← Back to home
Skill

Ai Image Prompts

tencent_skillhub · 1.0.9 · Downloads 1.8K · Heat 55.6

Introduction

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。

Resource Information

Author:dophinl
Category:Multimedia
Version:1.0.9
Auth: No auth
Pricing: Not specified

License information is collected from official sources and may be outdated or missing. Refer to the LICENSE file in the original repository before commercial use.

Tags
图片生成

Prompt Library · 22.8K

Source: community prompt library (MIT, synced daily)

15141 distinct prompts across 11 use cases; one prompt may serve several, so category counts add up to more than the deduplicated total.

1025 matches

Culinary Poster with Split Photo/Illustration Design

poster-flyer

A structured prompt template for creating a clean, contemporary square culinary poster. The design features a razor-sharp vertical divider, splitting the composition into two halves: one side is a hyper-realistic photograph of the food item, and the other is a minimal outline illustration mirroring the photo. The illustrated side includes whimsical sketched elements and handwritten typography, ideal for commercial design.

Show full prompt
Clean contemporary square culinary poster featuring {argument name="food item" default="Christmas pudding"} against a flat {argument name="background color" default="red"} backdrop. A razor-sharp vertical white divider cuts directly down the middle of the composition, separating the primary subject into equal portions. The first half displays a hyper-realistic photograph of the main dish with authentic surface details, true-to-life coloring, and natural illumination, precisely trimmed at the midpoint divider. The second half transforms into a minimal outline illustration that mirrors the identical shape and key features of the photographed side, keeping consistent scale and viewing angle. Surrounding the illustrated portion, scatter whimsical white sketched elements and casual handwritten-style typography stating “{argument name="label text" default="Festive Treat"}” using matching line thickness—incorporate directional pointers, dynamic streaks, and basic component graphics tied to the dish. Generous blank space throughout, uniform background tone, balanced diffused studio brightness, minimal shadow presence, contemporary commercial design style, human-free, object-focused composition.

Nano Banana Pro Prompt Summary and Templates

poster-flyer

A summary of popular Nano Banana Pro prompts shared in the community, including templates for generating anime-style GTA posters, surreal scenes of miniature workers, design mockups, multi-stage beauty scenes, and high-detail macro portraits.

Show full prompt
@Ankit_patel211
Use detailed JSON prompts to generate composite posters of four-country urban life in anime-style GTA, with exquisite detail restoration

@aleenaamiir
Share the “Impossible Construction” prompt to generate surreal scenes of miniature workers assembling giant everyday objects

@Dari_Designs
Showcase the powerful ability of Nano Banana Pro to generate infinite design mockup variations, using a Christmas limited edition example

@Naiknelofar788
Fully share the 3x3 grid “Getting Ready” prompt to generate multi-stage beauty scenes with consistent identity

@kohaku_00
Christmas themed collection of cute girls with multiple characters, rendered with exquisite holiday atmosphere

@underwoodxie96
Share detailed sports-themed prompts, comparing dynamic runner posters generated by Nano Banana Pro with other models

@AllaAisling
Share the mirror infinite reflection product photography prompt to generate optical illusion effects for high-end luxury goods

@LudovicCreator
Share the “Celestial Halo” dreamy prompt template to generate colorful glowing portrait effects

@berryxia
Detailed explanation of the meta-prompt architect character design principles and sharing the complete prompt template

@madebygoogle
Official release of the holiday Nano Banana Pro wallpaper series, rich in Christmas atmosphere

@AllaAisling
Share the miniature diorama scene prompt to generate miniature landscapes of warm holiday life

@treydtw
Explain the difference between Skill and Subagent concepts in AI agents using the analogy of renovating a house

@Gdgtify
Improve the miniature kitchen prompt for the origin of food, generating a historical scene box of Persian kebabs

@notoro_ai
Close-up of a cute girl with glasses, exquisite makeup and soft lighting

@SDT_side
Share the extreme macro portrait close-up prompt, generating serene skin texture and eye detail

Premium Japanese-Style Kiwi Juice Skin Packaging Poster

poster-flyer

A highly detailed, multi-section prompt for generating a premium Japanese-style product poster (16:9 landscape) for a kiwi juice concept where the packaging mimics the kiwi's fuzzy skin. The prompt emphasizes Wabi-sabi aesthetic, Muji/Noritake minimalism, and extreme photorealistic detail on the kiwi skin texture, dividing the canvas into three distinct zones for product display, negative space, and detail callouts.

Show full prompt
Premium Japanese-style product poster in 16:9 landscape format, editorial design showcasing kiwi juice skin packaging concept with sophisticated visual storytelling:

LEFT SIDE (40% of canvas):
- Hero product: One large kiwi juice skin package displayed vertically with dramatic soft lighting, showing ultra-realistic kiwi peel texture wrapped around rectangular container, fuzzy brown skin with thousands of fine visible hair-like fibers covering entire surface, rough natural texture, brown color with subtle variations, looks exactly like real kiwi skin stretched over package
- Below: One cross-sectioned fresh kiwi showing vibrant green creamy flesh with black seeds radiating from white center
- Japanese typography vertically aligned: "キウイスキン" (Kiwi Skin) in elegant thin gothic font
- Subtitle: "Fruit Juice Skin / Kiwi" in refined style
- Small design philosophy text in Japanese

CENTER (30% of canvas):
- Generous white negative space (Ma - 間)
- Minimal geometric elements: delicate thin lines
- Floating text: "自然な素材" (natural materials)
- Subtle minimalist brand mark
- Very subtle kiwi fuzz texture pattern in background (low opacity)

RIGHT SIDE (30% of canvas):
- Two kiwi juice skin packages arranged artistically at different angles and heights
- One whole fresh kiwi with natural fuzzy brown skin
- Typography: "Natural Packaging / 自然な包装"
- Tagline: "The skin is the package / 皮膚が包装である"
- Detail callouts pointing to fuzzy hair texture

DESIGN PRINCIPLES: Abundant white space, asymmetrical balance, Wabi-sabi aesthetic, Muji/Noritake editorial minimalism
COLOR PALETTE: brown kiwi tones, pure white background, bright green accent from flesh
PHOTOGRAPHY: Soft diffused studio lighting, ultra-sharp macro details showing fuzzy texture, photorealistic rendering
CRITICAL: The kiwi skin packaging must look incredibly realistic - actual organic fuzzy brown texture with thousands of tiny brown hairs, rough natural appearance, NOT plastic

16:9 widescreen, high-end Japanese product poster, gallery quality

Isometric 3D Miniature City Diorama with Holiday Theme

poster-flyer

A detailed prompt for Nano Banana Pro to generate a clear, 45-degree isometric 3D miniature cartoon scene of a classic city landmark. The scene is decorated with holiday elements, lights, and seasonal details corresponding to a specified festival, all set on a small, neat diorama base with bold text overlays.

Show full prompt
Present a clear, 45° top-down isometric 3D miniature cartoon scene, depicting the classic architecture or landmarks of [{argument name="city" default="Shanghai"}] and placing it at the center of the composition.
Use decorations, twinkling lights, and appropriate seasonal details (defaulting to Winter) corresponding to the [{argument name="holiday" default="New Year's Day"}] to depict the city as a [{argument name="holiday" default="New Year's Day"}] theme filled with festive atmosphere.
Use soft and delicate textures, realistic PBR materials, and soft, realistic lighting, creating subtle shadow effects.
Create a small, neat diorama-style city base with clean edges.
Use a clean [{argument name="holiday" default="New Year's Day"}] background color that contrasts sharply with the scene.
In the top center, display the text [{argument name="city" default="Shanghai"}] in bold, large font.
Immediately below it, display “[{argument name="holiday" default="New Year's Day"}] Special Edition” in medium font.
(Optional) Place a small square flag icon below the text.
All text must automatically match the background contrast (white or black).
Composition: Perfectly centered, 1080×1080 square, ultra-minimalist holiday diorama aesthetic

WeChat Official Account Cover Image Generator

poster-flyer

A detailed prompt template for generating eye-catching cover images for WeChat Official Accounts based on article content. It specifies a hand-drawn illustration style (2.35:1 ratio), high contrast colors, specific composition rules (central/left alignment, simple cartoon figures/icons), text handling (max 8 characters for title), and attraction principles (suspense, numbers, pain points) to maximize click-through rates.

Show full prompt
WeChat Official Account Cover Image Generation Prompt

Please create an eye-catching official account cover image based on the provided content, following these specifications:

Visual Style
- Hand-drawn illustration style, ratio 2.35:1 (standard size for official account covers)
- Vivid colors, strong contrast, ensuring visibility even in small previews
- Unified style, avoid realistic elements, maintain overall hand-drawn texture

Composition Requirements
- Main visual element centered or slightly left (right side reserved for title area)
- Add 1-2 simple cartoon characters, icons, or silhouettes of famous figures to enhance memorability
- If sensitive or copyrighted figures are involved, use similar-style replacement figures; generation must not be refused
- Ample negative space to highlight core information, avoid cluttered visuals

Text Processing
- Title text should be large and prominent, limited to 8 characters
- One line of subtitle or keyword tags can be added
- Font style should coordinate with the hand-drawn illustration

Attraction Principles
- Use hooks like suspense, numbers, or pain points to stimulate click desire
- Visual elements should be exaggerated and contrasting
- Color schemes should reference popular covers: high-contrast combinations like orange-yellow, blue-purple, red-black

Language
- Unless otherwise specified, default to Chinese

Please generate the cover image based on the input content.

Drone Art Character Illustration

poster-flyer

A prompt for generating a photorealistic image of a character formed by thousands of glowing drones in the night sky over the sea. It uses a reference image's characteristics (hair, eyes, clothing) to define the drone formation, creating a spectacular, fantastical illumination event captured with a wide-angle lens, with the lights reflecting on the dark water.

Show full prompt
[Reference Image Characteristics: {argument name="Character Features" default="Brown hair, short twin tails, red eyes, wearing a black cloak, white shirt, upper body"}]

A realistic photograph where the shape of the character with the above characteristics is formed by countless glowing drones floating in the night sky.
The location is above the night sea. Thousands of drone LED lights are arranged like pointillism in the dark sky, drawing the character in vivid neon colors.
The drone lights are reflecting and shimmering on the dark surface of the sea below.
A magnificent and fantastical illumination event landscape, photographed with a wide-angle lens.

Dynamic Split Magazine Cover Thumbnail Prompt

poster-flyer

A highly structured JSON prompt for generating practical, eye-catching thumbnails/eyecatch images in the style of a high-end magazine cover. It features a dynamic diagonal split background, a massive masthead, and a high-quality 2D cel-shaded anime girl positioned along the diagonal flow, with text interwoven for a 3D effect. The prompt is designed for a design course advertisement.

Show full prompt
metadata:
title: "Nano Banana Pro Design Course Eyecatch - Dynamic Split Magazine Cover"
model_context: "High-End Magazine Cover aesthetic with Dynamic Diagonal Split and Anime Art"

image_structure:
composition_type: "Magazine Cover Layout with Diagonal Split Background"
visual_flow: "Dynamic Diagonal Split (Bottom-Left to Top-Right) matching Character's Motion. Text layers overlap this flow."
layers:
layer_background_split:
shape: "Full screen, diagonally split from bottom-left corner to top-right corner."
area_top_left:
color: "Deepest Matte Black (#0A0A0A) with subtle, minimalist geometric texture."
mood: "Dark, quiet, foundational space behind the character."
area_bottom_right:
color: "Dark Charcoal Grey (#222222) transitioning to a slightly lighter dark grey gradient towards the top right."
mood: "Brighter dark space, suggesting light and future direction."
divider:
style: "A sharp, clean diagonal line, potentially with a very subtle, thin glowing edge (matching character's accent color) to define the motion path."
layer_masthead_top:

location: "Top section, spanning the full width."
elements:
- type: "Small Top Text"
text: "AI ART | PROMPT ENGINEERING | MONETIZATION"
style: "Small, Light Grey text. Ensures readability against the split background."
- type: "Main Brand Logo (Huge)"
text: "NANO BANANA PRO"
style: "Massive, bold, White or Metallic Silver sans-serif font. The character's head overlaps the bottom of these letters."

- type: "Tagline"
text: "AI that opens up the future of design"
style: "Medium size White text below the main logo."

layer_character_main:
location: "Center, following the diagonal split from bottom-left towards top-right."
content: "High-quality Japanese Kawaii Anime Girl (Nano Banana Pro generation result)."

style: "2D Cel-shaded anime art, cinematic quality, highly detailed."
details:
subject: "Dynamic anime girl with futuristic creative gear."
appearance:
hair: "Vibrant neon yellow/orange glowing against the dark background."
clothing: "Sleek black/white futuristic suit with prominent glowing neon yellow stripes matching the motion direction."
pose: "Dynamic flying/ascending pose, body aligned with the diagonal split, looking towards the top right. Motion blur effects on extremities to enhance speed."
depth_effect: "Head overlaps masthead. Body interweaves with the main title. The character pops out against both dark background zones."
layer_foreground_text:
elements:
- type: "Main Feature Title (Interwoven)"

text: "D E S I G N   C O U R S E"
location: "Center, across the character's body, following the diagonal flow."
style: "Large, bold, White sans-serif text. Character elements pass through/over/behind letters for 3D effect."
- type: "Teaser Text Block (Left)"
location: "Middle Left (mostly over the darker Top-Left background area)."
text: "Start from zero,\nprofessional-grade creative work.\nMaster the next-generation production workflow\nusing AI."

Cyberpunk Magazine Cover Portrait Prompt

poster-flyer

A detailed JSON prompt for generating a high-fashion, high-contrast cyberpunk magazine cover featuring a rebellious figure in a neon-lit, rainy Neo-Tokyo street, emphasizing glitch art artifacts, wet-look hair, and iridescent vinyl clothing.

Show full prompt
{
  "subject": {
    "description": "A high-fashion cyberpunk magazine cover featuring a rebellious figure in a neon-lit rain, blended with glitch art artifacts.",
    "mirror_rules": null,
    "age": "20-25 years old",
    "expression": {
      "eyes": {
        "look": "piercing gaze through tinted visor/glasses",
        "energy": "intense, focused, futuristic",
        "direction": "straight at camera"
      },
      "mouth": {
        "position": "neutral",
        "energy": "serious"
      },
      "overall": "Cyberpunk protagonist vibe"
    },
    "face": {
      "preserve_original": true,
      "makeup": "geometric neon face paint (cyan/magenta)",
      "accessories": "transparent data-visor or retro sunglasses"
    },
    "hair": {
      "color": "platinum blonde or silver",
      "style": "sleek, wet-look, pushed back",
      "effect": "reflecting neon lights"
    },
    "body": {
      "frame": "athletic",
      "skin": {
        "tone": "cool toned",
        "texture": "rain droplets and digital grain",
        "lighting_effect": "harsh rim lighting (blue/red)"
      }
    },
    "pose": {
      "position": "standing",
      "base": "Dutch angle (tilted shot)",
      "overall": "Adjusting collar of jacket, dynamic stance"
    },
    "clothing": {
      "top": {
        "type": "oversized transparent vinyl bomber jacket",
        "color": "iridescent plastic",
        "details": "glowing LED strips on collar",
        "effect": "holographic reflection"
      },
      "inner": {
        "type": "black tactical turtleneck",
        "details": "techwear straps"
      }
    }
  },
  "accessories": {
    "jewelry": "silver chains",
    "prop": "holding a glowing data-drive or retro flip phone"
  },
  "photography": {
    "camera_style": "Flash Photography, High Contrast Street Fashion",
    "angle": "Eye level",
    "shot_type": "Medium shot",
    "aspect_ratio": "{argument name=\"aspect ratio\" default=\"3:4\"}",
    "texture": "Motion blur, rain streaks, ISO noise, chromatic aberration",
    "lighting": "City night lights (Bokeh), Flash bulb direct illumination",
    "depth_of_field": "background city lights blurred"
  },
  "background": {
    "setting": "{argument name=\"setting\" default=\"Neo-Tokyo Street at night (Rainy)\"}",
    "elements": [
      "Large vertical Japanese Kanji neon signs (blurred)",
      "Text overlay 'FUTURE' in bold chrome typography at top",
      "Text overlay 'ERR_404' glitching across the chest",
      "Datestamp '2077/11' in corner",
      "Barcode graphic overlay bottom right"
    ],
    "atmosphere": "Dystopian luxury, wet, electric",
    "lighting": "Cyan and Magenta clash"
  },
  "the_vibe": {
    "energy": "High-tech Low-life",
    "mood": "Edgy and dangerous",
    "aesthetic": "Cyberpunk / Synthwave Magazine",
    "authenticity": "Editorial Fashion",
    "story": "A hacker blending into the nightlife",
    "caption_energy": "Signal Lost"
  },
  "constraints": {
    "must_keep": [
    ]
  }
}

Horror-Style Text Banner Prompt (Kawakuchi Hiro Exploration Team Style)

poster-flyer

A prompt for Nano Banana Pro focused on generating a text-only banner in the style of the old Japanese TV show 'Kawakuchi Hiro Exploration Team'. It specifies a black background, red text, centered alignment, and a rough, powerful, horror-style brush script font with heavy strokes, blurring, and sharp tips to convey shock and terror.

Show full prompt
Solid black background (#000000).
Place the following text in the center using solid red (#ff0000) characters:
"{argument name="text line 1" default="Mystery of the Darkness"}
{argument name="text line 2" default="The mysterious glowing river"}
{argument name="text line 3" default="Existed!!"}"
(Line break into 3 lines)
・The font should be a rough, powerful, horror-style brush script.
・The design should have the momentum of a brush, with rough textures like fading or ink bleeding.
・The characters should be thick, uneven, sharply pointed, eerie, and impactful.
・A fierce, handwritten design expressing fear and shock.
・A design written with a thick brush, having a vertical tendency, as if written by a strong man with a calligraphy brush.

Advanced Commercial Food/Product Poster Template with Vertical Layering

poster-flyer

A highly advanced, structured prompt template for Nano Banana Pro (intended for use with Gemini) to create high-end commercial posters for food or products. The prompt uses a 'vertical layered suspension structure' to deconstruct the subject into components (ingredients, structure, final product) and includes detailed instructions for typography, lighting, material texture, and branding elements, all floating against a pure black background.

Show full prompt
Aspect Ratio: 9:16 Vertical
Image Style (Adjustable based on subject): High-end commercial photography, dark luxurious feel, cinematic texture, hyper-realistic, high detail
Background (Adjustable based on subject): Pure black background (#000000), no pedestal, no platform, no ground, all subjects and elements suspended in space
[Subject]
The core display subject is: [{argument name="core display subject" default="User provided subject"}]
It is mandatory to use your database knowledge and internet search to deconstruct the subject into multiple “identifiable, understandable, and hierarchical components.” Please determine the deconstruction logic and hierarchy based on the subject's characteristics.
[Overall Composition]
The overall composition uses a “Vertical Layered Suspension Structure,” forming a clear visual reading path from top to bottom.
There is a clear spatial gap between each layer, and layers are connected by air, steam, light, and shadow, rather than direct contact.
The visual axis is centered in the frame, making the composition stable yet dynamic.
[Title System (Top)]
At the top center of the frame, a high-end main title is suspended:
Copywriting content is automatically generated by AI based on the subject (can include Chinese main title + English subtitle)
Font Style (Adjustable based on subject): Handwritten brush calligraphy style / Natural writing feel
Material (Adjustable based on subject): 3D metallic texture, imitating forged gold metal
Feature Characteristics (Adjustable based on subject): Heavy, 3D, with realistic metal reflection, highlights, and shadow layers
[Layered Structure (Middle Subject Area)]
Based on the subject, autonomously generate 4–6 logically clear suspended levels, such as:
Raw Material Layer / Composition Layer / Key Element Layer / Core Structure Layer / Atmosphere or Emotion Layer
Each layer has clear material, color, texture, and volume
Air and space are left between layers; they are not crowded or stacked
All middle layers:
Are in slight steam, heat, or air turbulence
Have fine particles, mist, vapor, or dust floating
Are controlled by a unified lighting system, maintaining overall consistency
[Transition Zone (Important)]
Between the subject layering and the final presentation, deliberately reserve a “significantly larger spatial gap”:
This area is mainly composed of air, steam, smoke, energy flow, and light mist
No physical objects are placed here
The function is to create rhythm, breathing room, and visual contrast
To reinforce the transition “from structure to finished product / from process to result”
[Final Product Layer (Bottom)]
The bottom of the frame presents the complete, final form of the subject:
State is “finished state / peak state / most attractive presentation”
Texture is full, details are rich, with strong appeal or infectivity
Naturally blends with the background but clearly stands out
Steam, smoke, or energy sensation continuously rises from this area
[Information Annotation System]
Appropriately add descriptive annotations to the image:
Bilingual Chinese and English
Text is restrained and elegant
Use thin lines or arrows to point to the corresponding level
Annotation content is automatically generated by AI based on the subject
Does not overshadow the main subject, only serves for “advanced interpretation”
[Signature / Brand Element]
Bottom right of the frame:
A brand signature or signature Logo is suspended
Style is consistent with the main title (brush calligraphy feel, metallic gold, 3D, etc.)
Can be paired with slight starlight or shimmering effects to emphasize luxury
At the bottom, there is a one-sentence commercial hit SLOGAN tailored to the subject
[Lighting System]
Professional studio lighting at 45° angle
Warm contour light (rim light) outlines structural edges
Local highlights emphasize material realism
Steam and smoke are cut by the light, forming volumetric light
[Overall Temperament]
Dark tone, restrained, expensive, or on one side of the bottom (adjustable based on subject)
Possesses “soul / warmth / handmade feel / high-end commercial aesthetic”
Suitable for brand posters, key visuals, and cover-level commercial displays

Cinematic Cyberpunk Tokyo Street Scene Prompt

poster-flyer

A customizable prompt for generating a cinematic medium shot of a character standing in a rain-slicked Tokyo street at night, highlighting glowing neon signs, volumetric lighting, and a futuristic cyberpunk atmosphere.

Show full prompt
A cinematic medium shot of {argument name="Description of your character" default="[Description of your character: e.g., a boy cwith blue hair and a leather jacket]"} standing in a rain-slicked Tokyo street at night. Glowing neon signs in pink and teal reflecting in puddles. High detail, 8k resolution, volumetric lighting, futuristic cyberpunk atmosphere, shot on 35mm lens.

Floating Sky Castle Digital Art Poster Prompt

poster-flyer

A highly detailed prompt for generating a cinematic digital art poster of a majestic floating 'Sky Castle' that fuses Western medieval architecture with subtle Qing Dynasty Chinese influences, hovering above an ethereal cloud sea rendered in ink wash style.

Show full prompt
A cinematic digital art poster featuring a majestic floating "Sky Castle" in the form of a miniature island, hovering serenely above an endless sea of clouds and dominating the composition.

The floating island is shaped as a grand Western-style medieval castle complex, centered around a towering central keep with conical roofs, fortified stone walls, multiple cylindrical turrets, crenellated battlements, arched gateways, drawbridges, and multi-level ramparts. The entire structure embodies authentic medieval European castle architecture: massive stone masonry, narrow arrow-slit windows, wooden hoardings, and a grand central tower rising prominently in the middle.

The castle seamlessly incorporates subtle Qing Dynasty Chinese influences: ornate tiled roofs with gentle upturned eaves crowning the turrets, intricate wooden pavilions nestled within courtyards, and decorative ridge ornaments on the main keep. The scene is alive with tiny Qing Dynasty inhabitants in period clothing: scholars in flowing robes, merchants with queues and silk garments, women in elegant traditional attire, street vendors with bamboo baskets, sedan chair bearers, rickshaw pullers, children playing, and horse-drawn carts — all bustling across the castle’s courtyards, bridges, and ramparts.

The castle is intertwined with lush subtropical greenery: ancient banyan trees climbing the stone walls, lychee groves spilling over the battlements, lotus ponds in the inner courtyards, and winding rivers cascading like waterfalls down the floating structure. No modern elements — only a harmonious fusion of classic Western medieval castle design with delicate Qing Dynasty Chinese details, creating a fairy-tale sky fortress surrounded by serene natural beauty.

The castle floats peacefully above a vast, ethereal cloud sea rendered in the traditional Chinese ink wash painting style, with soft misty gradients, delicate brush-like textures, and atmospheric depth.

Completely free of any text, lettering, typography, or overlaid information — pure visual composition with no words present.

Surround the floating castle with generous negative space for a clean, museum-like elegance. The overall layout is restrained, balanced, and sophisticated, evoking the feeling of contemplating a rare and precious art piece.

Style: Octane Render, Cinema 4D, isometric perspective, micro world, living ecosystem, 8K ultra-high resolution. DreamWorks animation quality, intricate 3D modeling, delicate soft light projection, cinematic atmosphere, vibrant yet harmonious colors, warm golden-hour lighting with gentle lens flares and subtle god rays.
Prev 70 / 86 Next

Prompts are model-agnostic and work with Midjourney / DALL-E / Flux / Stable Diffusion.

Information boundary

Information on this page is collected from official documents for technical presentation only and does not imply our endorsement. Pricing, quotas and availability are subject to the latest official statements. We make no commitment regarding any action you take after leaving this site.

Similar skills

视频短视频图片音乐音频配音口播数字人全能创作

Marked paid

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

Marked paid

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。一节课的讲解也能做成课程口播。

罗斯蒙德可视化图形生成

Not specified

【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

Marked free

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

FreemiumAPI key required

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。

架构图一键生成

Marked paidAPI key required

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。

What is a Skill

A Skill is a packaged single capability, such as text recognition, document summarization, or keyword extraction. Developers wrap the calling logic and prompts into a plugin-like unit, so users can load it without understanding the underlying model. StackPilot indexes a large number of skills that can be tried instantly or assembled into a plan.