gpt-image-2 — Skills — getagentictools

What it does

Use generations for public text-to-image calls.

Use edits for multipart image edits and mask uploads.

Use responses for advanced flows: streaming, mixed text + image input, previousresponseid, toolchoice, action, and optional toolmodel.

Process environment variables override .env; CLI flags override both.

Never print secrets.

--output takes either a single path or a pattern such as image-{index}.png for multi-image or streaming flows.

responses uses a top-level Responses model separate from the image model; default it to gpt-5.4 unless you need another text-capable model.

Requirements & configuration

7. Add --save-response <path> when the raw JSON body or SSE event stream needs to be kept for debugging.

responses uses a top-level Responses model separate from the image model; default it to gpt-5.4 unless you need another text-capable model.

quality on Responses tool flows is passed through, but final behavior still depends on the hosted image tool.

Configuration: OPENAI_BASE_URL

Full OpenAI-compatible GPT Image 2 API coverage with text-to-image, edits, and streaming responses.

Source

Repository: https://github.com/gargantuax/openskills

gpt-image-2 FAQ

What does the gpt-image-2 skill do?

Full OpenAI-compatible GPT Image 2 coverage across images/generations, images/edits, and responses with the image_generation tool. Use when the one-shot image helper is not enough - text-to-image, mask edits, multi-image batches, streaming, partial_images, and mixed text+image Responses flows. Reads .env and respects process environment variables; works with any OpenAI-compatible gateway. Use generations for public text-to-image calls. Use edits for multipart image edits and mask uploads.

What does gpt-image-2 require?

7. Add --save-response <path> when the raw JSON body or SSE event stream needs to be kept for debugging. responses uses a top-level Responses model separate from the image model; default it to gpt-5.4 unless you need another text-capable model. quality on Responses tool flows is passed through, but final behavior still depends on the hosted image tool. Configuration keys: OPENAI_BASE_URL.

How do I install gpt-image-2?

Run: npx -y skills add https://github.com/gargantuax/openskills --skill gpt-image-2 --agent claude-code — the source lives at github.com/gargantuax/openskills.

Maintain gpt-image-2?

Let people know it's listed here — add the badge (live metrics, light/dark aware) or a plain link to your README or docs.

[![gpt-image-2 on getagentictools](https://getagentictools.com/badge/skills/gargantuax-openskills-gpt-image-2.svg)](https://getagentictools.com/skills/gargantuax-openskills-gpt-image-2?ref=badge)

npx agentictools info skills/gargantuax-openskills-gpt-image-2

The second line is the CLI lookup for this page — handy in READMEs and docs.