skills.rest
doany-ai
doany-aiOFFICIAL
Explore all skills by this author →
WebsiteGitHub

gpt-image-edit

Edit images via RunComfy's CLI using OpenAI GPT Image 2.

5|2|Updated May 18, 2026
Search Tags:#brand-consistency#identity-preservation#image-edit#gpt-image-2#ai-edit#multilingual-edit#layout-precision
One-click install
npx skills add https://github.com/doany-ai/skills --skill gpt-image-edit-doany-ai
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: gpt-image-edit
Source: https://github.com/doany-ai/skills/tree/main/gpt-image-edit
Command: npx skills add https://github.com/doany-ai/skills --skill gpt-image-edit-doany-ai

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

GPT Image Edit provides targeted, identity-preserving image edits using the GPT Image 2 /edit endpoint on RunComfy. It documents prompting patterns to achieve sharper results and guides usage across multilingual text edits, multi-reference workflows, and layout-accurate changes.

Core Features & Use Cases

  • Multilingual in-image text edits with preserved layout and typography.
  • Identity-preserving edits across branding, headlines, and product visuals.
  • Reference-image guided edits with up to 10 inputs and precise composition.

Quick Start

Provide a primary image URL and a detailed edit prompt to apply the requested transformation.

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 images while preserving identity and brand consistency?▼

You can perform identity-preserving image edits by providing a primary image URL and a detailed edit prompt, ensuring brand consistency across product visuals and headlines without altering core design elements.

Can I edit text inside an image in multiple languages?▼

Yes, multilingual in-image text edits support modifying text while preserving the original layout and typography, allowing precise changes across different languages within the same visual composition.

How do I use reference images to guide layout-accurate edits?▼

Reference-image guided edits accept up to 10 input images to direct precise composition adjustments, applying layout-accurate changes based on the provided visual references and detailed edit prompts.

Do I need RunComfy CLI to apply GPT Image 2 edits?▼

Yes, RunComfy CLI must be installed with a valid account and connectivity to the model API, requiring inputs to conform to the documented schema to execute GPT Image 2 edits successfully.

What are the limitations of AI image editing for layout precision?▼

AI image editing requires inputs conforming to a documented schema and depends on API connectivity, meaning offline access is unsupported and complex multi-reference workflows may need precise prompt engineering to achieve layout precision.

Related Skills

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

image-to-video

Route still images to RunComfy image-to-video models for animated video output.

Official
Intermediate
NinaVerdeNinaVerde

Whisk God

Generate identity-preserving visual assets from Subject, Scene, and Style inputs.

Community
Advanced
runcomfy-comruncomfy-com
12

gpt-image-edit

Edit images via OpenAI GPT Image 2 endpoint using RunComfy CLI.

Official
Intermediate
YangeokYangeok

imagegen

Generate and edit bitmap images using OpenAI GPT Image models.

Community
Advanced