← 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License information is collected from official sources and may be outdated or missing.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.

702 matches

3D Pixar-Style Animated Character Grid Prompt

comic-storyboard

A prompt for generating a 6-panel grid of a 3D Pixar-style animated young female character. It specifies extreme close-ups, dynamic poses, unique expressions, bold backgrounds, and stylized cartoon proportions to emphasize a playful and adventurous personality.

Show full prompt
A 3D Pixar-style animated young female character in a 6-panel grid, each panel showing an extreme close-up or large full-body shot that fills almost the entire frame. Each panel features a unique expression, dynamic pose, and outfit. Bold, bright backgrounds (yellow, blue, red, pink, purple, green). She has glossy wavy hair, sparkling large eyes, smooth skin, and stylized cartoon proportions. Every panel emphasizes her playful, confident, and adventurous personality through expressive gestures, lively poses, and distinctive fashion—from sporty to magical to casual chic. Edge-to-edge framing highlights intricate details and vibrant colors.

Cinematic Film Still Grid Prompt for Home Dance Sequence

comic-storyboard

A detailed JSON prompt for Nano Banana Pro to generate a 2x3 grid of cinematic film stills capturing an intimate home dance sequence. The prompt specifies complex parameters including image-to-image mode, preservation of identity and pose, specific lighting (warm soft ambient), camera settings (35mm, f/2.0), and detailed subject wardrobe (deep red satin dress) and motion blur control.

Show full prompt
{
  "generation_request": {
    "meta_data": {
      "task_type": "home_dance_film_still_grid_2x3_red_satin",
      "language": "en",
      "priority": "highest",
      "version": "v1.0_HOME_DANCE_2X3_RED_SATIN_FILM"
    },
    "input": {
      "mode": "image_to_image",
      "reference_image_usage": "very_high",
      "preserve_identity": true,
      "preserve_facial_features": true,
      "preserve_pose_dynamics": true,
      "notes": "Use the reference collage as the primary anchor. Keep the same couple, same room, same framing and dance flow across six panels. Change the woman's dress to a deep red satin dress with elegant sheen. Maintain realistic motion blur from dancing while keeping faces readable."
    },
    "output": {
      "aspect_ratio": "1:1",
      "resolution": "ultra_high",
      "num_images": 1,
      "layout": {
        "type": "grid",
        "rows": 2,
        "cols": 3,
        "gutter": "thin",
        "panel_consistency": "high"
      },
      "sharpness": "filmic_soft",
      "grain": "subtle_analog",
      "halation": "soft"
    },
    "scene": {
      "concept": "intimate home dance sequence captured as cinematic film stills",
      "environment": "cozy interior hallway/living room, simple door and framed picture on wall, warm daylight or tungsten mix",
      "lighting": {
        "style": "warm soft ambient light",
        "key_light": "window-like soft side light",
        "fill_light": "gentle fill to keep skin detail",
        "shadow_behavior": "soft, slightly hazy",
        "avoid": "hard flash, harsh HDR"
      }
    },
    "camera": {
      "lens": "35mm",
      "aperture": "f/2.0",
      "depth_of_field": "shallow to medium",
      "look": "vintage film still, slight softness and bloom"
    },
    "subjects": {
      "count": 2,
      "type": "adult couple",
      "male": {
        "wardrobe": "white fitted t-shirt, dark trousers",
        "notes": "keep outfit simple and consistent across panels"
      },
      "female": {
        "wardrobe": {
          "dress": "deep red satin midi dress, elegant drape, fluid skirt, subtle sheen highlights, fitted bodice",
          "details": "satin fabric reflections should look realistic and soft, not metallic"
        },
        "hair": "short bob haircut (keep consistent with reference if visible)"
      },
      "anatomy_rules": "correct hands and fingers, natural grip during dance, realistic arm alignment"
    },
    "motion_style": {
      "dance_energy": "gentle but dynamic",
      "blur": "controlled motion blur on dress and arms during spins, faces remain mostly readable",
      "camera_motion": "static camera, movement comes from subjects"
    },
    "grid_plan": {
      "panel_1": "couple starting to dance, close playful steps near the door",
      "panel_2": "facing each other holding hands, smiling, preparing to spin",
      "panel_3": "man dips woman slightly, red satin skirt flowing",
      "panel_4": "wo
    }
  }
}

Glass Horse Figurine Transformation Cinematic (Video Prompt)

comic-storyboard

A prompt for generating a 15-20 second 3D cinematic video based on a storyboard, showing a translucent blue glass horse figurine transforming into radiant gold as it gallops into a golden sunset landscape, emphasizing glossy materials and volumetric lighting.

Show full prompt
Generate a TVC 3D cinematic with this storyboard. Following the exact frames, telling a story of A translucent blue glass horse figurine adorned with traditional floral engravings awakens in a stylized blue world, transforms through light into radiant gold, and gallops into a golden sunset landscape. Duration: ~15–20 seconds. Style: 3D cinematic, glossy translucent materials, volumetric lighting.

Character Pose Variation Prompt

comic-storyboard

A prompt used with Nano Banana Pro to generate four different views/poses of a character, starting from a frontal image, allowing for seamless video connection. This prompt is designed to create variations of an existing subject.

Show full prompt
1: The back view of this character (diagonal rear)
2: The beautiful profile of this character (right side)
3: The upper body, diagonal rear view of this character (diagonal rear)
4: Close-up profile of this character's face

Manga Evolution Architectural Section Prompt

comic-storyboard

A structured prompt designed to generate an image depicting the 'Evolution of Manga' as a detailed architectural section, showing four stacked strata representing different phases, complete with representative artifacts and educational transitions, rendered with architectural realism.

Show full prompt
Evolution of Manga --> <LAYOUT> A single chunky block (like a museum cutaway) sliced to reveal 4 stacked floors/strata. Each level represents an era/stage/version inferred from INPUT. Right side: a vertical legend bar with dates/period labels inferred by the model. </LAYOUT>
<INFER_AND_RENDER> Infer 4 major phases and depict each with representative artifacts, tools, and environments. Keep transitions educational: show what changed between levels (materials, scale, method). </INFER_AND_RENDER>
<STYLE_NOTES> Architectural section realism: visible thickness, rebar/fasteners if applicable, realistic debris at cut edge. </STYLE_NOTES>

Surreal Rubber-Hose Ink Style Illustration

comic-storyboard

A detailed JSON prompt for generating a black and white illustration in the surreal 1930s rubber hose animation style. The prompt emphasizes high-contrast line art, heavy cross-hatching/stippling, and specific character features like a melting/dripping aesthetic, wide toothy grins, and hollow black eyes, aiming for a vintage underground comic vibe.

Show full prompt
{
"style_name": "Surreal Rubber-Hose Ink",
"Subject": "{argument name=\"Subject\" default=\"[SUBJECT]\"}",
"prompt_structure": {
"prefix": "A subject designed in a surreal 1930s rubber hose animation style.",
"core_aesthetic": "Hand-drawn black and white ink illustration, clean white background.",
"shading_technique": "High-contrast line art, heavy use of cross-hatching and stippling for shading.",
"character_features": "Melting and dripping aesthetic, wide toothy grins, hollow black eyes.",
"vibe": "Vintage underground comic, minimalist but detailed textures, clean outlines.",
"full_composite_prompt": "Designed in a surreal 1930s rubber hose animation style. Hand-drawn black and white ink illustration on a clean white background. Features high-contrast line art with heavy use of cross-hatching and stippling for shading. The character has a melting, dripping aesthetic, wide toothy grins, and hollow black eyes. Vintage underground comic vibe, minimalist but detailed textures, clean outlines."
},
"negative_prompt": "color, gradients, 3d render, photo, realistic, grey tones, blurry, messy lines, background scenery, cropped, out of frame, cut off",
"recommended_settings": {
"aspect_ratio": "1:1",
"color_palette": "Monochrome / Black and White"
}
}

Giant Abstract Enemy Character Generation Prompt (Step 2)

comic-storyboard

The second step in a multi-step process, this prompt generates a high-resolution (4K recommended) image of a gigantic abstract enemy entity, described as being formed entirely from swirling black mist with a traditional Noh mask face, set against a dark, mountainous landscape.

Show full prompt
A gigantic abstract entity formed entirely from swirling black mist,
its body loosely humanoid but constantly shifting,
a large traditional Noh mask emerging from the fog as its face,
no solid body, only dense smoke shaping arms and torso,
black mist flowing and dissolving into the surrounding air,
dark mountainous landscape beneath,
soft diffused moonlight cutting through the fog,
highly cinematic realism, symbolic and minimal,
film still, subdued color palette, 35mm lens look

Morning Routine Video Generation using Kling 3.0

comic-storyboard

A detailed video prompt generated by Freepik's assistant (GPT-5) based on an image from Nano Banana Pro, used to create a short film sequence with Kling 3.0. The prompt outlines three scenes focusing on smooth camera movements, close-ups of morning rituals, and a cinematic conclusion.

Show full prompt
Scene 1
Use a smooth dolly shot to approach the window, transitioning from a long shot to a medium shot of the subject taking a deep breath in the morning light. Focus on subtle movements like relaxing the shoulders and finger reactions, creating an adorable atmosphere with distant natural sounds (birds chirping, wind) layered with delicate piano music. Crossfade to a close-up where the window light reflects on the fingertips.

Scene 2
Use close-ups focusing on steaming cups and small objects to rhythmically follow the hand movements (lifting the cup, stirring with a spoon, etc.). Use a combination of slow motion and light time-lapse to express warmth and innocence, layering sound effects like breathing and small laughs. The steam fills the screen and dissolves, leading to the next scene.

Scene 3
The camera pulls back to show the whole scene, concluding with the light movement of the subject ready to go out. Show the lingering atmosphere through the rhythm of steps and hand gestures, concluding cinematically with a backlit silhouette and soft color tones. The music gently fades out, leaving the lingering feeling of everyday life.

Cinematic Action Video Prompt: Banana Fairy vs. Zombies

comic-storyboard

A detailed video generation prompt for Vidu AI, creating a cinematic action scene where a banana fairy girl fights off zombies using only bananas as weapons in a fantastical indoor space filled with banana decorations. The prompt includes specific instructions for character, setting, action, camera work, lighting, and style.

Show full prompt
Use the woman in the attached image as the main character.
The setting is a fantastical indoor space surrounded by bananas, identical to the attached image.
Zombies attack one after another in a space lined with banana trees and giant banana objects.
The banana fairy girl quickly grabs bananas around her and throws them in rapid succession.
The only weapon is bananas.
The bananas fly straight while spinning at high speed, hitting the zombies' heads.
The moment of impact is in slow motion.
Strong shockwave effects, light trails, dynamic motion blur.
The hit zombies are blown away, collapsing while shaking the surrounding banana decorations.
The girl jumps onto a giant banana and throws bananas accurately while spinning.
Emphasize the impact with a low-angle hero shot.
Dynamic tracking camera following the flying bananas.

Camera Direction:
・High-speed dolly-in towards the girl
・Intense handheld-style shake when zombies approach
・Slow motion upon banana impact
・Smooth tracking shot following the flying bananas
・Tense low angle

Lighting:
Strong contrast
Rim light emphasizing contours
Contrast with the fantastical gold interior light

Style:
Anime Cinematic Action
High definition
Smooth animation
Strong motion blur
Dynamic composition
Depth of field

Atmosphere:
Tension
Thrilling
Heroic

No text
No subtitles

B2B Meta Ad Carousel Story Creation Prompt

comic-storyboard

A high-level instruction for Nano Banana Pro to generate a series of images suitable for a carousel ad format, specifically requesting the creation of a story-based comic strip creative for B2B Meta advertising.

Show full prompt
Just give instructions like turning the carousel story into a comic creative

Detailed Cinematic Wuxia Scene Prompt: Dark Raven vs. Azure Frost

comic-storyboard

An extremely detailed, multi-scene prompt designed for cinematic video or image generation, focusing on a Wuxia (Chinese martial arts fantasy) style. It outlines five distinct camera shots, character actions, visual elements (heavy rain, ancient temple, lightning), camera movements (Dolly Shot, Crane Up, Bullet Time), dialogue, and sound effects for a dramatic confrontation between two characters, Dark Raven and Azure Frost.

Show full prompt
Overall Style Prompt: Chinese Wuxia fantasy style, cinematic quality, motion blur, abandoned ancient temple in heavy rain, gloomy sky, lightning occasionally illuminating raindrops and broken eaves, the image is full of power and speed.

• Scene 1 (0-3 seconds): Dark Raven drags his sword, Azure Frost descends 
• Visuals: Rain pours down. Dark Raven wears heavy black armor emanating an ominous purple aura, dragging a massive chained dark iron greatsword with one hand. The blade scrapes the stone ground, creating dazzling sparks and ripples. His eyes are sinister as he looks ahead. Immediately after, Azure Frost lightly descends from the broken eaves of the ancient temple like a falling leaf. Her white and cyan tight-fitting outfit is sharp, her high ponytail flies, and the blue longsword in her hand is drawn with a 'zheng' sound, its cold aura pushing back the surrounding rain curtain. The two face off in the rain. 
• Cinematography: Extreme low-angle follow shot tracking the greatsword's path, then the camera quickly pulls back to show the full view of the confrontation in the rainy courtyard—one black and heavy, the other cyan and light. 
• Dialogue/Sound Effects: Dark Raven (low and hoarse): "{argument name="Dark Raven dialogue" default="You are beyond redemption."}" 
• Sound Effects: Heavy metal scraping, torrential rain, wind. 

• Scene 2 (3-6 seconds): Greatsword sweeps, light sword strikes like a flash • Visuals: Dark Raven suddenly exerts force, swinging the greatsword with both arms. A crescent-shaped black sword energy tears through the rain curtain and sweeps out. Raindrops evaporate in its path, and the stone ground is plowed open. Azure Frost's eyes narrow. Tapping the water surface with her toe, her body shoots up like a kite, executing a nimble side flip in the air, narrowly avoiding the sword energy. At the same time, using the momentum of her descent, the cold light of her sword tip condenses, striking straight at Dark Raven's throat like a meteor. 
• Cinematography: Fast-paced cuts. First, a side follow shot (Dolly Shot) captures the black sword energy slicing countless raindrops in slow motion, then switches to a high-angle view, showing the graceful trajectory of Azure Frost's aerial evasion and counterattack.
• Sound Effects: Heavy whistling of the greatsword cutting the air, 'chichi' sound of sword energy evaporating, sound of clothes tearing the wind. 

• Scene 3 (6-9 seconds): Mid-air clash, sparks fly • Visuals: Dark Raven swings his greatsword back, colliding precisely with Azure Frost's descending longsword! "Clang—!" The immense power of the greatsword fiercely clashes with the nimble cold aura of the longsword, erupting in dazzling blue-white sparks and a shockwave that pushes away all the surrounding rain. Dark Raven presses down with his strength advantage, while Azure Frost uses her light footwork, tapping the greatsword with her toe, using the force to backflip and resolve the immense pressure. 
• Cinematography: Orbiting shot (Bullet Time). The camera centers on the point of weapon collision, rotating 360 degrees rapidly, finally freezing on a close-up of the moment of maximum sparks and the two forces counteracting. 
• Dialogue/Sound Effects: Azure Frost (cold and firm): "{argument name="Azure Frost dialogue" default="Evil will not prevail!"}" 
• Sound Effects: Huge metal collision roar, humming sound of power confrontation. 

• Scene 4 (9-12 seconds): Azure shadows continuous, black wall defends • Visuals: The moment she lands, Azure Frost launches an attack. Her figure turns into a cyan afterimage, her longsword stabs rapidly, instantly transforming into several fierce cyan sword lights attacking Dark Raven from different angles. The cold aura of the sword tips leaves streaks of frost in the air. Dark Raven lets out a low roar, swinging the heavy greatsword into an impenetrable barrier, forming a purple-black sword energy shield. Amidst the dense 'ding-dang' sounds, the cyan sword lights are all blocked, but the powerful impact still forces Dark Raven to retreat three steps, each step crushing the stone bricks beneath his feet. 
• Cinematography: One-shot handheld follow shot (Shaky Cam). The camera closely follows Azure Frost's attack trajectory, with slight shaking accompanying each stab, then quickly pans to Dark Raven's defense and retreat, creating a strong sense of immersion. 
• Sound Effects: Dense, crisp sound of sword tips hitting the barrier, sound of stone bricks cracking, heavy footsteps and panting. 

• Scene 5 (12-15 seconds): Ultimate collision, swallowing the universe • Visuals: Dark Raven is enraged, injecting all his purple energy into the greatsword, plunging it into the ground! Boom! A thick purple-black light column shoots up into the sky, stirring the clouds above. Azure Frost shows no fear, pouring all her cold energy into her sword. Man and sword become one, transforming into a massive, pure cyan stream of light, descending like a comet, striking straight at the center of the light column. The two collide with a roar! Time seems to stand still, followed by an explosive, blinding white light and a circular airwave that sweeps away all the rain, debris, and dead leaves in the entire courtyard. 
• Cinematography: Rapid close-up zoom out. First, quick cuts between close-ups of Dark Raven's cold eyes and Azure Frost's determined eyes, then the camera rapidly pulls up and back like a rocket (Crane Up), turning into a distant overhead view, showing the shocking full scene of the expanding white light and the airwave sweeping across the ruins of the ancient temple. The image freezes at the peak of the white light. 
• Dialogue/Sound Effects: (Before collision) Dark Raven's roar and Azure Frost's clear shout intertwine.
• Sound Effects: Humming sound of energy convergence, earth-shattering explosion, followed by all sounds fading, leaving only the receding echo of the rain.

3D Animated Scene of Chicks and a Monster on Lily Pads

comic-storyboard

A prompt for generating a cinematic, ultra-detailed 3D animated film style image. It merges two concepts: two small fluffy chicks seen from behind on a floating lily pad, and a large purple stitched monster dominating the frame, set in a lush jungle pond environment with soft mist.

Show full prompt
Two small fluffy chicks seen from behind, standing together on a floating green lily pad, their backs fully facing the camera, maintaining their exact proportions and silhouettes.

The chicks are positioned at the very bottom foreground of the scene, while the large purple stitched monster remains dominant in the frame and subtly lowers its gaze downward.

Lush jungle pond environment with floating lily pads, soft mist near the water surface and warm natural daylight.

Cinematic, ultra-detailed, high-end 3D animated film style, soft realistic textures, no distortion, no stylization shift.
Prev 37 / 59 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。

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。

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。

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.