← 返回首页
技能

Ai Image Prompts

tencent_skillhub · 1.0.9 · 下载量 2,031 · 热度分 56.4

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 5717 条

Ultra Photorealistic Image Generation Prompt for Nano Banana Pro

product-marketing

A detailed, structured JSON prompt designed for Nano Banana Pro to generate an ultra-photorealistic image of a young woman resembling Sabrina Carpenter in a retro Americana pin-up style. The prompt specifies detailed attributes for the subject, attire, styling, environment, pose, lighting, and technical camera settings to achieve a high-quality, cinematic result.

展开提示词全文
{
  "image_generation_prompt": {
    "subject": {
      "description": "Young woman with a strong resemblance to {argument name="subject" default="Sabrina Carpenter"}.",
      "hair": "Voluminous, bombshell-style waves with heavy curtain bangs; thick texture with soft, airy physics and high-gloss shine.",
      "face": "Glamorous makeup with sharp winged eyeliner, full matte reddish-brown lips, and dewy skin texture with subtle visible pores and soft contouring.",
      "body": "Slender physique with a defined waist; soft skin texture with realistic highlights on the collarbones and midriff."
    },
    "attire": {
      "clothing": "Short-sleeved blue and white gingham button-down shirt tied or cropped to expose the midriff, paired with ultra-short white denim micro-shorts featuring a frayed hem.",
      "style": "Retro Americana Pin-up meets Modern Coquette."
    },
    "styling_and_accessories": {
      "jewelry": [
        "Large gold hoop earrings",
        "White lace garter belt with a small light blue satin bow on the right thigh"
      ]
    },
    "environment": {
      "setting": "An upscale, modern indoor lounge or kitchen area.",
      "background": "Dark wood cabinetry and shelving with warm integrated LED accent lighting; soft-focus background showing a dim living space.",
      "water": "None"
    },
    "pose": {
      "posture": "Standing upright with a slight tilt of the hips, leaning one hand against a countertop.",
      "arms": "Left arm extended downward resting on the counter; right arm bent at the elbow with the hand raised slightly in a relaxed, candid gesture.",
      "angle": "Eye-level, medium shot."
    },
    "lighting_and_mood": {
      "lighting": "Warm indoor ambient lighting mixed with a direct camera flash effect that creates sharp subjects and soft shadows against the back wall.",
      "mood": "Cinematic, sultry, and intimate.",
      "colors": "Rich wood browns, crisp whites, sky blue, and warm golden highlights."
    },
    "camera_and_technical": {
      "style": "Ultra Photorealistic, RAW photo.",
      "lens": "35mm",
      "aperture": "f/2.8 for moderate depth of field",
      "quality_tags": [
        "8k resolution",
        "highly detailed",
        "volumetric lighting",
        "ray tracing reflections",
        "hyper-realistic texture",
        "Hasselblad photography"
      ]
    }
  }
}

Comparing ChatGPT 5.2 and Nano Banana 2 for Devilman modeling

product-marketing

A comparison of generation results between ChatGPT 5.2 and Nano Banana 2 using past modeling data for 'Devilman Ver-Showa Anime Taste Edition'. The prompt asks for a front-diagonal angle of a figure based on a reference image, respecting the original design's details and coloring.

展开提示词全文
Please create a front-diagonal angle of the figure in the image. Respect and accurately reproduce the figure's details and color scheme based on the original design. The background should be white, the aspect ratio should be 1:1 square, and the size should be adjusted so that the entire figure fits comfortably within the frame.

Paper-Cut Character Art Generation Prompt

product-marketing

A prompt template for Nano Banana to generate a paper-cut art style figure of a character, including their pose and a classic quote, placed on a wooden desk.

展开提示词全文
A whimsical handmade paper art piece is placed on a wooden desk: a hand-drawn cartoon [{argument name="character" default="Dong Yuhui"}] is cut out from paper and folded into a three-dimensional standing figurine. [{argument name="character" default="Dong Yuhui"}] [{argument name="pose" default="cupping fists in congratulation"}]. On the paper next to it, there is not only the remaining blank silhouette but also a handwritten line of its [{argument name="classic line" default="Walking with Hui, living up to the best years"}]. 

Aspect ratio: 1080 x 1080

Commercial Prompts for Tomato Sales using Nano Banana 2

product-marketing

Two commercial-focused prompts for Nano Banana 2, designed for promoting tomatoes. The first generates a minimalist KV poster for offline promotion, and the second generates a Renaissance-style social media image with handwritten text for online promotion.

展开提示词全文
Design a minimalist organic brand for this pile of tomatoes, brand name '{argument name="brand name" default="Sincerity"}', generate a KV poster image placed on a high-end supermarket shelf.

Turn this pile of tomatoes into an image suitable for Xiaohongshu (Little Red Book) style. Change the background to a Renaissance-style dining table, and add a piece of fresh handwritten text in a prominent position: "{argument name="handwritten text" default="The first sweet and sour bite of summer"}", to capture a blockbuster feel.

3D Miniature Architectural Blueprint Prompt

product-marketing

A detailed prompt template for Nano Banana 2 to generate a photorealistic miniature architectural diorama emerging from a blueprint, focusing on construction details and cinematic lighting.

展开提示词全文
An architectural blueprint of {argument name="building name" default="BUILDING_NAME"} placed on a {argument name="surface" default="SURFACE"}, with a photorealistic miniature under-construction version of {argument name="building name 2" default="BUILDING_NAME"} emerging from it — {STRUCTURAL_ELEMENT_1}, {STRUCTURAL_ELEMENT_2}, {STRUCTURAL_ELEMENT_3}, {CONSTRUCTION_DETAIL}, {WORKER_SCENE}, {MATERIAL_ELEMENT}, and {EXTRA_DETAIL}. All elements grow from the blueprint like a 3D architectural diorama, steel beams rising from the drawn lines, scaffolding threading through the paper. Studio soft lighting, cinematic depth, 2:3

Fuchsia Corset Fashion Editorial

product-marketing

A highly detailed JSON prompt for generating a non-sexualized, fashion-focused full-body portrait of a woman seated diagonally on the floor. The prompt specifies a complex outfit including a fuchsia corset top, plaid mini skirt, and sheer black tights with a star pattern, set in a modern room with strong side lighting.

展开提示词全文
{
  "subject": {
    "desc": "Young adult woman, fair skin, extremely long loose blonde hair cascading past feet across floor, soft playful calm expression, direct eye contact",
    "makeup": "Clean editorial: defined brows, subtle eyeliner, soft pink lips",
    "clothing": "Fuchsia corset-style top with pink lace trim, pink choker collar, detached sheer black lace long sleeves, fuchsia-white plaid pleated mini skirt, sheer black tights with small stars pattern, bright glossy white high-heeled stilettos over tights",
    "accessories": "Minimal necklace with small stone pendant"
  },
  "pose": {
    "overall": "Seated diagonally on floor, body turned slightly right, upright spine",
    "head": "Subtle left tilt, chin slightly lowered, direct gaze",
    "arms": "Right index finger gently touching lower lip, left palm flat on floor beside left hip for support",
    "legs": "Right leg extended forward toward camera, toes slightly outward; left leg bent/folded to side, outer thigh on floor, heel near hip. Legs clearly separated, no crossing",
    "weight": "Shared between left hip and left hand, relaxed stable posture"
  },
  "environment": {
    "location": "Minimal modern indoor room, warm wooden floor, neutral yellow wall",
    "elements": [
      "Light wooden cabinet left frame",
      "Red faux-fur cushion vertical against wall behind subject",
      "Big strange Picasso painting",
      "Neon sign 'KeorUnreal' on wall"
    ]
  },
  "lighting": {
    "type": "Natural sunlight",
    "direction": "Strong side light from left",
    "effects": "Diagonal shadows on floor, soft highlights on legs/shoes/face"
  },
  "camera": {
    "angle": "Slightly above eye level, 10–15° downward",
    "framing": "Full-body vertical portrait, no cropping",
    "lens": "Portrait focal length, mild perspective compression",
    "composition": "Extended right leg leading foreground, subtle depth"
  },
  "style": {
    "mood": "Soft fashion editorial, playful and composed",
    "tone": "Non-sexualized, fashion-focused only",
    "quality": "High resolution, sharp focus, realistic anatomy"
  },
  "negative_prompt": [
    "sexualized content",
    "suggestive posing",
    "anatomical distortion",
    "extra limbs",
    "blur",
    "overexposure",
    "harsh artificial lighting",
    "cropped extremities"
  ]
}

Ralph Lauren Equestrian Editorial Portrait

product-marketing

A detailed JSON prompt for generating a high-dynamic-range, traditional portrait in the style of a Ralph Lauren equestrian campaign. It features a woman in riding gear (jodhpurs, white shirt, black boots) leaning in a rustic, dimly lit wooden tack room, emphasizing chiaroscuro lighting and authentic textures like leather and dust.

展开提示词全文
{
  "image_prompt": {
    "meta": {
      "aspect_ratio": "9:16",
      "style": "British Countryside, Equestrian editorial"
    },
    "subject": {
      "description": "24-year-old woman with a sharp, aristocratic profile",
      "face": "Flushed cheeks from a morning ride, natural matte skin, intense and commanding gaze looking slightly off-camera",
      "skin": "A light sheen of sweat on the neck, soft morning light hitting the jawline",
      "hair": "Messy low bun, pieces falling out and sticking to the neck",
      "pose": "Standing in a dimly lit tack room, leaning against a wooden wall, pulling off a tight leather riding glove by the fingertips",
      "outfit": "Tailored beige jodhpurs (riding pants), a crisp white cotton shirt unbuttoned deeply at the collar, tall polished black leather riding boots covered in light dust"
    },
    "environment": {
      "location": "A rustic, century-old wooden tack room in a countryside estate",
      "background_elements": [
        "Worn leather saddles and brass bridles hanging on the walls",
        "Hay dust floating in the air",
        "Rich, dark oak wood textures"
      ]
    },
    "lighting": {
      "type": "Morning Sun piercing through a small, dusty window",
      "characteristics": [
        "God-rays illuminating the floating dust motes",
        "Warm, earthy color palette (browns, golds, deep blacks)",
        "Chiaroscuro lighting emphasizing the textures of leather and wood"
      ]
    },
    "photography_style": {
      "style": "Ralph Lauren-style lifestyle campaign",
      "camera_look": "Medium format digital, high dynamic range",
      "imperfections": "Dust in the air, authentic dirt on the boots, raw unpolished edges",
      "mood": "Powerful, grounded, traditional, alluring"
    }
  }
}

Restomod Product Shot with Chiaroscuro Lighting

product-marketing

A structured JSON prompt for generating a photorealistic 8k Octane render of a product (placeholder) centered and levitating in a pitch-black void. The prompt specifies technical details like rim lighting, high-contrast chiaroscuro, specific metallic textures (titanium, aluminum), and optical effects like fluted glass distortion.

展开提示词全文
{
  "image_generation_request": {
    "subject": {
      "placeholder": "{argument name="product name" default="INSERT PRODUCT HERE"}",
      "position": "dead center, eye-level, perfectly centered in frame",
      "presentation": "levitating, floating in a weightless void, no stands, no platforms, no pedestals, no visible supports"
    },
    "environment": {
      "background": "absolute solid pitch black, hex code #000000, infinite void",
      "lighting": "rim lighting, cinematic chiaroscuro, high-contrast glints on metallic edges, soft orange glow from internal recesses"
    },
    "aesthetic_style": {
      "textures": [
        "shot-blasted matte titanium",
        "brushed aerospace-grade aluminum",
        "anodized dark grey metal",
        "ribbed industrial vertical cooling fins"
      ],
      "optical_effects": "viewed through vertical fluted reeded glass, subtle chromatic distortion, refractive glass warping, radial motion blur on outer edges",
      "color_palette": {
        "primary_background": "#000000",
        "secondary_metal": "#8E8E8E",
        "accent_glow": "#FF8C00",
        "highlights": "#FFFFFF"
      }
    },
    "composition_constraints": {
      "framing": "ensure full product visibility, do not cut off edges, wide safety margins around the subject",
      "elements_to_exclude": [
        "text",
        "logos",
        "watermarks",
        "softboxes",
        "light stands",
        "floor",
        "horizon line",
        "props",
        "human hands",
        "shadows on surfaces"
      ]
    },
    "technical_specs": {
      "focal_length": "85mm macro lens",
      "depth_of_field": "deep focus on product, blurred refractive foreground glass",
      "render_engine": "photorealistic octane render, 8k resolution, ray-traced reflections"
    }
  }
}

Neon Bi-Color Cinematic Portrait

product-marketing

A prompt for generating a hyper-realistic cinematic portrait of a young woman using high-contrast neon lighting—magenta on the left side of the face and cool blue on the right—with a shallow depth of field and a modern tech aesthetic.

展开提示词全文
Hyper-realistic cinematic portrait of a young women with looking slightly upward with a confident thoughtful expression. Neon magenta light illuminating the left side of her face and cool blue light illuminating the right side. Soft studio lighting, high contrast, sharp focus, detailed skin texture, shallow depth of field, blurred abstract purple-blue background with soft yellow foreground bokeh shapes. Shot on 85mm lens, f/1.8, professional DSLR, ultra high resolution, editorial photography, dramatic color grading, modern tech aesthetic, Instagram promotional style.

Scandinavian Beauty in Abandoned Onsen

product-marketing

A highly detailed JSON prompt for generating a high-fashion editorial image of a Scandinavian woman with a voluptuous figure, sitting in an industrial ruin (abandoned Onsen). The prompt emphasizes the contrast between her delicate white string bikini and a heavy olive khaki winter parka, focusing on specific lighting, texture, and a pensive expression.

展开提示词全文
{ "subject": { "description": "A stunning Scandinavian beauty with a voluptuous figure, sitting in an industrial ruin, wearing a delicate white string bikini contrasted with a heavy winter parka draped off her shoulders.", "mirror_rules": "N/A", "age": "early 20s", "expression": { "eyes": { "look": "pensive and slightly melancholic", "energy": "quiet thoughtfulness", "direction": "looking to the side, towards the camera" }, "mouth": { "position": "lips slightly parted, relaxed", "slight smile", "energy": "soft and relaxed" }, "overall": "serene, contrasting deeply with the harsh environment" }, "face": { "preserve_original": true, "makeup": "exquisite Japanese editorial makeup, soft peach blush, delicate eyeliner, glossy pink lips, flawless foundation" }, "hair": { "color": "Golden brown", "style": "tied back into a loose ponytail with wispy bangs framing the face", "effect": "held back by a white mesh headband, slightly messy from the environment" }, "body": { "frame": "hourglass, curvy, prominent cleavage, slim toned waist", "chest": "large and full, beautifully highlighted by the bikini", "waist": "slender and smooth", "legs": "long, gracefully bent", "skin": { "visible_areas": "torso, arms, chest, thighs", "tone": "fair, translucent cold-white tone", "texture": "feels powdery and velvety soft, a stark contrast to the cold, stone surrounding her", "lighting_effect": "sliced by harsh, distinct geometric shadows cast by an unseen source" } }, "pose": { "position": "sitting on the tiled ground, leaning back slightly", "base": "weight supported by her hands resting beside her thighs, right knee raised", "overall": "a static, vulnerable posture that feels accidentally captured" }, "clothing": { "top": { "type": "string bikini top", "color": "pure white", "details": "tiny triangle cups, thin tie straps", "effect": "struggling to contain her curves" }, "bottom": { "type": "string bikini bottom", "color": "pure white", "details": "very thin side straps riding high on the hips" }, "outerwear": { "type": "heavy winter parka", "color": "olive khaki green", "details": "thick faux fur hood, unzipped, intentionally falling off her shoulders to expose her upper body" } } }, "accessories": { "headwear": "wide white mesh headband", "jewelry": "gold hoop earrings, a thick black leather choker with a small golden rabbit", "prop": "clear plastic high heels carelessly removed and resting near her bare feet" }, "photography": { "camera_style": "professional DSLR, high-fashion editorial gravure photography", "angle": "high angle, shooting downwards to emphasize her form and the ground", "shot_type": "full body to three-quarter shot", "aspect_ratio": "2:3", "texture": "hyper-realistic, sharp focus on the skin and fabric, and background", "lighting": "har" } }

Ethereal Mint Lace Babydoll Portrait

product-marketing

A structured JSON prompt for generating a photorealistic, cinematic portrait in a high-fashion style. It emphasizes strict facial consistency based on a reference image, featuring the subject wearing a sheer mint green lace babydoll dress, seated on a grey upholstered couch with soft, diffused natural lighting.

展开提示词全文
{
  "generation_request": {
    "core_parameters": {
      "aspect_ratio": "4:5",
      "resolution": "high_definition",
      "style": "photorealistic, cinematic portrait, high fashion photography",
      "facial_consistency_mode": "strict"
    },
    "positive_prompt": {
      "subject": {
        "identity_preservation": "Prioritize the facial features from the provided reference image. Maintain the subject's identity accurately. Do not alter the core facial structure.",
        "physical_attributes": "Young woman, fair skin with a subtle beauty mark on the right cheek, voluminous dark brown wavy hair falling over the shoulders, striking light eyes.",
        "expression": "Serene, lips slightly parted, looking slightly upward and away from the camera."
      },
      "attire": {
        "garment": "Sheer lingerie babydoll dress",
        "color": "Pale mint green / soft aqua",
        "details": "Intricate floral lace detailing on the cups and hem, thin spaghetti straps, front tie with delicate ribbons, translucent flowing skirt draped over the legs."
      },
      "pose": {
        "action": "Sitting gracefully",
        "posture": "Relaxed, leaning slightly back, arms resting naturally at her sides on the furniture."
      },
      "environment": {
        "setting": "Elegant, modern indoor space",
        "furniture": "Light grey textured upholstered couch",
        "background": "Softly blurred (bokeh), warm neutral beige walls with subtle vertical structural paneling."
      },
      "lighting": {
        "type": "Soft, diffused natural indoor lighting",
        "effects": "Gentle highlights on the skin and hair, soft shadows, creating a luminous and ethereal atmosphere."
      }
    },
    "negative_prompt": {
      "unwanted_elements": [
        "altered facial structure",
        "mutated features",
        "bad anatomy",
        "harsh shadows",
        "overexposed lighting",
        "cartoon",
        "illustration",
        "anime",
        "cluttered background"
      ]
    },
    "advanced_settings": {
      "cfg_scale": 7.5,
      "sampling_steps": 40,
      "sampler": "DPM++ 2M Karras",
      "reference_image_weight": 1.0
    }
  }
}

Studio Portrait in Black Latex Bodysuit with Cherries

product-marketing

A highly detailed JSON prompt for generating a photorealistic studio photograph of a woman in a shiny black latex bodysuit with a prominent zipper, seated on the floor. The prompt includes specific details about her pose, makeup, and props, including cherries and sheer black pantyhose featuring cursive handwriting phrases.

展开提示词全文
{
  "image_prompt_data": {
    "metadata": {
      "format": "detailed_json",
      "style": "photorealistic studio photography",
      "intended_use": "text-to-image generation"
    },
    "subject_details": {
      "demographics": "Young adult female",
      "hair": "Long, thick, wavy blonde hair, parted slightly off-center, cascading over the right shoulder and down the back",
      "skin_tone": "Fair to medium with a warm, glowing complexion",
      "facial_features": "Soft yet defined jawline, full lips, prominent cheekbones",
      "makeup": "Glamorous studio makeup; glossy pink lipstick, soft rosy blush, contoured cheeks, defined eyebrows, smoky eyeshadow with dark eyelashes",
      "expression": "Alluring, confident, looking directly at the viewer with mouth slightly open in a suggestive manner"
    },
    "wardrobe": {
      "main_garment": {
        "type": "Bodysuit",
        "material": "Shiny, reflective material resembling latex, PVC, or pleather",
        "color": "Black",
        "details": "Sleeveless, high collar, featuring a prominent front zipper with ring pulls. The zipper is pulled down significantly, revealing deep cleavage."
      },
      "legwear": {
        "type": "Pantyhose / Tights",
        "material": "Sheer nylon",
        "color": "Black",
        "details": "Features distinct, delicate black cursive handwriting running vertically down the thighs. Visible phrases include 'Te quiero', 'Ich liebe dich', and 'love you'."
      }
    },
    "pose_and_composition": {
      "posture": "Seated on the floor, leaning backward dynamically",
      "right_arm": "Extended straight down behind her, hand resting on the floor to support her body weight",
      "left_arm": "Raised and bent at the elbow, hand positioned close to the mouth holding a prop",
      "legs": "Folded and resting sideways on the floor",
      "framing": "Medium-full shot capturing the subject from the mid-calf up to slightly above the head",
      "camera_angle": "Eye-level with the seated subject, creating an intimate perspective"
    },
    "props": {
      "prop_1": {
        "description": "A single, glossy dark red cherry held by its thin stem between the thumb and index finger of the left hand, hovering just above the subject's open lips."
      },
      "prop_2": {
        "description": "A small, clear, ribbed glass coupe or dessert bowl with a short stem, resting directly on the floor near the subject's right hip."
      },
      "prop_3": {
        "description": "A small cluster of three dark red cherries sitting inside the glass bowl."
      }
    },
    "environment_and_lighting": {
      "setting": "Indoor photography studio",
      "background": "Seamless, solid light grey or off-white backdrop with no distracting elements",
      "floor": "Matches the background, smooth and matte",
      "lighting": "Soft, diffused studio lighting. Brightly illuminates the subject while casting g"
    }
  }
}
上一页 165 / 477 下一页

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。一节课的讲解也能做成课程口播。

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。

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。

海报设计工作室

免费增值需申请 Key

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。

自动化克隆数字人口播混剪视频

免费增值需申请 Key

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

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。