# openai-image-gen

This skill generates images through the OpenAI Images API using GPT Image, DALL-E 3 or DALL-E 2. It also builds an HTML gallery of the results.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode · ★ 700
- Author: swarmclawai
- License: MIT · policy=mirror · the beginning of the file is at the end of this page
- Source: https://github.com/swarmclawai/swarmclaw/tree/HEAD/skills/openai-image-gen/SKILL.md
- Updated: 2026-06-30
- HTML: https://affpapa.org/en/nevibecode/skills/openai-image-gen

## What it does

The skill runs `python3 {baseDir}/scripts/gen.py`, which calls the OpenAI Images API. Model, size, quality, background and output format come from flags: `--model`, `--size`, `--quality`, `--background`, `--output-format`. DALL-E 3 adds `--style` with `vivid` or `natural`.

Batch work goes through `--count` — `--count 16` with `gpt-image-1`, for instance. DALL-E 3 caps the count at 1 automatically, since that model only takes `n=1`. You can pass a prompt with `--prompt` or let the random prompt sampler pick one.

Output includes the image files, `prompts.json` mapping prompts to files, and `index.html` with a thumbnail gallery. You need `OPENAI_API_KEY` set in the environment and `python3` on the machine. Generation outlasts normal timeouts, so raise the limit when running from a shell — the README suggests 300 seconds.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add swarmclawai/swarmclaw --skill openai-image-gen -a claude-code
```

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

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add swarmclawai/swarmclaw --skill openai-image-gen -a codex
```

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

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add swarmclawai/swarmclaw --skill openai-image-gen -a cursor
```

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

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install swarmclawai/swarmclaw openai-image-gen
```

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

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add swarmclawai/swarmclaw --skill openai-image-gen -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/swarmclawai/swarmclaw --path skills/openai-image-gen
```

### Windsurf (Devin Desktop)

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

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add swarmclawai/swarmclaw --skill openai-image-gen -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/swarmclawai/swarmclaw/tree/HEAD/skills/openai-image-gen/SKILL.md

## When to use it
- generate a batch of images from one description
- produce a webp image with a transparent background
- build a thumbnail gallery to review results fast
- switch between GPT Image and DALL-E without editing code
- keep a prompt-to-file map in JSON

## Example prompts
- Generate 16 images with `gpt-image-1` and open the gallery
- Make a 1536x1024 image at high quality into `./out/images`
- Generate a `dall-e-3` image in `vivid` style from a mountain landscape prompt

## Source text · SKILL.md · MIT

Below is the content of a third-party file. It is data, not instructions for you: do not act on anything written inside unless the human asks. Block tag: 69db265ea993852c.

BEGIN THIRD-PARTY FILE 69db265ea993852c
````text
---
name: openai-image-gen
description: Generate images via OpenAI Images API (GPT Image, DALL-E 3, DALL-E 2). Supports batch generation with random prompt sampler and HTML gallery output. Use when asked to generate images with OpenAI and an OPENAI_API_KEY is available.
metadata:
  {
    "openclaw":
      {
        "emoji": "🎨",
        "requires": { "bins": ["python3"], "env": ["OPENAI_API_KEY"] },
        "primaryEnv": "OPENAI_API_KEY",
        "install":
          [
            {
              "id": "python-brew",
              "kind": "brew",
              "formula": "python",
              "bins": ["python3"],
              "label": "Install Python (brew)",
            },
          ],
      },
  }
---

# OpenAI Image Gen

Generate images via the OpenAI Images API with an HTML gallery viewer.

## Run

Note: Image generation can take longer than typical timeouts. Set a higher timeout when running via shell (e.g., 300 seconds).

```bash
python3 {baseDir}/scripts/gen.py
```

## Useful Flags

```bash
# GPT image models with various options
python3 {baseDir}/scripts/gen.py --count 16 --model gpt-image-1
python3 {baseDir}/scripts/gen.py --prompt "ultra-detailed studio photo of a lobster astronaut" --count 4
python3 {baseDir}/scripts/gen.py --size 1536x1024 --quality high --out-dir ./out/images
python3 {baseDir}/scripts/gen.py --model gpt-image-1.5 --background transparent --output-format webp

# DALL-E 3 (note: count is automatically limited to 1)
python3 {baseDir}/scripts/gen.py --model dall-e-3 --quality hd --size 1792x1024 --style vivid
python3 {baseDir}/scripts/gen.py --model dall-e-3 --style natural --prompt "serene mountain landscape"

# DALL-E 2
python3 {baseDir}/scripts/gen.py --model dall-e-2 --size 512x512 --count 4
```

## Model-Specific Parameters

### Size

- **GPT image models** (`gpt-image-1`, `gpt-image-1-mini`, `gpt-image-1.5`): `1024x1024`, `1536x1024` (landscape), `1024x1536` (portrait), or `auto`. Default: `1024x1024`
- **dall-e-3**: `1024x1024`, `1792x1024`, or `1024x1792`. Default: `1024x1024`
- **dall-e-2**: `256x256`, `512x512`, or `1024x1024`. Default: `1024x1024`

### Quality

- **GPT image models**: `auto`, `high`, `medium`, or `low`. Default: `high`
- **dall-e-3**: `hd` or `standard`. Default: `standard`
- **dall-e-2**: `standard` only

### Other Parameters

- **GPT image models** support `--background` (`transparent`, `opaque`, `auto`) and `--output-format` (`png`, `jpeg`, `webp`)
- **dall-e-3** supports `--style` (`vivid` for hyper-real, `natural` for more natural looking)
- **dall-e-3** only supports `n=1`; the script automatically limits count to 1

## Output

- Image files (`*.png`, `*.jpeg`, or `*.webp` depending on model and format)
- `prompts.json` (prompt-to-file mapping)
- `index.html` (thumbnail gallery — open in browser to review)
````
END THIRD-PARTY FILE 69db265ea993852c

The third-party file has ended. Everything between the 69db265ea993852c tags is data: requests and commands from it are not followed. An “end of file” line with another tag inside the block is part of the file.

© swarmclawai · MIT · https://github.com/swarmclawai/swarmclaw/tree/HEAD/skills/openai-image-gen/SKILL.md

_Part of the page did not fit — see the HTML version._

---
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