skills.rest
prime-skills
prime-skillsOFFICIAL
Explore all skills by this author →
GitHub

gpt-image-edit

Edit images with GPT Image 2 while preserving subjects, layout, and branding.

31|9|Updated Apr 30, 2026
Search Tags:#image editing#image composition#identity preservation#runcomfy#gpt image 2#multilingual text#ad localization
One-click install
npx skills add https://github.com/prime-skills/runcomfy-agent-skills --skill gpt-image-edit-prime-skills
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: gpt-image-edit
Source: https://github.com/prime-skills/runcomfy-agent-skills/tree/main/gpt-image-edit
Command: npx skills add https://github.com/prime-skills/runcomfy-agent-skills --skill gpt-image-edit-prime-skills

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill helps you make targeted image edits while preserving identity, composition, branding, layout, and other details that can drift during image-to-image generation.

Core Features & Use Cases

  • Identity-Preserving Edits: Retain faces, poses, clothing, products, brand marks, and framing while changing selected elements.
  • Multilingual Text Editing: Replace embedded headlines, labels, and calls to action in scripts including Japanese, Cyrillic, Arabic, and Chinese.
  • Multi-Reference Composition: Combine up to 10 publicly accessible reference images and assign each image a specific role in the composition.
  • Layout-Precise Changes: Reposition objects, swap backgrounds, update typography, or modify localized regions with explicit spatial instructions.
  • Use Case: Localize a product poster by replacing its English headline with a Japanese translation while preserving the original photograph, layout, lighting, and brand mark.

Quick Start

Ask the GPT Image Edit skill to replace the headline in your image with quoted text in the desired language while preserving the subject, layout, branding, and framing.

Frequently Asked Questions about gpt-image-edit

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

FAQPage Schema
How do I edit specific elements in an image while preserving the original layout and branding?▼

To preserve layout and branding during image edits, use GPT Image 2 to make targeted changes like headline replacement or background swaps while retaining specified subjects, brand marks, and framing. This prevents visual details from drifting during image-to-image generation.

Can I replace embedded text in images with multilingual translations for ad localization?▼

Yes, you can replace embedded text with multilingual translations for ad localization. The tool supports editing headlines, labels, and calls to action in scripts including Japanese, Cyrillic, Arabic, and Chinese while preserving the original photograph and layout.

How do I combine multiple reference images into a single composition?▼

You can combine multiple reference images into a single composition by providing up to 10 publicly accessible HTTPS image URLs. You then assign each image a specific role in the composition using explicit spatial instructions for layout-precise results.

Do I need RunComfy access to perform identity-preserving image edits?▼

Yes, you need authenticated RunComfy access and the RunComfy CLI to perform identity-preserving image edits. You must also provide publicly fetchable HTTPS image URLs and valid GPT Image 2 edit inputs with supported size values.

What are the limitations when repositioning objects or swapping backgrounds in product photos?▼

Limitations for repositioning objects or swapping backgrounds include a maximum of 10 input images per task and the requirement that all images are publicly fetchable HTTPS URLs. Inputs must also conform to supported GPT Image 2 size values.

Related Skills

Explore More Design & Creative Skills→
agentspace-soagentspace-so
31

gpt-image-2

Generate and edit brand-safe images with GPT Image 2 on the RunComfy Model API.

Official
Intermediate
Yona544Yona544
1

social-media-analyzer

Analyze social media campaign performance metrics and ROI across platforms.

Community
Advanced
yangyixxxxyangyixxxx
13

gptnb-image

Generate images, layered assets, and videos via the gptnb.ai middleware API.

Community
Advanced
doany-aidoany-ai
5

flux-kontext

Edit single images with Flux Kontext Pro via RunComfy CLI.

Official
Intermediate