image-generation

Generate images from text prompts via SDK or CLI with multiple output sizes.

Updated Apr 7, 2026
One-click install
npx skills add https://github.com/felipesantiago-coder/fluxo-quadra --skill image-generation-felipesantiago-coder
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: image-generation
Source: https://github.com/felipesantiago-coder/fluxo-quadra/tree/main/skills/image-generation
Command: npx skills add https://github.com/felipesantiago-coder/fluxo-quadra --skill image-generation-felipesantiago-coder

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires z-ai-web-dev-sdk, and includes scripts (resource) components.

What problem does it solve?

Creating custom visual content manually is time-consuming and often requires professional design skills. This Skill eliminates that barrier by letting you generate high-quality images, artwork, and design assets directly from text descriptions, no design expertise needed.

Core Features & Use Cases

  • Text-to-Image Generation: Create high-quality images from detailed text prompts using the z-ai-web-dev-sdk, with support for 7 different output sizes for any use case.
  • Dual Access Methods: Use the programmatic SDK for backend application integration or the built-in CLI tool for quick command-line image generation without writing code.
  • Production-Ready Patterns: Includes examples for batch generation, caching to avoid redundant API calls, error handling with retries, and a ready-to-use Express.js API endpoint for web applications.
  • Common Use Cases: Generate website hero images, marketing graphics, product mockups, blog illustrations, social media content, and brand assets like logos.

Quick Start

Use the image-generation skill to generate a 1440x720 modern tech office hero banner and save it to ./hero.png.

Frequently Asked Questions about image-generation

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

FAQPage Schema
How do I generate custom images from text prompts in a backend application?

Text-to-image generation in a backend application is enabled through the z-ai-web-dev-sdk, allowing you to programmatically create visual assets from detailed descriptions. The skill supports base64 image decoding and 7 different output sizes for various development needs.

Can I generate AI artwork from the command line without writing code?

Yes, AI artwork generation is possible directly from the command line using the built-in CLI tool. This allows for quick image creation workflows from text prompts without needing to write or execute programmatic code.

What is the best way to handle batch generation of marketing graphics?

Batch generation of marketing graphics is best handled using the included production-ready patterns, which feature caching to avoid redundant API calls and error handling with retries. These patterns ensure reliable bulk asset creation for production environments.

Does this text-to-image tool provide an API endpoint for web applications?

Yes, the text-to-image tool provides a ready-to-use Express.js API endpoint for web applications. This allows you to easily integrate image generation capabilities into your web services and frontend workflows.

What output sizes are supported for generating website hero images?

Website hero images and other visual content can be generated in 7 different supported output sizes. This variety ensures you can create appropriately scaled assets for any website layout or marketing material requirement.