← 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

Selfie to Miniature Isometric Figurine Prompt (Simplified)

game-asset

A simplified, versatile prompt template for Nano Banana Pro designed to transform an uploaded selfie into a miniature, full-body, isometric, realistic figurine of the person. It allows customization of the figurine's attire and action.

展开提示词全文
Make a miniature, full-body, isometric, realistic figurine of this person, wearing {argument name="attire" default="ABC"}, doing {argument name="action" default="XYZ"}, on a white background, minimal, 4K resolution.

Selfie to Isometric Figurine Prompt Template

game-asset

A simple, versatile prompt template for Nano Banana Pro designed to transform an uploaded selfie into a miniature, full-body, isometric, realistic figurine of the person. It allows customization of the figurine's attire and action.

展开提示词全文
Design a highly realistic, miniature full-body isometric figurine of this person, wearing {argument name="attire" default="ABC"} and performing {argument name="action" default="XYZ"}, placed on a clean white minimal background, rendered in ultra-sharp 4K quality.

Miniature Isometric Figurine Prompt for nano banana pro

game-asset

A prompt template designed to generate a realistic, full-body, isometric miniature figurine image of a person, based on an uploaded selfie. The prompt allows customization of the figure's clothing and actions, set against a minimal white background.

展开提示词全文
Make a miniature, full-body, isometric, realistic figurine of this person, wearing {argument name="clothing description" default="ABC"}, doing {argument name="action description" default="XYZ"}, on a white background, minimal, 4K resolution

Epic 3D Architectural Blueprint Construction Scene

game-asset

A highly creative prompt for generating an epic 3D scene where an architectural blueprint dynamically rises off the drafting table and transforms into a fully realized, massive building. It emphasizes extreme scale contrast, photorealism, and coexisting construction phases.

展开提示词全文
Epic 3D scene: a massive architectural blueprint of [Name] pinned to a drafting table, its ink lines rising off the paper into fully realized construction. Blue lines become steel beams mid-weld, floor plans inflate into furnished rooms, elevation drawings push outward into facades with working windows. Construction phases coexist simultaneously: foundation being poured in one corner while the penthouse is already inhabited in another. Tiny workers, cranes, and scaffolding swarm the rising structure. The flat drawing and the living building merge at impossible angles. Technical annotations float as dimensional signage. Architect's coffee cup sits at the edge, casting shadow across unbuilt sections. Extreme scale contrast, construction dust catching afternoon light, 8K, photorealistic.

3D Paper Quilling Art: Samurai Warrior

game-asset

A highly specific, structured prompt for generating an image in the style of 3D paper quilling art (paper filigree). It details the subject (Samurai Warrior in O-Yoroi armor), the construction materials (coiled paper circles, sleek paper strips), dynamic pose (Hasso-no-kamae stance), and technical camera settings (100mm Macro lens, f/11 aperture) to emphasize tactile texture and depth.

展开提示词全文
"art_style_description": {
      "type": "3D Paper Quilling Art / Paper Filigree.",
      "technique": "Intricate strips of colored paper rolled, shaped, and glued together to create a decorative design. High tactile texture, volumetric depth, and layered relief.",
      "visual_aesthetic": "Handcrafted, meticulous, vibrant, clean edges, physical render simulation."
    },
    "subject_details": {
      "character": "Samurai Warrior.",
      "apparel": {
        "armor": "Full O-Yoroi armor constructed from tightly coiled paper circles and wavy paper strips. The shoulder guards (sode) and chest plate feature intricate looping patterns.",
        "helmet": "Ornate Kabuto helmet with gold paper accents and a crescent moon crest.",
        "weapon": "A long katana sword held over the shoulder, blade made of a single sleek strip of silver/white paper."
      },
      "surrounding_elements": "Swirling clouds of smoke and wind represented by flowing, ribbon-like strips of paper in teal, orange, and cream. Small square tiles (resembling dice or mahjong tiles) scattering in the air."
    },
    "exact_pose_anatomical": {
      "stance": "Dynamic action pose. The samurai is twisting the torso, preparing to strike or in the middle of a motion.",
      "arms": "Both hands gripping the katana handle, raised near the right ear (Hasso-no-kamae stance).",
      "flow": "The composition follows a diagonal S-curve flow, with ribbons and armor plating creating a sense of movement from top right to bottom left."
    },
    "colors_and_materials": {
      "palette": "Traditional Japanese color scheme: Deep Crimson Red, Teal/Turquoise, Cream/Off-White, and Metallic Gold accents.",
      "material_properties": "Matte paper texture with visible paper grain. Subtle shadows between the paper strips indicating physical depth."
    },
    "camera_technical_values": {
      "viewpoint": "Top-down Flat Lay (with 3D depth perception).",
      "lens": "100mm Macro Lens (To capture the minute details of the paper coils without distortion).",
      "aperture": "f/11 (Deep depth of field to keep all layers of the paper craft in focus).",
      "shutter_speed": "N/A (Static Subject).",
      "lighting": "Soft Studio Lighting (Global Illumination). Even light from above to cast soft, ambient shadows inside the paper coils, enhancing the 3D effect.",
      "resolution": "8k, hyper-detailed."
    }

}

Pixel Art Animal Grid for APNG

game-asset

A simple prompt for Nano Banana Pro aimed at generating a 4x4 grid of cute, colorful, pixel-art style animals on a white background. This is intended as a base for creating APNG animations.

展开提示词全文
Cute, colorful animals in a pixel art style, arranged in a 4x4 grid.
White background.

Plastic Model Kit Generation Prompt

game-asset

A detailed template prompt for Nano Banana Pro to generate an image of a plastic model kit (plamo) based on a specified character, including the runner frame, a completed figure, and a package box with specific branding ('Banana Model') and technical details, designed for a photorealistic hobby product photo style.

展开提示词全文
[Character Setting Section]
1. Character Appearance Details:
(Enter the characteristics of the original character here. Example: A magical girl with long blonde hair and a blue dress)
{argument name="character details" default="Brown hair, short twin tails, red eyes, slightly pointed teeth (giza teeth)."}

2. Text to Display on the Package:
(Enter the title you want written on the box in English or Roman letters here. Example: MAGIC GIRL)
{argument name="package title" default="Tsunochyan Assembly Kit"}

[Fixed Section]
Image Style:
Vivid, photorealistic product introduction photo for hobby products. Horizontal (16:9).

Main Subject (Hand):
In the center foreground of the image, a human hand is holding up the plastic model 'runner (frame)' toward the camera.

Important Shape Instruction: The parts on the runner are **deformed into a cute mini-character (SD style/chibi character) with two heads high** based on the specified "Character Appearance Details". The head part is large and rounded. **Only one head part** is placed. Do not show multiple face parts or spare heads. That single head part is large and clearly represents the character's features.

Important Color Instruction: The runner parts are not monochromatic gray, but are **"multi-colored"**. The plastic parts themselves are pre-colored red, blue, skin tone, white, etc., according to the character's color settings (to look like a specification that can be completed just by assembly).

Background (Work Desk):
Behind the hand on the desk, the following two items are placed:

Completed Product: A completed figure assembled in the same "mini-character" design as the runner is standing.

Package Box: The box is placed next to the completed product at an angle where the "front" and "side" are visible.

Front Design: Clearly display only the SD illustration of the specified character and the specified "Text to Display on the Package" as a large logo.

Manufacturer Logo (Important): Clearly place a logo mark reading "Banana Model" on the bottom right of the box front. Do not display any other existing logos or unknown marks.

Side Design (Important): The side of the box should be printed with a "specifications table" (a table with borders and a list of fine text) detailing the product's performance and values.
Tools: Only two items are placed on the desk: a green **"cutting mat" and "nippers"** for plastic models.

Overall Setting:
The background is moderately blurred with depth of field, and the composition highlights the colorful runner parts in the hand and the box with the specified text.

Cinematic Anime/Reality Action Blend Prompt

game-asset

A highly technical, structured prompt for Nano Banana Pro designed to blend a photorealistic live-action person (from a reference image) with a cel-shaded anime character in a single cinematic frame. The prompt enforces strict rules for identity preservation, scale matching, camera settings, and consistent lighting (stormy maritime noir) to ground the anime character realistically within the live-action environment.

展开提示词全文
{
  "generation_request": {
    "meta_data": {
      "tool": "NanoBanana Pro",
      "task_type": "cinematic_anime_reality_action_adventure",
      "version": "onepiece_storm_harbor_v7_CINEMATIC_GROUNDED_NO_STICKER",
      "priority": "highest"
    },

    "references": {
      "reference_image_1": {
        "source": "UPLOAD_REFERENCE_IMAGE (REQUIRED)",
        "purpose": "REFERENCE_PERSON_IDENTITY_AND_SCALE_ANCHOR",
        "strict_lock": true,
        "face_similarity_priority": "MAX",
        "preserve_body_proportions": true,
        "no_body_rescale": true,
        "no_identity_blending": true,
        "no_beautify": true,
        "no_age_shift": true,
        "preserve_skin_texture": true,
        "preserve_facial_proportions": true,
        "preserve_expression": true
      }
    },

    "output_settings": {
      "aspect_ratio": "16:9",
      "resolution_target": "ultra_high_res",
      "render_style": "cinematic_film_still",
      "sharpness": "crisp_but_natural",
      "film_grain": "subtle_true_35mm",
      "dynamic_range": "natural_not_hdr",
      "color_grade": "darker_stormy_maritime_noir_realism_low_saturation"
    },

    "camera": {
      "lens": "50mm_equivalent",
      "camera_height": "eye_level",
      "movement": "handheld_urgent_run_energy",
      "aperture": "f/2.8",
      "shutter_speed": "1/800",
      "iso": 800,
      "white_balance": "cool_4600K",
      "exposure_bias": "-0.5EV",
      "focus_priority": "reference_person_eyes_then_anime_character_face",
      "faces_must_be_sharp": true,
      "background_motion_blur_only": true,
      "depth_of_field_rule": "MATCH_REAL_LIVE_ACTION_DOF"
    },

    "global_rules": {
      "reality_rule": "REFERENCE PERSON AND ENVIRONMENT ARE FULLY PHOTOREAL LIVE-ACTION",
      "anime_rule": "ANIME CHARACTER REMAINS CEL-SHADED BUT MUST BE PHYSICALLY GROUNDED IN LIGHT, SHADOW, WEATHER, AND DEPTH",
      "scale_rule": [
        "ANIME CHARACTER HEIGHT WITHIN ±5% OF REFERENCE PERSON",
        "REALISTIC HUMAN BODY PROPORTIONS ONLY",
        "NO GIANT OR MINIATURE SCALE"
      ],
      "camera_rule": [
        "50MM LENS ONLY",
        "EYE-LEVEL CAMERA",
        "SAME CAMERA PLANE FOR ALL SUBJECTS",
        "NO WIDE-ANGLE DISTORTION"
      ],
      "action_rule": "SCENE MUST SHOW ACTIVE MOTION AND URGENCY, MID-STRIDE, WIND RESISTANCE, SPRAY IN AIR"
    },

    "lighting_rules": {
      "source": "overcast storm daylight + subtle practical harbor lights",
      "noir_exposure": "slightly underexposed low-key storm look",
      "shadows": [
        "MATCHED SHADOW DIRECTION",
        "CONTACT SHADOWS AT FEET",
        "CONSISTENT SHADOW SOFTNESS FROM OVERCAST SKY"
      ],
      "anime_lighting_match": "ANIME CHARACTER RECEIVES THE SAME OVERCAST KEY + WET DECK BOUNCE (WITHOUT BECOMING REALISTIC)"
    },

    "creative_prompt": {
      "story_context": "A high-stakes adventure sprint on a stormy harbor pier. Wind and sea spray whip across the frame. The referen"
}
}

Isometric Figurine from Selfie Prompt Template

game-asset

A simple, reusable prompt template for transforming a user's selfie into a miniature, full-body, isometric, realistic figurine. The template allows customization of the figurine's clothing (ABC) and action (XYZ), set against a minimal white background in 4K resolution.

展开提示词全文
"Make a miniature, full-body, isometric, realistic figurine of this person, wearing {argument name="clothing description" default="ABC"}, doing {argument name="action description" default="XYZ"}, on a white background, minimal, 4K resolution."

Anatomy Visualization Prompt Template (Great White Shark Example)

game-asset

A structured prompt template designed for creating incredible anatomical visualizations, specifically using glowing blue lines to map systems against a dark background. The example provided applies this template to a great white shark, highlighting its sensory anatomy (Ampullae of Lorenzini) with a pulsing red-orange glow, merging marine biology documentation with military targeting system aesthetics.

展开提示词全文
A digital illustration of a {argument name="subject" default="great white shark"} in {argument name="action/state" default="mid-hunting approach"}, portrayed with a network of glowing {argument name="primary color" default="cold bioluminescent blue"} lines mapping its {argument name="system type" default="sensory and predatory anatomy"}. The cartilaginous skeleton is rendered as flexible geometric framework, the lateral line system as a full-body motion detector array. The image is set against abyssal ocean black, depth pressure readings floating at the margins. The {argument name="area of interest" default="ampullae of Lorenzini, hundreds of electroreceptor pores clustered on the snout"}, are emphasized with a pulsing {argument name="accent color" default="red-orange"} glow, indicating {argument name="condition" default="active electromagnetic detection: the prey's heartbeat rendered as intercepted signal waves feeding into the shark's targeting consciousness"}. The teeth are visualized as serrated replacement queues. The style merges marine biology research documentation with military targeting system aesthetics, designed to resemble a naval analysis of nature's most refined predator, clinically respectful of four hundred million years of evolution.

Black and White Fantasy Action Weapon Prompt

game-asset

A prompt for generating a fantasy action scene with a focus on a large weapon and dramatic lighting. It uses specific weighting (::1.5:: and ::1.8::) to emphasize a black background, cel shading, chiaroscuro, and a red weapon trail, creating an intense, stylized combat image.

展开提示词全文
1.5::black background, simple background ::, 1.8::cel shading, hard shadows, chiaroscuro ::, oversize ({argument name="weapon type" default="weapon"}), swinging a fantasy ({argument name="weapon type 2" default="weapon"}), ornate details, red weapon trail, fancy red light particles, extreme energy slash, leather halter black top,

Generating Siblings Based on a Reference Character

game-asset

A prompt template for Nano Banana Pro designed to generate siblings (brothers/sisters) of a character based on a provided reference illustration. It allows specifying the number of siblings and their individual characteristics (e.g., 'funky sister', 'muscle-head brother').

展开提示词全文
This is a Nano Banana Pro prompt for generating siblings of a character based on a reference illustration.

It works by simply specifying sister or brother within the prompt.
It is likely possible to specify mother or grandfather as well.

It allows specifying multiple people, not just one.
It also allows specifying individual characteristics.
The first image was output with the following:

{argument name="Siblings to generate" default="One sister (funky), one sister (Jirai-kei), one brother (muscle-head), one sister (shut-in)"}

Sizes can also be customized, such as vertical, horizontal, or square, not just the original.

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。

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。

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。

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

海报设计工作室

免费增值需申请 Key

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。

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。