{
  "schemaVersion": "1.0",
  "item": {
    "slug": "gemini-image-gen",
    "name": "Gemini Image Gen",
    "source": "tencent",
    "type": "skill",
    "category": "开发工具",
    "sourceUrl": "https://clawhub.ai/IISweetHeartII/gemini-image-gen",
    "canonicalUrl": "https://clawhub.ai/IISweetHeartII/gemini-image-gen",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/gemini-image-gen",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=gemini-image-gen",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "HEARTBEAT.md",
      "INSTALL.md",
      "README.md",
      "SKILL.md",
      "package.json",
      "scripts/gen.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. Then review README.md for any prerequisites, environment setup, or post-install checks. 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. Then review README.md for any prerequisites, environment setup, or post-install checks. 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/gemini-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/gemini-image-gen",
    "agentPageUrl": "https://openagent3.xyz/skills/gemini-image-gen/agent",
    "manifestUrl": "https://openagent3.xyz/skills/gemini-image-gen/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/gemini-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. Then review README.md for any prerequisites, environment setup, or post-install checks. 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. Then review README.md for any prerequisites, environment setup, or post-install checks. Summarize what changed and any follow-up checks I should run."
      }
    ]
  },
  "documentation": {
    "source": "clawhub",
    "primaryDoc": "SKILL.md",
    "sections": [
      {
        "title": "Gemini Image Gen",
        "body": "Generate and edit images via the Google Gemini API using pure Python stdlib. Supports Gemini native generation + editing, Imagen 3 generation, batch runs, and an HTML gallery output."
      },
      {
        "title": "Quick Start",
        "body": "export GEMINI_API_KEY=\"your-key-here\"\n\n# Default: Gemini native, 4 random prompts\npython3 scripts/gen.py\n\n# Custom prompt\npython3 scripts/gen.py --prompt \"a cyberpunk cat riding a neon motorcycle through Tokyo at night\"\n\n# Imagen 3 engine\npython3 scripts/gen.py --engine imagen --count 4 --aspect 16:9\n\n# Edit an existing image (Gemini engine only)\npython3 scripts/gen.py --edit path/to/image.png --prompt \"change the background to a sunset beach\"\n\n# Use a style preset\npython3 scripts/gen.py --style watercolor --prompt \"floating islands above a calm sea\"\n\n# List available styles\npython3 scripts/gen.py --styles"
      },
      {
        "title": "Style Presets",
        "body": "StyleDescriptionphotoUltra-detailed photorealistic photography, 8K resolution, sharp focusanimeHigh-quality anime illustration, Studio Ghibli inspired, vibrant colorswatercolorDelicate watercolor painting on textured paper, soft edges, gentle color bleedingcyberpunkNeon-lit cyberpunk scene, rain-soaked streets, holographic displays, Blade Runner aestheticminimalistClean minimalist design, geometric shapes, limited color palette, white spaceoil-paintingClassical oil painting with visible brushstrokes, rich textures, Renaissance lightingpixel-artDetailed pixel art, retro 16-bit style, crisp edges, nostalgic palettesketchPencil sketch on cream paper, hatching and cross-hatching, artistic imperfections3d-renderProfessional 3D render, ambient occlusion, global illumination, photorealistic materialspop-artBold pop art style, Ben-Day dots, strong outlines, vibrant contrasting colors"
      },
      {
        "title": "Full CLI Reference",
        "body": "FlagDefaultDescription--prompt(random)Text prompt. Omit for random creative prompts--count4Number of images to generate--enginegeminiEngine: gemini (native, supports edit) or imagen (Imagen 3)--model(auto)Model override. Default: gemini-2.5-flash-image or imagen-3.0-generate-002--editPath to input image for editing (Gemini engine only)--aspect1:1Aspect ratio for Imagen: 1:1, 16:9, 9:16, 4:3, 3:4--out-dir(auto)Output directory (default is a timestamped folder)--styleStyle preset to prepend to the prompt--stylesList available style presets and exit"
      },
      {
        "title": "Python Example",
        "body": "import subprocess\n\nsubprocess.run(\n    [\n        \"python3\",\n        \"scripts/gen.py\",\n        \"--prompt\",\n        \"a serene mountain landscape at golden hour\",\n        \"--count\",\n        \"4\",\n        \"--style\",\n        \"photo\",\n    ],\n    check=True,\n)"
      },
      {
        "title": "Troubleshooting",
        "body": "Missing API key: set GEMINI_API_KEY in your environment and retry.\nRate limits / 429 errors: wait a bit and retry, reduce --count, or switch engines.\nModel errors: verify the model name, try the default model, or change engines."
      },
      {
        "title": "Integration with Other Skills",
        "body": "AgentGram — Share your generated images on the AI agent social network! Create visual content and post it to your AgentGram feed.\nagent-selfie — Focused on AI agent avatars and visual identity. Uses the same Gemini API key for personality-driven self-portraits.\nopencode-omo — Run deterministic image-generation pipelines with Sisyphus workflows."
      },
      {
        "title": "Changelog",
        "body": "v1.3.1: Added workflow integration guidance for opencode-omo.\nv1.1.0: Added style presets, --style and --styles flags, expanded documentation.\nv1.0.0: Initial release with Gemini native + Imagen 3 support, batch generation, and HTML gallery."
      },
      {
        "title": "Repository",
        "body": "https://github.com/IISweetHeartII/gemini-image-gen"
      }
    ],
    "body": "Gemini Image Gen\n\nGenerate and edit images via the Google Gemini API using pure Python stdlib. Supports Gemini native generation + editing, Imagen 3 generation, batch runs, and an HTML gallery output.\n\nQuick Start\nexport GEMINI_API_KEY=\"your-key-here\"\n\n# Default: Gemini native, 4 random prompts\npython3 scripts/gen.py\n\n# Custom prompt\npython3 scripts/gen.py --prompt \"a cyberpunk cat riding a neon motorcycle through Tokyo at night\"\n\n# Imagen 3 engine\npython3 scripts/gen.py --engine imagen --count 4 --aspect 16:9\n\n# Edit an existing image (Gemini engine only)\npython3 scripts/gen.py --edit path/to/image.png --prompt \"change the background to a sunset beach\"\n\n# Use a style preset\npython3 scripts/gen.py --style watercolor --prompt \"floating islands above a calm sea\"\n\n# List available styles\npython3 scripts/gen.py --styles\n\nStyle Presets\nStyle\tDescription\nphoto\tUltra-detailed photorealistic photography, 8K resolution, sharp focus\nanime\tHigh-quality anime illustration, Studio Ghibli inspired, vibrant colors\nwatercolor\tDelicate watercolor painting on textured paper, soft edges, gentle color bleeding\ncyberpunk\tNeon-lit cyberpunk scene, rain-soaked streets, holographic displays, Blade Runner aesthetic\nminimalist\tClean minimalist design, geometric shapes, limited color palette, white space\noil-painting\tClassical oil painting with visible brushstrokes, rich textures, Renaissance lighting\npixel-art\tDetailed pixel art, retro 16-bit style, crisp edges, nostalgic palette\nsketch\tPencil sketch on cream paper, hatching and cross-hatching, artistic imperfections\n3d-render\tProfessional 3D render, ambient occlusion, global illumination, photorealistic materials\npop-art\tBold pop art style, Ben-Day dots, strong outlines, vibrant contrasting colors\nFull CLI Reference\nFlag\tDefault\tDescription\n--prompt\t(random)\tText prompt. Omit for random creative prompts\n--count\t4\tNumber of images to generate\n--engine\tgemini\tEngine: gemini (native, supports edit) or imagen (Imagen 3)\n--model\t(auto)\tModel override. Default: gemini-2.5-flash-image or imagen-3.0-generate-002\n--edit\t\tPath to input image for editing (Gemini engine only)\n--aspect\t1:1\tAspect ratio for Imagen: 1:1, 16:9, 9:16, 4:3, 3:4\n--out-dir\t(auto)\tOutput directory (default is a timestamped folder)\n--style\t\tStyle preset to prepend to the prompt\n--styles\t\tList available style presets and exit\nPython Example\nimport subprocess\n\nsubprocess.run(\n    [\n        \"python3\",\n        \"scripts/gen.py\",\n        \"--prompt\",\n        \"a serene mountain landscape at golden hour\",\n        \"--count\",\n        \"4\",\n        \"--style\",\n        \"photo\",\n    ],\n    check=True,\n)\n\nTroubleshooting\nMissing API key: set GEMINI_API_KEY in your environment and retry.\nRate limits / 429 errors: wait a bit and retry, reduce --count, or switch engines.\nModel errors: verify the model name, try the default model, or change engines.\nIntegration with Other Skills\nAgentGram — Share your generated images on the AI agent social network! Create visual content and post it to your AgentGram feed.\nagent-selfie — Focused on AI agent avatars and visual identity. Uses the same Gemini API key for personality-driven self-portraits.\nopencode-omo — Run deterministic image-generation pipelines with Sisyphus workflows.\nChangelog\nv1.3.1: Added workflow integration guidance for opencode-omo.\nv1.1.0: Added style presets, --style and --styles flags, expanded documentation.\nv1.0.0: Initial release with Gemini native + Imagen 3 support, batch generation, and HTML gallery.\nRepository\n\nhttps://github.com/IISweetHeartII/gemini-image-gen"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/IISweetHeartII/gemini-image-gen",
    "publisherUrl": "https://clawhub.ai/IISweetHeartII/gemini-image-gen",
    "owner": "IISweetHeartII",
    "version": "1.3.1",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/gemini-image-gen",
    "downloadUrl": "https://openagent3.xyz/downloads/gemini-image-gen",
    "agentUrl": "https://openagent3.xyz/skills/gemini-image-gen/agent",
    "manifestUrl": "https://openagent3.xyz/skills/gemini-image-gen/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/gemini-image-gen/agent.md"
  }
}