{ "schemaVersion": "1.0", "item": { "slug": "liblib-ai-gen", "name": "LiblibAI Image & Video Gen", "source": "tencent", "type": "skill", "category": "开发工具", "sourceUrl": "https://clawhub.ai/xtaq/liblib-ai-gen", "canonicalUrl": "https://clawhub.ai/xtaq/liblib-ai-gen", "targetPlatform": "OpenClaw" }, "install": { "downloadMode": "redirect", "downloadUrl": "/downloads/liblib-ai-gen", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=liblib-ai-gen", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "installMethod": "Manual import", "extraction": "Extract archive", "prerequisites": [ "OpenClaw" ], "packageFormat": "ZIP package", "includedAssets": [ "SKILL.md", "scripts/liblib_client.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/liblib-ai-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/liblib-ai-gen", "agentPageUrl": "https://openagent3.xyz/skills/liblib-ai-gen/agent", "manifestUrl": "https://openagent3.xyz/skills/liblib-ai-gen/agent.json", "briefUrl": "https://openagent3.xyz/skills/liblib-ai-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": "LiblibAI Image & Video Generation", "body": "Generate images (Seedream4.5) and videos (Kling) via LiblibAI's API." }, { "title": "Prerequisites", "body": "Environment variables must be set:\n\nLIB_ACCESS_KEY — API access key\nLIB_SECRET_KEY — API secret key" }, { "title": "Usage", "body": "Run the CLI script at scripts/liblib_client.py:\n\n# Generate image\npython3 scripts/liblib_client.py image \"a cute cat wearing a hat\" --width 2048 --height 2048\n\n# Generate video from text\npython3 scripts/liblib_client.py text2video \"a rocket launching into space\" --model kling-v2-6 --duration 5\n\n# Generate video from image\npython3 scripts/liblib_client.py img2video \"the cat turns its head\" --start-frame https://example.com/cat.jpg\n\n# Check task status\npython3 scripts/liblib_client.py status " }, { "title": "Image Generation (Seedream4.5)", "body": "Endpoint: POST /api/generate/seedreamV4\nModel: doubao-seedream-4-5-251128\nDefault size: 2048×2048. For 4.5, min total pixels = 3,686,400 (e.g. 2560×1440)\nSupports reference images (1-14), prompt expansion, and sequential image generation\nOptions: --width, --height, --count (1-15), --ref-images, --prompt-magic" }, { "title": "Text-to-Video", "body": "Endpoint: POST /api/generate/video/kling/text2video\nModels: kling-v2-6 (latest, supports sound), kling-v2-1-master, kling-v2-5-turbo, etc.\nOptions: --model, --aspect (16:9/9:16/1:1), --duration (5/10s), --mode (std/pro), --sound (on/off)" }, { "title": "Image-to-Video", "body": "Endpoint: POST /api/generate/video/kling/img2video\nProvide --start-frame image URL; optionally --end-frame (v1-6 only)\nFor kling-v2-6: uses images array instead of startFrame/endFrame" }, { "title": "Async Pattern", "body": "All generation tasks are async:\n\nSubmit task → get generateUuid\nPoll POST /api/generate/status with { \"generateUuid\": \"...\" }\nResult contains images[].imageUrl or videos[].videoUrl\n\nThe script auto-polls by default. Use --no-poll to submit only." }, { "title": "Notes", "body": "QPS limit: 1 request/second for task submission\nMax concurrent tasks: 5\nImage URLs in results expire after 7 days\nFor kling-v2-5-turbo and kling-v2-6, mode must be \"pro\" (default)\nSound generation only supported on kling-v2-6+" } ], "body": "LiblibAI Image & Video Generation\n\nGenerate images (Seedream4.5) and videos (Kling) via LiblibAI's API.\n\nPrerequisites\n\nEnvironment variables must be set:\n\nLIB_ACCESS_KEY — API access key\nLIB_SECRET_KEY — API secret key\nUsage\n\nRun the CLI script at scripts/liblib_client.py:\n\n# Generate image\npython3 scripts/liblib_client.py image \"a cute cat wearing a hat\" --width 2048 --height 2048\n\n# Generate video from text\npython3 scripts/liblib_client.py text2video \"a rocket launching into space\" --model kling-v2-6 --duration 5\n\n# Generate video from image\npython3 scripts/liblib_client.py img2video \"the cat turns its head\" --start-frame https://example.com/cat.jpg\n\n# Check task status\npython3 scripts/liblib_client.py status \n\nImage Generation (Seedream4.5)\nEndpoint: POST /api/generate/seedreamV4\nModel: doubao-seedream-4-5-251128\nDefault size: 2048×2048. For 4.5, min total pixels = 3,686,400 (e.g. 2560×1440)\nSupports reference images (1-14), prompt expansion, and sequential image generation\nOptions: --width, --height, --count (1-15), --ref-images, --prompt-magic\nVideo Generation (Kling)\nText-to-Video\nEndpoint: POST /api/generate/video/kling/text2video\nModels: kling-v2-6 (latest, supports sound), kling-v2-1-master, kling-v2-5-turbo, etc.\nOptions: --model, --aspect (16:9/9:16/1:1), --duration (5/10s), --mode (std/pro), --sound (on/off)\nImage-to-Video\nEndpoint: POST /api/generate/video/kling/img2video\nProvide --start-frame image URL; optionally --end-frame (v1-6 only)\nFor kling-v2-6: uses images array instead of startFrame/endFrame\nAsync Pattern\n\nAll generation tasks are async:\n\nSubmit task → get generateUuid\nPoll POST /api/generate/status with { \"generateUuid\": \"...\" }\nResult contains images[].imageUrl or videos[].videoUrl\n\nThe script auto-polls by default. Use --no-poll to submit only.\n\nNotes\nQPS limit: 1 request/second for task submission\nMax concurrent tasks: 5\nImage URLs in results expire after 7 days\nFor kling-v2-5-turbo and kling-v2-6, mode must be \"pro\" (default)\nSound generation only supported on kling-v2-6+" }, "trust": { "sourceLabel": "tencent", "provenanceUrl": "https://clawhub.ai/xtaq/liblib-ai-gen", "publisherUrl": "https://clawhub.ai/xtaq/liblib-ai-gen", "owner": "xtaq", "version": "1.0.0", "license": null, "verificationStatus": "Indexed source record" }, "links": { "detailUrl": "https://openagent3.xyz/skills/liblib-ai-gen", "downloadUrl": "https://openagent3.xyz/downloads/liblib-ai-gen", "agentUrl": "https://openagent3.xyz/skills/liblib-ai-gen/agent", "manifestUrl": "https://openagent3.xyz/skills/liblib-ai-gen/agent.json", "briefUrl": "https://openagent3.xyz/skills/liblib-ai-gen/agent.md" } }