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

gpt-image-2

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

5|2|Updated May 18, 2026
Search Tags:#branding#image-generation#generate#text-rendering#ui-mockups#gpt-image-2#runcomfy
One-click install
npx skills add https://github.com/doany-ai/skills --skill gpt-image-2-doany-ai
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: gpt-image-2
Source: https://github.com/doany-ai/skills/tree/main/gpt-image-2
Command: npx skills add https://github.com/doany-ai/skills --skill gpt-image-2-doany-ai

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

GPT Image 2 solves the challenge of producing and refining brand-safe images with embedded text, logos, and multilingual typography while preserving composition through edits.

Core Features & Use Cases

  • Text-to-image and edit endpoints via the RunComfy CLI for deterministic image generation.
  • Three fixed output sizes (1024x1024, 1024x1536, 1536x1024) with an edit-preservation workflow to maintain subject and layout.
  • Strong text rendering for embedded text, branding, and multilingual typography, plus routing guidance to sibling models when specialized needs arise (Flux 2, Nano Banana Pro, Seedream).
  • Clear prompts, lightweight integration with existing product design workflows, and ready-to-use UI mockups and marketing visuals.

Quick Start

Run the RunComfy CLI to generate an image with openai/gpt-image-2/text-to-image or edit an existing image with openai/gpt-image-2/edit.

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 product images with embedded text and logos?▼

Generate product images with embedded text and logos by using the RunComfy CLI to access the openai/gpt-image-2/text-to-image endpoint, ensuring strong multilingual typography and layout fidelity for brand-safe marketing visuals.

Can I edit existing marketing visuals without losing the original composition?▼

Edit existing marketing visuals without losing the original composition by using the openai/gpt-image-2/edit endpoint, which features an edit-preservation workflow to maintain the subject and layout during refinements.

What output sizes are supported for UI mockups and signage?▼

Output sizes supported for UI mockups and signage include three fixed dimensions: 1024x1024, 1024x1536, and 1536x1024, providing deterministic layout fidelity for various product photography and marketing visual formats.

Does GPT Image 2 work with RunComfy CLI for text-to-image generation?▼

GPT Image 2 works directly with the RunComfy CLI for text-to-image generation, applying to product photography and UI mockups where precise text rendering and layout fidelity matter.

When should I use other image generation models instead of GPT Image 2?▼

Use other image generation models instead of GPT Image 2 when specialized needs arise, routing to sibling models like Flux 2, Nano Banana Pro, or Seedream for requirements beyond brand-safe multilingual typography and composition preservation.

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
DexterJieDexterJie

imagegen

Generate and edit AI bitmap images using the OpenAI API.

Community
Advanced
addisonkaddisonk
1

generating-images-with-fal

Generate images, icons, and visual assets using fal.ai models.

Community
Intermediate
gooseworks-aigooseworks-ai
6

create-image-gpt-image-fal

Generate photorealistic or designed images via OpenAI gpt-image on fal.ai.

Official
Advanced