{
  "schemaVersion": "1.0",
  "item": {
    "slug": "image-generation",
    "name": "Image Generation",
    "source": "tencent",
    "type": "skill",
    "category": "内容创作",
    "sourceUrl": "https://clawhub.ai/ivangdavila/image-generation",
    "canonicalUrl": "https://clawhub.ai/ivangdavila/image-generation",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/image-generation",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=image-generation",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "SKILL.md",
      "api-patterns.md",
      "benchmarks-2026.md",
      "flux.md",
      "gemini.md",
      "gpt-image.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": "2026-04-23T16:43:11.935Z",
      "expiresAt": "2026-04-30T16:43:11.935Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=4claw-imageboard",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=4claw-imageboard",
        "contentDisposition": "attachment; filename=\"4claw-imageboard-1.0.1.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/image-generation"
    },
    "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/image-generation",
    "agentPageUrl": "https://openagent3.xyz/skills/image-generation/agent",
    "manifestUrl": "https://openagent3.xyz/skills/image-generation/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/image-generation/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": "Setup",
        "body": "On first use, read setup.md."
      },
      {
        "title": "When to Use",
        "body": "User needs AI-generated visuals, edits, or consistent image sets.\nUse this skill to pick the right model, write stronger prompts, and avoid outdated model choices."
      },
      {
        "title": "Architecture",
        "body": "User preferences persist in ~/image-generation/. See memory-template.md for setup.\n\n~/image-generation/\n├── memory.md      # Preferred providers, project context, winning recipes\n└── history.md     # Optional generation log"
      },
      {
        "title": "Quick Reference",
        "body": "TopicFileInitial setupsetup.mdMemory templatememory-template.mdMigration guidemigration.mdBenchmark snapshotsbenchmarks-2026.mdPrompt techniquesprompting.mdAPI handlingapi-patterns.mdGPT Image (OpenAI)gpt-image.mdGemini and Imagen (Google)gemini.mdFLUX (Black Forest Labs)flux.mdMidjourneymidjourney.mdLeonardoleonardo.mdIdeogramideogram.mdReplicatereplicate.mdStable Diffusionstable-diffusion.md"
      },
      {
        "title": "1. Resolve aliases to official model IDs first",
        "body": "Community names shift quickly. Before calling an API, map the nickname to the provider model ID.\n\nCommunity labelOfficial model ID to try firstNotesNano Bananagemini-2.5-flash-image-previewCommon nickname, not an official Google model IDNano Banana 2 / ProVerify provider docsUsually a provider preset over Gemini image modelsGPT Image 1.5gpt-image-1.5Current OpenAI high-tier image modelGPT Image mini / iMinigpt-image-1-miniBudget/faster OpenAI variantFLUX 2 Pro / Maxflux-pro / flux-ultraMany platforms rename these SKUs"
      },
      {
        "title": "2. Pick models by task, not by hype",
        "body": "TaskFirst choiceBackupExact text in imagegpt-image-1.5IdeogramMulti-turn editsgemini-2.5-flash-image-previewflux-kontext-proPhotoreal hero shotsimagen-4.0-ultra-generate-001flux-ultraFast low-cost draftsgpt-image-1-miniimagen-4.0-fast-generate-001Character/product consistencyflux-kontext-maxgpt-image-1.5 with referencesLocal no-API workflowsflux-schnellSDXL"
      },
      {
        "title": "3. Use benchmark tables as dated snapshots",
        "body": "Benchmarks drift weekly. Use benchmarks-2026.md as a starting point, then recheck current rankings when quality is critical."
      },
      {
        "title": "4. Draft cheap, finish expensive",
        "body": "Start with 1-4 low-cost drafts, pick one, then upscale or rerender only the winner."
      },
      {
        "title": "5. Keep a fallback chain",
        "body": "If the preferred model is unavailable, fallback by tier:\n\nsame provider lower tier, 2) cross-provider equivalent, 3) local/open model."
      },
      {
        "title": "6. Treat DALL-E as legacy",
        "body": "OpenAI lists DALL-E 2/3 as legacy. Do not use them as default for new projects."
      },
      {
        "title": "Common Traps",
        "body": "Using vendor nicknames as model IDs -> API errors and wasted retries\nAssuming \"Nano Banana Pro\" or \"FLUX 2\" are universal IDs -> provider mismatch\nCopying old DALL-E prompt habits -> weaker output vs modern GPT/Gemini image models\nComparing text-to-image and image-editing scores as if they were the same benchmark\nOptimizing every draft at max quality -> cost spikes without quality gain"
      },
      {
        "title": "Security & Privacy",
        "body": "Data that leaves your machine:\n\nPrompt text\nReference images when editing or style matching\n\nData that stays local:\n\nProvider preferences in ~/image-generation/memory.md\nOptional local history file\n\nThis skill does NOT:\n\nStore API keys\nUpload files outside chosen provider requests\nPersist generated images unless user asks to save them"
      },
      {
        "title": "External Endpoints",
        "body": "ProviderEndpointData SentPurposeOpenAIapi.openai.comPrompt text, optional input imagesGPT Image generation/editingGoogle Gemini APIgenerativelanguage.googleapis.comPrompt text, optional input imagesGemini image generation/editingGoogle Vertex AIaiplatform.googleapis.comPrompt text, optional input imagesImagen 4 generationBlack Forest Labsapi.bfl.aiPrompt text, optional input imagesFLUX generation/editingReplicateapi.replicate.comPrompt text, optional input imagesHosted third-party image modelsMidjourneydiscord.comPrompt textMidjourney generation via Discord workflowsLeonardocloud.leonardo.aiPrompt text, optional input imagesLeonardo generation/editingIdeogramapi.ideogram.aiPrompt textTypography-focused image generation\n\nNo other data is sent externally."
      },
      {
        "title": "Migration",
        "body": "If upgrading from a previous version, read migration.md before updating local memory structure."
      },
      {
        "title": "Trust",
        "body": "This skill may send prompts and reference images to third-party AI providers.\nOnly install if you trust those providers with your content."
      },
      {
        "title": "Related Skills",
        "body": "Install with clawhub install <slug> if user confirms:\n\nimage-edit - Specialized inpainting, outpainting, and mask workflows\nvideo-generation - Convert image concepts into video pipelines\ncolors - Build palettes for visual consistency across assets\nffmpeg - Post-process image sequences and exports"
      },
      {
        "title": "Feedback",
        "body": "If useful: clawhub star image-generation\nStay updated: clawhub sync"
      }
    ],
    "body": "Setup\n\nOn first use, read setup.md.\n\nWhen to Use\n\nUser needs AI-generated visuals, edits, or consistent image sets. Use this skill to pick the right model, write stronger prompts, and avoid outdated model choices.\n\nArchitecture\n\nUser preferences persist in ~/image-generation/. See memory-template.md for setup.\n\n~/image-generation/\n├── memory.md      # Preferred providers, project context, winning recipes\n└── history.md     # Optional generation log\n\nQuick Reference\nTopic\tFile\nInitial setup\tsetup.md\nMemory template\tmemory-template.md\nMigration guide\tmigration.md\nBenchmark snapshots\tbenchmarks-2026.md\nPrompt techniques\tprompting.md\nAPI handling\tapi-patterns.md\nGPT Image (OpenAI)\tgpt-image.md\nGemini and Imagen (Google)\tgemini.md\nFLUX (Black Forest Labs)\tflux.md\nMidjourney\tmidjourney.md\nLeonardo\tleonardo.md\nIdeogram\tideogram.md\nReplicate\treplicate.md\nStable Diffusion\tstable-diffusion.md\nCore Rules\n1. Resolve aliases to official model IDs first\n\nCommunity names shift quickly. Before calling an API, map the nickname to the provider model ID.\n\nCommunity label\tOfficial model ID to try first\tNotes\nNano Banana\tgemini-2.5-flash-image-preview\tCommon nickname, not an official Google model ID\nNano Banana 2 / Pro\tVerify provider docs\tUsually a provider preset over Gemini image models\nGPT Image 1.5\tgpt-image-1.5\tCurrent OpenAI high-tier image model\nGPT Image mini / iMini\tgpt-image-1-mini\tBudget/faster OpenAI variant\nFLUX 2 Pro / Max\tflux-pro / flux-ultra\tMany platforms rename these SKUs\n2. Pick models by task, not by hype\nTask\tFirst choice\tBackup\nExact text in image\tgpt-image-1.5\tIdeogram\nMulti-turn edits\tgemini-2.5-flash-image-preview\tflux-kontext-pro\nPhotoreal hero shots\timagen-4.0-ultra-generate-001\tflux-ultra\nFast low-cost drafts\tgpt-image-1-mini\timagen-4.0-fast-generate-001\nCharacter/product consistency\tflux-kontext-max\tgpt-image-1.5 with references\nLocal no-API workflows\tflux-schnell\tSDXL\n3. Use benchmark tables as dated snapshots\n\nBenchmarks drift weekly. Use benchmarks-2026.md as a starting point, then recheck current rankings when quality is critical.\n\n4. Draft cheap, finish expensive\n\nStart with 1-4 low-cost drafts, pick one, then upscale or rerender only the winner.\n\n5. Keep a fallback chain\n\nIf the preferred model is unavailable, fallback by tier:\n\nsame provider lower tier, 2) cross-provider equivalent, 3) local/open model.\n6. Treat DALL-E as legacy\n\nOpenAI lists DALL-E 2/3 as legacy. Do not use them as default for new projects.\n\nCommon Traps\nUsing vendor nicknames as model IDs -> API errors and wasted retries\nAssuming \"Nano Banana Pro\" or \"FLUX 2\" are universal IDs -> provider mismatch\nCopying old DALL-E prompt habits -> weaker output vs modern GPT/Gemini image models\nComparing text-to-image and image-editing scores as if they were the same benchmark\nOptimizing every draft at max quality -> cost spikes without quality gain\nSecurity & Privacy\n\nData that leaves your machine:\n\nPrompt text\nReference images when editing or style matching\n\nData that stays local:\n\nProvider preferences in ~/image-generation/memory.md\nOptional local history file\n\nThis skill does NOT:\n\nStore API keys\nUpload files outside chosen provider requests\nPersist generated images unless user asks to save them\nExternal Endpoints\nProvider\tEndpoint\tData Sent\tPurpose\nOpenAI\tapi.openai.com\tPrompt text, optional input images\tGPT Image generation/editing\nGoogle Gemini API\tgenerativelanguage.googleapis.com\tPrompt text, optional input images\tGemini image generation/editing\nGoogle Vertex AI\taiplatform.googleapis.com\tPrompt text, optional input images\tImagen 4 generation\nBlack Forest Labs\tapi.bfl.ai\tPrompt text, optional input images\tFLUX generation/editing\nReplicate\tapi.replicate.com\tPrompt text, optional input images\tHosted third-party image models\nMidjourney\tdiscord.com\tPrompt text\tMidjourney generation via Discord workflows\nLeonardo\tcloud.leonardo.ai\tPrompt text, optional input images\tLeonardo generation/editing\nIdeogram\tapi.ideogram.ai\tPrompt text\tTypography-focused image generation\n\nNo other data is sent externally.\n\nMigration\n\nIf upgrading from a previous version, read migration.md before updating local memory structure.\n\nTrust\n\nThis skill may send prompts and reference images to third-party AI providers. Only install if you trust those providers with your content.\n\nRelated Skills\n\nInstall with clawhub install <slug> if user confirms:\n\nimage-edit - Specialized inpainting, outpainting, and mask workflows\nvideo-generation - Convert image concepts into video pipelines\ncolors - Build palettes for visual consistency across assets\nffmpeg - Post-process image sequences and exports\nFeedback\nIf useful: clawhub star image-generation\nStay updated: clawhub sync"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/ivangdavila/image-generation",
    "publisherUrl": "https://clawhub.ai/ivangdavila/image-generation",
    "owner": "ivangdavila",
    "version": "1.0.3",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/image-generation",
    "downloadUrl": "https://openagent3.xyz/downloads/image-generation",
    "agentUrl": "https://openagent3.xyz/skills/image-generation/agent",
    "manifestUrl": "https://openagent3.xyz/skills/image-generation/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/image-generation/agent.md"
  }
}