How does masking work for image editing?

Masking (supported by OpenAI) uses a PNG with transparent areas to tell the AI exactly which part of the original image should be modified.

Can I edit existing images using this skill?

Yes, you can use the -i or --input flag to provide source images for editing, style transfer, or targeted transformations using masks.

What are the required API keys?

You need an OPENAI_API_KEY to use the default OpenAI provider and a GEMINI_API_KEY for Google Gemini or Imagen models.

Which AI models are supported for image generation?

This skill supports OpenAI GPT Image 1.5, Google Gemini (Nano Banana/Pro), and Google Imagen 4.0.

Does it support high-resolution image output?

Yes, using the gemini-pro provider, you can generate high-resolution images up to 2048x2048 or 3072x2048.

AI Image Generation

Name: AI Image Generation
Author: mshuffett

bymshuffett

디자인 도구

Generates and edits high-quality visual assets using OpenAI and Google Gemini models directly from the command line.

소개

The Image Generation skill empowers developers to produce high-fidelity visual content, mockups, and illustrations without leaving their terminal. By integrating top-tier providers like OpenAI GPT Image 1.5 and Google Gemini (Nano Banana Pro), it offers versatile capabilities ranging from photorealistic text-to-image generation to advanced image editing with masks and style transfers. It is particularly effective for building design systems, generating UI assets in batch, and creating consistent visual language for software projects.

주요 기능

Support for high-resolution outputs up to 3K (3072x2048) with Gemini Pro
Sophisticated style transfer and multi-image composition capabilities
Advanced image editing using masks and reference images for targeted modifications
Multi-provider support including OpenAI GPT Image 1.5, Google Gemini, and Imagen 4.0
Streamlined batch generation workflows for creating consistent project assets
0 GitHub stars

사용 사례

Generating UI/UX mockups, placeholder assets, and icons for web and mobile applications
Creating consistent visual styles and illustrations for technical documentation and slide decks
Iterating on design systems by applying specific brand colors and styles to generated imagery

소개

주요 기능

Support for high-resolution outputs up to 3K (3072x2048) with Gemini Pro
Sophisticated style transfer and multi-image composition capabilities
Advanced image editing using masks and reference images for targeted modifications
Multi-provider support including OpenAI GPT Image 1.5, Google Gemini, and Imagen 4.0
Streamlined batch generation workflows for creating consistent project assets
0 GitHub stars

사용 사례

Generating UI/UX mockups, placeholder assets, and icons for web and mobile applications
Creating consistent visual styles and illustrations for technical documentation and slide decks
Iterating on design systems by applying specific brand colors and styles to generated imagery