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

gpt-image-2

Generate and edit images with embedded text using text prompts and reference images.

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

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill helps users generate and edit polished images with accurate embedded text, logos, multilingual typography, and precise composition without managing a direct OpenAI API integration.

Core Features & Use Cases

  • Text-to-Image Generation: Create product photography, advertisements, signage, posters, packaging mockups, UI concepts, and scientific illustrations.
  • Image Editing: Modify backgrounds, layouts, lighting, headlines, and other visual attributes while preserving identity, composition, branding, and framing.
  • Precision Prompting: Support fixed output sizes, quoted text, compositional cues, iterative refinement, and multi-image editing with up to 10 reference URLs.
  • Use Case: Create a multilingual e-commerce product hero image with a branded label, or update an existing campaign image while preserving the product and typography.

Quick Start

Ask the GPT Image 2 skill to generate or edit an image with your desired subject, composition, embedded text, output size, and preservation requirements.

Frequently Asked Questions about gpt-image-2

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

FAQPage Schema
How do I generate images with accurate embedded text and multilingual typography?▼

To generate images with accurate embedded text and multilingual typography, you provide text prompts specifying your desired subject, quoted embedded text, and composition. The Skill outputs polished visuals suitable for advertising, signage, and packaging mockups.

Can I edit existing product photography while preserving branding and framing?▼

Yes, you can edit existing product photography by providing up to 10 publicly fetchable HTTPS reference URLs. The Skill modifies backgrounds, lighting, and layouts while preserving the original identity, composition, branding, and framing.

Do I need RunComfy CLI to generate text-rich product mockups and UI concepts?▼

Yes, generating text-rich product mockups and UI concepts requires the RunComfy CLI, authenticated RunComfy access, and supported endpoint schemas. These prerequisites allow the Skill to process your text prompts and reference images.

What are the size limitations for image generation and editing?▼

Image generation is limited to three fixed output sizes, while image editing auto-preserves the original image sizing. You must specify one of these fixed generation sizes or rely on auto-preserved edit sizing when submitting prompts.

Why does image editing require publicly fetchable HTTPS reference URLs?▼

Image editing requires publicly fetchable HTTPS reference URLs so the RunComfy endpoint schemas can fetch and process your up to 10 reference images. This ensures accurate preservation of identity, composition, and typography during modifications.

Related Skills

Explore More Design & Creative Skills→
prime-skillsprime-skills
31

gpt-image-edit

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

Official
Advanced
quanganh208quanganh208

ck:media-processing

Process media files for encoding, conversion, filtering, thumbnails, and AI background removal.

Community
Advanced
doany-aidoany-ai
5

gpt-image-2

Generate and edit images via RunComfy CLI endpoints with fixed output sizes.

Official
Advanced
m0atm0at
1

generate-image

Generate and edit images using OpenRouter AI models.

Community
Intermediate