gpt-image-2
GPT Image 2 lets you create images directly from your existing ChatGPT subscription without extra fees or API keys. It supports text-to-image, image editing, style transfer, and multi-reference composition through the local Codex CLI, requiring only a ChatGPT Plus or Pro plan and the CLI installed.
GPT Image 2 generates images using your ChatGPT subscription via the local Codex CLI, with no separate API costs.
AI-generated summary based on this skill's SKILL.md
Decision gist · record as of 2026-04-28
GPT Image 2 generates images using your ChatGPT subscription via the local Codex CLI, with no separate API costs. GPT Image 2 lets you create images directly from your existing ChatGPT subscription without extra fees or API keys. It supports text-to-image, image editing, style transfer, and multi-reference composition through the local Codex CLI, requiring only a ChatGPT Plus or Pro plan and the CLI installed.
Use it when
- GPT Image 2 integrates into agent workflows through the local Codex CLI.
- Yes.
Verify before relying
Read SKILL.md below before installing (7 files). Open directory: indexed for reading, not audited.
Install
agentspace-so/agent-skills/gpt-image-2 · repository language: Shell
Open directory. Skills are indexed for reading, not audited. Review a skill's body before installing it.
Frequently asked questions
AI-generated answers based on this skill's SKILL.md and metadata
Can I generate images with my ChatGPT subscription using gpt-image-2?
Yes. GPT Image 2 lets you generate images directly from your existing ChatGPT Plus or Pro subscription without separate API costs or additional billing. Simply install the Codex CLI and invoke GPT Image 2 to create text-to-image outputs using your current plan.
How do I use GPT Image 2 to create a picture in my agent?
GPT Image 2 integrates into agent workflows through the local Codex CLI. Install the CLI, then invoke GPT Image 2 as a step within your agent to generate images. Your ChatGPT Plus or Pro subscription handles authentication—no separate API keys needed.
Does gpt-image-2 support image editing and style transfer?
Yes. GPT Image 2 supports image-to-image editing with multi-reference composition and style transfer. You can restyle and remix reference images, applying new styles or combining multiple references into a single output, all within your existing ChatGPT subscription.
Can I generate images without an OpenAI API key using gpt-image-2?
Absolutely. GPT Image 2 requires only a ChatGPT Plus or Pro subscription and the Codex CLI installed locally—no separate OpenAI API access or billing is needed. This makes it ideal for users who want image generation without additional costs.
What are the requirements to start using GPT Image 2?
GPT Image 2 requires a ChatGPT Plus or Pro subscription and the Codex CLI installed on your system. Once both are in place, you can invoke text-to-image, image editing, and style-transfer capabilities directly from the CLI or within agent workflows.
SKILL.md
Rendered from the published skill. Quoted content, verbatim.
🪞 GPT Image 2 — Image Generation via Your ChatGPT Subscription
Generate images with GPT Image 2 (ChatGPT Images 2.0) inside your agent, using your existing ChatGPT Plus or Pro subscription — no separate OpenAI access, no Fal or Replicate tokens, no per-image billing.
Text-to-image, image-to-image editing, style transfer, and multi-reference composition.
(truncated - see the full file via the links below)
File tree — 7 files
gpt-image-2/SKILL.md
gpt-image-2/gallery/a-poster.png
gpt-image-2/gallery/c1-logo.png
gpt-image-2/gallery/c2-tshirt.png
gpt-image-2/gallery/d-ukiyoe.png
gpt-image-2/scripts/extract_image.py
gpt-image-2/scripts/gen.sh
Let your AI agent find skills like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 56,283 agent skills by what they can do, searchable in plain language.
wish › “Generate images using existing ChatGPT Plus/Pro subscription without separate API costs”
Give your agent the search over MCP, or paste the wish link into any chat. No install? Search from any chat →
Related skills
Create and edit images using RunComfy's CLI with access to over a dozen AI models including FLUX 2, Google Nano Banana, OpenAI GPT Image 2, ByteDance Seedream, and others. The skill intelligently routes your request to the right model based on your intent—whether you need photoreal portraits, fast iteration, precise typography, or open-weights workflows—and provides the exact command to run.
GPT Image 2 turns text prompts into photorealistic visuals with exceptional text accuracy—ideal for posters, product mockups, and branded designs. The skill supports multiple models and resolutions up to 4K, plus image-to-image editing for refinement and variation.
Create images from text prompts or edit existing ones using OpenAI's gpt-image-2 model through AceDataCloud's API. The skill excels at compositing real assets like logos and QR codes into scenes while preserving their fidelity, and renders legible text directly in images.
This skill transforms your image concept into production-ready prompts for GPT-image-2, Gemini 3 Pro Image, and Midjourney v8.1 in a single workflow. It guides you through preset selection (product, portrait, illustration, landscape), targeted refinement questions, and aspect ratio choices—then maps your answers to each model's native format with recommended parameters and text-rendering rules.
This skill harnesses OpenAI's GPT Image 1.5 model to generate new images from text descriptions or edit existing images with precise control. It supports multiple output sizes and quality levels, with optional mask-based inpainting for targeted edits.
This skill harnesses the gpt-image-2-all model through API Yi's domestic proxy to create, modify, and merge images from natural language prompts. It supports text-to-image generation, single-image editing, multi-image blending, and style transformation—all at a flat $0.03 per image, with output typically ready in 60–300 seconds and native Chinese prompt support.