{
  "schemaVersion": "1.0",
  "item": {
    "slug": "qwenz-image-gen",
    "name": "qwenz-image-gen",
    "source": "tencent",
    "type": "skill",
    "category": "AI 智能",
    "sourceUrl": "https://clawhub.ai/irron/qwenz-image-gen",
    "canonicalUrl": "https://clawhub.ai/irron/qwenz-image-gen",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/qwenz-image-gen",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=qwenz-image-gen",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "SKILL.md",
      "scripts/generate.py"
    ],
    "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/qwenz-image-gen"
    },
    "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/qwenz-image-gen",
    "agentPageUrl": "https://openagent3.xyz/skills/qwenz-image-gen/agent",
    "manifestUrl": "https://openagent3.xyz/skills/qwenz-image-gen/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/qwenz-image-gen/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": "Qwen-Image / Z-Image Skill",
        "body": "基于阿里云百炼的文图生成技能，智能识别场景自动选择最佳模型：\n\n🧍 人像/照片 → z-image-turbo（专精高质量人像，支持胶片质感）\n🖼️ 通用文图 → qwen-image-max（擅长复杂文字渲染、艺术风格）"
      },
      {
        "title": "Features",
        "body": "🤖 智能模型选择：自动检测人像场景，无需手动选择模型\n🎨 双模型支持：Qwen-Image（通用） + Z-Image（人像）\n✍️ 中文文字渲染：在图像中完美呈现复杂中文字符\n📐 多尺寸支持：16:9、4:3、1:1、3:4、9:16 等多种比例\n🔧 可手动指定：支持强制使用特定模型"
      },
      {
        "title": "Setup",
        "body": "从 阿里云百炼控制台 获取 API Key\n配置方式选择其一：\n\n环境变量：export DASHSCOPE_API_KEY=\"sk-xxx\"\nTOOLS.md：在 TOOLS.md 中添加 DASHSCOPE_API_KEY: sk-xxx\n\n地域注意：北京和新加坡地域 API Key 不互通"
      },
      {
        "title": "Available Models",
        "body": "模型描述最佳场景qwen-image-max最佳质量，减少AI痕迹，文字渲染优秀漫画、插画、图文设计、风景、静物qwen-image-plus质量与速度平衡通用场景qwen-image基础模型快速生成z-image-turbo人像专精，胶片质感，真实感强人像照片、人像写真、film grain效果"
      },
      {
        "title": "Supported Sizes",
        "body": "尺寸比例说明1664*92816:9横向宽屏（通用默认）1472*11044:3标准比例1328*13281:1方形1104*14723:4竖向928*16649:16手机竖屏1120*14404:5人像推荐"
      },
      {
        "title": "🎯 快速入门（推荐）",
        "body": "直接写提示词，自动识别场景并选择最佳模型：\n\n# 人像类 → 自动使用 z-image-turbo\npython scripts/generate.py \"短发少女，清新自然风格，微笑\"\n\n# 通用类 → 自动使用 qwen-image-max\npython scripts/generate.py \"七龙珠孙悟空对战比克大魔王，漫画风格\"\n\n# 含film grain关键词 → 自动使用 z-image\npython scripts/generate.py \"胶片感，Kodak Portra 400风格的人像\""
      },
      {
        "title": "🔧 高级选项",
        "body": "python scripts/generate.py \"prompt\" \\\n    --model z \\              # 强制指定模型 (z/qwen/auto)\n    --size 1328*1328 \\       # 图片尺寸\n    --prompt-extend \\        # 开启提示词扩展\n    --no-watermark \\         # 禁用水印\n    --output my-image.png    # 输出路径"
      },
      {
        "title": "Auto-Detection Keywords",
        "body": "以下关键词会触发自动选择 z-image-turbo：\n\n人物类：人、女、男、少女、帅哥、美女、肖像、人物、face、facial\n\n照片/胶片类：photo、photograph、film grain、analog、Kodak、胶片、portra、cinematic、photorealistic、真实、写真人像"
      },
      {
        "title": "人像照片（z-image）",
        "body": "python scripts/generate.py \"东亚年轻女性，户外雪地场景，film grain效果，胶片质感\""
      },
      {
        "title": "漫画风格（qwen-image）",
        "body": "python scripts/generate.py \"七龙珠孙悟空对战比克大魔王，漫画风格，能量波爆炸，天空背景\""
      },
      {
        "title": "带中文文字的漫画",
        "body": "python scripts/generate.py \"一副对联，上联：智启千问，下联：机道为善，横批：人机共生\""
      },
      {
        "title": "Tips",
        "body": "人像首选 z-image：对面部细节、皮肤质感、胶片感优化更好\n文字渲染选 qwen：复杂中文、图文混排场景更精准\n自动模式省心：无需纠结选哪个模型\n提示词长度：正向 ≤800字符，负向 ≤500字符\n扩展提示词：--prompt-extend 可以让AI自动优化你的描述\n\nQwen-Image Skill - 国产文生图利器 🇨🇳"
      }
    ],
    "body": "Qwen-Image / Z-Image Skill\n\n基于阿里云百炼的文图生成技能，智能识别场景自动选择最佳模型：\n\n🧍 人像/照片 → z-image-turbo（专精高质量人像，支持胶片质感）\n🖼️ 通用文图 → qwen-image-max（擅长复杂文字渲染、艺术风格）\nFeatures\n🤖 智能模型选择：自动检测人像场景，无需手动选择模型\n🎨 双模型支持：Qwen-Image（通用） + Z-Image（人像）\n✍️ 中文文字渲染：在图像中完美呈现复杂中文字符\n📐 多尺寸支持：16:9、4:3、1:1、3:4、9:16 等多种比例\n🔧 可手动指定：支持强制使用特定模型\nSetup\n从 阿里云百炼控制台 获取 API Key\n配置方式选择其一：\n环境变量：export DASHSCOPE_API_KEY=\"sk-xxx\"\nTOOLS.md：在 TOOLS.md 中添加 DASHSCOPE_API_KEY: sk-xxx\n\n地域注意：北京和新加坡地域 API Key 不互通\n\nAvailable Models\n模型\t描述\t最佳场景\nqwen-image-max\t最佳质量，减少AI痕迹，文字渲染优秀\t漫画、插画、图文设计、风景、静物\nqwen-image-plus\t质量与速度平衡\t通用场景\nqwen-image\t基础模型\t快速生成\nz-image-turbo\t人像专精，胶片质感，真实感强\t人像照片、人像写真、film grain效果\nSupported Sizes\n尺寸\t比例\t说明\n1664*928\t16:9\t横向宽屏（通用默认）\n1472*1104\t4:3\t标准比例\n1328*1328\t1:1\t方形\n1104*1472\t3:4\t竖向\n928*1664\t9:16\t手机竖屏\n1120*1440\t4:5\t人像推荐\nUsage\n🎯 快速入门（推荐）\n\n直接写提示词，自动识别场景并选择最佳模型：\n\n# 人像类 → 自动使用 z-image-turbo\npython scripts/generate.py \"短发少女，清新自然风格，微笑\"\n\n# 通用类 → 自动使用 qwen-image-max\npython scripts/generate.py \"七龙珠孙悟空对战比克大魔王，漫画风格\"\n\n# 含film grain关键词 → 自动使用 z-image\npython scripts/generate.py \"胶片感，Kodak Portra 400风格的人像\"\n\n🔧 高级选项\npython scripts/generate.py \"prompt\" \\\n    --model z \\              # 强制指定模型 (z/qwen/auto)\n    --size 1328*1328 \\       # 图片尺寸\n    --prompt-extend \\        # 开启提示词扩展\n    --no-watermark \\         # 禁用水印\n    --output my-image.png    # 输出路径\n\nAuto-Detection Keywords\n\n以下关键词会触发自动选择 z-image-turbo：\n\n人物类：人、女、男、少女、帅哥、美女、肖像、人物、face、facial\n\n照片/胶片类：photo、photograph、film grain、analog、Kodak、胶片、portra、cinematic、photorealistic、真实、写真人像\n\n使用示例\n人像照片（z-image）\npython scripts/generate.py \"东亚年轻女性，户外雪地场景，film grain效果，胶片质感\"\n\n漫画风格（qwen-image）\npython scripts/generate.py \"七龙珠孙悟空对战比克大魔王，漫画风格，能量波爆炸，天空背景\"\n\n带中文文字的漫画\npython scripts/generate.py \"一副对联，上联：智启千问，下联：机道为善，横批：人机共生\"\n\nTips\n人像首选 z-image：对面部细节、皮肤质感、胶片感优化更好\n文字渲染选 qwen：复杂中文、图文混排场景更精准\n自动模式省心：无需纠结选哪个模型\n提示词长度：正向 ≤800字符，负向 ≤500字符\n扩展提示词：--prompt-extend 可以让AI自动优化你的描述\n\nQwen-Image Skill - 国产文生图利器 🇨🇳"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/irron/qwenz-image-gen",
    "publisherUrl": "https://clawhub.ai/irron/qwenz-image-gen",
    "owner": "irron",
    "version": "1.0.1",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/qwenz-image-gen",
    "downloadUrl": "https://openagent3.xyz/downloads/qwenz-image-gen",
    "agentUrl": "https://openagent3.xyz/skills/qwenz-image-gen/agent",
    "manifestUrl": "https://openagent3.xyz/skills/qwenz-image-gen/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/qwenz-image-gen/agent.md"
  }
}