image-inpainting

Remove or replace unwanted image regions using masks or descriptions.

31|9|Updated Apr 30, 2026
One-click install
npx skills add https://github.com/prime-skills/runcomfy-agent-skills --skill image-inpainting-prime-skills
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: image-inpainting
Source: https://github.com/prime-skills/runcomfy-agent-skills/tree/main/image-inpainting
Command: npx skills add https://github.com/prime-skills/runcomfy-agent-skills --skill image-inpainting-prime-skills

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill removes unwanted objects, watermarks, blemishes, and other selected regions from still images while preserving the surrounding content and visual context.

Core Features & Use Cases

  • Mask-Driven Inpainting: Replace or restore precisely selected areas using grayscale masks, with adjustable strength and control scale.
  • Description-Based Editing: Handle local edits without a mask by routing requests to identity-preserving image editing models.
  • Use Case: Remove overhead cables from a street photo, clean a watermark from a product image, or replace a masked background with a studio backdrop.

Quick Start

Ask the image-inpainting skill to remove the unwanted object from your image using the provided mask, or describe its location if no mask is available.

Frequently Asked Questions about image-inpainting

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I remove unwanted objects from a photo using image inpainting?

Image inpainting removes unwanted objects from a photo by replacing the selected region using a grayscale mask or description-based editing, preserving the surrounding visual context seamlessly.

What is the best way to remove watermarks from product images without leaving artifacts?

The best way to remove watermarks from product images is mask-driven inpainting, which targets the specific watermark region for cleanup while maintaining the integrity of the underlying image content.

Do I need a grayscale mask URL to perform local image retouching?

You do not strictly need a grayscale mask URL for local image retouching; the Skill supports description-based editing by routing requests to identity-preserving models when no mask is available.

Can I replace a masked background with a studio backdrop using RunComfy?

Yes, you can replace a masked background with a studio backdrop using RunComfy by providing the source image and a grayscale mask URL, which requires RunComfy CLI access and an authenticated RunComfy account.

Does description-based inpainting work for blemish retouching without precise masking?

Description-based inpainting works for blemish retouching without precise masking by routing requests to identity-preserving image editing models, allowing you to describe the blemish location instead.