{"id":"206d9696-1b2d-4056-a584-4ad61f4bb1dc","entityType":"agent","slug":"clawhub-wavespeed-wavespeed-watermark-remover","name":"WaveSpeedAI Watermark Remover","canonicalUrl":"https://www.xpersona.co/agent/clawhub-wavespeed-wavespeed-watermark-remover","canonicalPath":"/agent/clawhub-wavespeed-wavespeed-watermark-remover","generatedAt":"2026-10-10T13:39:56.567Z","source":"CLAWHUB","claimStatus":"UNCLAIMED","verificationTier":"NONE","summary":{"evidence":{"source":"editorial-content","verified":true,"confidence":"high","updatedAt":"2026-10-10T10:36:40.685Z","emptyReason":null},"description":"Remove watermarks, logos, captions, and text overlays from images and videos using WaveSpeed AI. Intelligently detects and removes watermarks while preserving texture and background. Supports images and videos up to 10 minutes. Only for media the user owns or is licensed to modify (e.g. cleaning their own exports, stock they have purchased, or overlays they added themselves); never to strip another party's copyright or attribution marks. Use when the user wants to remove watermarks or text overlays from their own media. Skill: WaveSpeedAI Watermark Remover Owner: wavespeed Summary: Remove watermarks, logos, captions, and text overlays from images and videos using WaveSpeed AI. Intelligently detects and removes watermarks while preserving texture and background. Supports images and videos up to 10 minutes. Only for media the user owns or is licensed to modify (e.g. cleaning their own exports, stock they have purchased, or overlays th","descriptionLabel":"Technical summary","evidenceSummary":"Capability contract not published. No trust telemetry is available yet. 1.5K downloads reported by the source. Last updated 10/10/2026.","installCommand":"clawhub skill install s17epnq4kcsv1261rq3e9gvwcx8dth5q:wavespeed-watermark-remover","sourceUrl":"https://clawhub.ai/wavespeed/wavespeed-watermark-remover","homepage":"https://clawhub.ai/wavespeed/skills/wavespeed-watermark-remover","primaryLinks":[{"label":"View on ClawHub","url":"https://clawhub.ai/wavespeed/wavespeed-watermark-remover","kind":"source"},{"label":"Homepage","url":"https://clawhub.ai/wavespeed/skills/wavespeed-watermark-remover","kind":"homepage"}],"safetyScore":84,"overallRank":62,"popularityScore":63,"trustScore":null,"claimedByName":null,"isOwner":false,"seoDescription":"Remove watermarks, logos, captions, and text overlays from images and videos using WaveSpeed AI. Intelligently detects and removes watermarks while preserving t"},"coverage":{"evidence":{"source":"public-profile","verified":false,"confidence":"medium","updatedAt":"2026-10-10T10:36:40.685Z","emptyReason":null},"protocols":[{"protocol":"OPENCLEW","label":"OpenClaw","status":"self-declared","notes":"Declared in the public agent profile."}],"capabilities":[],"verifiedCount":0,"selfDeclaredCount":1,"capabilityMatrix":{"rows":[{"key":"OPENCLEW","type":"protocol","support":"unknown","confidenceSource":"profile","notes":"Listed on profile"}],"flattenedTokens":"protocol:OPENCLEW|unknown|profile"}},"adoption":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-10T10:36:40.685Z","emptyReason":null},"stars":null,"forks":null,"downloads":1491,"packageName":null,"latestVersion":"2.0.1","tractionLabel":"1.5K downloads"},"release":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-10T10:36:40.684Z","emptyReason":null},"lastUpdatedAt":"2026-10-10T10:36:40.685Z","lastCrawledAt":"2026-10-10T10:36:40.684Z","lastIndexedAt":null,"nextCrawlAt":"2026-10-11T10:36:40.684Z","lastVerifiedAt":null,"highlights":[{"version":"2.0.1","createdAt":"2026-09-05T16:28:56.208Z","changelog":"Moved to the @wavespeed organization.","fileCount":3,"zipByteSize":4392},{"version":"2.0.0","createdAt":"2026-09-05T16:15:58.370Z","changelog":"Examples switched from the JS SDK to the wavespeed CLI (with the @wavespeed/mcp server as the MCP alternative): install + login setup, @path local-file upload, price quotes, --json output. SDK-specific sections (sync mode, custom client, runNoThrow) removed.","fileCount":3,"zipByteSize":4410},{"version":"1.1.0","createdAt":"2026-09-05T16:09:19.477Z","changelog":"Add Responsible use section: ownership or license required, never remove third-party copyright or attribution marks, no misrepresentation; scope narrowed to the user's own media.","fileCount":3,"zipByteSize":4138},{"version":"1.0.0","createdAt":"2026-03-02T06:49:08.630Z","changelog":"WaveSpeedAI Watermark Remover 1.0.0 – Initial Release - Supports removing watermarks, logos, captions, and text overlays from images and videos using WaveSpeed AI. - Preserves original texture and background with intelligent detection. - Video watermark remover uses temporal-aware inpainting to prevent flickering, for videos up to 10 minutes. - Provides simple API usage examples for both images and videos, plus advanced client options and error handling. - Transparent pricing: $0.012 per image, $0.01 per video second (min $0.05). - Lists security best practices, including proper API key handling and media input validation.","fileCount":3,"zipByteSize":3170}]},"execution":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No published capability contract is available yet."},"installCommand":"clawhub skill install s17epnq4kcsv1261rq3e9gvwcx8dth5q:wavespeed-watermark-remover","setupComplexity":"low","setupSteps":["Setup complexity is LOW. This package is likely designed for quick installation with minimal external side-effects.","Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data."],"contract":{"contractStatus":"missing","authModes":[],"requires":[],"forbidden":[],"supportsMcp":false,"supportsA2a":false,"supportsStreaming":false,"inputSchemaRef":null,"outputSchemaRef":null,"dataRegion":null,"contractUpdatedAt":null,"sourceUpdatedAt":null,"freshnessSeconds":null},"invocationGuide":{"preferredApi":{"snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-wavespeed-wavespeed-watermark-remover/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-wavespeed-wavespeed-watermark-remover/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-wavespeed-wavespeed-watermark-remover/trust"},"curlExamples":["curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-wavespeed-wavespeed-watermark-remover/snapshot\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-wavespeed-wavespeed-watermark-remover/contract\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-wavespeed-wavespeed-watermark-remover/trust\""],"jsonRequestTemplate":{"query":"summarize this repo","constraints":{"maxLatencyMs":2000,"protocolPreference":["OPENCLEW"]}},"jsonResponseTemplate":{"ok":true,"result":{"summary":"...","confidence":0.9},"meta":{"source":"CLAWHUB","generatedAt":"2026-10-10T13:39:56.566Z"}},"retryPolicy":{"maxAttempts":3,"backoffMs":[500,1500,3500],"retryableConditions":["HTTP_429","HTTP_503","NETWORK_TIMEOUT"]}},"endpoints":{"dossierUrl":"https://www.xpersona.co/api/v1/agents/clawhub-wavespeed-wavespeed-watermark-remover/dossier","snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-wavespeed-wavespeed-watermark-remover/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-wavespeed-wavespeed-watermark-remover/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-wavespeed-wavespeed-watermark-remover/trust"}},"reliability":{"evidence":{"source":"runtime-metrics","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No trust, reliability, or runtime telemetry is available."},"trust":{"status":"unavailable","handshakeStatus":"UNKNOWN","verificationFreshnessHours":null,"reputationScore":null,"p95LatencyMs":null,"successRate30d":null,"fallbackRate":null,"attempts30d":null,"trustUpdatedAt":null,"trustConfidence":"unknown","sourceUpdatedAt":null,"freshnessSeconds":null},"decisionGuardrails":{"doNotUseIf":["Contract metadata is missing or unavailable for deterministic execution."],"safeUseWhen":[],"riskFlags":["missing_or_unavailable_contract","trust_data_unavailable","schema_references_missing"],"operationalConfidence":"low"},"executionMetrics":{"observedLatencyMsP50":null,"observedLatencyMsP95":null,"estimatedCostUsd":null,"uptime30d":null,"rateLimitRpm":null,"rateLimitBurst":null,"lastVerifiedAt":null,"verificationSource":null},"runtimeMetrics":{"successRate":null,"avgLatencyMs":null,"avgCostUsd":null,"hallucinationRate":null,"retryRate":null,"disputeRate":null,"p50Latency":null,"p95Latency":null,"lastUpdated":null}},"benchmarks":{"evidence":{"source":"no-benchmark-data","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No benchmark suites or observed failure patterns are available."},"suites":[],"failurePatterns":[]},"artifacts":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"high","updatedAt":"2026-10-10T10:36:40.685Z","emptyReason":null},"readme":"Skill: WaveSpeedAI Watermark Remover\n\nOwner: wavespeed\n\nSummary: Remove watermarks, logos, captions, and text overlays from images and videos using WaveSpeed AI. Intelligently detects and removes watermarks while preserving texture and background. Supports images and videos up to 10 minutes. Only for media the user owns or is licensed to modify (e.g. cleaning their own exports, stock they have purchased, or overlays they added themselves); never to strip another party's copyright or attribution marks. Use when the user wants to remove watermarks or text overlays from their own media.\n\nTags: latest:2.0.1\n\nVersion history:\n\nv2.0.1 | 2026-09-05T16:28:56.208Z | user\n\nMoved to the @wavespeed organization.\n\nv2.0.0 | 2026-09-05T16:15:58.370Z | user\n\nExamples switched from the JS SDK to the wavespeed CLI (with the @wavespeed/mcp server as the MCP alternative): install + login setup, @path local-file upload, price quotes, --json output. SDK-specific sections (sync mode, custom client, runNoThrow) removed.\n\nv1.1.0 | 2026-09-05T16:09:19.477Z | user\n\nAdd Responsible use section: ownership or license required, never remove third-party copyright or attribution marks, no misrepresentation; scope narrowed to the user's own media.\n\nv1.0.0 | 2026-03-02T06:49:08.630Z | user\n\nWaveSpeedAI Watermark Remover 1.0.0 – Initial Release\n\n- Supports removing watermarks, logos, captions, and text overlays from images and videos using WaveSpeed AI.\n- Preserves original texture and background with intelligent detection.\n- Video watermark remover uses temporal-aware inpainting to prevent flickering, for videos up to 10 minutes.\n- Provides simple API usage examples for both images and videos, plus advanced client options and error handling.\n- Transparent pricing: $0.012 per image, $0.01 per video second (min $0.05).\n- Lists security best practices, including proper API key handling and media input validation.\n\nArchive index:\n\nArchive v2.0.1: 3 files, 4392 bytes\n\nFiles: skill-card.md (2545b), SKILL.md (6790b), _meta.json (146b)\n\nFile v2.0.1:SKILL.md\n\n---\nname: wavespeed-watermark-remover\ndescription: Remove watermarks, logos, captions, and text overlays from images and videos using WaveSpeed AI. Intelligently detects and removes watermarks while preserving texture and background. Supports images and videos up to 10 minutes. Only for media the user owns or is licensed to modify (e.g. cleaning their own exports, stock they have purchased, or overlays they added themselves); never to strip another party's copyright or attribution marks. Use when the user wants to remove watermarks or text overlays from their own media.\nmetadata:\n  author: wavespeedai\n  version: \"2.0\"\n---\n\n# WaveSpeedAI Watermark Remover\n\nRemove watermarks, logos, captions, and text overlays from images and videos using WaveSpeed AI. Intelligently detects and removes watermarks while preserving texture and background.\n\n**Read [Responsible use](#responsible-use) before running anything.** This tool is for media the user owns or is licensed to modify, not for stripping other people's copyright or attribution marks.\n\n## Setup\n\nInstall the open-source CLI once and sign in; the CLI stores the key, so never ask the user to paste an API key into the chat:\n\n```bash\nnpm install -g @wavespeed/cli\nwavespeed login          # opens https://wavespeed.ai/accesskey and stores the key\nwavespeed status         # confirms you are signed in\n```\n\nFor CI or one-off shells, `WAVESPEED_API_KEY` in the environment also works.\n\nPrefer MCP tools over shell commands? The same platform is exposed by [`@wavespeed/mcp`](https://github.com/WaveSpeedAI/mcp-server) (`npx -y @wavespeed/mcp`; tools `search_models`, `get_model_schema`, `get_price`, `upload_file`, `run_model`, `get_prediction`). It shares the CLI's stored login. Every example below maps one-to-one onto `run_model` with the same model id and input fields.\n\n## Quick Start\n\n### Image Watermark Removal\n\n```bash\n# Upload a local image to get a URL\nOUTPUT_URL=$(wavespeed run wavespeed-ai/image-watermark-remover \\\n  -i image=@./watermarked-image.png \\\n  --json | jq -r '.outputs[0]')\n```\n\n### Video Watermark Removal\n\n```bash\n# Upload a local video to get a URL\nOUTPUT_URL=$(wavespeed run wavespeed-ai/video-watermark-remover \\\n  -i video=@./watermarked-video.mp4 \\\n  --json | jq -r '.outputs[0]')\n```\n\nExisting URLs work as-is:\n\n```bash\nOUTPUT_URL=$(wavespeed run wavespeed-ai/image-watermark-remover \\\n  -i image=\"https://example.com/watermarked-image.jpg\" \\\n  --json | jq -r '.outputs[0]')\n```\n\n## API Endpoints\n\n### Image Watermark Remover\n\n**Model ID:** `wavespeed-ai/image-watermark-remover`\n\nRemove watermarks, logos, and text overlays from an image while preserving texture and background.\n\n#### Parameters\n\n| Parameter | Type | Required | Default | Description |\n|-----------|------|----------|---------|-------------|\n| `image` | string | Yes | -- | URL of the image to process |\n| `output_format` | string | No | `jpeg` | Output format. One of: `jpeg`, `png`, `webp` |\n\n#### Example\n\n```bash\nOUTPUT_URL=$(wavespeed run wavespeed-ai/image-watermark-remover \\\n  -i image=@./watermarked-photo.png \\\n  -i output_format=\"png\" \\\n  --json | jq -r '.outputs[0]')\n```\n\n### Video Watermark Remover\n\n**Model ID:** `wavespeed-ai/video-watermark-remover`\n\nRemove watermarks, logos, captions, and text overlays from a video. Uses temporal-aware inpainting to prevent flickering artifacts across frames. Supports videos up to 10 minutes.\n\n#### Parameters\n\n| Parameter | Type | Required | Default | Description |\n|-----------|------|----------|---------|-------------|\n| `video` | string | Yes | -- | URL of the video to process. Must be publicly accessible. Max 10 minutes. |\n\n#### Example\n\n```bash\nOUTPUT_URL=$(wavespeed run wavespeed-ai/video-watermark-remover \\\n  -i video=@./watermarked-video.mp4 \\\n  --json | jq -r '.outputs[0]')\n```\n\n\n## Pricing\n\n| Operation | Cost |\n|-----------|------|\n| Image watermark removal | $0.012 per image |\n| Video watermark removal | $0.01 per second (minimum $0.05 / 5 seconds) |\n\nVideo watermark removal supports videos up to 10 minutes. Processing time is approximately 5-20 seconds per 1 second of video.\n\n## Responsible use\n\nWatermarks and overlays are usually there to assert ownership or attribution. Before calling either endpoint, confirm the following with the user. If the answer is no or unclear, do not run the model and explain why.\n\n- **Ownership or license**: the user created the media, holds the rights to it, or has a license that permits removing the mark (for example, a purchased stock asset whose license allows clean use, or their own export from a tool that stamps a logo).\n- **Not someone else's mark**: do not remove a watermark, logo, credit, or copyright notice placed by a third party to identify their work. Stock-site preview watermarks, photographer credits, broadcaster logos, and platform attribution marks are all out of scope.\n- **No misrepresentation**: the result will not be passed off as original, unlicensed, or unedited work, and will not be used to evade licensing fees or attribution requirements.\n- **Legitimate overlays only**: typical valid uses are removing captions or subtitles the user added, cleaning timestamps from their own camera footage, or restoring an area under a logo they own.\n\nWaveSpeed's [Terms of Service](https://wavespeed.ai/static/terms) prohibit using the service to infringe intellectual property; requests that violate them are refused and accounts may be suspended.\n\n## CLI tips\n\n```bash\n# Inspect the live input schema before running (fields, enums, defaults)\nwavespeed run wavespeed-ai/image-watermark-remover -h\n\n# Quote the price first\nwavespeed price wavespeed-ai/image-watermark-remover -p \"...\" -i key=value\n\n# Save outputs to disk instead of only printing URLs\nwavespeed run wavespeed-ai/image-watermark-remover -p \"...\" --json --download \"./out/{index}.{ext}\"\n\n# Local files: prefix the path with @ and the CLI uploads it and passes the hosted URL\nwavespeed run wavespeed-ai/image-watermark-remover -i <field>=@./local-file.png --json\n\n# Recover a result if the run was interrupted (the id is in the --json output)\nwavespeed show <id>\n```\n\n`run --json` prints `{ id, model, prompt, outputs: [url, ...], saved: [path, ...], elapsed_ms, raw }`. Read `outputs[0]` for the result URL.\n\n## Security constraints\n\n- **Never ask for the key in chat**: `wavespeed login` handles auth; if `wavespeed status` says signed out, ask the user to run it.\n- **Local files only via `@`**: bare paths are passed through untouched and the model will reject them. Only `@`-prefixed values upload.\n- **No arbitrary URL loading**: only pass media URLs the user provided or that came back from a previous run.\n- **Input validation**: only pass parameters documented above; confirm with `wavespeed run <model> -h` when unsure.\n\nFile v2.0.1:_meta.json\n\n{\n  \"ownerId\": \"kn733k72mbe41a710dd1kfpg2s8257bs\",\n  \"slug\": \"wavespeed-watermark-remover\",\n  \"version\": \"2.0.1\",\n  \"publishedAt\": 1788625736208\n}\n\nFile v2.0.1:skill-card.md\n\n## Description:\n\nHelps agents remove watermarks, logos, captions, and text overlays from user-owned or licensed images and videos with WaveSpeed AI.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[wavespeed](https://clawhub.ai/user/wavespeed)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nExternal users, developers, and content operations teams use this skill to route eligible image or video watermark-removal requests through WaveSpeed AI. It is intended for media the user owns or is licensed to modify, with guardrails against removing third-party copyright, attribution, or preview marks.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: Media is uploaded to WaveSpeed's cloud service for processing.\n\nMitigation: Only process media the user is comfortable sending to WaveSpeed and that the user owns or is licensed to modify.\n\nRisk: Watermark removal can be misused to strip third-party copyright, attribution, or stock preview marks.\n\nMitigation: Confirm ownership or license before running the model, refuse unclear or infringing requests, and avoid outputs that misrepresent authorship or licensing.\n\nRisk: The documented setup uses global npm and npx commands that may install changing package versions.\n\nMitigation: Pin reviewed package versions where possible and run the CLI or MCP server in a least-privileged environment.\n\nRisk: Authentication material may be exposed if users paste keys into chat or commands are run in shared environments.\n\nMitigation: Use `wavespeed login` or a scoped `WAVESPEED_API_KEY` environment variable and never ask the user to paste secrets into the conversation.\n\n## Reference(s):\n\n- [ClawHub skill page](https://clawhub.ai/wavespeed/skills/wavespeed-watermark-remover)\n- [WaveSpeed MCP server](https://github.com/WaveSpeedAI/mcp-server)\n\n## Skill Output:\n\n**Output Type(s):** [Guidance, Shell commands, API Calls, Configuration]\n\n**Output Format:** [Markdown with inline bash commands and parameter tables]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Produces WaveSpeed CLI or MCP invocation guidance and result URLs; media processing happens through WaveSpeed's cloud service.]\n\n## Skill Version(s):\n\n2.0.1 (source: server release evidence)\n\n## Ethical Considerations:\n\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.\n\nArchive v2.0.0: 3 files, 4410 bytes\n\nFiles: skill-card.md (2538b), SKILL.md (6790b), _meta.json (146b)\n\nFile v2.0.0:SKILL.md\n\n---\nname: wavespeed-watermark-remover\ndescription: Remove watermarks, logos, captions, and text overlays from images and videos using WaveSpeed AI. Intelligently detects and removes watermarks while preserving texture and background. Supports images and videos up to 10 minutes. Only for media the user owns or is licensed to modify (e.g. cleaning their own exports, stock they have purchased, or overlays they added themselves); never to strip another party's copyright or attribution marks. Use when the user wants to remove watermarks or text overlays from their own media.\nmetadata:\n  author: wavespeedai\n  version: \"2.0\"\n---\n\n# WaveSpeedAI Watermark Remover\n\nRemove watermarks, logos, captions, and text overlays from images and videos using WaveSpeed AI. Intelligently detects and removes watermarks while preserving texture and background.\n\n**Read [Responsible use](#responsible-use) before running anything.** This tool is for media the user owns or is licensed to modify, not for stripping other people's copyright or attribution marks.\n\n## Setup\n\nInstall the open-source CLI once and sign in; the CLI stores the key, so never ask the user to paste an API key into the chat:\n\n```bash\nnpm install -g @wavespeed/cli\nwavespeed login          # opens https://wavespeed.ai/accesskey and stores the key\nwavespeed status         # confirms you are signed in\n```\n\nFor CI or one-off shells, `WAVESPEED_API_KEY` in the environment also works.\n\nPrefer MCP tools over shell commands? The same platform is exposed by [`@wavespeed/mcp`](https://github.com/WaveSpeedAI/mcp-server) (`npx -y @wavespeed/mcp`; tools `search_models`, `get_model_schema`, `get_price`, `upload_file`, `run_model`, `get_prediction`). It shares the CLI's stored login. Every example below maps one-to-one onto `run_model` with the same model id and input fields.\n\n## Quick Start\n\n### Image Watermark Removal\n\n```bash\n# Upload a local image to get a URL\nOUTPUT_URL=$(wavespeed run wavespeed-ai/image-watermark-remover \\\n  -i image=@./watermarked-image.png \\\n  --json | jq -r '.outputs[0]')\n```\n\n### Video Watermark Removal\n\n```bash\n# Upload a local video to get a URL\nOUTPUT_URL=$(wavespeed run wavespeed-ai/video-watermark-remover \\\n  -i video=@./watermarked-video.mp4 \\\n  --json | jq -r '.outputs[0]')\n```\n\nExisting URLs work as-is:\n\n```bash\nOUTPUT_URL=$(wavespeed run wavespeed-ai/image-watermark-remover \\\n  -i image=\"https://example.com/watermarked-image.jpg\" \\\n  --json | jq -r '.outputs[0]')\n```\n\n## API Endpoints\n\n### Image Watermark Remover\n\n**Model ID:** `wavespeed-ai/image-watermark-remover`\n\nRemove watermarks, logos, and text overlays from an image while preserving texture and background.\n\n#### Parameters\n\n| Parameter | Type | Required | Default | Description |\n|-----------|------|----------|---------|-------------|\n| `image` | string | Yes | -- | URL of the image to process |\n| `output_format` | string | No | `jpeg` | Output format. One of: `jpeg`, `png`, `webp` |\n\n#### Example\n\n```bash\nOUTPUT_URL=$(wavespeed run wavespeed-ai/image-watermark-remover \\\n  -i image=@./watermarked-photo.png \\\n  -i output_format=\"png\" \\\n  --json | jq -r '.outputs[0]')\n```\n\n### Video Watermark Remover\n\n**Model ID:** `wavespeed-ai/video-watermark-remover`\n\nRemove watermarks, logos, captions, and text overlays from a video. Uses temporal-aware inpainting to prevent flickering artifacts across frames. Supports videos up to 10 minutes.\n\n#### Parameters\n\n| Parameter | Type | Required | Default | Description |\n|-----------|------|----------|---------|-------------|\n| `video` | string | Yes | -- | URL of the video to process. Must be publicly accessible. Max 10 minutes. |\n\n#### Example\n\n```bash\nOUTPUT_URL=$(wavespeed run wavespeed-ai/video-watermark-remover \\\n  -i video=@./watermarked-video.mp4 \\\n  --json | jq -r '.outputs[0]')\n```\n\n\n## Pricing\n\n| Operation | Cost |\n|-----------|------|\n| Image watermark removal | $0.012 per image |\n| Video watermark removal | $0.01 per second (minimum $0.05 / 5 seconds) |\n\nVideo watermark removal supports videos up to 10 minutes. Processing time is approximately 5-20 seconds per 1 second of video.\n\n## Responsible use\n\nWatermarks and overlays are usually there to assert ownership or attribution. Before calling either endpoint, confirm the following with the user. If the answer is no or unclear, do not run the model and explain why.\n\n- **Ownership or license**: the user created the media, holds the rights to it, or has a license that permits removing the mark (for example, a purchased stock asset whose license allows clean use, or their own export from a tool that stamps a logo).\n- **Not someone else's mark**: do not remove a watermark, logo, credit, or copyright notice placed by a third party to identify their work. Stock-site preview watermarks, photographer credits, broadcaster logos, and platform attribution marks are all out of scope.\n- **No misrepresentation**: the result will not be passed off as original, unlicensed, or unedited work, and will not be used to evade licensing fees or attribution requirements.\n- **Legitimate overlays only**: typical valid uses are removing captions or subtitles the user added, cleaning timestamps from their own camera footage, or restoring an area under a logo they own.\n\nWaveSpeed's [Terms of Service](https://wavespeed.ai/static/terms) prohibit using the service to infringe intellectual property; requests that violate them are refused and accounts may be suspended.\n\n## CLI tips\n\n```bash\n# Inspect the live input schema before running (fields, enums, defaults)\nwavespeed run wavespeed-ai/image-watermark-remover -h\n\n# Quote the price first\nwavespeed price wavespeed-ai/image-watermark-remover -p \"...\" -i key=value\n\n# Save outputs to disk instead of only printing URLs\nwavespeed run wavespeed-ai/image-watermark-remover -p \"...\" --json --download \"./out/{index}.{ext}\"\n\n# Local files: prefix the path with @ and the CLI uploads it and passes the hosted URL\nwavespeed run wavespeed-ai/image-watermark-remover -i <field>=@./local-file.png --json\n\n# Recover a result if the run was interrupted (the id is in the --json output)\nwavespeed show <id>\n```\n\n`run --json` prints `{ id, model, prompt, outputs: [url, ...], saved: [path, ...], elapsed_ms, raw }`. Read `outputs[0]` for the result URL.\n\n## Security constraints\n\n- **Never ask for the key in chat**: `wavespeed login` handles auth; if `wavespeed status` says signed out, ask the user to run it.\n- **Local files only via `@`**: bare paths are passed through untouched and the model will reject them. Only `@`-prefixed values upload.\n- **No arbitrary URL loading**: only pass media URLs the user provided or that came back from a previous run.\n- **Input validation**: only pass parameters documented above; confirm with `wavespeed run <model> -h` when unsure.\n\nFile v2.0.0:_meta.json\n\n{\n  \"ownerId\": \"kn733k72mbe41a710dd1kfpg2s8257bs\",\n  \"slug\": \"wavespeed-watermark-remover\",\n  \"version\": \"2.0.0\",\n  \"publishedAt\": 1788624958370\n}\n\nFile v2.0.0:skill-card.md\n\n## Description:\n\nRemoves watermarks, logos, captions, and text overlays from images and videos using WaveSpeed AI, with responsible-use limits for media the user owns or is licensed to modify.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[wavespeed](https://clawhub.ai/user/wavespeed)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nExternal users and developers use this skill to run WaveSpeed image and video watermark-removal models for media they own or are licensed to modify, such as their own exports, purchased stock assets, or overlays they added themselves.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: The skill asks users to install mutable third-party npm packages that can execute locally and share stored WaveSpeed credentials.\n\nMitigation: Review npm package provenance before installation, prefer pinned versions or a project-local install, run the CLI or MCP under a least-privileged account, and rotate or revoke the WaveSpeed credential if compromise is suspected.\n\nRisk: Watermark removal can be misused to strip copyright, attribution, or ownership marks from third-party media.\n\nMitigation: Confirm the user owns the media or has a license that permits removing the mark; refuse requests involving third-party copyright or attribution marks.\n\nRisk: Processing media through an external service can expose user-provided images, videos, or URLs.\n\nMitigation: Use only media the user is authorized to send to WaveSpeed, pass local files with the documented @ upload syntax, and avoid arbitrary URLs beyond user-provided media or prior model outputs.\n\n## Reference(s):\n\n- [WaveSpeedAI Watermark Remover on ClawHub](https://clawhub.ai/wavespeed/skills/wavespeed-watermark-remover)\n- [WaveSpeed MCP Server](https://github.com/WaveSpeedAI/mcp-server)\n\n## Skill Output:\n\n**Output Type(s):** [text, markdown, shell commands, configuration, guidance]\n\n**Output Format:** [Markdown guidance with inline shell commands and CLI/MCP parameter examples]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Includes WaveSpeed model IDs, input fields, pricing notes, output URL handling, and responsible-use checks.]\n\n## Skill Version(s):\n\n2.0.0 (source: server release metadata)\n\n## Ethical Considerations:\n\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.\n\nArchive v1.1.0: 3 files, 4138 bytes\n\nFiles: skill-card.md (2438b), SKILL.md (7031b), _meta.json (146b)\n\nFile v1.1.0:SKILL.md\n\n---\nname: wavespeed-watermark-remover\ndescription: Remove watermarks, logos, captions, and text overlays from images and videos using WaveSpeed AI. Intelligently detects and removes watermarks while preserving texture and background. Supports images and videos up to 10 minutes. Only for media the user owns or is licensed to modify (e.g. cleaning their own exports, stock they have purchased, or overlays they added themselves); never to strip another party's copyright or attribution marks. Use when the user wants to remove watermarks or text overlays from their own media.\nmetadata:\n  author: wavespeedai\n  version: \"1.1\"\n---\n\n# WaveSpeedAI Watermark Remover\n\nRemove watermarks, logos, captions, and text overlays from images and videos using WaveSpeed AI. Intelligently detects and removes watermarks while preserving texture and background.\n\n**Read [Responsible use](#responsible-use) before running anything.** This tool is for media the user owns or is licensed to modify, not for stripping other people's copyright or attribution marks.\n\n## Authentication\n\n```bash\nexport WAVESPEED_API_KEY=\"your-api-key\"\n```\n\nGet your API key at [wavespeed.ai/accesskey](https://wavespeed.ai/accesskey).\n\n## Quick Start\n\n### Image Watermark Removal\n\n```javascript\nimport wavespeed from 'wavespeed';\n\n// Upload a local image to get a URL\nconst imageUrl = await wavespeed.upload(\"/path/to/watermarked-image.png\");\n\nconst output_url = (await wavespeed.run(\n  \"wavespeed-ai/image-watermark-remover\",\n  { image: imageUrl }\n))[\"outputs\"][0];\n```\n\n### Video Watermark Removal\n\n```javascript\nimport wavespeed from 'wavespeed';\n\n// Upload a local video to get a URL\nconst videoUrl = await wavespeed.upload(\"/path/to/watermarked-video.mp4\");\n\nconst output_url = (await wavespeed.run(\n  \"wavespeed-ai/video-watermark-remover\",\n  { video: videoUrl }\n))[\"outputs\"][0];\n```\n\nYou can also pass existing URLs directly:\n\n```javascript\nconst output_url = (await wavespeed.run(\n  \"wavespeed-ai/image-watermark-remover\",\n  { image: \"https://example.com/watermarked-image.jpg\" }\n))[\"outputs\"][0];\n```\n\n## API Endpoints\n\n### Image Watermark Remover\n\n**Model ID:** `wavespeed-ai/image-watermark-remover`\n\nRemove watermarks, logos, and text overlays from an image while preserving texture and background.\n\n#### Parameters\n\n| Parameter | Type | Required | Default | Description |\n|-----------|------|----------|---------|-------------|\n| `image` | string | Yes | -- | URL of the image to process |\n| `output_format` | string | No | `jpeg` | Output format. One of: `jpeg`, `png`, `webp` |\n\n#### Example\n\n```javascript\nimport wavespeed from 'wavespeed';\n\nconst imageUrl = await wavespeed.upload(\"/path/to/watermarked-photo.png\");\n\nconst output_url = (await wavespeed.run(\n  \"wavespeed-ai/image-watermark-remover\",\n  {\n    image: imageUrl,\n    output_format: \"png\"\n  }\n))[\"outputs\"][0];\n```\n\n### Video Watermark Remover\n\n**Model ID:** `wavespeed-ai/video-watermark-remover`\n\nRemove watermarks, logos, captions, and text overlays from a video. Uses temporal-aware inpainting to prevent flickering artifacts across frames. Supports videos up to 10 minutes.\n\n#### Parameters\n\n| Parameter | Type | Required | Default | Description |\n|-----------|------|----------|---------|-------------|\n| `video` | string | Yes | -- | URL of the video to process. Must be publicly accessible. Max 10 minutes. |\n\n#### Example\n\n```javascript\nimport wavespeed from 'wavespeed';\n\nconst videoUrl = await wavespeed.upload(\"/path/to/watermarked-video.mp4\");\n\nconst output_url = (await wavespeed.run(\n  \"wavespeed-ai/video-watermark-remover\",\n  { video: videoUrl }\n))[\"outputs\"][0];\n```\n\n## Advanced Usage\n\n### Sync Mode (Image Watermark Remover only)\n\n```javascript\nconst output_url = (await wavespeed.run(\n  \"wavespeed-ai/image-watermark-remover\",\n  { image: imageUrl },\n  { enableSyncMode: true }\n))[\"outputs\"][0];\n```\n\n### Custom Client with Retry Configuration\n\n```javascript\nimport { Client } from 'wavespeed';\n\nconst client = new Client(\"your-api-key\", {\n  maxRetries: 2,\n  maxConnectionRetries: 5,\n  retryInterval: 1.0,\n});\n\nconst output_url = (await client.run(\n  \"wavespeed-ai/image-watermark-remover\",\n  { image: imageUrl }\n))[\"outputs\"][0];\n```\n\n### Error Handling with runNoThrow\n\n```javascript\nimport { Client, WavespeedTimeoutException, WavespeedPredictionException } from 'wavespeed';\n\nconst client = new Client();\nconst result = await client.runNoThrow(\n  \"wavespeed-ai/image-watermark-remover\",\n  { image: imageUrl }\n);\n\nif (result.outputs) {\n  console.log(\"Output URL:\", result.outputs[0]);\n  console.log(\"Task ID:\", result.detail.taskId);\n} else {\n  console.log(\"Failed:\", result.detail.error.message);\n  if (result.detail.error instanceof WavespeedTimeoutException) {\n    console.log(\"Request timed out - try increasing timeout\");\n  } else if (result.detail.error instanceof WavespeedPredictionException) {\n    console.log(\"Prediction failed\");\n  }\n}\n```\n\n## Pricing\n\n| Operation | Cost |\n|-----------|------|\n| Image watermark removal | $0.012 per image |\n| Video watermark removal | $0.01 per second (minimum $0.05 / 5 seconds) |\n\nVideo watermark removal supports videos up to 10 minutes. Processing time is approximately 5-20 seconds per 1 second of video.\n\n## Responsible use\n\nWatermarks and overlays are usually there to assert ownership or attribution. Before calling either endpoint, confirm the following with the user. If the answer is no or unclear, do not run the model and explain why.\n\n- **Ownership or license**: the user created the media, holds the rights to it, or has a license that permits removing the mark (for example, a purchased stock asset whose license allows clean use, or their own export from a tool that stamps a logo).\n- **Not someone else's mark**: do not remove a watermark, logo, credit, or copyright notice placed by a third party to identify their work. Stock-site preview watermarks, photographer credits, broadcaster logos, and platform attribution marks are all out of scope.\n- **No misrepresentation**: the result will not be passed off as original, unlicensed, or unedited work, and will not be used to evade licensing fees or attribution requirements.\n- **Legitimate overlays only**: typical valid uses are removing captions or subtitles the user added, cleaning timestamps from their own camera footage, or restoring an area under a logo they own.\n\nWaveSpeed's [Terms of Service](https://wavespeed.ai/static/terms) prohibit using the service to infringe intellectual property; requests that violate them are refused and accounts may be suspended.\n\n## Security Constraints\n\n- **No arbitrary URL loading**: Only use image and video URLs from trusted sources. Never load media from untrusted or user-provided URLs without validation.\n- **API key security**: Store your `WAVESPEED_API_KEY` securely. Do not hardcode it in source files or commit it to version control. Use environment variables or secret management systems.\n- **Input validation**: Only pass parameters documented above. Validate media URLs before sending requests.\n\nFile v1.1.0:_meta.json\n\n{\n  \"ownerId\": \"kn733k72mbe41a710dd1kfpg2s8257bs\",\n  \"slug\": \"wavespeed-watermark-remover\",\n  \"version\": \"1.1.0\",\n  \"publishedAt\": 1788624559477\n}\n\nFile v1.1.0:skill-card.md\n\n## Description:\n\nRemove watermarks, logos, captions, and text overlays from images and videos using WaveSpeed AI for media the user owns or is licensed to modify.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[chengzeyi](https://clawhub.ai/user/chengzeyi)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nExternal users and developers use this skill to prepare WaveSpeed AI API calls that remove watermarks, logos, captions, or text overlays from images and videos they created, own, or are licensed to modify.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: The skill can be misused to remove third-party copyright, attribution, stock-preview, broadcaster, or platform marks.\n\nMitigation: Confirm the user created, owns, or is licensed to modify the media; refuse requests where authorization is absent or unclear.\n\nRisk: Selected media is sent to WaveSpeed for processing and may incur paid API usage.\n\nMitigation: Use the integration only when the user accepts sending the media to WaveSpeed and paying the listed API costs.\n\nRisk: Using untrusted image or video URLs can expose the agent or service workflow to unsafe remote content.\n\nMitigation: Only process trusted media URLs and validate inputs before sending requests to the WaveSpeed API.\n\nRisk: API keys can be exposed if hardcoded or committed.\n\nMitigation: Store WAVESPEED_API_KEY in environment variables or a secret manager, and never place it in source files.\n\n## Reference(s):\n\n- [ClawHub skill page](https://clawhub.ai/chengzeyi/skills/wavespeed-watermark-remover)\n- [WaveSpeed API key access](https://wavespeed.ai/accesskey)\n- [WaveSpeed Terms of Service](https://wavespeed.ai/static/terms)\n\n## Skill Output:\n\n**Output Type(s):** [text, markdown, code, shell commands, configuration, guidance]\n\n**Output Format:** [Markdown with JavaScript and bash code blocks]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [May include WaveSpeed API model IDs, request parameters, output URL handling, authentication setup, retry guidance, and responsible-use checks.]\n\n## Skill Version(s):\n\n1.1.0 (source: server release evidence)\n\n## Ethical Considerations:\n\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.\n\nArchive v1.0.0: 3 files, 3170 bytes\n\nFiles: skill-card.md (2145b), SKILL.md (5278b), _meta.json (146b)\n\nFile v1.0.0:SKILL.md\n\n---\nname: wavespeed-watermark-remover\ndescription: Remove watermarks, logos, captions, and text overlays from images and videos using WaveSpeed AI. Intelligently detects and removes watermarks while preserving texture and background. Supports images and videos up to 10 minutes. Use when the user wants to remove watermarks or text overlays from media.\nmetadata:\n  author: wavespeedai\n  version: \"1.0\"\n---\n\n# WaveSpeedAI Watermark Remover\n\nRemove watermarks, logos, captions, and text overlays from images and videos using WaveSpeed AI. Intelligently detects and removes watermarks while preserving texture and background.\n\n## Authentication\n\n```bash\nexport WAVESPEED_API_KEY=\"your-api-key\"\n```\n\nGet your API key at [wavespeed.ai/accesskey](https://wavespeed.ai/accesskey).\n\n## Quick Start\n\n### Image Watermark Removal\n\n```javascript\nimport wavespeed from 'wavespeed';\n\n// Upload a local image to get a URL\nconst imageUrl = await wavespeed.upload(\"/path/to/watermarked-image.png\");\n\nconst output_url = (await wavespeed.run(\n  \"wavespeed-ai/image-watermark-remover\",\n  { image: imageUrl }\n))[\"outputs\"][0];\n```\n\n### Video Watermark Removal\n\n```javascript\nimport wavespeed from 'wavespeed';\n\n// Upload a local video to get a URL\nconst videoUrl = await wavespeed.upload(\"/path/to/watermarked-video.mp4\");\n\nconst output_url = (await wavespeed.run(\n  \"wavespeed-ai/video-watermark-remover\",\n  { video: videoUrl }\n))[\"outputs\"][0];\n```\n\nYou can also pass existing URLs directly:\n\n```javascript\nconst output_url = (await wavespeed.run(\n  \"wavespeed-ai/image-watermark-remover\",\n  { image: \"https://example.com/watermarked-image.jpg\" }\n))[\"outputs\"][0];\n```\n\n## API Endpoints\n\n### Image Watermark Remover\n\n**Model ID:** `wavespeed-ai/image-watermark-remover`\n\nRemove watermarks, logos, and text overlays from an image while preserving texture and background.\n\n#### Parameters\n\n| Parameter | Type | Required | Default | Description |\n|-----------|------|----------|---------|-------------|\n| `image` | string | Yes | -- | URL of the image to process |\n| `output_format` | string | No | `jpeg` | Output format. One of: `jpeg`, `png`, `webp` |\n\n#### Example\n\n```javascript\nimport wavespeed from 'wavespeed';\n\nconst imageUrl = await wavespeed.upload(\"/path/to/watermarked-photo.png\");\n\nconst output_url = (await wavespeed.run(\n  \"wavespeed-ai/image-watermark-remover\",\n  {\n    image: imageUrl,\n    output_format: \"png\"\n  }\n))[\"outputs\"][0];\n```\n\n### Video Watermark Remover\n\n**Model ID:** `wavespeed-ai/video-watermark-remover`\n\nRemove watermarks, logos, captions, and text overlays from a video. Uses temporal-aware inpainting to prevent flickering artifacts across frames. Supports videos up to 10 minutes.\n\n#### Parameters\n\n| Parameter | Type | Required | Default | Description |\n|-----------|------|----------|---------|-------------|\n| `video` | string | Yes | -- | URL of the video to process. Must be publicly accessible. Max 10 minutes. |\n\n#### Example\n\n```javascript\nimport wavespeed from 'wavespeed';\n\nconst videoUrl = await wavespeed.upload(\"/path/to/watermarked-video.mp4\");\n\nconst output_url = (await wavespeed.run(\n  \"wavespeed-ai/video-watermark-remover\",\n  { video: videoUrl }\n))[\"outputs\"][0];\n```\n\n## Advanced Usage\n\n### Sync Mode (Image Watermark Remover only)\n\n```javascript\nconst output_url = (await wavespeed.run(\n  \"wavespeed-ai/image-watermark-remover\",\n  { image: imageUrl },\n  { enableSyncMode: true }\n))[\"outputs\"][0];\n```\n\n### Custom Client with Retry Configuration\n\n```javascript\nimport { Client } from 'wavespeed';\n\nconst client = new Client(\"your-api-key\", {\n  maxRetries: 2,\n  maxConnectionRetries: 5,\n  retryInterval: 1.0,\n});\n\nconst output_url = (await client.run(\n  \"wavespeed-ai/image-watermark-remover\",\n  { image: imageUrl }\n))[\"outputs\"][0];\n```\n\n### Error Handling with runNoThrow\n\n```javascript\nimport { Client, WavespeedTimeoutException, WavespeedPredictionException } from 'wavespeed';\n\nconst client = new Client();\nconst result = await client.runNoThrow(\n  \"wavespeed-ai/image-watermark-remover\",\n  { image: imageUrl }\n);\n\nif (result.outputs) {\n  console.log(\"Output URL:\", result.outputs[0]);\n  console.log(\"Task ID:\", result.detail.taskId);\n} else {\n  console.log(\"Failed:\", result.detail.error.message);\n  if (result.detail.error instanceof WavespeedTimeoutException) {\n    console.log(\"Request timed out - try increasing timeout\");\n  } else if (result.detail.error instanceof WavespeedPredictionException) {\n    console.log(\"Prediction failed\");\n  }\n}\n```\n\n## Pricing\n\n| Operation | Cost |\n|-----------|------|\n| Image watermark removal | $0.012 per image |\n| Video watermark removal | $0.01 per second (minimum $0.05 / 5 seconds) |\n\nVideo watermark removal supports videos up to 10 minutes. Processing time is approximately 5-20 seconds per 1 second of video.\n\n## Security Constraints\n\n- **No arbitrary URL loading**: Only use image and video URLs from trusted sources. Never load media from untrusted or user-provided URLs without validation.\n- **API key security**: Store your `WAVESPEED_API_KEY` securely. Do not hardcode it in source files or commit it to version control. Use environment variables or secret management systems.\n- **Input validation**: Only pass parameters documented above. Validate media URLs before sending requests.\n\nFile v1.0.0:_meta.json\n\n{\n  \"ownerId\": \"kn733k72mbe41a710dd1kfpg2s8257bs\",\n  \"slug\": \"wavespeed-watermark-remover\",\n  \"version\": \"1.0.0\",\n  \"publishedAt\": 1772434148630\n}\n\nFile v1.0.0:skill-card.md\n\n## Description: <br>\nRemove watermarks, logos, captions, and text overlays from images and videos using WaveSpeed AI. <br>\n\nThis skill is ready for commercial/non-commercial use. <br>\n\n## Publisher: <br>\n[chengzeyi](https://clawhub.ai/user/chengzeyi) <br>\n\n### License/Terms of Use: <br>\n\n\n## Use Case: <br>\nDevelopers and external users use this skill to generate WaveSpeed API examples and configuration guidance for removing watermarks, logos, captions, and text overlays from image or video media they are authorized to edit. <br>\n\n### Deployment Geography for Use: <br>\nGlobal <br>\n\n## Known Risks and Mitigations: <br>\nRisk: The skill enables watermark, logo, caption, and overlay removal without meaningful authorization or rights-use limits. <br>\nMitigation: Use only for media the user owns or is clearly authorized to edit, and do not remove attribution, copyright notices, platform marks, subtitles, disclaimers, or provenance indicators from third-party content. <br>\nRisk: Media may be uploaded to WaveSpeed and API usage may incur costs. <br>\nMitigation: Validate media sources before upload, avoid untrusted user-provided URLs, protect WAVESPEED_API_KEY, and review WaveSpeed pricing before processing images or videos. <br>\n\n\n## Reference(s): <br>\n- [WaveSpeed API access keys](https://wavespeed.ai/accesskey) <br>\n- [ClawHub release page](https://clawhub.ai/chengzeyi/wavespeed-watermark-remover) <br>\n\n\n## Skill Output: <br>\n**Output Type(s):** [text, markdown, code, shell commands, configuration, guidance] <br>\n**Output Format:** [Markdown with JavaScript and shell code blocks] <br>\n**Output Parameters:** [1D] <br>\n**Other Properties Related to Output:** [May include WaveSpeed model IDs, API key setup, media URL handling, pricing notes, and error-handling examples.] <br>\n\n## Skill Version(s): <br>\n1.0.0 (source: server release metadata) <br>\n\n## Ethical Considerations: <br>\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment. <br>","readmeExcerpt":"Skill: WaveSpeedAI Watermark Remover Owner: wavespeed Summary: Remove watermarks, logos, captions, and text overlays from images and videos using WaveSpeed AI. Intelligently detects and removes watermarks while preserving texture and background. Supports images and videos up to 10 minutes. Only for media the user owns or is licensed to modify (e.g. cleaning their own exports, stock they have purchased, or overlays th","codeSnippets":[],"executableExamples":[{"language":"bash","snippet":"npm install -g @wavespeed/cli\nwavespeed login          # opens https://wavespeed.ai/accesskey and stores the key\nwavespeed status         # confirms you are signed in"},{"language":"bash","snippet":"# Upload a local image to get a URL\nOUTPUT_URL=$(wavespeed run wavespeed-ai/image-watermark-remover \\\n  -i image=@./watermarked-image.png \\\n  --json | jq -r '.outputs[0]')"},{"language":"bash","snippet":"# Upload a local video to get a URL\nOUTPUT_URL=$(wavespeed run wavespeed-ai/video-watermark-remover \\\n  -i video=@./watermarked-video.mp4 \\\n  --json | jq -r '.outputs[0]')"},{"language":"bash","snippet":"OUTPUT_URL=$(wavespeed run wavespeed-ai/image-watermark-remover \\\n  -i image=\"https://example.com/watermarked-image.jpg\" \\\n  --json | jq -r '.outputs[0]')"},{"language":"bash","snippet":"OUTPUT_URL=$(wavespeed run wavespeed-ai/image-watermark-remover \\\n  -i image=@./watermarked-photo.png \\\n  -i output_format=\"png\" \\\n  --json | jq -r '.outputs[0]')"},{"language":"bash","snippet":"OUTPUT_URL=$(wavespeed run wavespeed-ai/video-watermark-remover \\\n  -i video=@./watermarked-video.mp4 \\\n  --json | jq -r '.outputs[0]')"}],"parameters":null,"dependencies":[],"permissions":[],"extractedFiles":[{"path":"SKILL.md","content":"---\nname: wavespeed-watermark-remover\ndescription: Remove watermarks, logos, captions, and text overlays from images and videos using WaveSpeed AI. Intelligently detects and removes watermarks while preserving texture and background. Supports images and videos up to 10 minutes. Only for media the user owns or is licensed to modify (e.g. cleaning their own exports, stock they have purchased, or overlays they added themselves); never to strip another party's copyright or attribution marks. Use when the user wants to remove watermarks or text overlays from their own media.\nmetadata:\n  author: wavespeedai\n  version: \"2.0\"\n---\n\n# WaveSpeedAI Watermark Remover\n\nRemove watermarks, logos, captions, and text overlays from images and videos using WaveSpeed AI. Intelligently detects and removes watermarks while preserving texture and background.\n\n**Read [Responsible use](#responsible-use) before running anything.** This tool is for media the user owns or is licensed to modify, not for stripping other people's copyright or attribution marks.\n\n## Setup\n\nInstall the open-source CLI once and sign in; the CLI stores the key, so never ask the user to paste an API key into the chat:\n\n```bash\nnpm install -g @wavespeed/cli\nwavespeed login          # opens https://wavespeed.ai/accesskey and stores the key\nwavespeed status         # confirms you are signed in\n```\n\nFor CI or one-off shells, `WAVESPEED_API_KEY` in the environment also works.\n\nPrefer MCP tools over shell commands? The same platform is exposed by [`@wavespeed/mcp`](https://github.com/WaveSpeedAI/mcp-server) (`npx -y @wavespeed/mcp`; tools `search_models`, `get_model_schema`, `get_price`, `upload_file`, `run_model`, `get_prediction`). It shares the CLI's stored login. Every example below maps one-to-one onto `run_model` with the same model id and input fields.\n\n## Quick Start\n\n### Image Watermark Removal\n\n```bash\n# Upload a local image to get a URL\nOUTPUT_URL=$(wavespeed run wavespeed-ai/image-watermark-remover \\\n  -i image=@./watermarked-image.png \\\n  --json | jq -r '.outputs[0]')\n```\n\n### Video Watermark Removal\n\n```bash\n# Upload a local video to get a URL\nOUTPUT_URL=$(wavespeed run wavespeed-ai/video-watermark-remover \\\n  -i video=@./watermarked-video.mp4 \\\n  --json | jq -r '.outputs[0]')\n```\n\nExisting URLs work as-is:\n\n```bash\nOUTPUT_URL=$(wavespeed run wavespeed-ai/image-watermark-remover \\\n  -i image=\"https://example.com/watermarked-image.jpg\" \\\n  --json | jq -r '.outputs[0]')\n```\n\n## API Endpoints\n\n### Image Watermark Remover\n\n**Model ID:** `wavespeed-ai/image-watermark-remover`\n\nRemove watermarks, logos, and text overlays from an image while preserving texture and background.\n\n#### Parameters\n\n| Parameter | Type | Required | Default | Description |\n|-----------|------|----------|---------|-------------|\n| `image` | string | Yes | -- | URL of the image to process |\n| `output_format` | string | No | `jpeg` | Output format. One of: `jpeg`, `png`, `webp` |\n\n#### Example\n\n```bash\nOUTPUT_URL=$(wavespeed "},{"path":"_meta.json","content":"{\n  \"ownerId\": \"kn733k72mbe41a710dd1kfpg2s8257bs\",\n  \"slug\": \"wavespeed-watermark-remover\",\n  \"version\": \"2.0.1\",\n  \"publishedAt\": 1788625736208\n}"},{"path":"skill-card.md","content":"## Description:\n\nHelps agents remove watermarks, logos, captions, and text overlays from user-owned or licensed images and videos with WaveSpeed AI.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[wavespeed](https://clawhub.ai/user/wavespeed)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nExternal users, developers, and content operations teams use this skill to route eligible image or video watermark-removal requests through WaveSpeed AI. It is intended for media the user owns or is licensed to modify, with guardrails against removing third-party copyright, attribution, or preview marks.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: Media is uploaded to WaveSpeed's cloud service for processing.\n\nMitigation: Only process media the user is comfortable sending to WaveSpeed and that the user owns or is licensed to modify.\n\nRisk: Watermark removal can be misused to strip third-party copyright, attribution, or stock preview marks.\n\nMitigation: Confirm ownership or license before running the model, refuse unclear or infringing requests, and avoid outputs that misrepresent authorship or licensing.\n\nRisk: The documented setup uses global npm and npx commands that may install changing package versions.\n\nMitigation: Pin reviewed package versions where possible and run the CLI or MCP server in a least-privileged environment.\n\nRisk: Authentication material may be exposed if users paste keys into chat or commands are run in shared environments.\n\nMitigation: Use `wavespeed login` or a scoped `WAVESPEED_API_KEY` environment variable and never ask the user to paste secrets into the conversation.\n\n## Reference(s):\n\n- [ClawHub skill page](https://clawhub.ai/wavespeed/skills/wavespeed-watermark-remover)\n- [WaveSpeed MCP server](https://github.com/WaveSpeedAI/mcp-server)\n\n## Skill Output:\n\n**Output Type(s):** [Guidance, Shell commands, API Calls, Configuration]\n\n**Output Format:** [Markdown with inline bash commands and parameter tables]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Produces WaveSpeed CLI or MCP invocation guidance and result URLs; media processing happens through WaveSpeed's cloud service.]\n\n## Skill Version(s):\n\n2.0.1 (source: server release evidence)\n\n## Ethical Considerations:\n\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment."}],"languages":[],"docsSourceLabel":"CLAWHUB","editorialOverview":"Remove watermarks, logos, captions, and text overlays from images and videos using WaveSpeed AI. Intelligently detects and removes watermarks while preserving texture and background. Supports images and videos up to 10 minutes. Only for media the user owns or is licensed to modify (e.g. cleaning their own exports, stock they have purchased, or overlays they added themselves); never to strip another party's copyright or attribution marks. Use when the user wants to remove watermarks or text overlays from their own media. Skill: WaveSpeedAI Watermark Remover Owner: wavespeed Summary: Remove watermarks, logos, captions, and text overlays from images and videos using WaveSpeed AI. Intelligently detects and removes watermarks while preserving texture and background. Supports images and videos up to 10 minutes. Only for media the user owns or is licensed to modify (e.g. cleaning their own exports, stock they have purchased, or overlays th","editorialQuality":{"score":100,"threshold":65,"status":"ready","wordCount":1261,"uniquenessScore":45,"reasons":[]}},"media":{"evidence":{"source":"no-media","verified":false,"confidence":"low","updatedAt":"2026-10-10T10:36:40.685Z","emptyReason":"No screenshots, media assets, or demo links are available."},"primaryImageUrl":null,"mediaAssetCount":0,"assets":[],"demoUrl":null},"ownerResources":{"evidence":{"source":"unclaimed","verified":false,"confidence":"low","updatedAt":"2026-10-10T10:36:40.685Z","emptyReason":"This page has not been claimed by the agent owner."},"hasCustomPage":false,"customPageUpdatedAt":null,"customLinks":[],"structuredLinks":{"docsUrl":null,"demoUrl":null,"supportUrl":null,"pricingUrl":null,"statusUrl":null},"customPage":null},"relatedAgents":{"evidence":{"source":"protocol-neighbors","verified":false,"confidence":"medium","updatedAt":"2026-10-10T13:39:56.567Z","emptyReason":null},"items":[{"id":"8ebccd8e-3863-4187-8355-c3f14e1f9edf","entityType":"agent","canonicalPath":"/agent/iofficeai-aionui","slug":"iofficeai-aionui","name":"AionUi","description":"Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!","url":"https://github.com/iOfficeAI/AionUi","homepage":"https://www.aionui.com","source":"GITHUB_REPOS","protocols":["MCP","OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-10-09T19:11:12.944Z","createdAt":"2026-02-25T03:38:16.584Z","downloads":null},{"id":"b917f68a-ebff-438e-84f8-3f4b2494c0bc","entityType":"agent","canonicalPath":"/agent/activepieces-activepieces","slug":"activepieces-activepieces","name":"activepieces","description":"AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents","url":"https://github.com/activepieces/activepieces","homepage":"https://www.activepieces.com","source":"GITHUB_REPOS","protocols":["OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-04-15T02:22:12.426Z","createdAt":"2026-02-25T03:38:12.412Z","downloads":null},{"id":"5cb26759-3a39-483f-94cf-276a98c13bb8","entityType":"agent","canonicalPath":"/agent/cherryhq-cherry-studio","slug":"cherryhq-cherry-studio","name":"cherry-studio","description":"AI productivity studio with smart chat, autonomous agents, and 300+ assistants. Unified access to frontier LLMs","url":"https://github.com/CherryHQ/cherry-studio","homepage":"https://cherry-ai.com","source":"GITHUB_REPOS","protocols":["MCP","OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-04-11T14:38:40.986Z","createdAt":"2026-02-25T03:38:19.379Z","downloads":null},{"id":"6f6582d0-5d76-4f0f-b81d-86520247950b","entityType":"agent","canonicalPath":"/agent/copilotkit-copilotkit","slug":"copilotkit-copilotkit","name":"CopilotKit","description":"The Frontend for Agents & Generative UI. React + Angular","url":"https://github.com/CopilotKit/CopilotKit","homepage":"https://docs.copilotkit.ai","source":"GITHUB_REPOS","protocols":["OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-03-25T09:50:57.846Z","createdAt":"2026-02-25T03:39:14.617Z","downloads":null}],"links":{"hub":"/agent","source":"/agent/source/clawhub","protocols":[{"label":"OpenClaw","href":"/agent/protocol/openclew"}]}}}