image-inpainting
Installation
Summary
Mask-driven region edits: remove objects, fill gaps, replace masked areas via RunComfy CLI.
- Routes to Z-Image Turbo Inpainting (default) when a binary mask is provided, with tunable strength (0.3–1.0) for retouching to full replacement; falls back to description-based models (Nano Banana 2 Edit, GPT Image 2 Edit, FLUX Kontext Pro) when no mask is available
- Supports object removal, watermark cleanup, blemish retouching, background replacement, and region-specific edits with optional LoRA style adapters
- Invoked via
runcomfy runwith image URL, mask URL (grayscale, white = inpaint region), and text prompt describing the fill or preservation constraints - Requires
runcomfyCLI installation and authentication; exit codes distinguish success, schema errors, timeouts, and auth failures
SKILL.md
Image Inpainting
Mask-driven region edits — remove objects, fill gaps, replace masked areas — on RunComfy via the runcomfy CLI. This skill routes to Z-Image Turbo Inpainting when a mask is available, and to instruction-driven edit models when the region must be described in prose.
runcomfy.com · Z-Image Inpainting · CLI docs
Powered by the RunComfy CLI
# 1. Install (see runcomfy-cli skill for details)
npm i -g @runcomfy/cli # or: npx -y @runcomfy/cli --version
# 2. Sign in
runcomfy login # or in CI: export RUNCOMFY_TOKEN=<token>
Installs
170.0K
Repository
agentspace-so/runcomfy-agent-skillsGitHub Stars
19
First Seen
May 13, 2026
Security Audits
Explore more of GLSRM