{ "schemaVersion": "1.0", "item": { "slug": "ai-media", "name": "Ai Media", "source": "tencent", "type": "skill", "category": "AI 智能", "sourceUrl": "https://clawhub.ai/bowen31337/ai-media", "canonicalUrl": "https://clawhub.ai/bowen31337/ai-media", "targetPlatform": "OpenClaw" }, "install": { "downloadMode": "redirect", "downloadUrl": "/downloads/ai-media", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=ai-media", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "installMethod": "Manual import", "extraction": "Extract archive", "prerequisites": [ "OpenClaw" ], "packageFormat": "ZIP package", "includedAssets": [ "README.md", "SKILL.md", "scripts/audio.sh", "scripts/comfyui_api.py", "scripts/image.sh", "scripts/talking-head.sh" ], "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": "2026-04-23T16:43:11.935Z", "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/ai-media" }, "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/ai-media", "agentPageUrl": "https://openagent3.xyz/skills/ai-media/agent", "manifestUrl": "https://openagent3.xyz/skills/ai-media/agent.json", "briefUrl": "https://openagent3.xyz/skills/ai-media/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": "ai-media - AI Media Generation", "body": "Full-stack AI media generation powered by GPU server (RTX 3090/3080/2070S)." }, { "title": "Capabilities", "body": "Image Generation — Photorealistic images via ComfyUI (z-image, Juggernaut XL)\nVideo Generation — Video synthesis via ComfyUI (AnimateDiff, LTX-2)\nTalking Heads — Animated talking faces via SadTalker\nVoice Synthesis — Natural TTS via Voxtral (whisper.cpp)" }, { "title": "GPU Server", "body": "Host: ${GPU_USER}@${GPU_HOST}\nSSH Key: ~/.ssh/id_ed25519_gpu\nComfyUI: /data/ai-stack/comfyui/ComfyUI/ (port 8188)\nSadTalker: /data/ai-stack/sadtalker/\nVoxtral: /data/ai-stack/whisper/\nOutput: /data/ai-stack/output/" }, { "title": "Generate Image", "body": "./scripts/image.sh \"lady on beach at sunset\" realistic\n./scripts/image.sh \"cyberpunk cityscape\" artistic\n\nArguments:\n\n$1: Prompt text\n$2: Style (realistic|artistic) — optional, default: realistic\n\nOutput: Path to generated image (e.g., /data/ai-stack/output/image_001.png)" }, { "title": "Generate Video", "body": "./scripts/video.sh \"waves crashing on shore\" animatediff 4\n./scripts/video.sh \"city traffic timelapse\" ltx2 8\n\nArguments:\n\n$1: Prompt text\n$2: Model (animatediff|ltx2) — optional, default: animatediff\n$3: Duration in seconds — optional, default: 4\n\nOutput: Path to generated video (e.g., /data/ai-stack/output/video_001.mp4)" }, { "title": "Generate Talking Head", "body": "./scripts/talking-head.sh \"Hello, I'm Agent\" gentle input.jpg\n./scripts/talking-head.sh \"Welcome to the future\" neutral photo.png\n\nArguments:\n\n$1: Speech text\n$2: Voice style (gentle|neutral|energetic) — optional, default: gentle\n$3: Avatar image path — optional, generates default if not provided\n\nOutput: Path to talking head video (e.g., /data/ai-stack/output/talking_001.mp4)" }, { "title": "Generate Audio", "body": "./scripts/audio.sh \"This is a test message\" en male\n./scripts/audio.sh \"Bonjour le monde\" fr female\n\nArguments:\n\n$1: Text to speak\n$2: Language code (en|fr|es|etc) — optional, default: en\n$3: Voice gender (male|female) — optional, default: male\n\nOutput: Path to audio file (e.g., /data/ai-stack/output/audio_001.wav)" }, { "title": "Image Models", "body": "z-image — 6B params, S3-DiT, photorealistic (downloading, 43% complete)\nJuggernaut XL v9 — SDXL-based, versatile (7.1GB, ready)" }, { "title": "Video Models", "body": "AnimateDiff — SD 1.5 motion module (512x512, working ✅)\nLTX-2 — 19B params, high quality (14GB checkpoint ready, Gemma encoder ready)" }, { "title": "Talking Head Models", "body": "SadTalker — Audio-driven head animation (working ✅)" }, { "title": "Voice Models", "body": "Voxtral — whisper.cpp-based TTS (installed)" }, { "title": "Dependencies", "body": "All dependencies are pre-installed on GPU server:\n\nComfyUI with custom nodes (AnimateDiff-Evolved, VideoHelperSuite)\nSadTalker with face enhancer\nVoxtral with whisper.cpp\nFFmpeg for video encoding" }, { "title": "Error Handling", "body": "Scripts will:\n\nCheck SSH connectivity before execution\nValidate GPU server is running\nReturn meaningful error messages\nClean up failed generations automatically" }, { "title": "Performance", "body": "Image: ~10-20s for 1024x1024\nVideo (AnimateDiff): ~20-30s for 512x512, 16 frames\nVideo (LTX-2): ~60-90s for 768x512, 4s @ 24fps\nTalking Head: ~30-40s for 10s video\nAudio: ~2-5s for 30s speech" }, { "title": "Future Enhancements", "body": "Batch generation support\n Style transfer capabilities\n Video upscaling (spatial + temporal)\n Multi-language voice cloning\n Real-time preview streaming\n\nStatus: Active development\nMaintainer: Agent\nGPU Server: ${GPU_USER}@${GPU_HOST}" } ], "body": "ai-media - AI Media Generation\n\nFull-stack AI media generation powered by GPU server (RTX 3090/3080/2070S).\n\nCapabilities\nImage Generation — Photorealistic images via ComfyUI (z-image, Juggernaut XL)\nVideo Generation — Video synthesis via ComfyUI (AnimateDiff, LTX-2)\nTalking Heads — Animated talking faces via SadTalker\nVoice Synthesis — Natural TTS via Voxtral (whisper.cpp)\nGPU Server\nHost: ${GPU_USER}@${GPU_HOST}\nSSH Key: ~/.ssh/id_ed25519_gpu\nComfyUI: /data/ai-stack/comfyui/ComfyUI/ (port 8188)\nSadTalker: /data/ai-stack/sadtalker/\nVoxtral: /data/ai-stack/whisper/\nOutput: /data/ai-stack/output/\nUsage\nGenerate Image\n./scripts/image.sh \"lady on beach at sunset\" realistic\n./scripts/image.sh \"cyberpunk cityscape\" artistic\n\n\nArguments:\n\n$1: Prompt text\n$2: Style (realistic|artistic) — optional, default: realistic\n\nOutput: Path to generated image (e.g., /data/ai-stack/output/image_001.png)\n\nGenerate Video\n./scripts/video.sh \"waves crashing on shore\" animatediff 4\n./scripts/video.sh \"city traffic timelapse\" ltx2 8\n\n\nArguments:\n\n$1: Prompt text\n$2: Model (animatediff|ltx2) — optional, default: animatediff\n$3: Duration in seconds — optional, default: 4\n\nOutput: Path to generated video (e.g., /data/ai-stack/output/video_001.mp4)\n\nGenerate Talking Head\n./scripts/talking-head.sh \"Hello, I'm Agent\" gentle input.jpg\n./scripts/talking-head.sh \"Welcome to the future\" neutral photo.png\n\n\nArguments:\n\n$1: Speech text\n$2: Voice style (gentle|neutral|energetic) — optional, default: gentle\n$3: Avatar image path — optional, generates default if not provided\n\nOutput: Path to talking head video (e.g., /data/ai-stack/output/talking_001.mp4)\n\nGenerate Audio\n./scripts/audio.sh \"This is a test message\" en male\n./scripts/audio.sh \"Bonjour le monde\" fr female\n\n\nArguments:\n\n$1: Text to speak\n$2: Language code (en|fr|es|etc) — optional, default: en\n$3: Voice gender (male|female) — optional, default: male\n\nOutput: Path to audio file (e.g., /data/ai-stack/output/audio_001.wav)\n\nModels Available\nImage Models\nz-image — 6B params, S3-DiT, photorealistic (downloading, 43% complete)\nJuggernaut XL v9 — SDXL-based, versatile (7.1GB, ready)\nVideo Models\nAnimateDiff — SD 1.5 motion module (512x512, working ✅)\nLTX-2 — 19B params, high quality (14GB checkpoint ready, Gemma encoder ready)\nTalking Head Models\nSadTalker — Audio-driven head animation (working ✅)\nVoice Models\nVoxtral — whisper.cpp-based TTS (installed)\nDependencies\n\nAll dependencies are pre-installed on GPU server:\n\nComfyUI with custom nodes (AnimateDiff-Evolved, VideoHelperSuite)\nSadTalker with face enhancer\nVoxtral with whisper.cpp\nFFmpeg for video encoding\nError Handling\n\nScripts will:\n\nCheck SSH connectivity before execution\nValidate GPU server is running\nReturn meaningful error messages\nClean up failed generations automatically\nPerformance\nImage: ~10-20s for 1024x1024\nVideo (AnimateDiff): ~20-30s for 512x512, 16 frames\nVideo (LTX-2): ~60-90s for 768x512, 4s @ 24fps\nTalking Head: ~30-40s for 10s video\nAudio: ~2-5s for 30s speech\nFuture Enhancements\n Batch generation support\n Style transfer capabilities\n Video upscaling (spatial + temporal)\n Multi-language voice cloning\n Real-time preview streaming\n\nStatus: Active development Maintainer: Agent GPU Server: ${GPU_USER}@${GPU_HOST}" }, "trust": { "sourceLabel": "tencent", "provenanceUrl": "https://clawhub.ai/bowen31337/ai-media", "publisherUrl": "https://clawhub.ai/bowen31337/ai-media", "owner": "bowen31337", "version": "1.0.1", "license": null, "verificationStatus": "Indexed source record" }, "links": { "detailUrl": "https://openagent3.xyz/skills/ai-media", "downloadUrl": "https://openagent3.xyz/downloads/ai-media", "agentUrl": "https://openagent3.xyz/skills/ai-media/agent", "manifestUrl": "https://openagent3.xyz/skills/ai-media/agent.json", "briefUrl": "https://openagent3.xyz/skills/ai-media/agent.md" } }