{
  "schemaVersion": "1.0",
  "item": {
    "slug": "runware",
    "name": "Runware Image & Video generation",
    "source": "tencent",
    "type": "skill",
    "category": "开发工具",
    "sourceUrl": "https://clawhub.ai/26medias/runware",
    "canonicalUrl": "https://clawhub.ai/26medias/runware",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/runware",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=runware",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "SKILL.md",
      "scripts/image.py",
      "scripts/video.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": "2026-05-07T17:22:31.273Z",
      "expiresAt": "2026-05-14T17:22:31.273Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=afrexai-annual-report",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=afrexai-annual-report",
        "contentDisposition": "attachment; filename=\"afrexai-annual-report-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/runware"
    },
    "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/runware",
    "agentPageUrl": "https://openagent3.xyz/skills/runware/agent",
    "manifestUrl": "https://openagent3.xyz/skills/runware/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/runware/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": "Runware",
        "body": "Image and video generation via Runware's unified API. Access FLUX, Stable Diffusion XL, Kling AI, and more."
      },
      {
        "title": "Setup",
        "body": "Set RUNWARE_API_KEY environment variable, or pass --api-key to scripts.\n\nGet API key: https://runware.ai"
      },
      {
        "title": "Text-to-Image",
        "body": "python3 scripts/image.py gen \"a cyberpunk city at sunset, neon lights, rain\" --count 2 -o ./images\n\nOptions:\n\n--model: Model ID (default: runware:101@1 / FLUX.1 Dev)\n--width/--height: Dimensions (default: 1024x1024)\n--steps: Inference steps (default: 25)\n--cfg: CFG scale (default: 7.5)\n--count/-n: Number of images\n--negative: Negative prompt\n--seed: Reproducible seed\n--lora: LoRA model ID\n--format: png/jpg/webp"
      },
      {
        "title": "Image-to-Image",
        "body": "Transform an existing image:\n\npython3 scripts/image.py img2img ./photo.jpg \"watercolor painting style\" --strength 0.7\n\n--strength: How much to transform (0=keep original, 1=ignore original)"
      },
      {
        "title": "Upscale",
        "body": "python3 scripts/image.py upscale ./small.png --factor 4 -o ./large.png"
      },
      {
        "title": "List Models",
        "body": "python3 scripts/image.py models"
      },
      {
        "title": "Text-to-Video",
        "body": "python3 scripts/video.py gen \"a cat playing with yarn, cute, high quality\" --duration 5 -o ./cat.mp4\n\nOptions:\n\n--model: Model ID (default: klingai:5@3 / Kling AI 1.6 Pro)\n--duration: Length in seconds\n--width/--height: Resolution (default: 1920x1080)\n--negative: Negative prompt\n--format: mp4/webm/mov\n--max-wait: Polling timeout (default: 600s)"
      },
      {
        "title": "Image-to-Video",
        "body": "Animate an image or interpolate between frames:\n\n# Single image (becomes first frame)\npython3 scripts/video.py img2vid ./start.png --prompt \"zoom out slowly\" -o ./animated.mp4\n\n# Two images (first and last frame)\npython3 scripts/video.py img2vid ./start.png ./end.png --duration 5"
      },
      {
        "title": "List Video Models",
        "body": "python3 scripts/video.py models"
      },
      {
        "title": "Image",
        "body": "ModelIDFLUX.1 Devrunware:101@1FLUX.1 Schnell (fast)runware:100@1FLUX.1 Kontextrunware:106@1Stable Diffusion XLcivitai:101055@128080RealVisXLcivitai:139562@297320"
      },
      {
        "title": "Video",
        "body": "ModelIDKling AI 1.6 Proklingai:5@3Kling AI 1.5 Proklingai:3@2Runway Gen-3runwayml:1@1\n\nBrowse all: https://runware.ai/models"
      },
      {
        "title": "Notes",
        "body": "Video generation is async; scripts poll until complete\nCosts vary by model — check https://runware.ai/pricing\nFLUX models are excellent for quality; Schnell is faster\nFor best video results, use descriptive prompts with motion words"
      }
    ],
    "body": "Runware\n\nImage and video generation via Runware's unified API. Access FLUX, Stable Diffusion XL, Kling AI, and more.\n\nSetup\n\nSet RUNWARE_API_KEY environment variable, or pass --api-key to scripts.\n\nGet API key: https://runware.ai\n\nImage Generation\nText-to-Image\npython3 scripts/image.py gen \"a cyberpunk city at sunset, neon lights, rain\" --count 2 -o ./images\n\n\nOptions:\n\n--model: Model ID (default: runware:101@1 / FLUX.1 Dev)\n--width/--height: Dimensions (default: 1024x1024)\n--steps: Inference steps (default: 25)\n--cfg: CFG scale (default: 7.5)\n--count/-n: Number of images\n--negative: Negative prompt\n--seed: Reproducible seed\n--lora: LoRA model ID\n--format: png/jpg/webp\nImage-to-Image\n\nTransform an existing image:\n\npython3 scripts/image.py img2img ./photo.jpg \"watercolor painting style\" --strength 0.7\n\n--strength: How much to transform (0=keep original, 1=ignore original)\nUpscale\npython3 scripts/image.py upscale ./small.png --factor 4 -o ./large.png\n\nList Models\npython3 scripts/image.py models\n\nVideo Generation\nText-to-Video\npython3 scripts/video.py gen \"a cat playing with yarn, cute, high quality\" --duration 5 -o ./cat.mp4\n\n\nOptions:\n\n--model: Model ID (default: klingai:5@3 / Kling AI 1.6 Pro)\n--duration: Length in seconds\n--width/--height: Resolution (default: 1920x1080)\n--negative: Negative prompt\n--format: mp4/webm/mov\n--max-wait: Polling timeout (default: 600s)\nImage-to-Video\n\nAnimate an image or interpolate between frames:\n\n# Single image (becomes first frame)\npython3 scripts/video.py img2vid ./start.png --prompt \"zoom out slowly\" -o ./animated.mp4\n\n# Two images (first and last frame)\npython3 scripts/video.py img2vid ./start.png ./end.png --duration 5\n\nList Video Models\npython3 scripts/video.py models\n\nPopular Models\nImage\nModel\tID\nFLUX.1 Dev\trunware:101@1\nFLUX.1 Schnell (fast)\trunware:100@1\nFLUX.1 Kontext\trunware:106@1\nStable Diffusion XL\tcivitai:101055@128080\nRealVisXL\tcivitai:139562@297320\nVideo\nModel\tID\nKling AI 1.6 Pro\tklingai:5@3\nKling AI 1.5 Pro\tklingai:3@2\nRunway Gen-3\trunwayml:1@1\n\nBrowse all: https://runware.ai/models\n\nNotes\nVideo generation is async; scripts poll until complete\nCosts vary by model — check https://runware.ai/pricing\nFLUX models are excellent for quality; Schnell is faster\nFor best video results, use descriptive prompts with motion words"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/26medias/runware",
    "publisherUrl": "https://clawhub.ai/26medias/runware",
    "owner": "26medias",
    "version": "1.0.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/runware",
    "downloadUrl": "https://openagent3.xyz/downloads/runware",
    "agentUrl": "https://openagent3.xyz/skills/runware/agent",
    "manifestUrl": "https://openagent3.xyz/skills/runware/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/runware/agent.md"
  }
}