{
  "schemaVersion": "1.0",
  "item": {
    "slug": "monet-ai",
    "name": "Monet AI",
    "source": "tencent",
    "type": "skill",
    "category": "开发工具",
    "sourceUrl": "https://clawhub.ai/seekton/monet-ai",
    "canonicalUrl": "https://clawhub.ai/seekton/monet-ai",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/monet-ai",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=monet-ai",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "SKILL.md"
    ],
    "primaryDoc": "SKILL.md",
    "quickSetup": [
      "Download the package from Yavira.",
      "Extract the archive and review SKILL.md first.",
      "Import or place the package into your OpenClaw setup."
    ],
    "agentAssist": {
      "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.",
      "steps": [
        "Download the package from Yavira.",
        "Extract it into a folder your agent can access.",
        "Paste one of the prompts below and point your agent at the extracted folder."
      ],
      "prompts": [
        {
          "label": "New install",
          "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete."
        },
        {
          "label": "Upgrade existing",
          "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run."
        }
      ]
    },
    "sourceHealth": {
      "source": "tencent",
      "status": "healthy",
      "reason": "direct_download_ok",
      "recommendedAction": "download",
      "checkedAt": "2026-04-30T16:55:25.780Z",
      "expiresAt": "2026-05-07T16:55:25.780Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=network",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=network",
        "contentDisposition": "attachment; filename=\"network-1.0.0.zip\"",
        "redirectLocation": null,
        "bodySnippet": null
      },
      "scope": "source",
      "summary": "Source download looks usable.",
      "detail": "Yavira can redirect you to the upstream package for this source.",
      "primaryActionLabel": "Download for OpenClaw",
      "primaryActionHref": "/downloads/monet-ai"
    },
    "validation": {
      "installChecklist": [
        "Use the Yavira download entry.",
        "Review SKILL.md after the package is downloaded.",
        "Confirm the extracted package contains the expected setup assets."
      ],
      "postInstallChecks": [
        "Confirm the extracted package includes the expected docs or setup files.",
        "Validate the skill or prompts are available in your target agent workspace.",
        "Capture any manual follow-up steps the agent could not complete."
      ]
    },
    "downloadPageUrl": "https://openagent3.xyz/downloads/monet-ai",
    "agentPageUrl": "https://openagent3.xyz/skills/monet-ai/agent",
    "manifestUrl": "https://openagent3.xyz/skills/monet-ai/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/monet-ai/agent.md"
  },
  "agentAssist": {
    "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.",
    "steps": [
      "Download the package from Yavira.",
      "Extract it into a folder your agent can access.",
      "Paste one of the prompts below and point your agent at the extracted folder."
    ],
    "prompts": [
      {
        "label": "New install",
        "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete."
      },
      {
        "label": "Upgrade existing",
        "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run."
      }
    ]
  },
  "documentation": {
    "source": "clawhub",
    "primaryDoc": "SKILL.md",
    "sections": [
      {
        "title": "Monet AI Skill",
        "body": "Comprehensive AI content generation API designed for AI agents. Monet AI provides unified access to state-of-the-art AI generation models for video (Sora, Veo, Doubao Seedance, Wan, Hailuo, Kling), image (GPT-4o, Nano Banana, Seedream, Flux, Imagen, Ideogram), and music (MiniMax Music) generation. Build intelligent workflows that combine multiple AI capabilities for automated content creation pipelines."
      },
      {
        "title": "When to Use",
        "body": "Use this skill when:\n\nVideo Generation: Create AI-generated videos from text prompts using state-of-the-art models\n\nSora: OpenAI's video generation model for high-quality, realistic videos\nVeo: Google's video generation model\nDoubao Seedance: ByteDance's AI video model with audio-visual sync\nWan: Alibaba's video generation model with excellent localization support\nHailuo: Fast video generation with good quality-speed balance\nKling: Kuaishou's video generation model\n\n\nImage Generation: Generate images from text descriptions with various artistic styles\n\nGPT-4o: OpenAI's multimodal model for image generation\nNano Banana: Google's image model with ultra-high character consistency\nSeedream: ByteDance's intelligent visual reasoning model\nWan: Alibaba's visual model for high-quality and expressive image generation\nFlux: High-quality photorealistic and artistic image generation\nImagen: Google's text-to-image model\nIdeogram: Specialized in text rendering and precise composition\n\n\nMusic Generation: Create original music and audio from text descriptions\n\nMiniMax Music: AI music generation with support for custom lyrics and text-to-music conversion\n\n\nAI Agent Integration: Build intelligent workflows that combine multiple AI generation capabilities for automated content creation pipelines"
      },
      {
        "title": "Getting API Key",
        "body": "Visit https://monet.vision to register an account\nAfter login, go to https://monet.vision/skills/keys to create an API Key\nConfigure the API Key in environment variables or code\n\nIf you don't have an API Key, ask your owner to apply at monet.vision."
      },
      {
        "title": "Create a Video Generation Task",
        "body": "curl -X POST https://monet.vision/api/v1/tasks/async \\\n  -H \"Content-Type: application/json\" \\\n  -H \"Authorization: Bearer $MONET_API_KEY\" \\\n  -d '{\n    \"type\": \"video\",\n    \"input\": {\n      \"model\": \"sora-2\",\n      \"prompt\": \"A cat running in the park\",\n      \"duration\": 5,\n      \"aspect_ratio\": \"16:9\"\n    },\n    \"idempotency_key\": \"unique-key-123\"\n  }'\n\n⚠️ Important: idempotency_key is required. Use a unique value (e.g., UUID) to prevent duplicate task creation if the request is retried.\n\nResponse:\n\n{\n  \"id\": \"task_abc123\",\n  \"status\": \"pending\",\n  \"type\": \"video\",\n  \"created_at\": \"2026-02-27T10:00:00Z\"\n}"
      },
      {
        "title": "Get Task Status and Result",
        "body": "Task processing is asynchronous. You need to poll the task status until it becomes success or failed. Recommended polling interval: 5 seconds.\n\ncurl https://monet.vision/api/v1/tasks/task_abc123 \\\n  -H \"Authorization: Bearer $MONET_API_KEY\"\n\nResponse when completed:\n\n{\n  \"id\": \"task_abc123\",\n  \"status\": \"success\",\n  \"type\": \"video\",\n  \"outputs\": [\n    {\n      \"model\": \"sora-2\",\n      \"status\": \"success\",\n      \"progress\": 100,\n      \"url\": \"https://files.monet.vision/...\"\n    }\n  ],\n  \"created_at\": \"2026-02-27T10:00:00Z\",\n  \"updated_at\": \"2026-02-27T10:01:30Z\"\n}\n\nExample: Poll until completion\n\nconst TASK_ID = \"task_abc123\";\nconst MONET_API_KEY = process.env.MONET_API_KEY;\n\nasync function pollTask() {\n  while (true) {\n    const response = await fetch(\n      `https://monet.vision/api/v1/tasks/${TASK_ID}`,\n      {\n        headers: {\n          Authorization: `Bearer ${MONET_API_KEY}`,\n        },\n      },\n    );\n\n    const data = await response.json();\n    const status = data.status;\n\n    if (status === \"success\") {\n      console.log(\"Task completed successfully!\");\n      console.log(JSON.stringify(data, null, 2));\n      break;\n    } else if (status === \"failed\") {\n      console.log(\"Task failed!\");\n      console.log(JSON.stringify(data, null, 2));\n      break;\n    } else {\n      console.log(`Task status: ${status}, waiting...`);\n      await new Promise((resolve) => setTimeout(resolve, 5000)); // Wait 5 seconds\n    }\n  }\n}\n\npollTask();"
      },
      {
        "title": "Video Generation",
        "body": "Sora (OpenAI)\n\nsora-2 - Sora 2\n\nOpenAI latest video generation model\n\n🎯 Use Cases: Video projects requiring OpenAI's latest technology\n⏱️ Duration: 10-15 seconds\n🎵 Features: Audio generation support, reference image support\n\n{\n  model: \"sora-2\",\n  prompt: string,                // Required\n  images?: string[],             // Optional: Reference images\n  duration?: 10 | 15,           // Optional, default: 10\n  aspect_ratio?: \"16:9\" | \"9:16\"\n}\n\nsora-2-pro - Sora 2 Pro\n\nPerfect quality for cinematic scenes\n\n🎯 Use Cases: Professional film, advertising, and high-end production\n⏱️ Duration: 15-25 seconds\n🎵 Features: Audio generation support, reference image support\n\n{\n  model: \"sora-2-pro\",\n  prompt: string,\n  images?: string[],\n  duration?: 15 | 25,           // Optional, default: 15\n  aspect_ratio?: \"16:9\" | \"9:16\"\n}\n\nVeo (Google)\n\nveo-3-1-fast - Google Veo 3.1 Fast\n\nUltra-fast video generation\n\n🎯 Use Cases: Video projects requiring fast generation\n⏱️ Duration: 8 seconds\n📺 Resolution: 1080p with audio generation support\n\n{\n  model: \"veo-3-1-fast\",\n  prompt: string,\n  images?: string[],             // Reference images\n  aspect_ratio?: \"16:9\" | \"9:16\"\n}\n\nveo-3-1 - Google Veo 3.1\n\nAdvanced AI video with sound\n\n🎯 Use Cases: Professional-grade video production\n⏱️ Duration: 8 seconds\n📺 Resolution: 1080p with audio generation support\n\n{\n  model: \"veo-3-1\",\n  prompt: string,\n  images?: string[],\n  aspect_ratio?: \"16:9\" | \"9:16\"\n}\n\nveo-3-fast - Google Veo 3 Fast\n\n30% faster than standard Veo 3\n\n🎯 Use Cases: Video projects requiring rapid iteration\n⏱️ Duration: 8 seconds\n📺 Resolution: 1080p, supports negative prompts\n\n{\n  model: \"veo-3-fast\",\n  prompt: string,\n  images?: string[],\n  negative_prompt?: string       // Specify unwanted content\n}\n\nveo-3 - Google Veo 3\n\nHigh-quality video generation\n\n🎯 Use Cases: Standard high-quality video production\n⏱️ Duration: 8 seconds\n📺 Resolution: 1080p, supports negative prompts\n\n{\n  model: \"veo-3\",\n  prompt: string,\n  images?: string[],\n  negative_prompt?: string\n}\n\nWan\n\nwan-2-6 - Wan 2.6\n\nMulti-shot and automatic audio\n\n🎯 Use Cases: Video production requiring multi-shot switching\n⏱️ Duration: 5-15 seconds\n📺 Resolution: 720p-1080p with audio generation support\n\n{\n  model: \"wan-2-6\",\n  prompt: string,\n  images?: string[],\n  duration?: 5 | 10 | 15,\n  resolution?: \"720p\" | \"1080p\",\n  aspect_ratio?: \"16:9\" | \"9:16\" | \"4:3\" | \"3:4\" | \"1:1\",\n  shot_type?: \"single\" | \"multi\"  // Single/multi-shot switching\n}\n\nwan-2-5 - Wan 2.5\n\nSupports automatic audio generation\n\n🎯 Use Cases: Quickly generating videos with audio\n⏱️ Duration: 5-10 seconds\n📺 Resolution: 480p-1080p with audio support\n\n{\n  model: \"wan-2-5\",\n  prompt: string,\n  images?: string[],\n  duration?: 5 | 10,\n  resolution?: \"480p\" | \"720p\" | \"1080p\",\n  aspect_ratio?: \"16:9\" | \"9:16\" | \"4:3\" | \"3:4\" | \"1:1\"\n}\n\nwan-2-2-flash - Wan 2.2 Flash\n\nInstruction understanding, controllable camera movement\n\n🎯 Use Cases: Scenarios requiring precise camera movement control\n⏱️ Duration: 5-10 seconds\n📺 Resolution: 480p-1080p\n\n{\n  model: \"wan-2-2-flash\",\n  prompt: string,\n  images?: string[],\n  duration?: 5 | 10,\n  resolution?: \"480p\" | \"720p\" | \"1080p\",\n  negative_prompt?: string\n}\n\nwan-2-2 - Wan 2.2\n\nExcellent image details, strong motion stability\n\n🎯 Use Cases: Video production requiring high stability\n⏱️ Duration: 5-10 seconds\n📺 Resolution: 480p-1080p\n\n{\n  model: \"wan-2-2\",\n  prompt: string,\n  images?: string[],\n  duration?: 5 | 10,\n  resolution?: \"480p\" | \"1080p\",\n  aspect_ratio?: \"16:9\" | \"9:16\" | \"4:3\" | \"3:4\" | \"1:1\",\n  negative_prompt?: string\n}\n\nKling\n\nkling-2-6 - Kling 2.6\n\nCinematic videos and audio\n\n🎯 Use Cases: Cinematic video production\n⏱️ Duration: 5-10 seconds\n✨ Features: Strong visual realism, audio generation support\n\n{\n  model: \"kling-2-6\",\n  prompt: string,\n  images?: string[],\n  duration?: 5 | 10,\n  aspect_ratio?: \"1:1\" | \"16:9\" | \"9:16\",\n  generate_audio?: boolean\n}\n\nkling-2-5 - Kling 2.5 Turbo\n\nSmooth motion, stronger consistency\n\n🎯 Use Cases: Video production requiring high consistency\n⏱️ Duration: 5-10 seconds\n✨ Features: Supports negative prompts\n\n{\n  model: \"kling-2-5\",\n  prompt: string,\n  images?: string[],\n  duration?: 5 | 10,\n  aspect_ratio?: \"1:1\" | \"16:9\" | \"9:16\",\n  negative_prompt?: string\n}\n\nkling-v2-1-master - Kling 2.1 Master\n\nStrong visual realism with enhanced features\n\n🎯 Use Cases: Professional-grade high-quality video production\n⏱️ Duration: 5-10 seconds\n✨ Features: Strength adjustment support, negative prompts\n\n{\n  model: \"kling-v2-1-master\",\n  prompt: string,\n  images?: string[],\n  duration?: 5 | 10,\n  aspect_ratio?: \"1:1\" | \"16:9\" | \"9:16\",\n  strength?: number,            // 0-1: Control generation effect\n  negative_prompt?: string\n}\n\nkling-v2-1 - Kling 2.1\n\nStrong visual realism\n\n🎯 Use Cases: High-realism video production\n⏱️ Duration: 5-10 seconds\n✨ Features: Strength adjustment, negative prompts\n\n{\n  model: \"kling-v2-1\",\n  prompt: string,\n  images?: string[],\n  duration?: 5 | 10,\n  aspect_ratio?: \"1:1\" | \"16:9\" | \"9:16\",\n  strength?: number,            // 0-1\n  negative_prompt?: string\n}\n\nkling-v2 - Kling 2.0\n\nExcellent aesthetics\n\n🎯 Use Cases: Artistic creation and aesthetically-oriented videos\n⏱️ Duration: 5-10 seconds\n✨ Features: Strength adjustment, negative prompts\n\n{\n  model: \"kling-v2\",\n  prompt: string,\n  images?: string[],\n  duration?: 5 | 10,\n  aspect_ratio?: \"1:1\" | \"16:9\" | \"9:16\",\n  strength?: number,            // 0-1\n  negative_prompt?: string\n}\n\nHailuo\n\nhailuo-2-3 - Hailuo 2.3\n\nExcellent body movements and physics performance\n\n🎯 Use Cases: Videos requiring realistic physics effects\n⏱️ Duration: 6-10 seconds\n📺 Resolution: 768p-1080p, extreme physics simulations\n\n{\n  model: \"hailuo-2-3\",\n  prompt: string,\n  images?: string[],\n  duration?: 6 | 10,\n  resolution?: \"768p\" | \"1080p\"\n}\n\nhailuo-2-3-fast - Hailuo 2.3 Fast\n\nFast generation speed\n\n🎯 Use Cases: Projects requiring rapid iteration\n⏱️ Duration: 6-10 seconds\n📺 Resolution: 768p-1080p\n\n{\n  model: \"hailuo-2-3-fast\",\n  prompt: string,\n  images?: string[],\n  duration?: 6 | 10,\n  resolution?: \"768p\" | \"1080p\"\n}\n\nhailuo-02 - Hailuo 02\n\nExtreme physics simulations\n\n🎯 Use Cases: Scenarios requiring accurate physics simulation\n⏱️ Duration: 6-10 seconds\n📺 Resolution: 768p-1080p\n\n{\n  model: \"hailuo-02\",\n  prompt: string,\n  images?: string[],\n  duration?: 6 | 10,\n  resolution?: \"768p\" | \"1080p\"\n}\n\nhailuo-01-live2d - Hailuo 01 Live2d\n\nHailuo Live2D model\n\n🎯 Use Cases: 2D character animation production\n✨ Features: Suitable for 2D character animation\n\n{\n  model: \"hailuo-01-live2d\",\n  prompt: string,\n  images?: string[]\n}\n\nhailuo-01 - Hailuo 01\n\nHighest video quality\n\n🎯 Use Cases: Video production requiring ultimate quality\n✨ Features: Suitable for high-quality needs\n\n{\n  model: \"hailuo-01\",\n  prompt: string,\n  images?: string[]\n}\n\nDoubao Seedance\n\ndoubao-seedance-1-5-pro - Seedance 1.5 Pro\n\nPro-grade audio-visual sync\n\n🎯 Use Cases: Professional production requiring audio-visual sync\n⏱️ Duration: 4-12 seconds\n📺 Resolution: 480p-720p with audio generation support\n\n{\n  model: \"doubao-seedance-1-5-pro\",\n  prompt: string,\n  images?: string[],\n  duration?: number,\n  resolution?: \"480p\" | \"720p\",\n  aspect_ratio?: \"1:1\" | \"4:3\" | \"16:9\" | \"3:4\" | \"9:16\" | \"21:9\",\n  generate_audio?: boolean\n}\n\ndoubao-seedance-1-0-pro-fast - Seedance 1.0 Pro Fast\n\nPremium quality & unbeatable efficiency\n\n🎯 Use Cases: Scenarios requiring fast high-quality output\n⏱️ Duration: 2-12 seconds\n📺 Resolution: 720p-1080p, ByteDance's next-gen AI video model\n\n{\n  model: \"doubao-seedance-1-0-pro-fast\",\n  prompt: string,\n  images?: string[],\n  duration?: number,\n  resolution?: \"720p\" | \"1080p\",\n  aspect_ratio?: \"1:1\" | \"4:3\" | \"16:9\" | \"3:4\" | \"9:16\" | \"21:9\"\n}\n\ndoubao-seedance-1-0-pro - Seedance 1.0 Pro\n\nStable motion performance\n\n🎯 Use Cases: Video production requiring stable motion\n⏱️ Duration: 5-10 seconds\n📺 Resolution: 480p-1080p\n\n{\n  model: \"doubao-seedance-1-0-pro\",\n  prompt: string,\n  images?: string[],\n  duration?: 5 | 10,\n  resolution?: \"480p\" | \"1080p\",\n  aspect_ratio?: \"1:1\" | \"4:3\" | \"16:9\" | \"3:4\" | \"9:16\"\n}\n\ndoubao-seedance-1-0-lite - Seedance 1.0 Lite\n\nPrecise semantic understanding\n\n🎯 Use Cases: Scenarios requiring precise semantic understanding\n⏱️ Duration: 5-10 seconds\n📺 Resolution: 480p-1080p\n\n{\n  model: \"doubao-seedance-1-0-lite\",\n  prompt: string,\n  images?: string[],\n  duration?: 5 | 10,\n  resolution?: \"480p\" | \"720p\" | \"1080p\"\n}\n\nSpecial Features\n\nkling-motion-control - Kling Motion Control\n\nPrecision motion control via video references\n\n🎯 Use Cases: Scenarios requiring motion replication from reference videos\n⏱️ Duration: 3-30 seconds\n📺 Resolution: 720p/1080p with audio generation support\n💰 Pricing: 720p: 8 credits/s, 1080p: 15 credits/s\n\n{\n  model: \"kling-motion-control\",\n  prompt: string,                // Required: Detailed motion description\n  images: string[],              // Required: min 1 reference image\n  videos: string[],              // Required: min 1 reference video\n  resolution?: \"720p\" | \"1080p\"\n}\n\nrunway-act-two - Runway Act Two\n\nRunway Next-Generation Motion Capture Model\n\n🎯 Use Cases: Capturing motion from videos and applying to new characters\n⏱️ Duration: 3-30 seconds\n✨ Features: Motion transfer support\n💰 Pricing: 10 credits/second\n\n{\n  model: \"runway-act-two\",\n  images: string[],              // Required: min 1 target character image\n  videos: string[],              // Required: min 1 motion reference video\n  aspect_ratio?: \"1:1\" | \"4:3\" | \"16:9\" | \"3:4\" | \"9:16\" | \"21:9\"\n}\n\nwan-animate-mix - Wan Animate Mix (Standard)\n\nPerfect for character replacement scenarios\n\n🎯 Use Cases: Video character replacement\n⏱️ Duration: 3-30 seconds\n✨ Features: Replace characters in videos with specified image characters\n💰 Pricing: 10 credits/second\n\n{\n  model: \"wan-animate-mix\",\n  videos: string[],              // Required: Original videos\n  images: string[]               // Required: Target character images\n}\n\nwan-animate-mix-pro - Wan Animate Mix Pro (Professional)\n\nHigh animation fluidity with better results\n\n🎯 Use Cases: Professional-grade video character replacement\n⏱️ Duration: 3-30 seconds\n✨ Features: Higher quality character replacement effects\n💰 Pricing: 20 credits/second\n\n{\n  model: \"wan-animate-mix-pro\",\n  videos: string[],              // Required\n  images: string[]               // Required\n}\n\nwan-animate-move - Wan Animate Move (Standard)\n\nReplicate dance and challenging body movements\n\n🎯 Use Cases: Motion capture and transfer\n⏱️ Duration: 3-30 seconds\n✨ Features: Apply motion from reference videos to target images\n💰 Pricing: 10 credits/second\n\n{\n  model: \"wan-animate-move\",\n  videos: string[],              // Required: Motion reference videos\n  images: string[]               // Required: Target character images\n}\n\nwan-animate-move-pro - Wan Animate Move Pro (Professional)\n\nHigh animation fluidity with better results\n\n🎯 Use Cases: Professional-grade motion capture and transfer\n⏱️ Duration: 3-30 seconds\n✨ Features: Higher quality motion transfer effects\n💰 Pricing: 20 credits/second\n\n{\n  model: \"wan-animate-move-pro\",\n  videos: string[],              // Required\n  images: string[]               // Required\n}"
      },
      {
        "title": "Image Generation",
        "body": "GPT (OpenAI)\n\ngpt-4o - GPT 4o\n\nAccurate, realistic output\n\n🎯 Use Cases: High-quality, photorealistic image generation\n✨ Features: Supports multiple reference images, multiple aspect ratios, customizable style\n\n{\n  model: \"gpt-4o\",\n  prompt: string,\n  images?: string[],             // Reference images for style guidance\n  aspect_ratio?: \"1:1\" | \"4:3\" | \"3:2\" | \"16:9\" | \"3:4\" | \"2:3\" | \"9:16\",\n  style?: string                 // Custom style description\n}\n\ngpt-image-1-5 - GPT Image 1.5\n\nTrue-color precision rendering\n\n🎯 Use Cases: Professional image generation requiring color accuracy\n✨ Features: Supports up to 10 reference images, adjustable quality\n\n{\n  model: \"gpt-image-1-5\",\n  prompt: string,\n  images?: string[],             // max 10 reference images\n  aspect_ratio?: \"1:1\" | \"3:2\" | \"2:3\",\n  quality?: \"auto\" | \"low\" | \"medium\" | \"high\"\n}\n\nNano Banana (Google)\n\nnano-banana-1 - Google Nano Banana\n\nUltra-high character consistency\n\n🎯 Use Cases: Image series requiring consistent character appearance\n✨ Features: Supports up to 5 reference images, multiple aspect ratio options\n\n{\n  model: \"nano-banana-1\",\n  prompt: string,\n  images?: string[],             // max 5 reference images\n  aspect_ratio?: \"1:1\" | \"2:3\" | \"3:2\" | \"4:3\" | \"3:4\" | \"16:9\" | \"9:16\"\n}\n\nnano-banana-1-pro - Nano Banana Pro\n\nGoogle's flagship generation model\n\n🎯 Use Cases: Professional-grade high-quality image generation\n✨ Features: Supports 1K-4K resolution, up to 14 reference images, ultra-wide 21:9\n\n{\n  model: \"nano-banana-1-pro\",\n  prompt: string,\n  images?: string[],             // max 14 reference images\n  aspect_ratio?: \"1:1\" | \"2:3\" | \"3:2\" | \"4:3\" | \"3:4\" | \"4:5\" | \"5:4\" | \"16:9\" | \"9:16\" | \"21:9\",\n  resolution?: \"1K\" | \"2K\" | \"4K\"\n}\n\nnano-banana-2 - Nano Banana 2\n\nGoogle Gemini latest model\n\n🎯 Use Cases: Latest technology for high-quality image generation\n✨ Features: Supports 1K-4K resolution, up to 14 reference images, ultra-wide 8:1 ratio\n\n{\n  model: \"nano-banana-2\",\n  prompt: string,\n  images?: string[],             // max 14 reference images\n  aspect_ratio?: \"1:1\" | \"2:3\" | \"3:2\" | \"4:3\" | \"3:4\" | \"4:5\" | \"5:4\" | \"16:9\" | \"9:16\" | \"21:9\" | \"4:1\" | \"1:4\" | \"8:1\" | \"1:8\",\n  resolution?: \"1K\" | \"2K\" | \"4K\"\n}\n\nWan\n\nwan-i-2-6 - Wan 2.6\n\nHigh-quality and expressive\n\n🎯 Use Cases: Creative image generation requiring high expressiveness\n✨ Features: Supports up to 4 reference images, ultra-wide 21:9\n\n{\n  model: \"wan-i-2-6\",\n  prompt: string,\n  images?: string[],             // max 4 reference images\n  aspect_ratio?: \"1:1\" | \"4:3\" | \"3:2\" | \"16:9\" | \"3:4\" | \"2:3\" | \"9:16\" | \"21:9\"\n}\n\nwan-2-5 - Wan 2.5\n\nFast, creative image generation\n\n🎯 Use Cases: Quick creation and iteration\n✨ Features: Supports up to 2 reference images, ultra-wide 21:9\n\n{\n  model: \"wan-2-5\",\n  prompt: string,\n  images?: string[],             // max 2 reference images\n  aspect_ratio?: \"1:1\" | \"4:3\" | \"3:2\" | \"16:9\" | \"3:4\" | \"2:3\" | \"9:16\" | \"21:9\"\n}\n\nSeedream (ByteDance)\n\nseedream-5-0 - Seedream 5.0 Lite\n\nIntelligent visual reasoning\n\n🎯 Use Cases: Complex scenarios requiring intelligent understanding and reasoning\n✨ Features: 2K-3K resolution, up to 14 reference images, ultra-wide 21:9\n\n{\n  model: \"seedream-5-0\",\n  prompt: string,\n  images?: string[],             // max 14 reference images\n  aspect_ratio?: \"1:1\" | \"2:3\" | \"3:2\" | \"3:4\" | \"4:3\" | \"4:5\" | \"5:4\" | \"9:16\" | \"16:9\" | \"21:9\",\n  resolution?: \"2K\" | \"3K\"\n}\n\nseedream-4-5 - Seedream 4.5\n\nByteDance's 4K image model\n\n🎯 Use Cases: High-resolution professional image generation\n✨ Features: 2K-4K resolution, up to 14 reference images, ultra-wide 21:9\n\n{\n  model: \"seedream-4-5\",\n  prompt: string,\n  images?: string[],             // max 14 reference images\n  aspect_ratio?: \"1:1\" | \"2:3\" | \"3:2\" | \"3:4\" | \"4:3\" | \"4:5\" | \"5:4\" | \"9:16\" | \"16:9\" | \"21:9\",\n  resolution?: \"2K\" | \"4K\"\n}\n\nseedream-4-0 - Seedream 4.0\n\nSupport images with cohesive styles\n\n🎯 Use Cases: Image series requiring consistent style\n✨ Features: Supports up to 10 reference images\n\n{\n  model: \"seedream-4-0\",\n  prompt: string,\n  images?: string[],             // max 10 reference images\n  aspect_ratio?: \"1:1\" | \"4:3\" | \"3:2\" | \"16:9\" | \"3:4\" | \"2:3\" | \"9:16\"\n}\n\nFlux (Black Forest Labs)\n\nflux-2-dev - Flux.2 Dev\n\nPhotorealistic output\n\n🎯 Use Cases: Image generation requiring high photorealism\n✨ Features: Model by Black Forest Labs, multiple aspect ratio options\n\n{\n  model: \"flux-2-dev\",\n  prompt: string,\n  aspect_ratio?: \"1:1\" | \"4:3\" | \"3:2\" | \"16:9\" | \"3:4\" | \"2:3\" | \"9:16\"\n}\n\nflux-kontext-pro - Flux Kontext Pro\n\nPerfect for editing, compositing\n\n🎯 Use Cases: Professional image editing and compositing work\n✨ Features: Supports reference images, customizable style\n\n{\n  model: \"flux-kontext-pro\",\n  prompt: string,\n  images?: string[],\n  aspect_ratio?: \"1:1\" | \"4:3\" | \"3:2\" | \"16:9\" | \"3:4\" | \"2:3\" | \"9:16\",\n  style?: string\n}\n\nflux-kontext-max - Flux Kontext Max\n\nExcellent for prompt accuracy\n\n🎯 Use Cases: Scenarios requiring precise control of generation results\n✨ Features: Supports reference images, customizable style\n\n{\n  model: \"flux-kontext-max\",\n  prompt: string,\n  images?: string[],\n  aspect_ratio?: \"1:1\" | \"4:3\" | \"3:2\" | \"16:9\" | \"3:4\" | \"2:3\" | \"9:16\",\n  style?: string\n}\n\nflux-1-schnell - Flux Schnell\n\nSuitable for simple basic scenes\n\n🎯 Use Cases: Quick prototyping and simple scenarios\n✨ Features: Fast generation speed\n\n{\n  model: \"flux-1-schnell\",\n  prompt: string\n}\n\nImagen (Google)\n\nimagen-3-0 - Imagen 3.0\n\nFast, high-quality results\n\n🎯 Use Cases: Fast high-quality image generation\n✨ Features: Google's advanced image model, customizable style\n\n{\n  model: \"imagen-3-0\",\n  prompt: string,\n  aspect_ratio?: \"1:1\" | \"3:4\" | \"4:3\" | \"9:16\" | \"16:9\",\n  style?: string\n}\n\nimagen-4-0 - Imagen 4.0\n\nGoogle's latest generation model\n\n🎯 Use Cases: High-quality images requiring latest technology\n✨ Features: Higher quality and precision, customizable style\n\n{\n  model: \"imagen-4-0\",\n  prompt: string,\n  aspect_ratio?: \"1:1\" | \"3:4\" | \"4:3\" | \"9:16\" | \"16:9\",\n  style?: string\n}\n\nIdeogram\n\nideogram-v2 - Ideogram V2\n\nHighly recommended for text editing\n\n🎯 Use Cases: Scenarios requiring text in images\n✨ Features: Excellent text rendering performance\n\n{\n  model: \"ideogram-v2\",\n  prompt: string,\n  aspect_ratio?: \"1:1\" | \"4:3\" | \"3:2\" | \"16:9\" | \"3:4\" | \"2:3\" | \"9:16\",\n  style?: string\n}\n\nideogram-v3 - Ideogram V3\n\nOutstanding design capabilities\n\n🎯 Use Cases: First choice for designers and creative professionals\n✨ Features: Better text rendering and typography\n\n{\n  model: \"ideogram-v3\",\n  prompt: string,\n  aspect_ratio?: \"1:1\" | \"4:3\" | \"3:2\" | \"16:9\" | \"3:4\" | \"2:3\" | \"9:16\",\n  style?: string\n}\n\nStability AI\n\nstability-1-0 - Stability 1.0\n\nPerfect for generating detailed images\n\n🎯 Use Cases: Image generation requiring fine control and high detail\n✨ Features: Supports negative prompts, customizable style\n\n{\n  model: \"stability-1-0\",\n  prompt: string,\n  aspect_ratio?: \"1:1\" | \"4:3\" | \"3:2\" | \"16:9\" | \"3:4\" | \"2:3\" | \"9:16\",\n  style?: string,\n  negative_prompt?: string       // Specify unwanted content\n}"
      },
      {
        "title": "Music Generation",
        "body": "minimax-music - MiniMax Music\n\nAI music generation from text with custom lyrics support\n\n🎯 Provider: MiniMax\n✨ Features: Text-to-music conversion, supports custom lyrics\n🎵 Use Cases: Music creation from text descriptions or lyrics\n\n{\n  model: \"minimax-music\",\n  prompt: string,                // Required: Music generation description (max 300 characters)\n  lyrics?: string                // Optional: Custom lyrics (max 3000 characters)\n}"
      },
      {
        "title": "Create Task (Async)",
        "body": "POST /api/v1/tasks/async - Create an async task. Returns immediately with task ID.\n\nRequest:\n\ncurl -X POST https://monet.vision/api/v1/tasks/async \\\n  -H \"Content-Type: application/json\" \\\n  -H \"Authorization: Bearer $MONET_API_KEY\" \\\n  -d '{\n    \"type\": \"video\",\n    \"input\": {\n      \"model\": \"sora-2\",\n      \"prompt\": \"A cat running\"\n    },\n    \"idempotency_key\": \"unique-key-123\"\n  }'\n\n⚠️ Important: idempotency_key is required. Use a unique value (e.g., UUID) to prevent duplicate task creation if the request is retried.\n\nResponse:\n\n{\n  \"id\": \"task_abc123\",\n  \"status\": \"pending\",\n  \"type\": \"video\",\n  \"created_at\": \"2026-02-27T10:00:00Z\"\n}"
      },
      {
        "title": "Create Task (Streaming)",
        "body": "POST /api/v1/tasks/sync - Create a task with SSE streaming. Waits for completion and streams progress.\n\nRequest:\n\ncurl -X POST https://monet.vision/api/v1/tasks/sync \\\n  -H \"Content-Type: application/json\" \\\n  -H \"Authorization: Bearer $MONET_API_KEY\" \\\n  -N \\\n  -d '{\n    \"type\": \"video\",\n    \"input\": {\n      \"model\": \"sora-2\",\n      \"prompt\": \"A cat running\"\n    },\n    \"idempotency_key\": \"unique-key-123\"\n  }'"
      },
      {
        "title": "Get Task",
        "body": "GET /api/v1/tasks/{taskId} - Get task status and result.\n\nRequest:\n\ncurl https://monet.vision/api/v1/tasks/task_abc123 \\\n  -H \"Authorization: Bearer $MONET_API_KEY\"\n\nResponse:\n\n{\n  \"id\": \"task_abc123\",\n  \"status\": \"success\",\n  \"type\": \"video\",\n  \"outputs\": [\n    {\n      \"model\": \"sora-2\",\n      \"status\": \"success\",\n      \"progress\": 100,\n      \"url\": \"https://files.monet.vision/...\"\n    }\n  ],\n  \"created_at\": \"2026-02-27T10:00:00Z\",\n  \"updated_at\": \"2026-02-27T10:01:30Z\"\n}"
      },
      {
        "title": "List Tasks",
        "body": "GET /api/v1/tasks/list - List tasks with pagination.\n\nRequest:\n\ncurl \"https://monet.vision/api/v1/tasks/list?page=1&pageSize=20\" \\\n  -H \"Authorization: Bearer $MONET_API_KEY\"\n\nResponse:\n\n{\n  \"tasks\": [\n    {\n      \"id\": \"task_abc123\",\n      \"status\": \"success\",\n      \"type\": \"video\",\n      \"outputs\": [\n        {\n          \"model\": \"sora-2\",\n          \"status\": \"success\",\n          \"progress\": 100,\n          \"url\": \"https://files.monet.vision/...\"\n        }\n      ],\n      \"created_at\": \"2026-02-27T10:00:00Z\",\n      \"updated_at\": \"2026-02-27T10:01:30Z\"\n    }\n  ],\n  \"page\": 1,\n  \"pageSize\": 20,\n  \"total\": 100\n}"
      },
      {
        "title": "Upload File",
        "body": "POST /api/v1/files - Upload a file to get an online access URL.\n\n📁 File Storage: Uploaded files are stored for 24 hours and will be automatically deleted after expiration.\n\nRequest:\n\ncurl -X POST https://monet.vision/api/v1/files \\\n  -H \"Authorization: Bearer $MONET_API_KEY\" \\\n  -F \"file=@/path/to/your/file.mp4\" \\\n  -v\n\nUse Cases:\n\nUpload reference images for video/image generation tasks\nUpload video files for video processing\nUpload audio files for music tasks\nGet temporary online URLs for file sharing\n\nResponse:\n\n{\n  \"id\": \"file_xyz789\",\n  \"url\": \"...\",\n  \"filename\": \"file.mp4\",\n  \"size\": 1048576,\n  \"content_type\": \"video/mp4\",\n  \"created_at\": \"2026-02-27T10:00:00Z\"\n}"
      },
      {
        "title": "Environment Variables",
        "body": "export MONET_API_KEY=\"monet_xxx\""
      },
      {
        "title": "Authentication",
        "body": "All API requests require authentication via the Authorization header:\n\nAuthorization: Bearer monet_xxx"
      }
    ],
    "body": "Monet AI Skill\n\nComprehensive AI content generation API designed for AI agents. Monet AI provides unified access to state-of-the-art AI generation models for video (Sora, Veo, Doubao Seedance, Wan, Hailuo, Kling), image (GPT-4o, Nano Banana, Seedream, Flux, Imagen, Ideogram), and music (MiniMax Music) generation. Build intelligent workflows that combine multiple AI capabilities for automated content creation pipelines.\n\nWhen to Use\n\nUse this skill when:\n\nVideo Generation: Create AI-generated videos from text prompts using state-of-the-art models\nSora: OpenAI's video generation model for high-quality, realistic videos\nVeo: Google's video generation model\nDoubao Seedance: ByteDance's AI video model with audio-visual sync\nWan: Alibaba's video generation model with excellent localization support\nHailuo: Fast video generation with good quality-speed balance\nKling: Kuaishou's video generation model\nImage Generation: Generate images from text descriptions with various artistic styles\nGPT-4o: OpenAI's multimodal model for image generation\nNano Banana: Google's image model with ultra-high character consistency\nSeedream: ByteDance's intelligent visual reasoning model\nWan: Alibaba's visual model for high-quality and expressive image generation\nFlux: High-quality photorealistic and artistic image generation\nImagen: Google's text-to-image model\nIdeogram: Specialized in text rendering and precise composition\nMusic Generation: Create original music and audio from text descriptions\nMiniMax Music: AI music generation with support for custom lyrics and text-to-music conversion\nAI Agent Integration: Build intelligent workflows that combine multiple AI generation capabilities for automated content creation pipelines\nGetting API Key\nVisit https://monet.vision to register an account\nAfter login, go to https://monet.vision/skills/keys to create an API Key\nConfigure the API Key in environment variables or code\n\nIf you don't have an API Key, ask your owner to apply at monet.vision.\n\nQuick Start\nCreate a Video Generation Task\ncurl -X POST https://monet.vision/api/v1/tasks/async \\\n  -H \"Content-Type: application/json\" \\\n  -H \"Authorization: Bearer $MONET_API_KEY\" \\\n  -d '{\n    \"type\": \"video\",\n    \"input\": {\n      \"model\": \"sora-2\",\n      \"prompt\": \"A cat running in the park\",\n      \"duration\": 5,\n      \"aspect_ratio\": \"16:9\"\n    },\n    \"idempotency_key\": \"unique-key-123\"\n  }'\n\n\n⚠️ Important: idempotency_key is required. Use a unique value (e.g., UUID) to prevent duplicate task creation if the request is retried.\n\nResponse:\n\n{\n  \"id\": \"task_abc123\",\n  \"status\": \"pending\",\n  \"type\": \"video\",\n  \"created_at\": \"2026-02-27T10:00:00Z\"\n}\n\nGet Task Status and Result\n\nTask processing is asynchronous. You need to poll the task status until it becomes success or failed. Recommended polling interval: 5 seconds.\n\ncurl https://monet.vision/api/v1/tasks/task_abc123 \\\n  -H \"Authorization: Bearer $MONET_API_KEY\"\n\n\nResponse when completed:\n\n{\n  \"id\": \"task_abc123\",\n  \"status\": \"success\",\n  \"type\": \"video\",\n  \"outputs\": [\n    {\n      \"model\": \"sora-2\",\n      \"status\": \"success\",\n      \"progress\": 100,\n      \"url\": \"https://files.monet.vision/...\"\n    }\n  ],\n  \"created_at\": \"2026-02-27T10:00:00Z\",\n  \"updated_at\": \"2026-02-27T10:01:30Z\"\n}\n\n\nExample: Poll until completion\n\nconst TASK_ID = \"task_abc123\";\nconst MONET_API_KEY = process.env.MONET_API_KEY;\n\nasync function pollTask() {\n  while (true) {\n    const response = await fetch(\n      `https://monet.vision/api/v1/tasks/${TASK_ID}`,\n      {\n        headers: {\n          Authorization: `Bearer ${MONET_API_KEY}`,\n        },\n      },\n    );\n\n    const data = await response.json();\n    const status = data.status;\n\n    if (status === \"success\") {\n      console.log(\"Task completed successfully!\");\n      console.log(JSON.stringify(data, null, 2));\n      break;\n    } else if (status === \"failed\") {\n      console.log(\"Task failed!\");\n      console.log(JSON.stringify(data, null, 2));\n      break;\n    } else {\n      console.log(`Task status: ${status}, waiting...`);\n      await new Promise((resolve) => setTimeout(resolve, 5000)); // Wait 5 seconds\n    }\n  }\n}\n\npollTask();\n\nSupported Models\nVideo Generation\nSora (OpenAI)\n\nsora-2 - Sora 2\n\nOpenAI latest video generation model\n\n🎯 Use Cases: Video projects requiring OpenAI's latest technology\n⏱️ Duration: 10-15 seconds\n🎵 Features: Audio generation support, reference image support\n{\n  model: \"sora-2\",\n  prompt: string,                // Required\n  images?: string[],             // Optional: Reference images\n  duration?: 10 | 15,           // Optional, default: 10\n  aspect_ratio?: \"16:9\" | \"9:16\"\n}\n\n\nsora-2-pro - Sora 2 Pro\n\nPerfect quality for cinematic scenes\n\n🎯 Use Cases: Professional film, advertising, and high-end production\n⏱️ Duration: 15-25 seconds\n🎵 Features: Audio generation support, reference image support\n{\n  model: \"sora-2-pro\",\n  prompt: string,\n  images?: string[],\n  duration?: 15 | 25,           // Optional, default: 15\n  aspect_ratio?: \"16:9\" | \"9:16\"\n}\n\nVeo (Google)\n\nveo-3-1-fast - Google Veo 3.1 Fast\n\nUltra-fast video generation\n\n🎯 Use Cases: Video projects requiring fast generation\n⏱️ Duration: 8 seconds\n📺 Resolution: 1080p with audio generation support\n{\n  model: \"veo-3-1-fast\",\n  prompt: string,\n  images?: string[],             // Reference images\n  aspect_ratio?: \"16:9\" | \"9:16\"\n}\n\n\nveo-3-1 - Google Veo 3.1\n\nAdvanced AI video with sound\n\n🎯 Use Cases: Professional-grade video production\n⏱️ Duration: 8 seconds\n📺 Resolution: 1080p with audio generation support\n{\n  model: \"veo-3-1\",\n  prompt: string,\n  images?: string[],\n  aspect_ratio?: \"16:9\" | \"9:16\"\n}\n\n\nveo-3-fast - Google Veo 3 Fast\n\n30% faster than standard Veo 3\n\n🎯 Use Cases: Video projects requiring rapid iteration\n⏱️ Duration: 8 seconds\n📺 Resolution: 1080p, supports negative prompts\n{\n  model: \"veo-3-fast\",\n  prompt: string,\n  images?: string[],\n  negative_prompt?: string       // Specify unwanted content\n}\n\n\nveo-3 - Google Veo 3\n\nHigh-quality video generation\n\n🎯 Use Cases: Standard high-quality video production\n⏱️ Duration: 8 seconds\n📺 Resolution: 1080p, supports negative prompts\n{\n  model: \"veo-3\",\n  prompt: string,\n  images?: string[],\n  negative_prompt?: string\n}\n\nWan\n\nwan-2-6 - Wan 2.6\n\nMulti-shot and automatic audio\n\n🎯 Use Cases: Video production requiring multi-shot switching\n⏱️ Duration: 5-15 seconds\n📺 Resolution: 720p-1080p with audio generation support\n{\n  model: \"wan-2-6\",\n  prompt: string,\n  images?: string[],\n  duration?: 5 | 10 | 15,\n  resolution?: \"720p\" | \"1080p\",\n  aspect_ratio?: \"16:9\" | \"9:16\" | \"4:3\" | \"3:4\" | \"1:1\",\n  shot_type?: \"single\" | \"multi\"  // Single/multi-shot switching\n}\n\n\nwan-2-5 - Wan 2.5\n\nSupports automatic audio generation\n\n🎯 Use Cases: Quickly generating videos with audio\n⏱️ Duration: 5-10 seconds\n📺 Resolution: 480p-1080p with audio support\n{\n  model: \"wan-2-5\",\n  prompt: string,\n  images?: string[],\n  duration?: 5 | 10,\n  resolution?: \"480p\" | \"720p\" | \"1080p\",\n  aspect_ratio?: \"16:9\" | \"9:16\" | \"4:3\" | \"3:4\" | \"1:1\"\n}\n\n\nwan-2-2-flash - Wan 2.2 Flash\n\nInstruction understanding, controllable camera movement\n\n🎯 Use Cases: Scenarios requiring precise camera movement control\n⏱️ Duration: 5-10 seconds\n📺 Resolution: 480p-1080p\n{\n  model: \"wan-2-2-flash\",\n  prompt: string,\n  images?: string[],\n  duration?: 5 | 10,\n  resolution?: \"480p\" | \"720p\" | \"1080p\",\n  negative_prompt?: string\n}\n\n\nwan-2-2 - Wan 2.2\n\nExcellent image details, strong motion stability\n\n🎯 Use Cases: Video production requiring high stability\n⏱️ Duration: 5-10 seconds\n📺 Resolution: 480p-1080p\n{\n  model: \"wan-2-2\",\n  prompt: string,\n  images?: string[],\n  duration?: 5 | 10,\n  resolution?: \"480p\" | \"1080p\",\n  aspect_ratio?: \"16:9\" | \"9:16\" | \"4:3\" | \"3:4\" | \"1:1\",\n  negative_prompt?: string\n}\n\nKling\n\nkling-2-6 - Kling 2.6\n\nCinematic videos and audio\n\n🎯 Use Cases: Cinematic video production\n⏱️ Duration: 5-10 seconds\n✨ Features: Strong visual realism, audio generation support\n{\n  model: \"kling-2-6\",\n  prompt: string,\n  images?: string[],\n  duration?: 5 | 10,\n  aspect_ratio?: \"1:1\" | \"16:9\" | \"9:16\",\n  generate_audio?: boolean\n}\n\n\nkling-2-5 - Kling 2.5 Turbo\n\nSmooth motion, stronger consistency\n\n🎯 Use Cases: Video production requiring high consistency\n⏱️ Duration: 5-10 seconds\n✨ Features: Supports negative prompts\n{\n  model: \"kling-2-5\",\n  prompt: string,\n  images?: string[],\n  duration?: 5 | 10,\n  aspect_ratio?: \"1:1\" | \"16:9\" | \"9:16\",\n  negative_prompt?: string\n}\n\n\nkling-v2-1-master - Kling 2.1 Master\n\nStrong visual realism with enhanced features\n\n🎯 Use Cases: Professional-grade high-quality video production\n⏱️ Duration: 5-10 seconds\n✨ Features: Strength adjustment support, negative prompts\n{\n  model: \"kling-v2-1-master\",\n  prompt: string,\n  images?: string[],\n  duration?: 5 | 10,\n  aspect_ratio?: \"1:1\" | \"16:9\" | \"9:16\",\n  strength?: number,            // 0-1: Control generation effect\n  negative_prompt?: string\n}\n\n\nkling-v2-1 - Kling 2.1\n\nStrong visual realism\n\n🎯 Use Cases: High-realism video production\n⏱️ Duration: 5-10 seconds\n✨ Features: Strength adjustment, negative prompts\n{\n  model: \"kling-v2-1\",\n  prompt: string,\n  images?: string[],\n  duration?: 5 | 10,\n  aspect_ratio?: \"1:1\" | \"16:9\" | \"9:16\",\n  strength?: number,            // 0-1\n  negative_prompt?: string\n}\n\n\nkling-v2 - Kling 2.0\n\nExcellent aesthetics\n\n🎯 Use Cases: Artistic creation and aesthetically-oriented videos\n⏱️ Duration: 5-10 seconds\n✨ Features: Strength adjustment, negative prompts\n{\n  model: \"kling-v2\",\n  prompt: string,\n  images?: string[],\n  duration?: 5 | 10,\n  aspect_ratio?: \"1:1\" | \"16:9\" | \"9:16\",\n  strength?: number,            // 0-1\n  negative_prompt?: string\n}\n\nHailuo\n\nhailuo-2-3 - Hailuo 2.3\n\nExcellent body movements and physics performance\n\n🎯 Use Cases: Videos requiring realistic physics effects\n⏱️ Duration: 6-10 seconds\n📺 Resolution: 768p-1080p, extreme physics simulations\n{\n  model: \"hailuo-2-3\",\n  prompt: string,\n  images?: string[],\n  duration?: 6 | 10,\n  resolution?: \"768p\" | \"1080p\"\n}\n\n\nhailuo-2-3-fast - Hailuo 2.3 Fast\n\nFast generation speed\n\n🎯 Use Cases: Projects requiring rapid iteration\n⏱️ Duration: 6-10 seconds\n📺 Resolution: 768p-1080p\n{\n  model: \"hailuo-2-3-fast\",\n  prompt: string,\n  images?: string[],\n  duration?: 6 | 10,\n  resolution?: \"768p\" | \"1080p\"\n}\n\n\nhailuo-02 - Hailuo 02\n\nExtreme physics simulations\n\n🎯 Use Cases: Scenarios requiring accurate physics simulation\n⏱️ Duration: 6-10 seconds\n📺 Resolution: 768p-1080p\n{\n  model: \"hailuo-02\",\n  prompt: string,\n  images?: string[],\n  duration?: 6 | 10,\n  resolution?: \"768p\" | \"1080p\"\n}\n\n\nhailuo-01-live2d - Hailuo 01 Live2d\n\nHailuo Live2D model\n\n🎯 Use Cases: 2D character animation production\n✨ Features: Suitable for 2D character animation\n{\n  model: \"hailuo-01-live2d\",\n  prompt: string,\n  images?: string[]\n}\n\n\nhailuo-01 - Hailuo 01\n\nHighest video quality\n\n🎯 Use Cases: Video production requiring ultimate quality\n✨ Features: Suitable for high-quality needs\n{\n  model: \"hailuo-01\",\n  prompt: string,\n  images?: string[]\n}\n\nDoubao Seedance\n\ndoubao-seedance-1-5-pro - Seedance 1.5 Pro\n\nPro-grade audio-visual sync\n\n🎯 Use Cases: Professional production requiring audio-visual sync\n⏱️ Duration: 4-12 seconds\n📺 Resolution: 480p-720p with audio generation support\n{\n  model: \"doubao-seedance-1-5-pro\",\n  prompt: string,\n  images?: string[],\n  duration?: number,\n  resolution?: \"480p\" | \"720p\",\n  aspect_ratio?: \"1:1\" | \"4:3\" | \"16:9\" | \"3:4\" | \"9:16\" | \"21:9\",\n  generate_audio?: boolean\n}\n\n\ndoubao-seedance-1-0-pro-fast - Seedance 1.0 Pro Fast\n\nPremium quality & unbeatable efficiency\n\n🎯 Use Cases: Scenarios requiring fast high-quality output\n⏱️ Duration: 2-12 seconds\n📺 Resolution: 720p-1080p, ByteDance's next-gen AI video model\n{\n  model: \"doubao-seedance-1-0-pro-fast\",\n  prompt: string,\n  images?: string[],\n  duration?: number,\n  resolution?: \"720p\" | \"1080p\",\n  aspect_ratio?: \"1:1\" | \"4:3\" | \"16:9\" | \"3:4\" | \"9:16\" | \"21:9\"\n}\n\n\ndoubao-seedance-1-0-pro - Seedance 1.0 Pro\n\nStable motion performance\n\n🎯 Use Cases: Video production requiring stable motion\n⏱️ Duration: 5-10 seconds\n📺 Resolution: 480p-1080p\n{\n  model: \"doubao-seedance-1-0-pro\",\n  prompt: string,\n  images?: string[],\n  duration?: 5 | 10,\n  resolution?: \"480p\" | \"1080p\",\n  aspect_ratio?: \"1:1\" | \"4:3\" | \"16:9\" | \"3:4\" | \"9:16\"\n}\n\n\ndoubao-seedance-1-0-lite - Seedance 1.0 Lite\n\nPrecise semantic understanding\n\n🎯 Use Cases: Scenarios requiring precise semantic understanding\n⏱️ Duration: 5-10 seconds\n📺 Resolution: 480p-1080p\n{\n  model: \"doubao-seedance-1-0-lite\",\n  prompt: string,\n  images?: string[],\n  duration?: 5 | 10,\n  resolution?: \"480p\" | \"720p\" | \"1080p\"\n}\n\nSpecial Features\n\nkling-motion-control - Kling Motion Control\n\nPrecision motion control via video references\n\n🎯 Use Cases: Scenarios requiring motion replication from reference videos\n⏱️ Duration: 3-30 seconds\n📺 Resolution: 720p/1080p with audio generation support\n💰 Pricing: 720p: 8 credits/s, 1080p: 15 credits/s\n{\n  model: \"kling-motion-control\",\n  prompt: string,                // Required: Detailed motion description\n  images: string[],              // Required: min 1 reference image\n  videos: string[],              // Required: min 1 reference video\n  resolution?: \"720p\" | \"1080p\"\n}\n\n\nrunway-act-two - Runway Act Two\n\nRunway Next-Generation Motion Capture Model\n\n🎯 Use Cases: Capturing motion from videos and applying to new characters\n⏱️ Duration: 3-30 seconds\n✨ Features: Motion transfer support\n💰 Pricing: 10 credits/second\n{\n  model: \"runway-act-two\",\n  images: string[],              // Required: min 1 target character image\n  videos: string[],              // Required: min 1 motion reference video\n  aspect_ratio?: \"1:1\" | \"4:3\" | \"16:9\" | \"3:4\" | \"9:16\" | \"21:9\"\n}\n\n\nwan-animate-mix - Wan Animate Mix (Standard)\n\nPerfect for character replacement scenarios\n\n🎯 Use Cases: Video character replacement\n⏱️ Duration: 3-30 seconds\n✨ Features: Replace characters in videos with specified image characters\n💰 Pricing: 10 credits/second\n{\n  model: \"wan-animate-mix\",\n  videos: string[],              // Required: Original videos\n  images: string[]               // Required: Target character images\n}\n\n\nwan-animate-mix-pro - Wan Animate Mix Pro (Professional)\n\nHigh animation fluidity with better results\n\n🎯 Use Cases: Professional-grade video character replacement\n⏱️ Duration: 3-30 seconds\n✨ Features: Higher quality character replacement effects\n💰 Pricing: 20 credits/second\n{\n  model: \"wan-animate-mix-pro\",\n  videos: string[],              // Required\n  images: string[]               // Required\n}\n\n\nwan-animate-move - Wan Animate Move (Standard)\n\nReplicate dance and challenging body movements\n\n🎯 Use Cases: Motion capture and transfer\n⏱️ Duration: 3-30 seconds\n✨ Features: Apply motion from reference videos to target images\n💰 Pricing: 10 credits/second\n{\n  model: \"wan-animate-move\",\n  videos: string[],              // Required: Motion reference videos\n  images: string[]               // Required: Target character images\n}\n\n\nwan-animate-move-pro - Wan Animate Move Pro (Professional)\n\nHigh animation fluidity with better results\n\n🎯 Use Cases: Professional-grade motion capture and transfer\n⏱️ Duration: 3-30 seconds\n✨ Features: Higher quality motion transfer effects\n💰 Pricing: 20 credits/second\n{\n  model: \"wan-animate-move-pro\",\n  videos: string[],              // Required\n  images: string[]               // Required\n}\n\nImage Generation\nGPT (OpenAI)\n\ngpt-4o - GPT 4o\n\nAccurate, realistic output\n\n🎯 Use Cases: High-quality, photorealistic image generation\n✨ Features: Supports multiple reference images, multiple aspect ratios, customizable style\n{\n  model: \"gpt-4o\",\n  prompt: string,\n  images?: string[],             // Reference images for style guidance\n  aspect_ratio?: \"1:1\" | \"4:3\" | \"3:2\" | \"16:9\" | \"3:4\" | \"2:3\" | \"9:16\",\n  style?: string                 // Custom style description\n}\n\n\ngpt-image-1-5 - GPT Image 1.5\n\nTrue-color precision rendering\n\n🎯 Use Cases: Professional image generation requiring color accuracy\n✨ Features: Supports up to 10 reference images, adjustable quality\n{\n  model: \"gpt-image-1-5\",\n  prompt: string,\n  images?: string[],             // max 10 reference images\n  aspect_ratio?: \"1:1\" | \"3:2\" | \"2:3\",\n  quality?: \"auto\" | \"low\" | \"medium\" | \"high\"\n}\n\nNano Banana (Google)\n\nnano-banana-1 - Google Nano Banana\n\nUltra-high character consistency\n\n🎯 Use Cases: Image series requiring consistent character appearance\n✨ Features: Supports up to 5 reference images, multiple aspect ratio options\n{\n  model: \"nano-banana-1\",\n  prompt: string,\n  images?: string[],             // max 5 reference images\n  aspect_ratio?: \"1:1\" | \"2:3\" | \"3:2\" | \"4:3\" | \"3:4\" | \"16:9\" | \"9:16\"\n}\n\n\nnano-banana-1-pro - Nano Banana Pro\n\nGoogle's flagship generation model\n\n🎯 Use Cases: Professional-grade high-quality image generation\n✨ Features: Supports 1K-4K resolution, up to 14 reference images, ultra-wide 21:9\n{\n  model: \"nano-banana-1-pro\",\n  prompt: string,\n  images?: string[],             // max 14 reference images\n  aspect_ratio?: \"1:1\" | \"2:3\" | \"3:2\" | \"4:3\" | \"3:4\" | \"4:5\" | \"5:4\" | \"16:9\" | \"9:16\" | \"21:9\",\n  resolution?: \"1K\" | \"2K\" | \"4K\"\n}\n\n\nnano-banana-2 - Nano Banana 2\n\nGoogle Gemini latest model\n\n🎯 Use Cases: Latest technology for high-quality image generation\n✨ Features: Supports 1K-4K resolution, up to 14 reference images, ultra-wide 8:1 ratio\n{\n  model: \"nano-banana-2\",\n  prompt: string,\n  images?: string[],             // max 14 reference images\n  aspect_ratio?: \"1:1\" | \"2:3\" | \"3:2\" | \"4:3\" | \"3:4\" | \"4:5\" | \"5:4\" | \"16:9\" | \"9:16\" | \"21:9\" | \"4:1\" | \"1:4\" | \"8:1\" | \"1:8\",\n  resolution?: \"1K\" | \"2K\" | \"4K\"\n}\n\nWan\n\nwan-i-2-6 - Wan 2.6\n\nHigh-quality and expressive\n\n🎯 Use Cases: Creative image generation requiring high expressiveness\n✨ Features: Supports up to 4 reference images, ultra-wide 21:9\n{\n  model: \"wan-i-2-6\",\n  prompt: string,\n  images?: string[],             // max 4 reference images\n  aspect_ratio?: \"1:1\" | \"4:3\" | \"3:2\" | \"16:9\" | \"3:4\" | \"2:3\" | \"9:16\" | \"21:9\"\n}\n\n\nwan-2-5 - Wan 2.5\n\nFast, creative image generation\n\n🎯 Use Cases: Quick creation and iteration\n✨ Features: Supports up to 2 reference images, ultra-wide 21:9\n{\n  model: \"wan-2-5\",\n  prompt: string,\n  images?: string[],             // max 2 reference images\n  aspect_ratio?: \"1:1\" | \"4:3\" | \"3:2\" | \"16:9\" | \"3:4\" | \"2:3\" | \"9:16\" | \"21:9\"\n}\n\nSeedream (ByteDance)\n\nseedream-5-0 - Seedream 5.0 Lite\n\nIntelligent visual reasoning\n\n🎯 Use Cases: Complex scenarios requiring intelligent understanding and reasoning\n✨ Features: 2K-3K resolution, up to 14 reference images, ultra-wide 21:9\n{\n  model: \"seedream-5-0\",\n  prompt: string,\n  images?: string[],             // max 14 reference images\n  aspect_ratio?: \"1:1\" | \"2:3\" | \"3:2\" | \"3:4\" | \"4:3\" | \"4:5\" | \"5:4\" | \"9:16\" | \"16:9\" | \"21:9\",\n  resolution?: \"2K\" | \"3K\"\n}\n\n\nseedream-4-5 - Seedream 4.5\n\nByteDance's 4K image model\n\n🎯 Use Cases: High-resolution professional image generation\n✨ Features: 2K-4K resolution, up to 14 reference images, ultra-wide 21:9\n{\n  model: \"seedream-4-5\",\n  prompt: string,\n  images?: string[],             // max 14 reference images\n  aspect_ratio?: \"1:1\" | \"2:3\" | \"3:2\" | \"3:4\" | \"4:3\" | \"4:5\" | \"5:4\" | \"9:16\" | \"16:9\" | \"21:9\",\n  resolution?: \"2K\" | \"4K\"\n}\n\n\nseedream-4-0 - Seedream 4.0\n\nSupport images with cohesive styles\n\n🎯 Use Cases: Image series requiring consistent style\n✨ Features: Supports up to 10 reference images\n{\n  model: \"seedream-4-0\",\n  prompt: string,\n  images?: string[],             // max 10 reference images\n  aspect_ratio?: \"1:1\" | \"4:3\" | \"3:2\" | \"16:9\" | \"3:4\" | \"2:3\" | \"9:16\"\n}\n\nFlux (Black Forest Labs)\n\nflux-2-dev - Flux.2 Dev\n\nPhotorealistic output\n\n🎯 Use Cases: Image generation requiring high photorealism\n✨ Features: Model by Black Forest Labs, multiple aspect ratio options\n{\n  model: \"flux-2-dev\",\n  prompt: string,\n  aspect_ratio?: \"1:1\" | \"4:3\" | \"3:2\" | \"16:9\" | \"3:4\" | \"2:3\" | \"9:16\"\n}\n\n\nflux-kontext-pro - Flux Kontext Pro\n\nPerfect for editing, compositing\n\n🎯 Use Cases: Professional image editing and compositing work\n✨ Features: Supports reference images, customizable style\n{\n  model: \"flux-kontext-pro\",\n  prompt: string,\n  images?: string[],\n  aspect_ratio?: \"1:1\" | \"4:3\" | \"3:2\" | \"16:9\" | \"3:4\" | \"2:3\" | \"9:16\",\n  style?: string\n}\n\n\nflux-kontext-max - Flux Kontext Max\n\nExcellent for prompt accuracy\n\n🎯 Use Cases: Scenarios requiring precise control of generation results\n✨ Features: Supports reference images, customizable style\n{\n  model: \"flux-kontext-max\",\n  prompt: string,\n  images?: string[],\n  aspect_ratio?: \"1:1\" | \"4:3\" | \"3:2\" | \"16:9\" | \"3:4\" | \"2:3\" | \"9:16\",\n  style?: string\n}\n\n\nflux-1-schnell - Flux Schnell\n\nSuitable for simple basic scenes\n\n🎯 Use Cases: Quick prototyping and simple scenarios\n✨ Features: Fast generation speed\n{\n  model: \"flux-1-schnell\",\n  prompt: string\n}\n\nImagen (Google)\n\nimagen-3-0 - Imagen 3.0\n\nFast, high-quality results\n\n🎯 Use Cases: Fast high-quality image generation\n✨ Features: Google's advanced image model, customizable style\n{\n  model: \"imagen-3-0\",\n  prompt: string,\n  aspect_ratio?: \"1:1\" | \"3:4\" | \"4:3\" | \"9:16\" | \"16:9\",\n  style?: string\n}\n\n\nimagen-4-0 - Imagen 4.0\n\nGoogle's latest generation model\n\n🎯 Use Cases: High-quality images requiring latest technology\n✨ Features: Higher quality and precision, customizable style\n{\n  model: \"imagen-4-0\",\n  prompt: string,\n  aspect_ratio?: \"1:1\" | \"3:4\" | \"4:3\" | \"9:16\" | \"16:9\",\n  style?: string\n}\n\nIdeogram\n\nideogram-v2 - Ideogram V2\n\nHighly recommended for text editing\n\n🎯 Use Cases: Scenarios requiring text in images\n✨ Features: Excellent text rendering performance\n{\n  model: \"ideogram-v2\",\n  prompt: string,\n  aspect_ratio?: \"1:1\" | \"4:3\" | \"3:2\" | \"16:9\" | \"3:4\" | \"2:3\" | \"9:16\",\n  style?: string\n}\n\n\nideogram-v3 - Ideogram V3\n\nOutstanding design capabilities\n\n🎯 Use Cases: First choice for designers and creative professionals\n✨ Features: Better text rendering and typography\n{\n  model: \"ideogram-v3\",\n  prompt: string,\n  aspect_ratio?: \"1:1\" | \"4:3\" | \"3:2\" | \"16:9\" | \"3:4\" | \"2:3\" | \"9:16\",\n  style?: string\n}\n\nStability AI\n\nstability-1-0 - Stability 1.0\n\nPerfect for generating detailed images\n\n🎯 Use Cases: Image generation requiring fine control and high detail\n✨ Features: Supports negative prompts, customizable style\n{\n  model: \"stability-1-0\",\n  prompt: string,\n  aspect_ratio?: \"1:1\" | \"4:3\" | \"3:2\" | \"16:9\" | \"3:4\" | \"2:3\" | \"9:16\",\n  style?: string,\n  negative_prompt?: string       // Specify unwanted content\n}\n\nMusic Generation\n\nminimax-music - MiniMax Music\n\nAI music generation from text with custom lyrics support\n\n🎯 Provider: MiniMax\n✨ Features: Text-to-music conversion, supports custom lyrics\n🎵 Use Cases: Music creation from text descriptions or lyrics\n{\n  model: \"minimax-music\",\n  prompt: string,                // Required: Music generation description (max 300 characters)\n  lyrics?: string                // Optional: Custom lyrics (max 3000 characters)\n}\n\nAPI Reference\nCreate Task (Async)\n\nPOST /api/v1/tasks/async - Create an async task. Returns immediately with task ID.\n\nRequest:\n\ncurl -X POST https://monet.vision/api/v1/tasks/async \\\n  -H \"Content-Type: application/json\" \\\n  -H \"Authorization: Bearer $MONET_API_KEY\" \\\n  -d '{\n    \"type\": \"video\",\n    \"input\": {\n      \"model\": \"sora-2\",\n      \"prompt\": \"A cat running\"\n    },\n    \"idempotency_key\": \"unique-key-123\"\n  }'\n\n\n⚠️ Important: idempotency_key is required. Use a unique value (e.g., UUID) to prevent duplicate task creation if the request is retried.\n\nResponse:\n\n{\n  \"id\": \"task_abc123\",\n  \"status\": \"pending\",\n  \"type\": \"video\",\n  \"created_at\": \"2026-02-27T10:00:00Z\"\n}\n\nCreate Task (Streaming)\n\nPOST /api/v1/tasks/sync - Create a task with SSE streaming. Waits for completion and streams progress.\n\nRequest:\n\ncurl -X POST https://monet.vision/api/v1/tasks/sync \\\n  -H \"Content-Type: application/json\" \\\n  -H \"Authorization: Bearer $MONET_API_KEY\" \\\n  -N \\\n  -d '{\n    \"type\": \"video\",\n    \"input\": {\n      \"model\": \"sora-2\",\n      \"prompt\": \"A cat running\"\n    },\n    \"idempotency_key\": \"unique-key-123\"\n  }'\n\nGet Task\n\nGET /api/v1/tasks/{taskId} - Get task status and result.\n\nRequest:\n\ncurl https://monet.vision/api/v1/tasks/task_abc123 \\\n  -H \"Authorization: Bearer $MONET_API_KEY\"\n\n\nResponse:\n\n{\n  \"id\": \"task_abc123\",\n  \"status\": \"success\",\n  \"type\": \"video\",\n  \"outputs\": [\n    {\n      \"model\": \"sora-2\",\n      \"status\": \"success\",\n      \"progress\": 100,\n      \"url\": \"https://files.monet.vision/...\"\n    }\n  ],\n  \"created_at\": \"2026-02-27T10:00:00Z\",\n  \"updated_at\": \"2026-02-27T10:01:30Z\"\n}\n\nList Tasks\n\nGET /api/v1/tasks/list - List tasks with pagination.\n\nRequest:\n\ncurl \"https://monet.vision/api/v1/tasks/list?page=1&pageSize=20\" \\\n  -H \"Authorization: Bearer $MONET_API_KEY\"\n\n\nResponse:\n\n{\n  \"tasks\": [\n    {\n      \"id\": \"task_abc123\",\n      \"status\": \"success\",\n      \"type\": \"video\",\n      \"outputs\": [\n        {\n          \"model\": \"sora-2\",\n          \"status\": \"success\",\n          \"progress\": 100,\n          \"url\": \"https://files.monet.vision/...\"\n        }\n      ],\n      \"created_at\": \"2026-02-27T10:00:00Z\",\n      \"updated_at\": \"2026-02-27T10:01:30Z\"\n    }\n  ],\n  \"page\": 1,\n  \"pageSize\": 20,\n  \"total\": 100\n}\n\nUpload File\n\nPOST /api/v1/files - Upload a file to get an online access URL.\n\n📁 File Storage: Uploaded files are stored for 24 hours and will be automatically deleted after expiration.\n\nRequest:\n\ncurl -X POST https://monet.vision/api/v1/files \\\n  -H \"Authorization: Bearer $MONET_API_KEY\" \\\n  -F \"file=@/path/to/your/file.mp4\" \\\n  -v\n\n\nUse Cases:\n\nUpload reference images for video/image generation tasks\nUpload video files for video processing\nUpload audio files for music tasks\nGet temporary online URLs for file sharing\n\nResponse:\n\n{\n  \"id\": \"file_xyz789\",\n  \"url\": \"...\",\n  \"filename\": \"file.mp4\",\n  \"size\": 1048576,\n  \"content_type\": \"video/mp4\",\n  \"created_at\": \"2026-02-27T10:00:00Z\"\n}\n\nConfiguration\nEnvironment Variables\nexport MONET_API_KEY=\"monet_xxx\"\n\nAuthentication\n\nAll API requests require authentication via the Authorization header:\n\nAuthorization: Bearer monet_xxx"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/seekton/monet-ai",
    "publisherUrl": "https://clawhub.ai/seekton/monet-ai",
    "owner": "seekton",
    "version": "1.0.9",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/monet-ai",
    "downloadUrl": "https://openagent3.xyz/downloads/monet-ai",
    "agentUrl": "https://openagent3.xyz/skills/monet-ai/agent",
    "manifestUrl": "https://openagent3.xyz/skills/monet-ai/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/monet-ai/agent.md"
  }
}