt for generating an image where a silverback gorilla transitions seamlessly from a 2D charcoal sketch on paper to a hyper-realistic 3D figure at the waistline. The 3D arm is shown drawing the 2D legs, set on a charcoal-dusted industrial desk with dramatic side-lighting.

Show full prompt
{

  "camera": {

    "angle": "high-angle",

    "scale": "macro"

  },

  "environment": {

    "surface": "charcoal-dusted desk",

    "aesthetic": "industrial"

  },

  "subject": {

    "type": "silverback gorilla",

    "composition": "single continuous figure",

    "upper_body": {

      "dimension": "hyper-realistic 3D",

      "style": "hyper-realistic physical form",

      "extent": "upper torso rising vertically from the paper"

    },

    "lower_body": {

      "dimension": "2D",

      "style": "charcoal sketch",

      "extent": "lower body on paper"

    },

    "transition": {

      "location": "waistline",

      "quality": "seamless",

      "alignment": "perfect anatomical alignment between 3D fur and 2D sketch lines"

    },

    "action": {

      "arm": "physical arm",

      "tool": "charcoal pencil",

      "interaction": "drawing the sketched legs"

    }

  },

  "lighting": {

    "style": "dramatic side-lighting"

  }

}

Abstract Expressionist Portrait with Chaotic Color Fields

others

A prompt for transforming an uploaded image into a striking portrait rendered in the style of Abstract Expressionism. It emphasizes explosive, chaotic color fields, heavy impasto texture, and dynamic brushstrokes, using a saturated palette of reds, oranges, and blacks to prioritize movement and energy over realistic form.

Show full prompt
A striking portrait of the subject in the uploaded image rendered in the style of Abstract Expressionism, focusing on explosive, chaotic color fields and heavy impasto texture. Dynamic, raw brushstrokes and paint drips dominate the canvas, utilizing a saturated palette of deep reds, fiery oranges, and contrasting blacks, prioritizing movement and energy over realistic form, against a loosely textured, neutral background.

Construction of the Impossible Prompt: Miniature Engineers

others

A prompt for Gemini Nano Banana Pro to generate an image of a large-scale construction site where tiny engineers or builders are assembling an oversized everyday object piece by piece, focusing on realistic materials and dramatic lighting.

Show full prompt
A large-scale construction site where tiny {argument name="workers" default="ENGINEERS / BUILDERS"} assemble an oversized {argument name="object" default="EVERYDAY OBJECT"} piece by piece. Scattered components, tools scaled correctly, realistic materials, dramatic worksite lighting.

Magical Shadow Illusion Prompt for Nano Banana Pro

others

A creative prompt for Nano Banana Pro focusing on an impossible visual illusion: a single tree on a flat field at sunset where the shadow is darker than normal, but contains soft glowing patches shaped like leaves, suggesting the shadow stores sunlight.

Show full prompt
A single tree on a flat field at sunset. Illusion: the tree’s shadow is darker than normal, but embedded inside it are soft glowing patches shaped like leaves, light inside shadow, impossible. As if the shadow is a container that stores sunlight. The glow patches cast faint light onto grass blades within the shadow only, making micro-caustics. Outside the shadow, no glow exists. The tree itself looks ordinary; only the shadow is magical-physical. Keep the scene extremely simple: horizon, tree, shadow, sky gradient. Photoreal grass detail, dreamy but grounded, “wow” from one impossible rule change.

Neo-Traditional Tattoo Flash Prompt

others

A prompt requesting a highly detailed Neo-Traditional Tattoo Flash interpretation of a subject on a motorcycle, specifying artistic elements like thick black linework, deep primary colors, mechanical internal details, and surrounding motifs like chrome and barbed wire.

Show full prompt
A highly detailed Neo-Traditional Tattoo Flash interpretation of the subject on the motorcycle, featuring thick black linework, deep primary colors (crimson, cyan, jet black), mechanical internal details subtly showing through skin tears, surrounded by stylized chrome and barbed wire motifs, highly detailed shading.

Hyper-Realistic Documentary Photography Style Prompt

others

A detailed, technical prompt designed to be appended to any base prompt in Nano Banana Pro to enforce an extreme level of hyper-realism, mimicking an unedited RAW documentary photograph taken with professional Sony gear, focusing on clinical focus, micro-contrast, and the absence of typical AI 'gloss' or cinematic effects.

Show full prompt
The image is a hyper-realistic documentary photograph captured with a Sony A7R V and a 35mm prime lens, stopped down to f/11 for a deep depth of field where every element from foreground to background is in tack-sharp, clinical focus. The aesthetic is 'unobserved reality' as if the camera is an invisible witness to a spontaneous moment. Lighting is unmediated and situational, capturing the high-dynamic range of the environment exactly as the human eye perceives it, without artificial bounce or flattering diffusion. Surfaces are rendered with extreme micro-contrast, highlighting the tactile physicality and natural imperfections of materials without 'AI gloss' or plastic smoothing. Human skin subtle asymmetries. The composition is unstructured and asymmetrical, avoiding all 'golden ratio' or cinematic framing. No lens flares, no bokeh, no film grain, no post-processing, and no stylistic filters. The final result should be indistinguishable from a high-resolution RAW file of an actual event

Cinematic Realism Portrait Prompt

others

A structured JSON prompt for generating a cinematic realism image of a woman in a pastel bikini by a suburban pool, specifying details like soft lighting, camera lens, and mood, while including a negative prompt to ensure appropriate content.

Show full prompt
{
  "prompt": "Adult woman with girl-next-door beauty, soft facial features, light freckles, medium brown hair, natural curves, pastel bikini, teasing confident pose, suburban pool setting, cinematic realism with soft depth of field",
  "style": "cinematic realism",
  "quality": "ultra",
  "lighting": "soft afternoon light",
  "camera": "50mm lens",
  "mood": "playful, teasing",
  "negative_prompt": "childlike appearance, nudity, explicit sexual detail"
}

Nano Banana Pro Miniature Effect Prompt

others

This prompt describes a process where an uploaded image is processed by Nano Banana Pro (or similar tools like Grock) to apply a miniature effect. The prompt itself is implied to be the instruction to apply the effect to the uploaded image.

Show full prompt
After changing the PRODUCT section to Image upload and attaching the photo to be applied, the miniature effect is applied to that photo.

Fashion Arrangement Prompt for High School Characters

others

A detailed Japanese prompt template for Nano Banana Pro that takes a reference character's clothing and rearranges it into three distinct styles—Gal, Honor Student, and Otaku—while maintaining the original color and context of a Japanese high school setting. This is useful for quickly generating variations for background characters.

Show full prompt
# Settings
[Type of Clothing] = {argument name="clothing type" default="High School Girl Uniform"}
[Worldview] = {argument name="worldview" default="Modern Japan"}

# Absolute Generation Rules
- Absolutely do not depict items that do not exist in the specified [Worldview].
- The characteristics of "Gal," "Honor Student," and "Otaku" should be expressed through items and ways of dressing that fit within that worldview.
- Please arrange the following four characters horizontally in a row, equally spaced, on a white background with a horizontal aspect ratio (16:9). Depict all characters full-body, with natural shadows at their feet.

# Character Composition (Left to Right)

1. **[Normal (Reference)]**
- Attire: Standard and orthodox design of [Type of Clothing].
- Features: Natural smile, protagonist-like presence.

2. **[Gal Style Arrangement (Flashy and Open)]**
- Concept: Loves flashiness, exposure, cutting-edge trends, confidence.
- Clothing Transformation: The **color of the [Type of Clothing] remains the same**. Shorten the length and open the chest within the limits allowed by the [Worldview]. Dress boldly, such as exposing shoulders or rolling up hems.
- Accessories: Frequent use of "flashy accessories" (jewelry, gold work, hair ornaments) available in that world.
- Pose: Open and confident pose.

3. **[Honor Student Style Arrangement (Discipline and Formality)]**
- Concept: Rule-abiding, conservative, intellectual, clean appearance.
- Clothing Transformation: The **color of the [Type of Clothing] remains the same**. Attire close to "formal wear" in the [Worldview]. Minimize skin exposure, perfectly tie buttons and laces. Dress extremely strictly. Collars are tightly closed, with no disarray. Minimal exposure.
- Accessories: "Intellectual items" (books, scrolls, glasses, monocles, insignia) suited to the [Worldview].
- Pose: Straight back, dignified expression.

4. **[Otaku Style Arrangement (Collecting Habit and Immersion)]**
- Concept: Niche hobbies, collecting habit, focus on practicality or indifference.
- Clothing Transformation: The **color of the [Type of Clothing] remains the same**. "Unfashionable" dressing in the [Worldview]. Excessive layering for functionality, or dirty clothing.
- Accessories: Heavily equipped with "hobby items" from the [Worldview] (many amulets, talismans, bottles of magic potions, large bags filled with collected materials). The concept of "Oshi" (favorite) is expressed as an obsession with idols or symbols of that world.
- Pose: Slightly hunched over, engrossed in observing or collecting something. Glasses or goggles.

# Image Specifications
- Background: White background
- Art Style: High-quality anime style

Semi-Realistic Dogfight between Santa and Reindeer Robots

others

A Japanese prompt for Nano Banana Pro to generate a semi-realistic animation style image of a dogfight between two slim robots—a red metallic Santa and a brown metallic reindeer—shot from behind, set on a narrow mountain road with deep sea of clouds.

Show full prompt
A dogfight between two slim robots (a red metallic Santa and a brown metallic reindeer). Shot from behind. The setting is a narrow mountain road and a deep sea of clouds. Semi-realistic animation.

Negative Prompt for Photorealistic Fashion Image

others

This is the negative prompt used alongside the main prompt to ensure the generated image avoids common artifacts and low-quality elements, focusing on achieving a clean, photorealistic, and professional fashion aesthetic.

Show full prompt
low quality, bad quality, sketches, painting, artwork, illustration, cartoon, anime, bad anatomy, bad hands, missing fingers, extra fingers, cropping, blurry, out of frame, distortion, deformity, ugly, watermark, text, signature

Miniature Diorama Prompt (Tilt-Shift)

others

A prompt template for creating a photorealistic miniature diorama image using tilt-shift photography effects, focusing on tiny handcrafted figures, meticulous details, and warm golden-hour lighting.

Show full prompt
A cozy miniature diorama of {argument name="activity" default="[ACTIVITY]"}, tiny handcrafted figures with subtle expressions, meticulously detailed props at 1:87 scale, warm golden-hour lighting casting soft shadows, dust motes visible in light beams, a gentle slice-of-life atmosphere. Tilt-shift photography effect, shallow depth of field, nostalgic and intimate.
Prev 57 / 92 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。

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。

AI Image Prompts · 绘画提示词库

Marked free

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

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,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。

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.