← Back to home
Skill

Ai Image Prompts

tencent_skillhub · 1.0.9 · Downloads 2K · Heat 56.2

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License information is collected from official sources and may be outdated or missing.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

5717 matches

Daikan-yama Morning Scene with Layered Textures

product-marketing

A detailed prompt describing a photorealistic scene in Daikan-yama on a rainy morning, focusing on the layered textures of a shell pink crochet knit and the contrast of light and skin, emphasizing the realism of Nano Banana Pro.

Show full prompt
Daikan-yama, 8 AM, March 27, 2026. Clear light after the rain. Today's theme is 'Layering of Textures.' A shell pink crochet knit stands out in the morning sun. The contrast between the light peeking through the mesh and the skin. Into that 'gap,' the realism of Nano Banana Pro is injected.

Tangible Melancholy: Surreal Editorial Portrait

product-marketing

A complex, highly artistic prompt for a surreal editorial portrait, titled 'Tangible Melancholy,' featuring a subject whose face and hair are adorned with physical props like vintage buttons and dried flowers, set in a dusty antique restoration workshop. The prompt emphasizes texture, razor-thin depth of field (Hasselblad camera style), and a melancholic mood.

Show full prompt
{
  "vibe_title_en": "Tangible Melancholy",
  "master_prompt": "A hyper-realistic, close-up portrait of The Protagonist transformed into a living scrapbook, set within a sun-drenched, dusty antique restoration workshop. The subject's forehead and hair are adorned with physical, high-fidelity props: oversized glossy vintage campaign buttons, ceramic pins with hand-painted sad faces, and dried pressed wildflowers adhered to the skin with visible theatrical spirit gum. Words like 'fragile' and 'echo' are scrawled directly onto the cheekbones in smeared grease pencil, showcasing authentic skin texture and pores beneath the markings. The subject wears a delicate, antique lace collar that feels brittle to the touch. The lighting is soft, diffused northern window light, highlighting the dust motes dancing in the air and the microscopic scratches on the plastic buttons. Shot on a Hasselblad H6D-100c with an 80mm f/1.9 lens to create a razor-thin depth of field, blurring the background shelves filled with porcelain limbs and glass eyes. The color grade mimics Kodak Portra 160—soft, pastel, and slightly desaturated, emphasizing the tactile reality of this surreal emotional inventory.",
  "meta": {
    "intent": "Editorial Portraiture",
    "priorities": "Texture, Emotion, Surrealism",
    "device_profile": "High-End Medium Format"
  },
  "frame": {
    "aspect": "4:5",
    "composition": "Center-weighted close-up",
    "layout": "Symmetrical balance with chaotic elements",
    "camera_angle": "Eye-level",
    "tilt_roll_degrees": "0"
  },
  "subject": {
    "gender": "Female",
    "identity": "The Living Canvas",
    "demographics": "Young Adult",
    "face": "Neutral expression, adorned with physical props (buttons, stickers, writing)",
    "hair": "Messy, textured updo intertwined with dried flora and pins",
    "body": "Head and shoulders only",
    "expression": "Melancholic, vacant stare, slightly parted lips",
    "pose": "Static, facing forward, confronting the viewer"
  },
  "wardrobe_accessories": {
    "garments": [
      {
        "item": "Victorian Collar",
        "material": "Antique Lace",
        "color": "Off-white / Cream",
        "fit": "Tight / Choker style"
      }
    ],
    "accessories": [
      {
        "item": "Oversized Pin Buttons",
        "color": "White, Red, Black",
        "material": "Glossy Plastic and Tin",
        "brand_style": "Vintage Punk / DIY"
      },
      {
        "item": "Dried Flowers",
        "color": "Faded Pink, Brown",
        "material": "Organic matter",
        "brand_style": "Nature"
      }
    ]
  },
  "environment": {
    "setting": "Antique Restoration Workshop",
    "surfaces": "Dusty wood, porcelain, glass",
    "depth": "Shallow depth of field (Bokeh)",
    "atmosphere": "Quiet, dusty, nostalgic",
    "lens_interaction": "Sharp focus on eyes/buttons, creamy fall-off"
  },
  "lighting": {
    "key": "Soft North Window Light",
    "fill": "White"
  }
}

Stranger Things Duo in Retro Arcade (3 Prompts)

product-marketing

Three distinct prompts used with Gemini Nano Banana Pro to generate images of Sadie Sink and Millie Bobby Brown (Max and Eleven) in a retro arcade setting, focusing on Y2K fashion, specific camera shots (full shot, arcade aisle perspective, close-up portrait), and detailed lighting effects from the arcade machines.

Show full prompt
Image 1 Prompt: Frontal Full Shot.

A high-resolution wide shot featuring two young women standing centrally in a retro "Palace Arcade." On the left, a woman with long ginger hair in braids wears a vibrant {argument name="left hoodie color" default="orange"} cropped hoodie with gothic "Chrome" lettering and olive green baggy cargo trousers. On the right, a woman with a sleek high ponytail wears a bubblegum {argument name="right hoodie color" default="pink"} cropped hoodie and a distressed black denim micro-skirt. Both are wearing oversized, shaggy faux-fur boots, one pair in solid black and the other in a brown-tan mix. They hold small metallic designer handbags. The background is filled with glowing arcade cabinets like "Pac-Man" and "Hawkins Arcade" neon signs, creating a moody, cinematic atmosphere with purple and blue ambient lighting.

Image 2 Prompt: Perspective Arcade Aisle.

A medium-full shot taken from a slight side angle, emphasizing the depth of the arcade aisle. The two women maintain their outfits: the orange cropped sweatshirt and green cargos on the left, and the pink cropped sweatshirt with the black denim skirt on the right. The woman in pink has her hands tucked into her skirt pockets, revealing a peek of white undergarments at the waistband, a hallmark of Y2K fashion. The lighting is dominated by the glowing yellow and blue screens of "Dig Dug" and "Pac-Man" machines. The floor is a polished concrete reflecting the neon "Palace" sign above.

Image 3 Prompt: Close-up Duo Portrait:

"A focused medium-close shot highlighting the subjects' styling and accessories. Both women have long, thick blonde-toned braids draped over their shoulders. The woman on the left wears the orange cropped "Chrome" jersey, while the woman on the right wears the pink version. The woman on the right also sports a large, distinctive silver "D" logo belt buckle on her denim skirt. They pose with neutral, high-fashion expressions against a backdrop of "Pac-Man" and "Galaga" cabinets. Above them, a bright yellow "Arcade" neon sign and a blue "Hawkins Arcade" sign provide sharp, high-contrast backlighting that catches the edges of their hair."

High-Fashion Doll Aesthetic Portrait of Margot Robbie Lookalike

product-marketing

A detailed, structured prompt for generating an ultra-photorealistic, high-fashion editorial portrait of a young woman resembling Margot Robbie, emphasizing a stylized, plastic doll aesthetic with specific attire, pose, and studio lighting conditions.

Show full prompt
{
  "image_generation_prompt": {
    "subject": {
      "description": "Young woman with a strong resemblance to Margot Robbie.",
      "hair": "Long, voluminous, cascading loose waves.",
      "face": "Contoured makeup, full lips, sharp gaze.",
      "body": "Slim, toned physique."
    },
    "attire": {
      "clothing": "Fuchsia beret, halter crop top, opaque tights, massive platform block heels.",
      "style": "High-fashion doll aesthetic."
    },
    "styling_and_accessories": {
      "jewelry": [
        "Tiny gold charm on shoe strap"
      ]
    },
    "environment": {
      "setting": "Minimalist studio setup.",
      "background": "Seamless grey backdrop.",
      "water": "None."
    },
    "pose": {
      "posture": "Leaning back, torso elevated, knees bent sharply.",
      "arms": "Extended backwards to support body weight.",
      "angle": "Low-angle side profile."
    },
    "lighting_and_mood": {
      "lighting": "Crisp studio lighting, sharp floor shadows.",
      "mood": "Editorial, plastic, stylized.",
      "colors": "Fuchsia pink against neutral grey."
    },
    "camera_and_technical": {
      "style": "Ultra Photorealistic, RAW photo.",
      "lens": "50mm",
      "aperture": "f/5.6",
      "quality_tags": [
        "8k resolution",
        "highly detailed",
        "studio lighting",
        "hyper-realistic"
      ]
    }
  }
}

Sensual Editorial Portrait Grid with Identity Preservation

product-marketing

A highly structured JSON prompt for Nano Banana 2 designed to create a 3x3 editorial portrait grid (image-to-image mode) with a soft, sensual, high-fashion aesthetic. It mandates strict identity preservation from a reference image and specifies nine different panel compositions focusing on face and hand interactions.

Show full prompt
{
  "generation_request": {
    "meta_data": {
      "tool": "Nano Banana 2",
      "task_type": "face_focused_sensual_editorial_grid",
      "language": "en",
      "priority": "highest"
    },

    "input": {
      "mode": "image_to_image",
      "reference_image_usage": "high",
      "preserve_identity": true,
      "preserve_facial_features": true,
      "notes": "Use the uploaded image as the facial reference. Maintain consistent identity across all panels while creating a photoreal 3x3 editorial portrait grid with a soft, sensual, high-fashion aesthetic. Focus on subtle emotional variation, refined expressions, and natural interaction between face and hands. Keep the composition minimal, elegant, and visually cohesive."
    },

    "output_settings": {
      "aspect_ratio": "1:1",
      "orientation": "square",
      "resolution_target": "ultra_high_res",
      "num_images": 1,
      "layout": {
        "type": "grid",
        "rows": 3,
        "cols": 3,
        "gutter": "thin",
        "outer_border": "none",
        "panel_consistency": "maximum"
      },
      "render_style": "soft_luxury_editorial_realism",
      "sharpness": "skin_detail_high",
      "grain": "very_subtle_film",
      "dynamic_range": "soft_natural",
      "color_grade": "warm_daylight_neutral"
    },

    "subject": {
      "identity": "consistent facial identity from reference",
      "hair": "soft natural brunette hair, loosely styled, consistent across panels",
      "makeup": "sensual editorial makeup with natural skin glow, defined eyes, deep rose or red lips",
      "outfit": "black minimal thin-strap top with sheer long gloves",
      "styling": "clean, minimal, intimate editorial"
    },

    "pose_language": {
      "direction": "close-up and medium close-up compositions centered on face and hands",
      "movement": "subtle, controlled, natural transitions",
      "expression": "calm, confident, slightly mysterious",
      "hands": "soft interaction with face, chin, cheeks, lips, and neck"
    },

    "panel_direction": {
      "panel_1": "side gaze with chin resting on hand",
      "panel_2": "direct gaze with relaxed shoulders",
      "panel_3": "soft smirk with composed posture",
      "panel_4": "head tilt with fingers touching cheek",
      "panel_5": "centered pose with chin supported by hand",
      "panel_6": "both hands framing the face",
      "panel_7": "side profile with hands near shoulders",
      "panel_8": "hands under chin with lifted gaze",
      "panel_9": "gentle turn toward camera with refined expression"
    },

    "camera": {
      "lens": "85mm portrait lens",
      "framing": "tight portrait and medium close-up",
      "angle": "eye-level editorial",
      "focus": "sharp on eyes and skin texture",
      "depth_of_field": "soft background blur"
    },

    "lighting": {
      "type": "soft natural daylight",
      "direction": "side-lit window light",
      "quality": "diffused, clean, flat"
    }
  }
}

High-Contrast Mountain Dew Can Product Shot

product-marketing

A highly technical JSON prompt comparing GPT Image 1.5 and Nano Banana 2 outputs, designed to generate a hyper-realistic, 8K product shot of a Mountain Dew can with explosive liquid burst effects, detailed condensation, and cinematic high-contrast studio lighting against a deep emerald green background. This prompt is model-agnostic but was used for comparison with Nano Banana 2.

Show full prompt
{"header":{"resolution":"8K_UHD","renderEngine":"Hyper-Realistic AI-Modified","aspectRatio":"3:4","postProcessing":["extreme-micro-detail","zero-noise","clean-gradients"]},"sceneComposition":{"primarySubject":{"model":"Mountain Dew Aluminum Can","transform":{"position":"Center","tilt":"Slightly Backward","lean":"Subtle Diagonal"},"surface":{"material":"Metallic Matte/Gloss Hybrid","overlay":"Dense condensation droplets","branding":"Logo fully sharp, legible, and centered"}},"fx_dynamics":{"liquidBurst":{"color":"Neon Green","behavior":"Explosive upward/outward eruption","source":"Behind can","geometry":"Symmetrical crown-like burst","particles":"Hundreds of frozen mid-air droplets"}},"assets":[{"type":"Ice Cubes","properties":["Transparent","Sharp-edged","Refractive"],"distribution":"Floating at varying Z-depths"},{"type":"Limes","states":["Wedges showing pulp texture","Whole fruit with pebble-grain peel"]}],"lightingAndEnv":{"style":"Cinematic Studio / High-Contrast","highlights":"Specular icy-white","background":{"fill":"Deep Emerald Green Gradient","bokeh":"Soft green glowing particles","focus":"Shallow depth of field (Subject: Sharp, BG: Soft)"}}}}

Neon Orange Fashion Portrait of Sadie Sink

product-marketing

A highly detailed JSON prompt for Nano Banana 2 to generate an 8k photorealistic fashion portrait of Sadie Sink in a neon orange outfit against a neon purple tiled background, specifying biometric details, wardrobe, pose, and cinematic lighting setup.

Show full prompt
{
  "subject": {
    "identity": {
      "biometric_reference": "{argument name="biometric reference" default="Sadie Sink"}",
      "facial_anatomy": {
        "description": "heart-shaped face, defined cheekbones, expressive blue-green eyes, natural lashes",
        "skin": "fair skin with freckles, visible pores, realistic texture"
      },
      "hair": {
        "color": "warm golden blonde",
        "state": "natural loose strands with soft movement"
      },
      "body": {
        "morphology": "slender natural proportions"
      }
    }
  },
  "wardrobe": {
    "upper_body": "neon orange cropped top with deep V neckline, fitted silhouette",
    "lower_body": "matching neon orange pleated mini-skirt with structured pleats",
    "hosiery": "black mesh stockings with natural fit"
  },
  "pose_action": {
    "description": "low-angle full-body shot, grounded crouch pose with confident stance",
    "fidelity": "natural balanced posture"
  },
  "scene": {
    "environment": "90-degree corner with glossy neon purple tiles",
    "wall_art": "grunge graffiti '{argument name="graffiti text" default="Love"}' integrated into tiles",
    "props": "large pink faux-fur plush rabbit"
  },
  "lighting": {
    "setup": "cinematic lighting with warm key and purple rim",
    "specular": "subtle reflections across surfaces"
  },
  "camera": {
    "aspect_ratio": "9:16",
    "lens": "24mm wide-angle f/2.8",
    "format": "8k RAW photorealistic"
  },
  "negative_constraints": {
    "forbidden": [
      "extra limbs",
      "distorted anatomy",
      "logos/text except 'Love'",
      "watermarks",
      "plastic skin"
    ]
  }
}

Low-Angle Fashion Campaign Photograph

product-marketing

A prompt for generating a commercial fashion campaign photograph using Nano Banana Pro, focusing on an exaggerated low-angle perspective where a product dominates the foreground and the model is visible in the background against a clean white studio setting.

Show full prompt
Low-angle fashion campaign photograph of a confident model holding a large {argument name="product name" default="[product name]"} very close to the camera, exaggerated perspective with the hand and product dominating the foreground, full-body pose visible in the background, wide stance, dynamic posture, clean pure white studio background, high-key lighting, sharp focus on product, slight depth of field on the model, bold colorful outfit with strong contrast tones, modern beauty advertising aesthetic, ultra-clean composition, commercial studio photography, glossy packaging detail visible, crisp shadows

Pop-Art Comic Artist Diorama Prompt for Nano Banana Pro

product-marketing

A complex, weighted prompt for Nano Banana Pro and Nano Banana 2 to generate a 2x2 grid featuring 3D dioramas of legendary comic artists, rendered in a pop-art installation style with exaggerated comic proportions, Ben-Day dots, flat lighting, and strong negative weights against photorealism.

Show full prompt
Prompt:   `2x2 grid, do this for 4 Legendary Comic Artists (e.g. {argument name="artist names" default="Jack Kirby, Stan Lee, Moebius"})` <instructions>   input:   `Artist Name`   Anchor:   `A 3D diorama of the artist drawing at a drafting table, with a giant speech bubble with word inferred by AI, their famous superhero creations bursting out of the paper in 3D::3.5`   Morphology:   `Exaggerated comic proportions, thick black outlines on 3D objects, dynamic forced perspective::3`   Material Physics:   `Matte painted surfaces, visible Ben-Day dot textures on skin and clothes, flat primary colors::3`   Illumination:   `Flat graphic lighting, no realistic gradients, hard black shadows::1.5`   Render Stack:   `Pop-art installation photography, vibrant saturation, clean vector edges::1`   Negative:   `[Photorealism, muted colors, soft gradients, realistic skin textures, 3D clay]:: -1`

2x2 Grid Pop-Up Cookbook Diorama Prompt for Nano Banana

product-marketing

A structured instruction set for Nano Banana to generate a 2x2 grid, where each panel represents an open book spread for a different country's dish, featuring 2D vintage sketches on the left page and a 3D pop-up diorama of the finished dish on the right, all styled as a cohesive atlas series.

Show full prompt
<instructions>
[Use the UNIVERSAL WRAPPER above exactly as-is.]

If input includes ingredients, pick 4 distinct countries with famous dishes that fit those ingredients (hidden gems welcome). Output one 2x2 grid: each panel shows an open book spread for that country.

Per panel:
- Left page: 2D vintage sepia sketches (timeline/illustrated recipe flow, minimal text).
- Right page: 3D pop-up diorama of the finished steaming dish emerging from the page.
- A tiny chef mini stands beside the dish.
- All 4 books look like one cohesive atlas series.
- Only readable text: engraved plate “Dish ({argument name="country name" default="Country"})”.

Style: Cinematic top-down lighting emphasizing 2D vs 3D depth, macro detail, cohesive atlas design, clean background, shallow DOF, no logos, no long text.
</instructions>

Hyper-Realistic 3D CGI Collectible Figurine Prompt for Nano Banana 2

product-marketing

A detailed prompt for Nano Banana 2 to convert an existing character concept into a hyper-realistic 3D CGI collectible figurine render, emphasizing physically-based rendering, material realism (fabric, metal, skin), anatomical correctness, and a clean studio aesthetic.

Show full prompt
Convert to hyper-realistic 3D CGI collectible figurine render. Physically-based rendering, octane render quality. Preserve the original character design, pose, and outfit exactly. Transform all surfaces into real-world materials: fabric with visible weave and drape, metal with wear, scratches and oxidation, synthetic matte skin. Pure white studio background, clean seamless white backdrop, soft diffused lighting with subtle rim light. No cel shading, no toon rendering. High-end statue/collectible photography aesthetic. Ultra detailed, 8K. Fix and reconstruct all hands and fingers with correct anatomy: natural finger count, proper joint articulation, realistic proportions, no fused or melted digits. Remove all 2D artifacts, compression glitches, and Midjourney inconsistencies. Ensure full anatomical coherence across the entire figure: symmetrical features, clean silhouette, no floating elements, no distorted limbs, no duplicated body parts. Hyper-detailed hair simulation: individual strand rendering, realistic hair clumping, natural flow and gravity, visible scalp at roots, micro flyaways, SSS translucency on hair tips. Every surface pushed to maximum realism: pore-level skin texture, fabric fiber micro-detail, specular highlights on every material, depth in shadows

9-Panel Editorial Grid Portrait with Cat for Nano Banana Pro

product-marketing

A highly specific prompt for Nano Banana Pro to generate a 3x3 editorial portrait grid, strictly preserving the identity of an uploaded woman across all panels, showing her interacting affectionately with a photorealistic white Van cat with blue eyes, set in a clean minimal studio with soft lighting.

Show full prompt
Use the uploaded woman as the exact subject. Keep her face, skin tone, proportions, and natural beauty identical. Create a 3x3 editorial portrait grid where she appears in all panels with subtle but professionally styled pose variations. She is holding and interacting lovingly with a small white Van cat with bright blue eyes. The cat must look adorable, elegant, calm, and photorealistic. The interactions should feel affectionate, natural, and editorial, including gentle cuddling, kissing the cat, holding it close, and soft cheek-to-fur contact.

Subject: Same woman from reference image with long straight brunette hair, natural flow, consistent across panels. Soft natural glam, glowing skin, neutral lips, defined eyes. Minimal white tank top and light blue jeans, unchanged across all panels. Small fluffy white Van cat with vivid blue eyes, elegant face, soft fur, photorealistic, anatomically correct, consistent across panels.

Scene: Clean minimal studio with soft neutral background. Soft daylight, diffused, even skin illumination. Intimate, calm, warm, affectionate, natural, effortless beauty.

Panel directions: panel_1 - holding the white blue-eyed Van cat close to her chest, face near the cat, soft affectionate expression; panel_2 - direct eye contact with camera while gently cradling the cat in her arms, calm editorial pose; panel_3 - looking lovingly at the cat, cheek softly touching its fur, intimate and tender moment; panel_4 - kissing the cat gently on the head, elegant posture, soft emotional beauty portrait; panel_5 - hero center pose, holding the cat securely and naturally, confident and warm editorial composition; panel_6 - slight smile while hugging the cat close, relaxed shoulders, soft luxury portrait feeling; panel_7 - three-quarter profile, cat nestled in her arms, graceful neck line, refined magazine-style composition; panel_8 - chin slightly lifted, cat close to her shoulder, poised and elegant gaze, affectionate but polished; panel_9 - soft turn toward camera while cuddling the cat, serene expression, intimate final frame.

Pose language: very subtle, refined model-like shifts only. Soft, confident, loving, elegant expression. Natural and gentle hands, securely supporting the cat with realistic hand placement. Elongated neck, relaxed shoulders, subtle editorial asymmetry. Gentle cuddling, soft kissing, cheek contact, loving embrace, calm cat handling.

Camera: 85mm portrait lens, close-up to mid shot framing, eye-level angle, sharp focus on eyes, skin texture, and cat fur detail, soft background blur depth of field.

Output style: clean_beauty_editorial, ultra_skin_detail sharpness, very_subtle grain, soft_natural dynamic range, neutral_skin_tone color grade. 4:5 aspect ratio, portrait orientation, ultra_high_res resolution. 3x3 grid layout with thin gutter, no outer border, maximum_identity_lock panel consistency.

Must have: 3x3 grid, same woman in all panels, perfect identity preservation, small white blue-eyed Van cat, natural affectionate interaction with the cat, photorealistic cat anatomy and fur, natural skin texture, clean background, subtle but professional pose variations, editorial beauty portrait feeling, no text.

Negative prompt: identity change, different outfit, different cat color, extra animals, cat distortion, mutated cat face, unrealistic fur, bad anatomy, extra fingers, awkward pose, stiff expression, heavy makeup, harsh lighting, plastic skin, low quality, text, logo, watermark.
Prev 112 / 477 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。

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。

自动化克隆数字人口播混剪视频

FreemiumAPI key required

抖音短视频双路径生产体系(单 Skill 版)。Path A[付费·高质量]:策略大脑→(可选:素材混剪/AI高光提取)→脚本优化→AI生图/素材准备→配音渲染(百炼/GPT-SoVITS/CosyVoice/VoxCPM2+剪映/Remotion/ffmpeg/数字人)。Path B[免费·动画风]:采集热点→脚本→edge-tts免费配音+HyperFrames开源渲染→MP4,零云费开箱快。触发词分层:①"抖音短视频/选题规划/合规闸门/运营策略" ②"口播脚本/AI生图/AI配音/视频渲染/Remotion渲染" ③"蹭热点/快速出片/免费做视频" ④"混剪/高光提取/素材粗剪/autoclip

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,在海报排版上搭配清晰视觉层级、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.