Edit video frames by region to remove objects or artifacts via RunComfy CLI.
npx skills add https://github.com/doany-ai/skills --skill video-inpainting-doany-ai
Please help me install this Agent Skill. Skill: video-inpainting Source: https://github.com/doany-ai/skills/tree/main/video-inpainting Command: npx skills add https://github.com/doany-ai/skills --skill video-inpainting-doany-ai
Region edits across video frames — remove an object that appears across many frames, clean up wires or watermarks, replace a region with matching motion. This skill routes across the prompt-driven video edit endpoints in the RunComfy catalog and gives the agent a clear default for each intent.
Install the RunComfy CLI and run a video edit with Wan 2-7 edit-video by providing a video URL and a region-based prompt.
High-intent search queries and answers about installing and using this skill.
Remove objects from a video by applying region-based inpainting across all frames using prompt-driven workflows. This skill routes your request through the RunComfy CLI to the Wan 2-7 edit-video endpoint, ensuring frame-by-frame consistency throughout the clip.
Prompt-driven video inpainting is a technique that edits specific regions across video frames using text instructions. It removes artifacts or objects while maintaining frame consistency by automatically routing prompts through models like Wan 2-7 Edit-Video.
Yes, you can achieve identity-stable video restyles by routing your prompt to the Lucy Edit Restyle model. This alternative path ensures the subject's identity remains stable while applying region-aware edits across the entire video sequence.
Perform sequential video edits frame-by-frame by routing your prompt to the Seedream 4-0 Edit-Sequential model. This approach processes the video sequence step-by-step to ensure precise frame-by-frame consistency during the region inpainting task.
Use mask-driven ComfyUI workflows for video editing when you need pixel-precise propagation for region edits. This approach is recommended over prompt-driven video inpainting when exact mask control is required to remove objects or artifacts across frames.
Yes, you need the RunComfy CLI to edit video regions using this skill. The CLI posts your video URL and region-based prompt to the video edit endpoints, automatically selecting the appropriate model route and outputting the video to a specified directory.
prime-skillsRemove or replace targeted regions across video frames while preserving motion.
openclaw-easyExtract video frames and thumbnails at precise timestamps or frame indices using ffmpeg.
agentspace-soRemove unwanted objects across video frames via RunComfy prompt-driven region edits.
runcomfy-comInpaint unwanted regions across video frames via the RunComfy CLI.
