image-inpainting
🎯Skillfrom prime-skills/runcomfy-agent-skills
Installation
npx vibeindex add prime-skills/runcomfy-agent-skills --skill image-inpaintingnpx skills add prime-skills/runcomfy-agent-skills --skill image-inpainting~/.claude/skills/image-inpainting/SKILL.md
|A skill for mask-driven image inpainting via RunComfy CLI, routing to Z-Image Turbo Inpainting for precise region edits with binary masks and to description-based models (Nano Banana 2 Edit, GPT Image 2 Edit, Flux Kontext Pro) when no mask is available.
Overview
This skill performs mask-driven region edits on still images using the RunComfy CLI. It routes to Z-Image Turbo Inpainting as the default when a binary mask is available, providing precise control over object removal, watermark cleanup, background replacement, and blemish retouching with adjustable strength and control-scale parameters. When no mask is available, it falls back to description-based edit models (Nano Banana 2 Edit, GPT Image 2 Edit, or Flux Kontext Pro) that identify target regions from spatial language in the prompt.
Key Features
- Dedicated mask-driven inpainting: Z-Image Turbo Inpainting accepts a grayscale mask (white = inpaint, black = preserve) with adjustable strength (0.3-1.0) for tasks ranging from light retouching to full region replacement
- LoRA-compatible inpainting: Z-Image Turbo Inpainting LoRA variant applies fine-tuned style adapters during inpainting for brand-style-locked edits
- Description-based fallback: Nano Banana 2 Edit handles region edits using spatial language ("the watermark in the bottom-right corner") when no mask is available
- Multi-reference complex edits: GPT Image 2 Edit supports up to 10 reference images for complex layout repositioning where the masked region needs context from other images
- Maximum-preservation local edits: Flux Kontext Pro provides "keep everything except X" style edits without requiring a mask or reference image
- Strength-based workflow guidance: Built-in recommendations for strength values by intent (0.3-0.5 for retouching, 0.6-0.7 for object replacement, 0.8-1.0 for full region replacement)
Who is this for?
- Photographers and retouchers who need automated object removal, blemish cleanup, or background replacement with precise mask control
- E-commerce teams performing batch product photo cleanup such as background swaps and watermark removal
- Developers building image editing pipelines that require programmatic access to mask-driven inpainting through a CLI interface
Same repository
prime-skills/runcomfy-agent-skills(25 items)
SKILL.md
More from this repository10
A smart intent-routing skill for video editing on RunComfy that automatically selects the best model (Wan 2.7 Edit-Video, Kling 2.6 Pro Motion Control, or Lucy Edit Restyle) based on what the user wants to do, from general restyling and background swaps to precise motion transfer and outfit changes.
A smart intent-routing skill that animates still images on RunComfy by selecting the optimal model: HappyHorse 1.0 I2V for general portrait and product animation with native audio, Wan 2.7 for custom-voiceover lip-sync, or Seedance 2.0 Pro for multi-modal composition with image, video, and audio references.
A skill for generating images with Google Nano Banana 2, the flash-tier text-to-image model in the Gemini family on RunComfy, optimized for rapid iteration, batch ideation, in-image typography rendering, and optional web-grounded context with support for resolutions from 0.5K to 4K.
A smart intent-routing skill for image editing on RunComfy that selects the optimal model from Nano Banana Edit (batch up to 20 images), GPT Image 2 Edit (multilingual text rewrite, multi-ref composition), Flux Kontext Pro (single-shot precise local edit), or Z-Image Turbo Inpaint (mask-driven region edit) based on user intent.
A Claude Code skill that enables precise single-image editing using Black Forest Labs's Flux 1 Kontext Pro model through the RunComfy CLI, with built-in prompting patterns for high-fidelity local edits.
A skill for generating text-to-video with Wan 2.7, Wan-AI's flagship motion model on RunComfy, featuring multi-reference conditioning, audio-driven lip-sync via custom audio tracks, smooth transition physics, prompt expansion control, and up to 1080p output at 15 seconds duration.
A Claude Code skill for generating text-to-video clips with HappyHorse 1.0 via the RunComfy CLI. HappyHorse 1.0 is currently ranked #1 on the Artificial Analysis Video Arena, producing native 1080p video with in-pass synchronized audio and multi-shot character consistency.
A Claude Code skill for generating video with Kling 3.0 via the RunComfy CLI. Covers all six Kling 3.0 endpoints across three rendering tiers (Standard, Pro, 4K) and two modes (text-to-video, image-to-video), with native synchronized audio and multi-shot character consistency.
A Claude Code skill that generates custom OpenAI Codex Pets from a single reference image via the RunComfy CLI. It produces a Codex-compatible spritesheet (1536x1872, 8 columns x 9 rows) and pet.json manifest using GPT Image 2 and ImageMagick, without requiring Codex Pro or an OPENAI_API_KEY.
A Claude Code skill that acts as a smart router for AI video generation across the full RunComfy model catalog. Supports text-to-video, image-to-video, and video-extend modes with models including HappyHorse 1.0, Kling 3.0, Wan 2.7, Seedance, Veo 3.1, and more.