← 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

Exaggerated 3D Caricature Character Portrait

game-asset

A detailed prompt for Gemini Nano Banana 2 to create an exaggerated, stylized 3D caricature portrait based on a reference photo, focusing on intentional deformation, clean studio finish, and specific luxury street-wear accessories.

展开提示词全文
Create an exaggerated stylized 3D caricature character portrait with strong intentional deformation and a clean, controlled surface finish. Use the person from reference photo.Preserve the subject’s identity, facial likeness, skin tone, and defining features, but reinterpret them into a bold caricatured 3D form with an elongated neck, oversized head-to-neck ratio, droopy eyelids, heavy lips, and slightly asymmetrical facial structure.Render as a human-like 3D character with smooth, studio-clean skin and intentionally designed detail, avoiding random texture or noise. Style with bold accessories such as round or oval glasses, hoop earrings, gold chains, headscarves or bandanas, and street-luxury clothing.

Use neutral studio lighting with soft shadows and even illumination, no dramatic contrast, against a plain neutral grey or off-white background. The overall aesthetic should feel weird, fashion-forward, collectible, and character-driven rather than cute or realistic.

Ultra high definition, premium cinematic 3D render quality, hyper-realistic hyper realism, clean materials, no freckles, no dirt, no grain, no noise, no speckling, no text, no logos, no watermarks.

Aspect ratio 4:5.

Sleek LCD-Face Robot Prompt

game-asset

A reusable prompt template for generating hyper-realistic, sleek modern robots with a large rectangular LCD screen as a face, emphasizing industrial design, dramatic lighting, and high detail. The prompt is designed for Nano Banana (used in Adobe Firefly).

展开提示词全文
hyper-realistic close-up of a sleek modern robot with a large rectangular LCD screen as its face, high-resolution display showing **{argument name="display content" default="display content"}**, sharp crisp pixels and subtle backlight glow, matte black metallic body with subtle panel lines and brushed aluminum accents, glowing blue LED trim around the screen edges, articulated neck and shoulders with visible cables and servos, cool industrial design with faint reflections on the screen glass, dramatic cinematic studio lighting with strong rim light and soft volumetric highlights, ultra detailed screen texture, realistic LCD bloom and slight scan lines, futuristic yet grounded aesthetic, masterpiece, sharp focus

Cinematic Superhero Rooftop Prompt

game-asset

A detailed prompt for generating a cinematic film still of a superhero (in a red and blue spider suit) sitting on a skyscraper rooftop, focusing on specific camera angles, lighting (overcast/diffused daylight), texture realism (torn suit fabric), and cool color grading.

展开提示词全文
A superhero in a {argument name="suit color" default="red and blue"} spider suit sits on the edge of a skyscraper rooftop, viewed from the back, in a close-up medium shot, with the hero in the center of the frame. He is leaning slightly forward, one hand resting on his knee. On his back is a large red spider logo. At the top of the suit, there is a small torn hole on the right shoulder, revealing the texture of the fabric. The background is a densely built-up metropolis with beige and gray high-rises in the New York style, the windows repeating in a geometric pattern. The city is slightly blurred (slight depth of field), the hero is in sharp focus. The weather is overcast, soft diffused daylight, a cloudy sky without bright sun. The cinematic style of a 2010s superhero film, realistic texture of the suit fabric (micromesh, volumetric pattern), physically correct lighting, natural shadows, light atmospheric haze between the buildings. Color grading: cool bluish-teal tone, muted colors, reduced saturation, soft contrast, slight gray-green tint in the shadows, slightly darkened and not acidic red suit. Overall tone is dramatic, calm, slightly melancholic. Camera: 70-100mm lens, eye level, waist-length framing, cinematic framing. No action, static scene. High detail, realism, film still, ultra realistic, soft natural lighting, shallow depth of field, subtle film grain.

Stylized 3D Caricature Portrait Prompt

game-asset

A detailed prompt for creating an exaggerated, stylized 3D caricature portrait based on a reference photo, requiring intentional deformation (oversized head, heavy lips) while preserving facial likeness, rendered with clean materials and neutral studio lighting for a weird, fashion-forward aesthetic.

展开提示词全文
Create an exaggerated stylized 3D caricature character portrait with strong intentional deformation and a clean, controlled surface finish. Use the person from the ATTACHED REFERENCE PHOTO. Preserve the subject’s identity, facial likeness, skin tone, and defining features, but reinterpret them into a bold caricatured 3D form with an elongated neck, oversized head-to-neck ratio, droopy eyelids, heavy lips, and slightly asymmetrical facial structure.Render as a human-like 3D character with smooth, studio-clean skin and intentionally designed detail, avoiding random texture or noise. Style with bold accessories such as {argument name="accessories" default="round or oval glasses, hoop earrings, gold chains"}, headscarves or bandanas, and street-luxury clothing.

Use neutral studio lighting with soft shadows and even illumination, no dramatic contrast, against a plain neutral grey or off-white background. The overall aesthetic should feel weird, fashion-forward, collectible, and character-driven rather than cute or realistic.

Ultra high definition, premium cinematic 3D render quality, hyper-realistic hyper realism, clean materials, no freckles, no dirt, no grain, no noise, no speckling, no text, no logos, no watermarks.

Aspect ratio 4:5.

Photorealistic Superhero on Skyscraper Rooftop

game-asset

A highly detailed prompt for generating a photorealistic image of a superhero (Spider-Man suit) sitting on a skyscraper rooftop, with the mask removed to reveal the face of Caleb McLaughlin (using reference image 2). It specifies the pose, suit details (torn shoulder), background (industrial rooftop), overcast lighting, and a cool bluish-teal cinematic color correction.

展开提示词全文
A superhero in a red and blue spider suit sits on the edge of a skyscraper rooftop, frontal view, camera at eye level, waist-length medium shot. The pose is identical to the first shot: the body is slightly leaning forward, one hand resting on the knee, a static, cinematic composition.

The mask is removed and held in the hand or lowered downwards. Face: Use the face from the uploaded reference photo 2 (identity reference 2), as photorealistic as possible, without stylization, with natural skin texture and natural shadows. Expression: calm, pensive, slightly tired, with a dramatic mood.

The suit is completely identical to the first shot: 
red and blue, micro-mesh texture, 3D webbing, realistic fabric, and retains a small torn detail on the shoulder. Physically correct fit.

The background corresponds to the camera's 180-degree rotation around the hero: 
another part of the roof features industrial elements—ventilation units, metal structures, and technical equipment. Beyond the roof are lower city buildings, an urban landscape, concrete facades, and a subtle industrial atmosphere. The city is slightly blurred (shallow depth of field). Atmospheric haze.

The lighting is identical to the first shot: 
an overcast day, soft, diffused light, and a cloudy sky, without harsh shadows. The light falls as naturally as in the first scene.

The color correction is exactly the same as in photo 1: 
a cool bluish-teal tone, muted colors, reduced saturation, soft contrast, a slight gray-green tint in the shadows, and a darkened, not bright, red suit. A dramatic, calm, cinematic tone.

Camera: 
70–100mm lens, cinematic framing, shallow depth of field, hero in focus, background slightly blurred. Ultra-realistic, film still, subtle film grain, physically accurate lighting, cinematic superhero movie 2010s style.

Maximum realism, the feeling of a real film frame, without CGI stylization.

Cinematic 3D Render Conversion

game-asset

A prompt instructing the AI to convert a character (presumably from a reference image) into a modern cinematic 3D render with high-fashion grading, natural contrast, filmic color science, and realistic materials, while preserving the original camera framing.

展开提示词全文
Convert character into a modern cinematic 3D render with a high-fashion grade, punchy yet natural contrast, filmic color science, subtle halation/bloom, controlled highlights, realistic materials, preserve the original camera framing, no text, no logo

Cinematic Dark Fantasy Portrait Prompt for Nano Banana 2

game-asset

A highly detailed prompt for generating an ultra-realistic cinematic side profile portrait of a mysterious hooded warrior in a dark fantasy setting, requiring an uploaded image to maintain facial features and specifying dramatic lighting and textures.

展开提示词全文
Generate an Ultra-realistic cinematic side profile portrait of a mysterious hooded warrior in a dark fantasy setting. Rugged middle-aged man with piercing glowing blue eyes, sharp jawline, thick salt-and-pepper beard, and weathered skin showing realistic pores, fine wrinkles and beard texture. Keep facial features 100% same as in uploaded image

The warrior is wearing a heavy ancient hooded cloak made from rough distressed fabric with frayed and torn edges, dark charcoal and deep blue tones. The hood partially covers his head while layered cloth wraps around his shoulders and neck like a nomadic fighter or medieval assassin.

Arabic calligraphy tattoo is visible across his cheekbone, inked deeply into the skin with a slightly worn ancient appearance, giving him a mystical warrior identity.

Lighting is dramatic warm firelight coming from the front side, casting golden highlights across the cloak and face while cool blue ambient light fills the shadows. Floating sparks and embers drift through the air around him, suggesting a nearby fire or battlefield aftermath.

Background is dark, smoky, and cinematic with glowing particles, soft bokeh, and atmospheric haze. The environment feels epic and mysterious like a dark fantasy film scene.

Highly detailed fabric textures with visible fibers, dust and wear marks. Skin micro-detail is hyper realistic with subtle sweat sheen and natural imperfections.

Shot with an 85mm cinematic portrait lens, f/1.8 aperture, extremely shallow depth of field, ultra sharp eye focus, professional film lighting, dramatic contrast, volumetric smoke, cinematic color grading, epic fantasy realism, 8K resolution, Unreal Engine quality render, photorealistic masterpiece.

Character Reference Sheet Prompt for Nano Banana

game-asset

A structured prompt for generating a professional character reference sheet of an elegant young woman, specifying subject details, outfit, cinematic realism style, and layout requirements including multiple views and consistent anatomy.

展开提示词全文
[SUBJECT] = {argument name="subject description" default="elegant attractive young woman with blonde bob hair, large almond-shaped blue eyes, narrow nose, high cheekbones and delicate angular facial structure"}
[OUTFIT] = {argument name="outfit description" default="A dark charcoal or muted navy thin knit top paired with a long, softly draped cardigan or a simple coat made from a gentle textured fabric. The look is completed with straight-cut dark trousers or a matte fabric skirt. Accessories are kept minimal, such as small earrings and a delicate thin ring. The hair appears slightly tousled and natural, avoiding an overly polished or carefully styled look."}
[OUTPUT_STYLE] = cinematic realism.

Make a professional character reference sheet of [SUBJECT] in [OUTPUT_STYLE] in 16:9 aspect ratio. Use a full-frame camera with a 50mm lens when rendering photographic styles. Set a plain pure white background with no environment elements. Place a large full-body front view of [SUBJECT] standing upright in a neutral pose on the left side of the sheet. Place two smaller turnaround views in the upper right section. Show a full-body back view standing upright in the same neutral pose. Show a full-body left side profile standing upright in the same neutral pose. Place one dynamic full-body action pose of [SUBJECT] in the middle right section. Place a side profile portrait close-up of [SUBJECT] in the lower right section. Show [SUBJECT] wearing [OUTFIT] consistently across all views. Keep anatomy, proportions, outfit details and hairstyle perfectly consistent across all views. Use soft studio key light from front-left. Use subtle fill light from front-right. Use a soft rim light from behind for silhouette separation. Ensure clarity, accuracy, and professional finish.

3x3 Grid Character Consistency Prompt

game-asset

A prompt for Nano Banana 2 instructing the model to generate a 3x3 grid where each cell has a 2:3 aspect ratio, showing the same character from different angles with randomized poses while maintaining scene consistency.

展开提示词全文
In a 3×3 grid, each cell should have an aspect ratio of 2:3. Show the same character from different angles while keeping the scene consistent, with randomized poses in each cell.

Mechanical Wind-Up Diorama Concept

game-asset

A complex, structured prompt template for Nano Banana Pro designed to visualize a mechanical wind-up diorama where a superhero bursts free from comic panels, specifying base setup, core action, variants, narrative elements, and technical details like steampunk aesthetic and octane render.

展开提示词全文
2x2 grid, do this for 4 lesser known scifi movies <instructions>
 
concept: a mechanical wind-up diorama where a superhero activates and bursts free from confining comic panels in perpetual motion.
input variables:
[insert superhero character]
[insert signature action or power]
[insert mechanical elements]
[insert surrounding props]
workflow:
base setup: intricate brass and wood kinetic sculpture on a desk, with visible gears, springs, and [insert mechanical elements] implying automated movement.
core action/composition: [insert superhero character] posed mid-[insert signature action or power], breaking out of hinged comic panel frames that flip open like doors.
variants and details: multiple pose variants connected via hidden mechanisms, with scattered tools hinting at handmade construction.
narrative/interactive elements: implied perpetual motion as the figure "escapes" repeatedly, with engraved onomatopoeia plates.
god-level details: steampunk-inspired macro photography angle, warm tungsten lighting casting gear shadows, polished metal reflections and aged paper textures, hyper-realistic kinetic blur, 8k octane render with caustic light play.
</instructions>

Anime Character Reference Sheet Prompt (Nano Banana 2)

game-asset

A detailed prompt for Nano Banana 2 designed to generate a character reference sheet (SFW version, no underwear) based on an input image. It specifies the layout, required elements like facial expressions and outfit layering, and technical tags for an anime style.

展开提示词全文
(masterpiece, best quality, official art, character design sheet, reference sheet, settai-ga, production materials), (cel shading, flat colors, clean lines),
(central anchor:1.5): (full-body standing pose:1.4) of the character from image_8.png, positioned prominently in the center of the sheet, large scale.
(Maintain original art style and character details from image_8.png exactly:1.6), including hair color, eye color, skin tone, and outfit.
(No back view:1.5).

(Surrounding elements), arranged neatly with annotated leader lines:
[Facial Expressions]: A row of 5 distinct headshots showing different emotions (e.g., joyful, angry, sorrowful, surprised, blushing).
[Outfit Layering]: Exploded view of the main outfit showing outer layers removed to reveal inner clothing structure.
(Do not include "innerwear specification" or any other innerwear section:1.5).
[Accessories & Props]: Close-up details of shoes, jewelry, or weapons held by the character.

(Text & Annotations): All text annotations are in JAPANESE kanji and kana (e.g., "Expression Collection", "Outfit Composition", "Material Specification", "Color Palette"). Hand-drawn notes style.

(Technical Tags): (anime coloring:1.4), (line art:1.3), (flat colors:1.2), clean lines, precise details, white background.
(Negative prompt): (3d, realistic, photorealistic, cgi:1.5), (altering character features:1.5), (changing hairstyle:1.5), (western comic style), shading, complex background, (real world brand logos:1.5), messy layout, (multiple full body views:1.5), (back view:1.5), (conflicting innerwear sections:1.5).

Kawaii Great White Shark Vector Prompt

game-asset

A prompt for Nano Banana 2 to generate a flat vector style illustration of an adorable kawaii great white shark holding a shiny red balloon, featuring retro muted pastel colors and a striped background.

展开提示词全文
an adorable kawaii cartoon great white shark with big sparkling eyes holding a shiny red balloon on a delicate string, flat vector style with clean bold outlines, retro muted pastel colors, centered composition, deep warm tan colored background with evenly spaced navy horizontal stripes, soft subtle shadow beneath the shark for depth

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。