openai-image-cli

What This Skill Does

The openai-image-cli skill provides a powerful command-line interface for interacting with OpenAI's image generation models. It enables users to generate high-fidelity images from natural language prompts, perform advanced in-painting and editing on existing image files, and create aesthetic variations of source imagery. The skill supports multiple model tiers, ranging from the high-quality gpt-image-1.5 to cost-effective mini versions, and offers granular control over output dimensions, file formats, and moderation settings directly through the terminal.

Installation

To integrate this skill into your OpenClaw environment, execute the following installation command in your terminal:

clawhub install openclaw/skills/skills/g9pedro/openai-image-cli

Ensure you have configured your OpenAI API credentials via the environment variable OPENAI_API_KEY or by running openai-image config set api-key <your-key> before attempting to run generation commands.

Use Cases

This skill is perfect for developers, designers, and creative professionals who need to streamline their image creation workflow. Use it for generating rapid prototypes of UI assets, creating custom social media graphics, editing photos through natural language, or batch-processing image variations for A/B testing campaigns. Its ability to handle masking for inpainting makes it particularly useful for removing objects from photos or inserting new elements into existing scenes.

Example Prompts

1. "OpenAI Image CLI, generate a photorealistic image of a vintage coffee shop interior in London with soft morning light, sized for a landscape header."
2. "Use the edit command on profile.png to remove the background and replace it with a clean solid navy blue, then save the result as a PNG."
3. "Take the logo.png file and generate 4 variations that explore different color palettes while maintaining the original geometry."

Tips & Limitations

• Model Deprecation: Note that both DALL-E 2 and DALL-E 3 are scheduled for deprecation in May 2026. Prioritize using gpt-image-1.5 for all future-proof projects.
• Quality vs. Cost: Use gpt-image-1-mini for draft work to conserve your API credit balance, reserving the higher-quality models for final assets.
• File Formats: While the tool supports various formats, ensure you specify the correct compression levels when using JPEG or WEBP to balance file size against visual clarity.
• Masking: When using the --mask option for editing, ensure the mask image is the exact same resolution as the base image for the best alignment results.