video-inpainting
๐ฏSkillfrom agentspace-so/runcomfy-agent-skills
|A Claude Code skill for region editing across video frames via the RunComfy CLI, enabling object removal, watermark cleanup, and motion-consistent region replacement using Wan 2-7 edit-video and other prompt-driven video edit endpoints.
Overview
Video Inpainting is a Claude Code skill for region editing across video frames via the RunComfy CLI. It enables object removal, watermark cleanup, wire removal, and region replacement while maintaining motion consistency across frames. The skill routes to Wan 2-7 edit-video for prompt-driven region edits using spatial language, Lucy Edit Restyle for identity-stable region-aware restyling, and Seedream 4-0 edit-sequential for treating clips as frame stacks. The agent picks the right route based on whether the change is prose-driven, identity-locked, or needs frame-by-frame still inpaint.
Key Features
- Prompt-driven region edits across frames - Uses Wan 2-7 edit-video (the default route) to resolve targeted regions from spatial language across all frames, enabling changes like "remove the watermark in the bottom-right" or "replace the sky with a sunset" without an explicit mask.
- Identity-stable restyling - Routes to Lucy Edit Restyle for lightweight region-aware edits that need to track a subject's identity across frames, such as outfit or object swaps.
- Multiple edit strategies - Selects between prompt-driven whole-clip edits, identity-locked restyling, and frame-by-frame still inpainting chained into video depending on the edit requirements.
- Motion-consistent output - All routes preserve the original clip's motion, timing, and unedited regions while applying the targeted changes across the full frame sequence.
Who is this for?
- Video editors and post-production teams who need to remove unwanted objects, watermarks, or wires from video footage without manual frame-by-frame editing
- Content creators who want to modify specific regions of video clips while preserving the natural motion and timing of the original footage
- Developers building automated video cleanup pipelines who need a skill that selects the right inpainting strategy based on edit intent
Same repository
agentspace-so/runcomfy-agent-skills(30 items)
Installation
npx vibeindex add agentspace-so/runcomfy-agent-skills --skill video-inpaintingnpx skills add agentspace-so/runcomfy-agent-skills --skill video-inpainting~/.claude/skills/video-inpainting/SKILL.mdSKILL.md
More from this repository10
A smart intent-routing skill for video editing on RunComfy that selects the best model based on the user's intent. Routes to Wan 2.7 Edit-Video for restyle and background swaps, Kling 2.6 Pro for precise motion transfer, or Lucy Edit for lightweight identity-stable restyle and outfit swaps.
A smart intent-routing skill for image-to-video generation on RunComfy that automatically selects the best model for the task. Routes to HappyHorse 1.0 I2V for general animations, Wan 2.7 for custom-voiceover lip-sync, or Seedance 2.0 Pro for multi-modal composition from image, video, and audio references.
A smart intent-routing skill for image editing on RunComfy that selects the best model based on the editing task. Routes to Nano Banana Edit for batch edits up to 20 images, GPT Image 2 for multilingual text rewrite, Flux Kontext Pro for single-shot precise edits, or Z-Image Turbo for mask-driven inpainting.
Edit images with Black Forest Labs' Flux 1 Kontext Pro on RunComfy, specializing in single-reference precise local edits with high-fidelity source preservation. Ideal for targeted changes like adding objects or modifying details while keeping the rest of the image unchanged.
A RunComfy skill that generates images using Google Nano Banana 2, the flash-tier text-to-image model in the Gemini family. Optimized for rapid iteration, social thumbnails, and in-image typography with configurable resolution tiers and safety tolerance.
Edit images with Google Nano Banana 2 on RunComfy, supporting batch edits of up to 20 images per call with strong identity preservation. Features localized edits using spatial language, background swaps, and configurable resolution up to 4K.
Generate text-to-video with HappyHorse 1.0 on RunComfy, currently ranked #1 on Artificial Analysis Video Arena. Supports native 1080p with in-pass synchronized audio, multi-shot character consistency, and 6-language prompt support via the RunComfy CLI.
Generate text-to-video with Wan-AI's Wan 2.7 on RunComfy, featuring multi-reference conditioning and audio-driven lip-sync via custom audio tracks. Supports prompt expansion, negative prompts, and up to 1080p resolution through the RunComfy CLI.
Generate cinematic short-form video with ByteDance Seedance 2.0 Pro on RunComfy, supporting multi-modal references including up to 9 images, 3 videos, and 3 audio tracks. Features native lip-synced audio generation and is ideal for brand-consistent multi-language narratives.
Edit images with OpenAI GPT Image 2 on RunComfy, excelling at multilingual in-image text editing across any script (Latin, kana, CJK, Cyrillic, Arabic) and multi-reference composition with up to 10 input images. Ideal for identity-preserving edits and layout-precise repositioning.