video-inpainting
video-inpainting is an agent skill published by genmedia-labs, listed under images, audio & video. It lives in the genmedia-labs/skills repository, which has 27 GitHub stars and is licensed under MIT; we last read it on 2026-09-16.
This tool edits regions across video frames using the `runcomfy` CLI, removing objects, cleaning up wires or watermarks, and replacing regions with matching motion. It supports different editing methods based on the nature of the change, including prompt-driven region edits, identity-stable region-aware restyling, and frame-by-frame inpainting.
Install
skills is a generic installer for any repository of Claude agent skills -- it reads genmedia-labs/skills’s own structure rather than assuming one, the same way this page reads the skill’s own SKILL.md rather than assuming a format.
npx skills add genmedia-labs/skills
Maintenance
Region edits across video frames on RunComfy via the `runcomfy` CLI — remove an object that appears across many frames, clean up wires or watermarks, replace a region with matching motion. Routes across Wan 2-7 edit-video (default, prompt-driven region edits with spatial language), Lucy Edit Restyle (identity-stable region-aware restyle), and Seedream 4-0 edit-sequential (when treating the clip as a frame stack). Picks the right route based on whether the change is prose-driven, identity-locked, or needs frame-by-frame still inpaint chained into a video. Triggers on "video inpaint", "video inpainting", "remove from video", "mask region in video", "clean up video", "remove object from clip", "video patch", "frame-by-frame edit", "remove watermark from video", "remove passing person", or any explicit ask to edit a region across video frames.
video-inpainting compared with similar skills
| Skill | Publisher | What it does | Repo stars | Last update |
|---|---|---|---|---|
| video-inpainting (this page) | genmedia-labs | Region edits across video frames on RunComfy via the `runcomfy` CLI — remove an object that appears across ma… | 27 | 2026-09-07 |
| ace-step(same repository) | genmedia-labs | Generate, inpaint, and outpaint music with ACE Step on RunComfy via the `runcomfy` CLI. ACE Step is StepFun-A… | 27 | 2026-09-07 |
| ai-image-generation(same repository) | genmedia-labs | Generate and edit images on RunComfy via the `runcomfy` CLI — a smart router across the full image-model cata… | 27 | 2026-09-07 |
| ai-music(same repository) | genmedia-labs | Generate AI music on RunComfy via the `runcomfy` CLI — a smart router across the music-model catalog. Routes… | 27 | 2026-09-07 |
| elevenlabs-music-generation(same repository) | genmedia-labs | Generate full songs and instrumental tracks with ElevenLabs Music on RunComfy via the `runcomfy` CLI. ElevenL… | 27 | 2026-09-07 |
| transformers-js | huggingface | Use Transformers.js to run state-of-the-art machine learning models directly in JavaScript/TypeScript. Suppor… | 11,213 | 2026-10-23 |
| gemini-live-api-dev | google-gemini | Use this skill when building real-time, bidirectional streaming applications with the Gemini Live API, or mig… | 4,341 | 2026-10-13 |
Skills from the same repository first, then others for this job by repository stars. Figures are from each repository when we last read it.
Common questions about video-inpainting
- What does video-inpainting do?
- This tool edits regions across video frames using the `runcomfy` CLI, removing objects, cleaning up wires or watermarks, and replacing regions with matching motion. It supports different editing methods based on the nature of the change, including prompt-driven region edits, identity-stable region-aware restyling, and frame-by-frame inpainting.
- How do I install video-inpainting?
- Run npx skills add genmedia-labs/skills. The skills installer reads the repository’s own structure, so it works for any repository of agent skills.
- Who publishes video-inpainting?
- genmedia-labs.
- Is video-inpainting maintained, and what licence does it use?
- Its repository has 27 GitHub stars and its state in our directory is listed. Its last commit we recorded was on 2026-09-07. The repository declares the MIT licence.
More agent skills for images, audio & video
- ai-avatar-videoby 101-skills
- ai-marketing-videosby 101-skills
- ai-podcastby 101-skills
- ai-social-media-contentby 101-skills
- ai-voice-cloningby 101-skills
- book-cover-designby 101-skills