← 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

Kamen Rider Armor Transformation Sequence Prompt

game-asset

A detailed prompt for generating a dynamic video sequence of a subject inserting a glowing Ridewatch into a Ziku-Driver, triggering a 'mechanical reveal' transformation into armored form, concluding with a combat stance. Designed for video generation tools like Veo 3.1 or Nano Banana 2.

展开提示词全文
Subject inserts a glowing Ridewatch into the Ziku-Driver and spins it 360 degrees. A 'mechanical reveal' begins as white and gold armor plates materialize piece-by-piece, snapping onto the torso, shoulders, and legs with robotic precision. Rapidly rotating golden clock hands and glowing orange pixelated data streams wrap around her body against a giant glowing crescent moon background. The sequence concludes with the helmet visor flashing pink katakana eyes as she shifts into a powerful combat stance, executing a sharp martial arts strike with her white cape flowing majestically.

Custom Architectural Chessboard Diorama Prompt Template

game-asset

A complex, multi-part prompt template for generating hyper-detailed, playable diorama chessboards where the board and pieces are constructed entirely from miniature architectural components (e.g., Cyberpunk Neon City or Gothic Cathedrals). It uses anchors and morphology sections to enforce the structural engineering and material physics of the chosen theme.

展开提示词全文
Anchor:   `[{argument name="board game" default="Chess Set / Backgammon"}] :: [{argument name="architectural theme" default="Cyberpunk Neon City / Gothic Cathedrals"}]::3`
    Morphology:   `Hyper-detailed playable diorama, [Board Game] board and pieces constructed entirely via the assemblage of [Architectural Theme] components, pawns and tiles formed from miniature constituent parts of [Architectural Theme], tabletop structural engineering::3`
    Material Physics:   `Material properties of [Architectural Theme] applied to game pieces, illuminated windows, realistic city textures replacing wood/plastic, perfect grid layout maintained within the chaos::3`
    Illumination:   `Top-down dramatic table lighting, glowing elements from within the [Architectural Theme], deep ambient occlusion in the miniature streets::2`
    Render Stack:   `Tilt-shift tabletop photography, macro lens, f/4, 8k, extreme depth of field, photorealistic miniatures::1`
    Negative:   `[Standard Staunton chess pieces, flat cardboard, people playing, giant hands, messy, disorganized, 2D]:: -1`

PS1 Low-Poly Video Game Background

game-asset

A prompt used with Google Gemini 3.1 Image Generator by Nano Banana Pro to create a background image that looks like a low-poly video game from the PlayStation 1 era.

展开提示词全文
a background that graphic looks like a PlayStation1's low-poly video game

48-Panel Studio Expression Contact Sheet

game-asset

A highly detailed, structured prompt for Nano Banana Pro to generate a 6x8 grid (48 panels) contact sheet. The goal is to maintain the exact identity, framing, and background of an adult male subject while generating 48 distinct facial expressions and minimal hand gestures, ensuring extreme consistency across all panels for a clean editorial portrait style.

展开提示词全文
{
  "generation_request": {
    "meta_data": {
      "tool": "NanoBanana Pro",
      "task_type": "studio_expression_contact_sheet_6x8_clean",
      "language": "en",
      "priority": "highest",
      "version": "v1.0_48_PANEL_FACE_LOCK"
    },
    "input": {
      "mode": "image_to_image",
      "reference_image_usage": "very_high",
      "preserve_identity": true,
      "preserve_facial_features": true,
      "preserve_hairstyle": true,
      "preserve_wardrobe": true,
      "notes": "Create a 6x8 grid (48 panels) studio expression contact sheet. Same adult male identity in every panel. White seamless background. Head-and-shoulders framing locked. Only facial expressions and minimal hand gestures change. No text, no watermark, no logos."
    },
    "output_settings": {
      "aspect_ratio": "4:5",
      "resolution_target": "ultra_high_res",
      "num_images": 1,
      "layout": {
        "type": "grid",
        "rows": 8,
        "cols": 6,
        "gutter": "thin_white",
        "outer_border": "none",
        "panel_consistency": "extreme"
      },
      "sharpness": "studio_crisp",
      "grain": "none",
      "render_style": "clean_editorial_portrait"
    },
    "scene": {
      "environment": "white seamless studio backdrop",
      "lighting": {
        "style": "soft frontal portrait lighting",
        "key_light": "large diffused softbox centered",
        "fill": "balanced fill, minimal shadow",
        "avoid": "dramatic contrast, colored gels, HDR"
      },
      "camera": {
        "lens": "85mm portrait lens",
        "distance": "tight head-and-shoulders crop",
        "focus": "eyes razor sharp",
        "perspective_lock": "strict"
      }
    },
    "subject": {
      "type": "adult male",
      "wardrobe": "simple white shirt",
      "hair": "natural medium-length dark hair",
      "anatomy_rules": "realistic proportions, correct hands and fingers"
    },
    "expression_rule": "Each of the 48 panels must show a different expression: neutral, subtle smile, full smile, laugh, smirk, raised eyebrow, wink, surprise, shock, wide eyes, open mouth, dramatic gasp, side-eye, squint, anger, frown, clenched jaw, puffed cheeks, tongue out, exaggerated grin, mock scream, intense stare, skeptical look, confused look, doubtful smirk, playful cross-eye, big laugh, fake cry, hands on cheeks, fingers around eyes binocular gesture, covering face partially, stretching mouth sideways, chin on fist, overjoyed grin, serious stare, calm look, narrowed eyes, mock frustration, dramatic sigh, exaggerated shock, goofy face, proud smile, sarcastic grin, puzzled tilt, confident smirk, blank expression, relaxed ending pose.",
    "quality_control": {
      "identity_lock": "maximum",
      "background_lock": "maximum",
      "crop_lock": "maximum",
      "avoid": [
        "face distortion",
        "eye misalignment",
        "extra fingers",
        "missing fingers",
        "warped anatomy",
        "h"
    ]
  }
}

Sabrina Carpenter Hyper-Realistic Portrait Prompt

game-asset

An extremely detailed, structured JSON prompt for generating a hyper-realistic portrait of Sabrina Carpenter. It meticulously specifies biometric details, body morphology, wardrobe (ribbed cotton bodysuit, rabbit ears), pose, and scene physics, including subsurface scattering and high-density fiber simulations for the sofa.

展开提示词全文
{
  "subject": {
    "identity": {
      "biometric_reference": "{argument name="subject name" default="Sabrina Carpenter"}",
      "facial_morphology": "Heart-shaped visage, defined zygomatic arches with an approximate 15-degree elevation, petite nasal bridge with a slightly upturned apex, and a distinct cupid's bow philtrum.",
      "dentition": "Natural maxillary central incisors with anatomical symmetry, visible during a neutral or closed-mouth expression as per cranial structure.",
      "ocular_physics": {
        "iris_pattern": "Highly detailed cerulean blue iris with distinct radiating stroma and a dark pupillary ring.",
        "sclera_clarity": "High-vascularity detail, photorealistic moisture levels."
      }
    },
    "body": {
      "somatotype": "Petite mesomorph with high muscle definition in the lower extremities.",
      "height_cm": 152,
      "morphology": "Hourglass silhouette with a biological waist-to-hip ratio of approximately 0.70. Natural skin texture with visible micro-pores and subtle epidermal variations.",
      "skin_tone": {
        "hex": "#F5E1D2",
        "physics": "Subsurface scattering (SSS) with realistic light absorption and reflectance on the dermis."
      },
      "hair": {
        "color_hex": "#E3C58B",
        "texture": "Voluminous, long blonde waves with realistic follicular density and specular highlights on individual strands."
      }
    },
    "wardrobe": {
      "primary": {
        "type": "Ribbed cotton bodysuit",
        "color_hex": "#FFFFFF",
        "material_physics": "Micro-weave texture, elastic tension pulling at the seams, realistic fabric folds."
      },
      "secondary": {
        "type": "High-denier opaque tights",
        "color_hex": "#FFFFFF",
        "opacity": "90%",
        "texture": "Matte nylon finish with subtle sheen on curved surfaces."
      },
      "accessory": {
        "type": "Plush rabbit ear headband",
        "material": "Faux fur and satin interior, white with pale pink inner lining (#F8D7DA)."
      }
    },
    "pose_action": {
      "description": "Reclining laterally on a sofa, weight distributed on the left hip and forearm. The right leg is elevated at a 45-degree angle with the foot pointed in plantar flexion. The left leg remains bent at the knee, resting naturally on the seat cushion.",
      "gaze": "Candid, looking slightly downward and away from the lens.",
      "hand_placement": "Natural finger curvature resting on the abdominal region, displaying anatomical knuckle detail and nail bed realism."
    },
    "scene": {
      "furniture": {
        "type": "Oversized faux-fur sofa",
        "color_hex": "#F4C2C2",
        "physics": "High-density fiber simulations, individual fur strands reacting to the subject's weight via compression physics."
      },
      "background": {
        "type": "Solid studio backdrop with embedded neon sign",
        "color_hex": "#D38B8E",
        "finish": "Matte, seaml"
      }
    }
  }
}

Ornate Box Diorama Master Prompt (Mughal Hall Interior)

game-asset

A complex, structured master prompt for generating an ultra-realistic miniature diorama inside an ornate box, using an auto-theming system. The box itself forms the architecture of a Marble Mughal Hall Interior, detailing structural integration, material style, lighting, and miniature realism.

展开提示词全文
Scene:
ORNATE BOX DIORAMA — AUTO-THEME MASTER PROMPT
========================
SMART VARIABLE GUIDE
THEME_LOCATION = {argument name="theme location" default="Marble Mughal Hall Interior"}
AUTO RULES:
• If THEME_LOCATION is filled → automatically infer:
PRIMARY_ACTIVITY
STAIR_TYPE
CEILING_DETAILS
THEME_MATERIAL_STYLE 
PROP_LIST
THEME_LIGHT_SOURCE
BASE_MATERIAL_COLOR
THEME_PALETTE
FOCAL_SUBJECT
All inferred values must be logically consistent with THEME_LOCATION.
• If THEME_LOCATION is blank → first invent a visually rich miniature environment theme, assign it to THEME_LOCATION, then automatically infer all other variables from it.
• Always prioritize strong environmental storytelling, believable materials, and handcrafted miniature realism when inferring values.
========================
SUBJECT:
A two-level miniature THEME_LOCATION where the ornate open box itself forms the architecture, the base container acting as the full ground floor chamber with the box walls serving directly as the structural walls. The sides of the box must contain functional doors and windows, with the front-facing side featuring a wide open doorway and visible windows. No side of the box may be removed, cut away, or missing. The box height:width:length ratio is 1:4:7 (the width four times the height). The scene features PRIMARY_ACTIVITY actively interacting with the environment. The structure must be fully integrated into the box material itself — not a room inserted inside, not a display frame, not a cutaway model. The ground floor must be constructed from the same material as the box exterior.
ENVIRONMENT:
The base of the ornate box forms the ground floor surface and foundation. Its interior sides transform into the architectural walls containing carved doorways and window openings seamlessly cut into the box sides and aligned with exterior ornamentation. A mezzanine or upper level is built above with structural elements attached directly to the box walls and connected via STAIR_TYPE. The inside of the open lid functions as the vaulted ceiling decorated with CEILING_DETAILS.
DETAILS:
Intricately carved ornate box styled according to THEME_MATERIAL_STYLE. Exterior ornamentation must continue logically into interior architecture. Doors and windows must be precisely cut into the box sides following decorative carving patterns. Include believable miniature structural joins where beams meet the container walls. Include ultra-fine theme-specific props such as PROP_LIST. Include floating dust, micro-surface wear, tactile handcrafted realism, and environmental storytelling details.
STYLE:
Ultra-realistic cinematic miniature diorama photography, museum-grade handcrafted realism, extreme macro detail, physically believable materials, strong architectural style integration of container and structure.
LIGHTING:
Primary lighting motivated by THEME_LIGHT_SOURCE combined with subtle environmental secondary lighting entering through box windows

Final Fantasy transformation prompt (Nano Banana Pro)

game-asset

An image generation attempt using Nano Banana Pro (Gemini 3 Pro Image). The prompt instructs the AI to transform the user (referred to as 'I') into the Great Sorceress Barbara from Final Fantasy, positioned in the bottom right, looking up and to the left, with a background of space and many shining shooting stars, battling Griever.

展开提示词全文
Final Fantasy
Place the person (I) in the bottom right of the screen, facing diagonally up and to the left
Transform into the Great Sorceress Barbara
Background is space, many shining shooting stars
VS Griever

Final Fantasy transformation prompt (Nano Banana Pro)

game-asset

An image generation attempt using Nano Banana Pro (Gemini 3 Pro Image). The prompt instructs the AI to transform the user (referred to as 'I') into the Great Sorceress Barbara from Final Fantasy, positioned in the bottom right, looking up and to the left, with a background of space and many shining shooting stars, battling Griever. (Duplicate prompt of 2027718880488264322)

展开提示词全文
Final Fantasy
Place the person (I) in the bottom right of the screen, facing diagonally up and to the left
Transform into the Great Sorceress Barbara
Background is space, many shining shooting stars
VS Griever

Generating Pokémon Zukan (Illustrated Guide) Style Art

game-asset

The user generated Pokémon Zukan-style illustrations of their characters using Nano Banana (not Pro) to celebrate Pokémon's 30th anniversary. The prompt is shared in the ALT text.

展开提示词全文
Referencing this character, generate a Pokémon Zukan-style illustration. The Zukan No. is {argument name="Zukan Number" default="[Enter Zukan No.]"}. The background is white. The Zukan description text is {argument name="Description Text" default="[Enter description text]"}. Reproduce the Zukan layout and design.

Pokémon Overworld Screenshot Generation

game-asset

A prompt for Nano Banana 2 instructing it to create a screenshot of a game's overworld in a specific area, featuring one Pokémon following the player, while matching the vibe of a provided reference image.

展开提示词全文
create a screenshot of the overworld for this game in the same area, with one pokemon following the player, fit the vibe of the reference

Creating LINE Stickers with Nano Banana 2

game-asset

A prompt template for generating a set of 16 LINE stickers using Nano Banana 2, emphasizing cute deformation, variety in poses and text, and suitability for high school girl daily conversations.

展开提示词全文
Referencing this character, create a cute deformation. Design 16 types of LINE stickers. Ensure a rich variety of sets by devising poses and text placements so that there are no similar stickers. The dialogue should be in Japanese with pop-style characters. The background should be white. Create a set that is easy to use in the daily conversations of a "{argument name="target" default="high school girl"}".

Monster Hunter Alatreon Battle Scene

game-asset

A prompt used with Nano Banana Pro to generate an image of the Monster Hunter creature Alatreon in a scorching background, being attacked by ballista fire.

展开提示词全文
Background: Scorching heat
Monster Hunter
Alatreon etc

Alatreon

Illustration of repeatedly firing ballista shots

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。