← 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

Sci-Fi Punk Japanese Woman View

game-asset

A multi-view prompt for a woman in a sci-fi punk outfit, specifying a white color scheme with orange accents on a clean white background.

展开提示词全文
elegant {argument name="ethnicity" default="japanese woman"} in her {argument name="age" default="30s"} who is cool and sophisitcated in a {argument name="style" default="scifi punk"} outfit on on white background. front view, side view, back view in a whiteoutfit with orange design lines

Multi-View Car Sheet

game-asset

A prompt for generating a four-view design sheet of a sports car, covering front, side, top, and back perspectives with photorealistic quality.

展开提示词全文
photorealism, {argument name="subject" default="car sheet"}, four-view, side view, top view, backside view, front view  
- car has {argument name="wheels" default="4"} wheels  
- car is a {argument name="car type" default="double seater sports car"}  
- back wheels are same with as the car

Cockpit Interior Grid View

game-asset

A prompt for generating a realistic 2x2 grid showing various angles of a detailed vehicle cockpit interior, including steering wheel and dashboard views.

展开提示词全文
photorealism, {argument name="grid layout" default="2x2"} grid of detailed {argument name="subject" default="cockpit interior"} views: wideangle inside, steering wheel, dashboard, view from the passenger seat towards the driver seat

3D Paper-Cut Illustration Style

game-asset

This prompt transforms photos into charming 3D paper-cut illustrations using the Nano Banana model. It features a tactile paper texture, soft pastel colors, and a distinctive sticker-style border, perfect for creating stylized avatars or creative ID photos.

展开提示词全文
Charming 3D paper-cut illustration, smooth rounded shapes, minimal character features ({argument name="character features" default="dot eyes, blush cheeks"}), {argument name="border style" default="thick white sticker border"} around subjects, {argument name="color palette" default="gentle pastel colors"}, soft even lighting, matte tactile art paper texture.

Viking Tree Carvings

game-asset

A high-detail prompt for generating realistic wood carvings of specific subjects on ancient mossy tree trunks with Norse motifs.

展开提示词全文
{argument name="subject" default="[subject]"} hyper-realistic close-up of a massive ancient tree trunk with an incredibly detailed Viking-style carving of that subject deeply engraved into the bark, intricate Norse knotwork borders, runes and symbolic Viking motifs surrounding the carving, hyper-detailed wood grain, deep chisel marks, {argument name="bark texture" default="realistic bark texture with moss and natural cracks"}, {argument name="lighting" default="dramatic side lighting with strong rim light and deep shadows"} that emphasize the carved depth and relief, misty Nordic forest atmosphere in the background, masterpiece, photorealistic, ultra detailed carving and wood textures

3D Squishy Candy Alphabet

game-asset

A whimsical prompt for creating cute, candy-themed 3D letters from A to Z with soft textures and pastel colors.

展开提示词全文
3d squishy kawaii letters from {argument name="letters" default="A to Z"}, {argument name="theme" default="candyland"} theme, glossy pastel colors, soft rounded shapes like marshmallows and gummies, each letter made of different sweets such as lollipops, jelly beans, cotton candy, and chocolate, arranged in alphabetical order on a {argument name="background" default="plain blank white background"}, soft studio lighting, high-resolution, ultra-cute and whimsical style

3D Fluffy Monster Bursting Through Wall

game-asset

A creative 3D cartoon style prompt for creating a playful, energetic monster bursting through a wall with cinematic lighting and high detail.

展开提示词全文
A close-up, vertical shot features a {argument name="monster description" default="fluffy, blue monster"} with {argument name="eyes" default="wide, green eyes"} and a large, open mouth revealing two small teeth. The monster is bursting through a {argument name="wall description" default="cracked, lime-green wall"}, with pieces of the wall scattered around its head and body. Playful, energetic, colorful, 3D cartoon style, high detail, cinematic lighting

Steampunk Miniature Clockwork Machine

game-asset

A detailed prompt for creating hyper-realistic, intricate steampunk sculptures of any subject, featuring brass gears, cogs, and glowing lights on a wooden base.

展开提示词全文
{argument name="subject" default="miniature clockwork machine"} hyper-realistic miniature clockwork machine version of the subject, extremely intricate and highly detailed steampunk-style mechanical sculpture, thousands of tiny brass gears, springs, levers, cogs, pistons and delicate clockwork mechanisms visibly working, polished brass and copper components with realistic patina and wear, tiny glass tubes and glowing indicator lights, masterpiece of miniature engineering, displayed on a dark wooden base under dramatic focused lighting with soft highlights and deep shadows emphasizing the mechanical details, ultra detailed textures, photorealistic, collector quality

Hyper-realistic Cyborg Side Profile

game-asset

A high-detail prompt for generating a half-human, half-cyborg portrait with a mix of digital painting and architectural sketch styles.

展开提示词全文
A hyper-realistic side profile of a {argument name="subject" default="man"}, half-human half-cyborg. Left side of the face is deconstructed to show complex {argument name="armor color" default="red"} armor plates, gears, and wires. Sharp, melancholic gaze. Style: detailed digital painting mixed with {argument name="background style" default="white background architectural sketches"}.

High-contrast lighting, 8k resolution, cinematic. ar 4:5

Cinematic Dark Fantasy Scene of Elemental Collision

game-asset

A complex, multi-part prompt recommended for Gemini Nano Banana, generating a cinematic dark fantasy scene where an uploaded character sits in a basement, creating rivers of molten lava and freezing ice from their palms, which collide to form a symbolic, destructive meeting point and actively generate creatures.

展开提示词全文
A cinematic dark fantasy scene of the uploaded reference character seated in a basement at the exact point where opposite elemental forces are born from their own body. Likeness Integrity (CRITICAL) Preserve the exact identity of the uploaded character. Maintain exact proportions, eye shape, spacing, stylization, silhouette, and material identity. Do not humanize. Do not reinterpret anatomy. Do not modify facial structure. Do not add unintended accessories. Identity must remain instantly recognizable. Core Scene The character is sitting in a melancholic, emotionally heavy pose at the center of a cold unfinished basement. From one open palm, molten lava pours downward in a continuous glowing stream. From the other open palm, freezing ice and frost pour downward in a continuous crystalline stream. Both elements spill onto the basement floor and form two separate flowing rivers: one lava river, one ice river. They travel across the concrete floor in opposite directions and meet nearby in the same scene. Elemental Interaction Where the rivers meet, the collision creates violent physical contrast: steam, glowing cracks, frost bloom, blackened wet concrete, cooling rock, and frozen shards. The meeting point must feel emotionally symbolic, like two inner states colliding. Creature Creation Story (CRITICAL) The lava and ice pouring from the palms are actively creating creatures on the floor. These creatures must feel born from the flowing material itself, not placed into the scene afterward. Some creatures are still forming out of the streams. Some are fully shaped and wandering around the seated character. Lava creatures: glowing, semi-molten, ember-veined, heat-distorted silhouettes. Ice creatures: translucent, frosted, crystalline, sharp-edged, cold-vapor silhouettes. They should vary in size and animals language, all kind of animals and insects. A few lava and ice creatures are already surrounding the character in quiet loyalty or silent observation. Character Pose & Emotion The character is seated, still, introspective, emotionally exhausted. Head slightly lowered. Shoulders carrying invisible weight. Palms open and angled downward so the lava and ice pour naturally from them. The pose must feel like grief, restraint, and power at the same time. Not a triumphant spellcasting pose. Not action-hero energy. Quiet sorrow. Controlled destruction. Environment A dark basement interior with: unfinished concrete floor, aged walls, pipes and exposed structure, subtle moisture stains, minimal objects, deep negative space. The basement should feel real, sparse, and slightly abandoned. The elemental rivers become the main environmental storytelling device. Camera & Perspective Use a low cinematic perspective, slightly below the seated character's eye line. Lens: 24mm or 28mm. The camera is close enough to feel intimate but wide enough to show the rivers spreading across the floor and the creatures surrounding the character. Composition should be slightly off-center, not symmetrical. Use foreground depth with one or two blurred creatures or fragments near the lens. The seated character remains the emotional anchor. Depth of Field Primary focal plane locked on the character's face, upper torso, and both pouring palms. Nearest creatures and the river collision point can remain slightly readable. Foreground and far background fall progressively out of focus. No full-frame sharpness. Lighting Main light: a weak cool basement lamp overhead, dim and emotionally cold. Ambient: dark blue low-light atmosphere throughout the basement. Secondary light comes naturally from the lava itself, casting warm orange-red underlight onto parts of the character and nearby creatures. Ice contributes faint cold reflections and subtle blue-white edge highlights. Lighting must stay directional and cinematic, with deep shadow mass and controlled contrast. No flat lighting. Color Grade Dominant palette: dark blue, cold grey, black shadow. Accents: molten orange-red from lava, pale cyan-blue from ice. The warm and cool elements must remain clearly separated and emotionally readable. Controlled saturation, cinematic highlight roll-off, no color flooding. Atmosphere Thin basement haze. Steam rising where lava and ice meet. Cold vapor around the ice creatures. Subtle airborne dust catching the weak overhead lamp. The air should feel heavy and lonely. Mood Melancholic. Mythic but grounded. The scene should feel like inner conflict externalized into the physical world. The character is not commanding the creatures. They are simply emerging from what the character cannot hold inside. Negative Constraints No heroic battle pose. No cheerful fantasy lighting. No flat basement rendering. No symmetrical centered composition. No generic fireballs or magic aura. No full-body sharpness. No random clutter. No cute cartoon expression unless it already belongs to the character identity. Aspect Ratio ar 16:9

3D Character Sheet for Varsity Jacket Prompt

game-asset

A prompt for generating a photorealistic 3D character sheet of a male figure, emphasizing specific fashion details (Aimé Leon Dore-style varsity jacket, gold herringbone chain), high-key lighting, and advanced 3D rendering techniques like Subsurface Scattering for realistic textures.

展开提示词全文
A photorealistic 3D character sheet of a male figure with a sharp fade haircut and a meticulously groomed beard. He is wearing a heavyweight {argument name="jacket color" default="cream-colored"} Aimé Leon Dore-style wool varsity jacket with leather sleeves and a large "NY" chenille patch. Layered with a thick gold herringbone chain. Front orthographic and three-quarter views. Soft, global illumination with high-key lighting to emphasize PBR albedo textures. Intricate mesh detail on the knit collar, realistic skin pores, rendered with high-end Subsurface Scattering.

Photoreal Character Reference Sheet Prompt for Nano Banana Pro

game-asset

A highly detailed prompt for Nano Banana Pro to create an 8-panel photoreal character reference sheet of a 29-year-old woman in sci-fi tactical gear, specifying layout, consistency requirements, and output quality.

展开提示词全文
Create a photoreal character reference sheet on a pure white background.

Character:
A 29-year-old woman with a lean athletic build, short black hair with a silver streak, steel-blue eyes, a stern intelligent expression, and a lightly weathered face. She wears an asymmetrical dark graphite tactical coat with a fitted high collar, a matte black bodysuit, segmented forearm armour, a compact chest rig, a slim utility belt, fitted tactical trousers, and reinforced boots. The overall look is a modern sci-fi operative aesthetic with realistic fabric, subtle worn metal, dust, and light scratches.

Layout:
Strict 8-panel turnaround sheet.
Top row: full-body front view, full-body back view, full-body left side view, full-body right side view.
Bottom row: close-up head front view, close-up head back view, close-up head left side view, close-up head right side view.

Requirements:
Pure white background, no shadows, evenly spaced panels, highly accurate identity consistency, highly accurate facial consistency, highly accurate outfit consistency, highly accurate proportions, clean production-ready presentation, exact side views, no three-quarter views.

Pose:
Neutral standing pose, arms relaxed at sides.

Output:
Photoreal, ultra-detailed, sharp focus, no props, no weapons, no text, no labels, no logos.

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。