skills.rest
agentspace-so
agentspace-soOFFICIAL
Explore all skills by this author →
GitHub

image-edit

Route image editing requests to the appropriate RunComfy edit model.

31|9|Updated Apr 30, 2026
Search Tags:#image editing#batch processing#inpainting#intent routing#multilingual text#background swap#RunComfy CLI
One-click install
npx skills add https://github.com/agentspace-so/runcomfy-agent-skills --skill image-edit-agentspace-so
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: image-edit
Source: https://github.com/agentspace-so/runcomfy-agent-skills/tree/main/image-edit
Command: npx skills add https://github.com/agentspace-so/runcomfy-agent-skills --skill image-edit-agentspace-so

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Editing images usually forces you to guess which model and parameters will produce the best result, causing wasted iterations and inconsistent outputs.

Core Features & Use Cases

  • Intent-routed model selection: Automatically matches your request to the best RunComfy edit model (batch identity-preserving edits, multilingual in-image text rewrite, single-shot precise edits, or mask-driven region replacement).
  • Prompting patterns bundled per route: Uses model-specific prompting guidance to improve edit sharpness while reducing trial-and-error.
  • Supports common edit scenarios: Background swaps, object removal/addition, multilingual headline rewriting, multi-reference compositions, precise repositioning, and inpainting with masks.

Quick Start

Ask the agent to edit an image with a clear goal like: Replace the in-image headline with Japanese text while keeping the photo layout and brand mark exactly the same.

Frequently Asked Questions about image-edit

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

FAQPage Schema
How do I choose the right model for image editing tasks like inpainting or background swaps?▼

Choosing the right model for image editing is simplified by intent routing, which automatically matches your request to the correct RunComfy edit model for consistent, high-quality results.

How do I rewrite multilingual text inside an image without altering the background layout?▼

To rewrite multilingual text inside an image, the intent router selects a specialized model that preserves the photo layout and brand mark while accurately rewriting the in-image headline.

Can I do batch image edits and multi-reference compositions using a single command?▼

Batch image edits and multi-reference compositions are supported by routing your request to the appropriate model, allowing consistent identity-preserving edits across multiple images.

Does RunComfy support mask-driven inpainting for precise object removal and repositioning?▼

RunComfy supports mask-driven inpainting for precise object removal and repositioning by routing your intent to the Z-Image Turbo Inpaint model using the corresponding JSON schema.

What is the best way to get high-quality results when swapping backgrounds in product photos?▼

The best way to swap backgrounds in product photos is using intent-routed model selection, which applies model-specific prompting patterns to improve edit sharpness and reduce trial-and-error.

Related Skills

Explore More Design & Creative Skills→
runcomfy-comruncomfy-com
12

image-edit

Route image editing requests to RunComfy edit models by intent.

Official
Advanced
agentspace-soagentspace-so
31

video-edit

Route video editing intents to RunComfy models and execute endpoints.

Official
Intermediate
prime-skillsprime-skills
31

image-edit

Route image editing requests to the appropriate RunComfy model and execute them.

Official
Advanced
doany-aidoany-ai
5

image-edit

Route image edits to the best RunComfy model and download results.

Official
Intermediate