← 返回首页
技能

Ai Image Prompts

tencent_skillhub · 1.0.9 · 下载量 1,827 · 热度分 55.6

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 725 条

Disintegration Effect Function Prompt

game-asset

A fun, highly technical prompt designed as a Python function to apply a specific disintegration effect to an uploaded image, preserving the original pose. The function defines the direction, speed, and particle type of the disintegration, resulting in a dynamic, particle-cloud effect.

展开提示词全文
``python def disintegrate(Subject): Direction = "{argument name="disintegration direction" default="Left to Right"}" Wind_Speed = "{argument name="wind speed" default="100 km/h"}" Particle_Type = "{argument name="particle type" default="Black Volcanic Ash and Embers"}" >Execution Left_Side_of_Subject = "Solid, Intact" Center_of_Subject = "Cracking, glowing cracks" Right_Side_of_Subject = "Fully dispersed into particle cloud" return Render(Motion_Blur=True, Glow=True) ```  Instruction:  Preserve the exact pose of [UPLOADED_IMAGE], but apply the `disintegrate()` function described above.

Vast Open-World Game Environment Generator

game-asset

A template prompt designed to generate expansive, cinematic fantasy game environment illustrations based on a single conceptual theme. It specifies a distant, environment-focused camera, monumental sky features, and constraints to ensure the scene feels like an uninhabited, high-budget open-world vista.

展开提示词全文
[THEME] = "{argument name="theme" default="Enter a theme here"}" 

Make a wide cinematic fantasy game environment illustration inspired by [THEME].
Use a distant environment-focused camera with an expansive sense of scale and exploration.
Set the scene as a vast open world shaped entirely by the logic, atmosphere and materials implied by [THEME].
Show a monumental sky feature or celestial presence that visually defines the world and reinforces the theme.
Let the terrain, colors, surface forms and horizon geometry emerge naturally from [THEME] without explicit constraints.
Keep the environment uninhabited with no characters, creatures, vehicles or structures.
Use soft, immersive lighting appropriate to the world, favoring mood and scale over realism.
Apply game-style atmospheric perspective to suggest depth, distance and exploration.
Compose the scene to feel like a high-budget open-world game vista rather than a photograph.
Ensure the final image feels serene, epic and discovery-driven, clearly readable as a game world shaped by [THEME].

Hyper-realistic Action Video Generation from Image Reference

game-asset

This complex prompt is designed for video generation using Google Veo 3.1 and Nano Banana Pro, instructing the AI to create a hyper-realistic action sequence based on an uploaded image reference. The video features a monster charging and striking a Monster Energy can with an axe, with strict constraints on camera movement and scene setup.

展开提示词全文
Create a hyper-realistic action video using the uploaded image as the exact visual reference.

SCENE SETUP:
A Monster Energy can stands perfectly upright at the center of the frame.
The environment stays dark, green, and fog-filled as in the reference image.
A large humanoid monster is visible in the background, partially obscured by green fog.

CAMERA:
Camera is completely locked.
Same angle throughout the entire video.
No zoom.
No pan.
No rotation.
No camera shake.

ACTION SEQUENCE:
➟ The video starts with stillness.
   The can does not move.
   The monster is visible but stationary in the background.

➟ The monster suddenly charges forward at full speed toward the can.
   Running motion is aggressive, fast, and direct.
   No slow motion at any point.
   No pauses.

➟ The monster holds a heavy axe with both hands while running.
   The axe is raised as it approaches the can.

➟ The monster strikes the can with full force using the axe.
   The impact is violent and instantaneous.

3D Pixar-Style Sticker Pack Generation from Reference Image

game-asset

A comprehensive prompt, provided in both English and Japanese, designed to generate a collage of over 20 distinct sticker-style illustrations of a female character based on an uploaded reference image. The prompt specifies a 3D Pixar/Disney art style, soft cinematic lighting, pastel colors, and detailed character features (lightly permed black hair, beige cardigan). It requires a variety of expressions and reactions, all arranged in a single, high-resolution collage with white borders and soft shadows, ideal for creating sticker packs for social media.

展开提示词全文
Please use the attached reference image as the base character.
Create a single high-resolution collage containing at least 20 cute sticker-style illustrations of the same female character. Ensure the face, skin tone, hairstyle, and overall appearance perfectly match the reference image.
Art Style: {argument name="art style" default="3D Pixar-style / Disney-style cartoon"}, soft cinematic lighting, smooth pastel colors, large expressive eyes, rounded cute facial proportions, ultra-detailed 3D rendering.
Character Details:
– Lightly permed black hair
– Large expressive eyes
– Beige cardigan
– Cute, slightly chubby proportions
Expressions and Reactions (all distinct):
Happy smile, surprised, shocked, shy smile, angry, confused, crying, sleepy, winking, peace sign, blowing a kiss, holding a cell phone, thinking, covering face, holding coffee, covering mouth while laughing, annoyed, excited, affectionate expression, cute neutral pose (over 20 total).
Sticker Design:
– Each reaction as a separate sticker
– Clean white border on all stickers
– Soft drop shadow
– No text, no watermark
Layout:
– All stickers neatly arranged in one collage
– Balanced grid layout
– Soft beige/pastel-toned background
– Instagram/WhatsApp-style sticker pack design
Quality:
Ultra-high definition, high resolution, smooth 3D finish, professional-grade sticker pack style, lovingly expressive.

Transformative Photo Enhancement Prompt

game-asset

A prompt instructing the AI to transform an original photo into four distinct, dramatic, photorealistic styles, each featuring a mid-close-up, wide-angle shot with extreme camera angles, complex poses, cinematic lighting, and high contrast, while maintaining the original environment.

展开提示词全文
Transform the original photo into a dramatic, photorealistic, ultra-detailed set of 4 styles characters are included , each a mid close up wide-angle shot with an extreme, dynamic camera angle complex, powerful pose in a consistent, expanded version of the original environment, with cinematic lighting, high contrast, crisp textures, and precise color grading.

Vintage Black and White RPG Rulebook Illustration

game-asset

A prompt to generate an illustration in the style of a vintage black and white RPG rulebook from the 1970s. It focuses on a character study in combat attire, using line art with hatching techniques to achieve an intricate, classic D&D aesthetic.

展开提示词全文
Vintage black and white RPG rulebook illustration style. Character study in combat attire, fantasy archetype art. Line art with hatching technique, 1970s D&D aesthetic, intricate detail.

RPG Game Asset Sheet for Monsters

game-asset

A prompt for generating a structured game asset sheet for a fantasy RPG. It requires a grid layout showing various monsters, each with a unique design, color-coded by difficulty, and listing item drops, all rendered in a high-quality game art style.

展开提示词全文
Make a game asset sheet for an RPG fantasy game with monsters, with different levels and item drops. Grid layout, each monster with unique design, color-coded by difficulty. High-quality game art style.

Hyperrealistic D&D Female Fire Mage

game-asset

A prompt for generating a hyperrealistic digital painting of a female fantasy RPG wizard casting a volatile fire spell. It specifies cinematic chiaroscuro lighting, a brilliant orange fireball illuminating her features, and a blend of realistic anime aesthetic with D&D fantasy styling in 8K resolution.

展开提示词全文
A hyperrealistic, ultra-detailed digital painting of a beautiful blonde female fantasy RPG wizard, casting a volatile magical spell, a brilliant orange fireball effect intensely illuminating her features. Volumetric, cinematic chiaroscuro lighting. Realistic anime aesthetic meets D&D fantasy styling. 8K resolution.

3D Pirate Character in T-Pose for Modeling

game-asset

A prompt designed to generate a whimsical, cartoonish 3D pirate character in a perfect T-pose, suitable for 3D modeling assets. It emphasizes oversized features, clay textures, vibrant colors, clean cel-shading, and bright, even lighting on a plain white background.

展开提示词全文
A whimsical, cartoonish 3D pirate character designed for 3D modeling. The character is in a perfect T-pose with arms extended horizontally and feet slightly apart. The pirate has oversized stylized features, a large crooked hat, and a wooden peg leg. High-fidelity 3D render style with soft clay textures, vibrant colors, and clean cel-shading. The lighting is bright and even to show all details. Full body shot, centered, on a solid plain white background

Image Style Transfer Prompt: Viking to Dragon Quest X 'Sage's Breath of God'

game-asset

A prompt for Nano Banana Pro (Gemini 3 Pro Image) instructing it to take an input image (of the comedy duo Viking) and transform the right side of the image into the style of the Dragon Quest X Sage's ability, 'Breath of God.' The user noted this attempt was a failure, possibly due to misinterpretation of the reference image.

展开提示词全文
Take this image (photo of Viking) and make the right side look like the Dragon Quest X Sage's 'Breath of God'!

Image Style Transfer Prompt: Viking to Dragon Quest X 'Chamber of Vows'

game-asset

A prompt for Nano Banana Pro (Gemini 3 Pro Image) instructing it to take an input image (of the comedy duo Viking) and transform the right side of the image into the style of the 'Chamber of Vows' from Dragon Quest X. The user noted this attempt was a failure.

展开提示词全文
Take this image (photo of Viking) and make the right side look like the 'Chamber of Vows' from Dragon Quest X!

Voluptuous Harley Quinn Cosplay Portrait Prompt

game-asset

A detailed prompt for generating a photorealistic, full-body portrait of a voluptuous woman resembling Sadie Sink in a detailed Harley Quinn cosplay (Suicide Squad style). The prompt is highly specific about anatomy, outfit details, the chaotic apartment environment, and includes a strong negative prompt to prevent aesthetic alterations like slimming or plastic skin.

展开提示词全文
{
  "subject": {
    "desc": "Realistic Voluptuous hourglass {argument name="subject name" default="Sadie Sink"} in detailed Harley Quinn cosplay, long blonde hair in high pigtails with pink and blue dyed tips, fair natural skin texture, dramatic Harley makeup with pale foundation, black eye mask smudges, red lipstick, and heart cheek tattoo",
    "outfit": "Classic Suicide Squad Harley Quinn cosplay: cropped white 'Lil Monster' t-shirt, tiny red and black sequined hot pants with belt, black fishnet stockings, red and blue mismatched wrist cuffs, 'Puddin' choker, layered necklaces, and mismatched red/blue boots optional but visible",
    "anatomy": "Preserve full heavy projecting bust, wide curvy hips, thick natural thighs, no reduction/normalization of curves or volume"
  },
  "pose": {
    "desc": "Full-body standing, one hand raised playfully touching a pigtail and the other resting on hip or holding baseball bat loosely, elbows flared, slight spine arch with playful tilt",
    "stance": "Weight on left leg (viewer's right), right leg bent forward with heel down",
    "head": "Slight tilt to her right, direct mischievous confident gaze at camera with signature Harley grin",
    "orientation": "Front-facing, slightly angled to viewer's left"
  },
  "environment": {
    "setting": "Harley Quinn's chaotic apartment room from Suicide Squad movie, colorful graffiti-covered walls, scattered weapons (baseball bat, mallet), neon signs, hanging Joker cards, messy bed with pink sheets, scattered clothing and toys",
    "ground": "Cluttered hardwood floor with scattered items like playing cards, confetti, and small props around her feet"
  },
  "camera": {
    "shot": "Full-body vertical portrait",
    "angle": "Eye-level to slightly low",
    "lens": "35-50mm standard, no wide distortion",
    "framing": "Subject centered"
  },
  "lighting": "Warm chaotic indoor lighting with colorful neon glows from signs, pink and purple accents, soft overhead light with playful shadows",
  "mood": "Mischievous alluring playful, signature Harley grin with tongue out or slight smile, intense engaging gaze",
  "style": "Photorealistic high-fidelity photo, sharp details on fabric/skin/hair/room clutter",
  "colors": "Vibrant red/blue/pink/black cosplay against chaotic colorful room with graffiti and neon, fair warm skin, cinematic balance",
  "quality": "High resolution, sharp subject focus, visible fabric sequins/skin pores/hair strands/room details",
  "aspect_ratio": "3:4 portrait",
  "negative_prompt": "anime, draw, small/reduced bust, flattened breasts, lifted breasts, slimmed torso/hips, proportion averaging, beautification, skin smoothing, plastic skin, stylization, depth flattening, wide distortion"
}

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。

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。

架构图一键生成

官方标注收费需申请 Key

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。

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

架构图一键生成

官方标注收费需申请 Key

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。

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。