image-gen

Generate images via OpenAI, Google, and DashScope APIs with text prompts.

4|1|Updated Mar 14, 2026
One-click install
npx skills add https://github.com/GPTtang/skill-atlas --skill image-gen-gpttang
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: image-gen
Source: https://github.com/GPTtang/skill-atlas/tree/main/skills/document/image-gen
Command: npx skills add https://github.com/GPTtang/skill-atlas --skill image-gen-gpttang

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill allows users to generate images using various AI models and APIs, simplifying the process of creating visual content.

Core Features & Use Cases

  • Multi-API Support: Integrates with OpenAI, Google (Gemini/Imagen), and DashScope (Aliyun).
  • Customization: Supports aspect ratios, image sizes, and quality presets.
  • Reference Images: Enables image generation based on provided reference images (for supported providers).
  • Use Case: Create a unique illustration for a blog post about space exploration by providing a text prompt and specifying a 16:9 aspect ratio.

Quick Start

Generate an image of a cat with the prompt "A fluffy cat sitting on a windowsill" and save it as "cat.png".

Frequently Asked Questions about image-gen

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I generate AI images from text using multiple APIs?

To generate AI images from text, this Skill sends prompts to OpenAI, Google Gemini, or DashScope APIs. It supports aspect ratio customization and outputs the generated visual content file.

Can I use a reference image for AI art generation with OpenAI or Google Gemini?

Yes, you can use a reference image for AI art generation with supported providers. The Skill enables image generation based on provided reference images to guide the visual output alongside your text prompt.

Do I need API keys to generate text-to-image content with DashScope and OpenAI?

Yes, you need API keys to generate text-to-image content. The Skill requires API keys for OpenAI, Google, and DashScope services, which can be configured via environment variables or an EXTEND.md file.

How do I configure default aspect ratios and image sizes for AI image generation?

You configure default aspect ratios and image sizes for AI image generation by setting environment variables or creating an EXTEND.md file. This allows you to define default settings for quality presets and dimensions.

What are the limitations of generating images with different AI art APIs?

Limitations of generating images with different AI art APIs include provider-specific support for reference images and varying quality presets. You must ensure you have valid API keys and configure settings correctly for each specific service.