{ "schemaVersion": "1.0", "item": { "slug": "veed-ugc", "name": "VEED UGC", "source": "tencent", "type": "skill", "category": "AI 智能", "sourceUrl": "https://clawhub.ai/PauldeLavallaz/veed-ugc", "canonicalUrl": "https://clawhub.ai/PauldeLavallaz/veed-ugc", "targetPlatform": "OpenClaw" }, "install": { "downloadMode": "redirect", "downloadUrl": "/downloads/veed-ugc", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=veed-ugc", "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/veed-ugc" }, "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/veed-ugc", "agentPageUrl": "https://openagent3.xyz/skills/veed-ugc/agent", "manifestUrl": "https://openagent3.xyz/skills/veed-ugc/agent.json", "briefUrl": "https://openagent3.xyz/skills/veed-ugc/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": "Veed-UGC", "body": "Generate UGC (User Generated Content) style promotional videos with AI lip-sync using ComfyDeploy's Veed-UGC workflow." }, { "title": "Overview", "body": "Veed-UGC transforms static images into dynamic promotional videos:\n\nTakes a photo of a person with a product (from Morpheus or Ad-Ready)\nReceives a script (pure dialogue text)\nCreates a lip-synced video of the person speaking the script\n\nPerfect for creating authentic-feeling promotional content at scale." }, { "title": "API Details", "body": "Endpoint: https://api.comfydeploy.com/api/run/deployment/queue\nDeployment ID: 627c8fb5-1285-4074-a17c-ae54f8a5b5c6" }, { "title": "Required Inputs", "body": "InputDescriptionExampleimageURL of person+product imageOutput from Morpheus/Ad-ReadyscriptPure dialogue text\"Hola che! Cómo anda todo por allá?\"voice_idElevenLabs voice IDDefault: PBi4M0xL4G7oVYxKgqww" }, { "title": "⚠️ CRITICAL: Script Format", "body": "The script input must be PURE DIALOGUE ONLY:\n\n✅ CORRECT:\n\nHola che! Cómo anda todo por allá? Mirá esto que acabo de probar, una locura total.\n\n❌ WRONG - No annotations:\n\n[Entusiasta] Hola che! (pausa) Cómo anda?\n\n❌ WRONG - No tone directions:\n\nTono argentino informal: Hola che!\n\n❌ WRONG - No stage directions:\n\n*sonríe* Hola che! *levanta el producto*\n\n❌ WRONG - No titles/labels:\n\nESCENA 1:\nHola che!\n\nJust write exactly what the person should say. Nothing else." }, { "title": "Voice IDs (ElevenLabs)", "body": "VoiceIDDescriptionDefaultPBi4M0xL4G7oVYxKgqwwMain voice\n\nMore voices can be added from ElevenLabs" }, { "title": "Usage", "body": "uv run ~/.clawdbot/skills/veed-ugc/scripts/generate.py \\\n --image \"https://example.com/person-with-product.png\" \\\n --script \"Hola! Les quiero mostrar este producto increíble que acabo de probar.\" \\\n --output \"ugc-video.mp4\"" }, { "title": "With local image file:", "body": "uv run ~/.clawdbot/skills/veed-ugc/scripts/generate.py \\\n --image \"./morpheus-output.png\" \\\n --script \"Mirá, yo antes no usaba esto pero ahora no puedo vivir sin él.\" \\\n --voice-id \"PBi4M0xL4G7oVYxKgqww\" \\\n --output \"promo-video.mp4\"" }, { "title": "Direct API Call", "body": "const response = await fetch(\"https://api.comfydeploy.com/api/run/deployment/queue\", {\n method: \"POST\",\n headers: {\n \"Content-Type\": \"application/json\",\n \"Authorization\": \"Bearer YOUR_API_KEY\"\n },\n body: JSON.stringify({\n \"deployment_id\": \"627c8fb5-1285-4074-a17c-ae54f8a5b5c6\",\n \"inputs\": {\n \"image\": \"/* put your image url here */\",\n \"voice_id\": \"PBi4M0xL4G7oVYxKgqww\",\n \"script\": \"Hola che! Cómo anda todo por allá?\"\n }\n })\n});" }, { "title": "Typical Pipeline", "body": "Generate image with Morpheus/Ad-Ready\nuv run morpheus... --output product-shot.png\n\n\n\nWrite the script (pure dialogue)\n\n\nCreate UGC video from the image\nuv run veed-ugc... --image product-shot.png --script \"...\" --output promo.mp4" }, { "title": "Output", "body": "The workflow outputs an MP4 video file with:\n\nThe original image animated with lip-sync\nAI-generated voiceover from the script\nNatural head movements and expressions" }, { "title": "Notes", "body": "Image should clearly show a person's face (frontal or 3/4 view works best)\nScript is spoken exactly as written - no interpretation\nVideo length depends on script length\nProcessing time: ~2-5 minutes depending on script length" } ], "body": "Veed-UGC\n\nGenerate UGC (User Generated Content) style promotional videos with AI lip-sync using ComfyDeploy's Veed-UGC workflow.\n\nOverview\n\nVeed-UGC transforms static images into dynamic promotional videos:\n\nTakes a photo of a person with a product (from Morpheus or Ad-Ready)\nReceives a script (pure dialogue text)\nCreates a lip-synced video of the person speaking the script\n\nPerfect for creating authentic-feeling promotional content at scale.\n\nAPI Details\n\nEndpoint: https://api.comfydeploy.com/api/run/deployment/queue Deployment ID: 627c8fb5-1285-4074-a17c-ae54f8a5b5c6\n\nRequired Inputs\nInput\tDescription\tExample\nimage\tURL of person+product image\tOutput from Morpheus/Ad-Ready\nscript\tPure dialogue text\t\"Hola che! Cómo anda todo por allá?\"\nvoice_id\tElevenLabs voice ID\tDefault: PBi4M0xL4G7oVYxKgqww\n⚠️ CRITICAL: Script Format\n\nThe script input must be PURE DIALOGUE ONLY:\n\n✅ CORRECT:\n\nHola che! Cómo anda todo por allá? Mirá esto que acabo de probar, una locura total.\n\n\n❌ WRONG - No annotations:\n\n[Entusiasta] Hola che! (pausa) Cómo anda?\n\n\n❌ WRONG - No tone directions:\n\nTono argentino informal: Hola che!\n\n\n❌ WRONG - No stage directions:\n\n*sonríe* Hola che! *levanta el producto*\n\n\n❌ WRONG - No titles/labels:\n\nESCENA 1:\nHola che!\n\n\nJust write exactly what the person should say. Nothing else.\n\nVoice IDs (ElevenLabs)\nVoice\tID\tDescription\nDefault\tPBi4M0xL4G7oVYxKgqww\tMain voice\n\nMore voices can be added from ElevenLabs\n\nUsage\nuv run ~/.clawdbot/skills/veed-ugc/scripts/generate.py \\\n --image \"https://example.com/person-with-product.png\" \\\n --script \"Hola! Les quiero mostrar este producto increíble que acabo de probar.\" \\\n --output \"ugc-video.mp4\"\n\nWith local image file:\nuv run ~/.clawdbot/skills/veed-ugc/scripts/generate.py \\\n --image \"./morpheus-output.png\" \\\n --script \"Mirá, yo antes no usaba esto pero ahora no puedo vivir sin él.\" \\\n --voice-id \"PBi4M0xL4G7oVYxKgqww\" \\\n --output \"promo-video.mp4\"\n\nDirect API Call\nconst response = await fetch(\"https://api.comfydeploy.com/api/run/deployment/queue\", {\n method: \"POST\",\n headers: {\n \"Content-Type\": \"application/json\",\n \"Authorization\": \"Bearer YOUR_API_KEY\"\n },\n body: JSON.stringify({\n \"deployment_id\": \"627c8fb5-1285-4074-a17c-ae54f8a5b5c6\",\n \"inputs\": {\n \"image\": \"/* put your image url here */\",\n \"voice_id\": \"PBi4M0xL4G7oVYxKgqww\",\n \"script\": \"Hola che! Cómo anda todo por allá?\"\n }\n })\n});\n\nWorkflow Integration\nTypical Pipeline\n\nGenerate image with Morpheus/Ad-Ready\n\nuv run morpheus... --output product-shot.png\n\n\nWrite the script (pure dialogue)\n\nCreate UGC video from the image\n\nuv run veed-ugc... --image product-shot.png --script \"...\" --output promo.mp4\n\nOutput\n\nThe workflow outputs an MP4 video file with:\n\nThe original image animated with lip-sync\nAI-generated voiceover from the script\nNatural head movements and expressions\nNotes\nImage should clearly show a person's face (frontal or 3/4 view works best)\nScript is spoken exactly as written - no interpretation\nVideo length depends on script length\nProcessing time: ~2-5 minutes depending on script length" }, "trust": { "sourceLabel": "tencent", "provenanceUrl": "https://clawhub.ai/PauldeLavallaz/veed-ugc", "publisherUrl": "https://clawhub.ai/PauldeLavallaz/veed-ugc", "owner": "PauldeLavallaz", "version": "1.0.1", "license": null, "verificationStatus": "Indexed source record" }, "links": { "detailUrl": "https://openagent3.xyz/skills/veed-ugc", "downloadUrl": "https://openagent3.xyz/downloads/veed-ugc", "agentUrl": "https://openagent3.xyz/skills/veed-ugc/agent", "manifestUrl": "https://openagent3.xyz/skills/veed-ugc/agent.json", "briefUrl": "https://openagent3.xyz/skills/veed-ugc/agent.md" } }