# gpt-image-v2

gpt-image-v2 is a Claude Code skill for creating and editing images through EachLabs with GPT Image v2 models.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode, Windsurf (Devin Desktop), Claude.ai · 169 installs · ★ 48 repo stars
- Author: eachlabs
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/eachlabs/skills/tree/HEAD/skills/gpt-image-v2/SKILL.md
- Updated: 2026-10-07
- Security check: automated, 2026-11-16 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/skills/gpt-image-v2

## What it does

The gpt-image-v2 skill sends requests to the EachLabs Predictions API and returns image outputs from `gpt-image-v2-text-to-image` or `gpt-image-v2-edit`. One model creates an image from a prompt; the other applies an instruction to an existing image while preserving selected details.

Its flow covers model-schema lookup, prediction creation, and status checks through polling or a webhook. It requires the `EACHLABS_API_KEY` environment variable. Image inputs must use public HTTPS URLs, so `localhost` and data URIs cannot be used.

The key is sent in the `X-API-Key` header. Results come from the `output` array, while failed requests expose `message` and `details`.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add eachlabs/skills --skill gpt-image-v2 -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/gpt-image-v2/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/gpt-image-v2/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add eachlabs/skills --skill gpt-image-v2 -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/gpt-image-v2/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add eachlabs/skills --skill gpt-image-v2 -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/gpt-image-v2/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install eachlabs/skills skills/gpt-image-v2
```

2. **Manually: put the files in place**
- File: `.github/skills/gpt-image-v2/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add eachlabs/skills --skill gpt-image-v2 -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/eachlabs/skills --path skills/gpt-image-v2
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/gpt-image-v2/SKILL.md` — The legacy .windsurf/skills/ path still works

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add eachlabs/skills --skill gpt-image-v2 -a opencode
```

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/eachlabs/skills/tree/HEAD/skills/gpt-image-v2/SKILL.md

## When to use it
- create an image from a text prompt
- replace the background of an existing image
- preserve a product label and camera angle during an edit
- retrieve a prediction result through polling or a webhook

## Example prompts
- Create a product poster with exact wording and specified typography through GPT Image v2.
- Edit `product.jpg` by replacing its background while keeping the label and camera angle unchanged.
- Look up the schema for `gpt-image-v2-edit`, create the prediction, and wait for its webhook result.

## Similar
- [gpt-image-skill](https://affpapa.org/en/nevibecode/skills/gpt-image-skill.md) — skill · 156 installs
- [gpt-image-2](https://affpapa.org/en/nevibecode/skills/acedatacloud-gpt-image-2.md) — skill · 219 installs
- [gpt-image](https://affpapa.org/en/nevibecode/skills/gpt-image.md) — skill · 14600 installs
- [scenario-gpt-image](https://affpapa.org/en/nevibecode/skills/scenario-gpt-image.md) — skill · 877 installs
- [ideogram-image](https://affpapa.org/en/nevibecode/skills/ideogram-image.md) — skill · 137 installs
- [gpt-image-edit](https://affpapa.org/en/nevibecode/skills/gpt-image-edit.md) — skill · 447000 installs

From the same set: [eachlabs/skills](https://affpapa.org/en/nevibecode/by/eachlabs/skills.md) — 102 cards

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
