/image-generation

name: image-generation
description: Implement AI image generation capabilities using the z-ai-web-dev-sdk. Use this skill when the user needs to create images from text descriptions, generate visual content, create artwork, design assets, or build applications with AI-powered image creation. Supports multiple image sizes and returns base64 encoded images. Also includes CLI tool for quick image generation.
license: MIT

Image Generation Skill

This skill guides the implementation of image generation functionality using the z-ai-web-dev-sdk package and CLI tool, enabling creation of high-quality images from text descriptions.

Skills Path

**Skill Location**: `{project_path}/skills/image-generation`

this skill is located at above path in your project.

**Reference Scripts**: Example test scripts are available in the `{Skill Location}/scripts/` directory for quick testing and reference. See `{Skill Location}/scripts/image-generation.ts` for a working example.

Overview

Image Generation allows you to build applications that create visual content from text prompts using AI models, enabling creative workflows, design automation, and visual content production.

**IMPORTANT**: z-ai-web-dev-sdk MUST be used in backend code only. Never use it in client-side code.

Prerequisites

The z-ai-web-dev-sdk package is already installed. Import it as shown in the examples below.

Basic Image Generation

Simple Image Creation

import ZAI from 'z-ai-web-dev-sdk';
import fs from 'fs';

async function generateImage(prompt, outputPath) {
  const zai = await ZAI.create();

  const response = await zai.images.generations.create({
    prompt: prompt,
    size: '1024x1024'
  });

  const imageBase64 = response.data[0].base64;
  
  // Save image
  const buffer = Buffer.from(imageBase64, 'base64');
  fs.writeFileSync(outputPath, buffer);
  
  console.log(`Image saved to ${outputPath}`);
  return outputPath;
}

// Usage
await generateImage(
  'A cute cat playing in the garden',
  './cat_image.png'
);

Multiple Image Sizes

import ZAI from 'z-ai-web-dev-sdk';
import fs from 'fs';

// Supported sizes
const SUPPORTED_SIZES = [
  '1024x1024',  // Square
  '768x1344',   // Portrait
  '864x1152',   // Portrait
  '1344x768',   // Landscape
  '1152x864',   // Landscape
  '1440x720',   // Wide landscape
  '720x1440'    // Tall portrait
];

async function generateImageWithSize(prompt, size, outputPath) {
  if (!SUPPORTED_SIZES.includes(size)) {
    throw new Error(`Unsupported size: ${size}. Use one of: ${SUPPORTED_SIZES.join(', ')}`);
  }

  const zai = await ZAI.create();

  const response = await zai.images.generations.create({
    prompt: prompt,
    size: size
  });

  const imageBase64 = response.data[0].base64;
  const buffer = Buffer.from(imageBase64, 'base64');
  fs.writeFileSync(outputPath, buffer);

  return {
    path: outputPath,
    size: size,
    fileSize: buffer.length
  };
}

// Usage - Different sizes
await generateImageWithSize(
  'A beautiful landscape',
  '1344x768',
  './landscape.png'
);

await generateImageWithSize(
  'A portrait of a person',
  '768x1344',
  './portrait.png'
);

CLI Tool Usage

The z-ai CLI tool provides a convenient way to generate images directly from the command line.

Basic CLI Usage

# Generate image with full options
z-ai image --prompt "A beautiful landscape" --output "./image.png"

# Short form
z-ai image -p "A cute cat" -o "./cat.png"

# Specify size
z-ai image -p "A sunset" -o "./sunset.png" -s 1344x768

# Portrait orientation
z-ai image -p "A portrait" -o "./portrait.png" -s 768x1344

CLI Use Cases

# Website hero image
z-ai image -p "Modern tech office with diverse team collaborating" -o "./hero.png" -s 1440x720

# Product image
z-ai image -p "Sleek smartphone on minimalist desk, professional product photography" -o "./product.png" -s 1024x1024

# Blog post illustration
z-ai image -p "Abstract visualization of data flowing through networks" -o "./blog_header.png" -s 1344x768

# Social media content
z-ai image -p "Vibrant illustration of community connection" -o "./social.png" -s 1024x1024

# Website favicon/logo
z-ai image -p "Simple geometric logo with blue gradient, minimal design" -o "./logo.png" -s 1024x1024

# Background pattern
z-ai image -p "Subtle geometric pattern, pastel colors, website background" -o "./bg_pattern.png" -s 1440x720

Advanced Use Cases

Batch Image Generation

import ZAI from 'z-ai-web-dev-sdk';
import fs from 'fs';
import path from 'path';

async function generateImageBatch(prompts, outputDir, size = '1024x1024') {
  const zai = await ZAI.create();

  // Ensure output directory exists
  if (!fs.existsSync(outputDir)) {
    fs.mkdirSync(outputDir, { recursive: true });
  }

  const results = [];

  for (let i = 0; i < prompts.length; i++) {
    try {
      const prompt = prompts[i];
      const filename = `image_${i + 1}.png`;
      const outputPath = path.join(outputDir, filename);

      const response = await zai.images.generations.create({
        prompt: prompt,
        size: size
      });

      const imageBase64 = response.data[0].base64;
      const buffer = Buffer.from(imageBase64, 'base64');
      fs.writeFileSync(outputPath, buffer);

      results.push({
        success: true,
        prompt: prompt,
        path: outputPath,
        size: buffer.length
      });

      console.log(`✓ Generated: ${filename}`);
    } catch (error) {
      results.push({
        success: false,
        prompt: prompts[i],
        error: error.message
      });

      console.error(`✗ Failed: ${prompts[i]} - ${error.message}`);
    }
  }

  return results;
}

// Usage
const prompts = [
  'A serene mountain landscape at sunset',
  'A futuristic city with flying cars',
  'An underwater coral reef teeming with life'
];

const results = await generateImageBatch(prompts, './generated-images');
console.log(`Generated ${results.filter(r =>