skills.rest
revfactory
revfactoryCOMMUNITY
Explore all skills by this author →
GitHub

gpt-image2

Generate and edit images with the gpt-image-2 model via Image and Responses APIs.

68|29|Updated Jan 26, 2026
Search Tags:#streaming#image-generation#image-editing#masking#responses-api#multi-reference#gpt-image-2
One-click install
npx skills add https://github.com/revfactory/skills --skill gpt-image2
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: gpt-image2
Source: https://github.com/revfactory/skills/tree/main/gpt-image2
Command: npx skills add https://github.com/revfactory/skills --skill gpt-image2

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires openai, Pillow, and includes scripts (resource) and references (resource) components.

What problem does it solve?

Generate a reliable, model-fixed pipeline for high-fidelity image generation and editing using the gpt-image-2 model, enabling designers and creators to produce logos, product mockups, infographics, and photorealistic art with precision.

Core Features & Use Cases

  • Fixed model: gpt-image-2 for high-resolution outputs up to 3840px on a side, with strong text rendering and asset preservation.
  • Supports two workflows: Image API for generation/editing and Responses API for multi-turn refining, including masking and multi-reference composites.
  • Streaming support to receive partial images during generation for better UX.
  • Includes a CLI helper (scripts/generate_image.py) and a reference API guide (references/api_reference.md).

Quick Start

Generate a high-quality image using gpt-image-2 by providing a clear prompt.

Frequently Asked Questions about gpt-image2

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

FAQPage Schema
How do I generate high-resolution images up to 3840px with precise text rendering?▼

Generate high-resolution images using the gpt-image-2 model, which supports outputs up to 3840px on a side with strong text rendering. You can produce logos and photorealistic art by providing clear prompts with explicit size and quality controls.

Can I edit specific areas of an existing image using masking and multi-reference composites?▼

Yes, image editing with masking is fully supported for multi-reference compositions. You can use the Image API workflow to apply masks and preserve specific assets while editing, or the Responses API for multi-turn refining of composite images.

Does this image generation pipeline work with Python and what dependencies are required?▼

The pipeline requires Python with the openai and Pillow dependencies installed. It includes a CLI helper script for direct generation tasks and a reference API guide to help you integrate both Image API and Responses API workflows.

What are the limitations when using gpt-image-2 for iterative product mockups and infographics?▼

Limitations include explicit moderation controls that may restrict certain content generation. For iterative product mockups, use the Responses API for multi-turn refining, as the fixed gpt-image-2 model requires precise prompts and careful masking to preserve assets correctly.

Related Skills

Explore More Design & Creative Skills→
sentientspritesentientsprite

openai-image-gen

Generate images from text prompts using the OpenAI Images API.

Community
Intermediate
michaelvolzmichaelvolz

gemini-imagegen

Generate and edit images from text prompts via Gemini API endpoints.

Community
Intermediate
tercumantanumuttercumantanumut
167

imagegen

Automate image generation and editing via the OpenAI Image API.

Community
Advanced
wwloreywwlorey

generate-image

Generate or modify images using OpenAI GPT Image models.

Community
Advanced