Skip to content
Back to skills

Chatgpt Imagegen

ASecurity

Generates or edits raster images through OpenAI's Image API. Use for text-to-image work, reference-based edits, masks, transparent assets, and product or editorial visuals.

  • 5 stars
  • 0 votes
  • 1 copy
  • 12 views
  • Added September 10, 2026
ai-agentspythongobashapi

Works with

  • cli
  • api

Security analysis

A96/100
  • mediumInstalls packages at runtime which could introduce malicious dependencies

Pro scans all 4 files and shows the line behind each finding

Scanned October 5, 2026

npx -y skills add iurysza/agent-skills --skill chatgpt-imagegen --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Chatgpt Imagegen?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Chatgpt Imagegen
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/iurysza-chatgpt-imagegen/badge)](https://www.skillsdirectory.com/skills/iurysza-chatgpt-imagegen)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: chatgpt-imagegen
description: Generates or edits raster images through OpenAI's Image API. Use for text-to-image work, reference-based edits, masks, transparent assets, and product or editorial visuals.
compatibility: Requires Python 3.10+, openai 2.16+, network access, and an OpenAI API key.
metadata:
  category: visual-media
---

# ChatGPT Image Generation

Use the bundled `chatgpt-img` CLI for generation and edits. Resolve its path relative to this `SKILL.md`.

## Setup

```bash
python3 -m pip install -r <skill-directory>/requirements.txt
export OPENAI_API_KEY='...'
```

`OPENCODE_OPENAI_API_KEY` is accepted as a fallback. `CHATGPT_IMAGE_DEFAULT` overrides the default model.

Image requests cost money. Confirm scope before generating many images or using high quality repeatedly.

## Generate

```bash
<skill-directory>/scripts/chatgpt-img \
  'A linocut illustration of a lighthouse in heavy rain' \
  ./lighthouse.png \
  --size 1536x1024 \
  --quality high
```

## Edit

Single reference:

```bash
<skill-directory>/scripts/chatgpt-img edit \
  ./portrait.png \
  'Use warm editorial lighting; preserve identity, pose, and clothing' \
  ./portrait-edited.png \
  --quality high
```

Multiple references:

```bash
<skill-directory>/scripts/chatgpt-img \
  --input ./portrait.png \
  --input ./moodboard.png \
  'Apply the moodboard lighting and palette while preserving the portrait identity' \
  ./portrait-styled.png
```

Optional masked edit:

```bash
<skill-directory>/scripts/chatgpt-img edit \
  ./input.png \
  'Replace the masked background with a cloudy coastline' \
  ./output.png \
  --mask ./mask.png
```

## Important options

- `--model`: defaults to `gpt-image-2.5-sunburst`, the newest model. It accepts `--background transparent`. `gpt-image-2` rejects transparent backgrounds, so pass `--model gpt-image-2` only when you need it
- `--size`: supported dimensions or `auto`
- `--quality`: GPT Image uses `auto`, `low`, `medium`, or `high`
- `--background`: `auto`, `transparent`, or `opaque`
- `--format`: `png`, `jpeg`, or `webp`
- `--compression`: `0` through `100` for JPEG/WebP
- `--num`: number of outputs
- `--input`: repeatable reference image for edit mode
- `--mask`: optional edit mask
- `--input-fidelity`: supported by selected older GPT Image models, not `gpt-image-2`

Use `--help` and `edit --help` for the complete interface.

## Prompting edits

State both the change and the invariants. For example, name the identity, geometry, text, logos, pose, camera angle, or materials that must remain unchanged. Describe lighting, palette, composition, and finish positively instead of relying on long negative lists.

## Verification

1. Check the process exit status.
2. Confirm every expected output file exists and is non-empty.
3. Report exact paths and any revised prompt returned by the API.
4. Inspect the image with an available viewer when visual verification is part of the task.

Never expose API keys. Error output may include safe request metadata, but it must not include prompt contents or credentials.

Files in this skill

  • SKILL.md2.8 KB
  • requirements.txt18 B
  • scripts/chatgpt-img455 B
  • scripts/generate_image.py18.2 KB

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

View all in ai-agents →

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.