Back to Details

image-generation

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Image Generation Skill

AI图像生成技能

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.
本技能指导如何使用z-ai-web-dev-sdk包和CLI工具实现图像生成功能，支持根据文本描述创建高质量图像。

Skills Path

技能路径

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.
技能位置：
{project_path}/skills/image-generation
本技能位于项目中的上述路径。
参考脚本：
{Skill Location}/scripts/
目录下提供了示例测试脚本，可用于快速测试和参考。
{Skill Location}/scripts/image-generation.ts
为可运行的示例文件。

Overview

概述

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.
图像生成功能允许你构建基于AI模型的应用，通过文本提示创建视觉内容，支持创意工作流、设计自动化和视觉内容生产。
重要提示：z-ai-web-dev-sdk仅能在后端代码中使用，绝不能在客户端代码中使用。

Prerequisites

前提条件

The z-ai-web-dev-sdk package is already installed. Import it as shown in the examples below.
z-ai-web-dev-sdk包已预先安装，可按照下方示例导入使用。

Basic Image Generation

基础图像生成

Simple Image Creation

简单图像创建

javascript
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'
);
javascript
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;
  
  // 保存图像
  const buffer = Buffer.from(imageBase64, 'base64');
  fs.writeFileSync(outputPath, buffer);
  
  console.log(`图像已保存至 ${outputPath}`);
  return outputPath;
}

// 使用示例
await generateImage(
  '一只在花园里玩耍的可爱猫咪',
  './cat_image.png'
);

Multiple Image Sizes

多尺寸图像生成

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

// 支持的尺寸
const SUPPORTED_SIZES = [
  '1024x1024',  // 正方形
  '768x1344',   // 竖版
  '864x1152',   // 竖版
  '1344x768',   // 横版
  '1152x864',   // 横版
  '1440x720',   // 宽幅横版
  '720x1440'    // 长竖版
];

async function generateImageWithSize(prompt, size, outputPath) {
  if (!SUPPORTED_SIZES.includes(size)) {
    throw new Error(`不支持的尺寸：${size}。请使用以下尺寸之一：${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
  };
}

// 使用示例 - 不同尺寸
await generateImageWithSize(
  '一幅美丽的风景画',
  '1344x768',
  './landscape.png'
);

await generateImageWithSize(
  '一幅人物肖像',
  '768x1344',
  './portrait.png'
);

CLI Tool Usage

CLI工具使用

The z-ai CLI tool provides a convenient way to generate images directly from the command line.
z-ai CLI工具提供了从命令行直接生成图像的便捷方式。

Basic CLI Usage

基础CLI使用

bash
undefined
bash
undefined

Generate image with full options

完整参数生成图像

z-ai image --prompt "A beautiful landscape" --output "./image.png"
z-ai image --prompt "一幅美丽的风景画" --output "./image.png"

Short form

简写形式

z-ai image -p "A cute cat" -o "./cat.png"
z-ai image -p "一只可爱的猫咪" -o "./cat.png"

Specify size

指定尺寸

z-ai image -p "A sunset" -o "./sunset.png" -s 1344x768
z-ai image -p "日落景象" -o "./sunset.png" -s 1344x768

Portrait orientation

竖版肖像

z-ai image -p "A portrait" -o "./portrait.png" -s 768x1344
undefined
z-ai image -p "一幅肖像" -o "./portrait.png" -s 768x1344
undefined

CLI Use Cases

CLI使用场景

bash
undefined
bash
undefined

Website hero image

网站首屏横幅

z-ai image -p "Modern tech office with diverse team collaborating" -o "./hero.png" -s 1440x720
z-ai image -p "多元化团队协作的现代科技办公室" -o "./hero.png" -s 1440x720

Product image

产品图片

z-ai image -p "Sleek smartphone on minimalist desk, professional product photography" -o "./product.png" -s 1024x1024
z-ai image -p "极简桌面上的时尚智能手机，专业产品摄影风格" -o "./product.png" -s 1024x1024

Blog post illustration

博客文章插图

z-ai image -p "Abstract visualization of data flowing through networks" -o "./blog_header.png" -s 1344x768
z-ai image -p "数据在网络中流动的抽象可视化图" -o "./blog_header.png" -s 1344x768

Social media content

社交媒体内容

z-ai image -p "Vibrant illustration of community connection" -o "./social.png" -s 1024x1024
z-ai image -p "充满活力的社区连接插画" -o "./social.png" -s 1024x1024

Website favicon/logo

网站图标/Logo

z-ai image -p "Simple geometric logo with blue gradient, minimal design" -o "./logo.png" -s 1024x1024
z-ai image -p "带有蓝色渐变的简约几何Logo，极简设计" -o "./logo.png" -s 1024x1024

Background pattern

背景图案

z-ai image -p "Subtle geometric pattern, pastel colors, website background" -o "./bg_pattern.png" -s 1440x720
undefined
z-ai image -p "柔和的几何图案，马卡龙色系，网站背景" -o "./bg_pattern.png" -s 1440x720
undefined

Advanced Use Cases

高级使用场景

Batch Image Generation

批量图像生成

javascript
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 => r.success).length} images`);
javascript
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();

  // 确保输出目录存在
  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(`✓ 已生成：${filename}`);
    } catch (error) {
      results.push({
        success: false,
        prompt: prompts[i],
        error: error.message
      });

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

  return results;
}

// 使用示例
const prompts = [
  "日落时分宁静的山景",
  "拥有飞行汽车的未来城市",
  "充满生机的水下珊瑚礁"
];

const results = await generateImageBatch(prompts, './generated-images');
console.log(`成功生成${results.filter(r => r.success).length}张图像`);

Image Generation Service

图像生成服务类

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

class ImageGenerationService {
  constructor(outputDir = './generated-images') {
    this.outputDir = outputDir;
    this.zai = null;
    this.cache = new Map();
  }

  async initialize() {
    this.zai = await ZAI.create();
    
    if (!fs.existsSync(this.outputDir)) {
      fs.mkdirSync(this.outputDir, { recursive: true });
    }
  }

  generateCacheKey(prompt, size) {
    return crypto
      .createHash('md5')
      .update(`${prompt}-${size}`)
      .digest('hex');
  }

  async generate(prompt, options = {}) {
    const {
      size = '1024x1024',
      useCache = true,
      filename = null
    } = options;

    // Check cache
    const cacheKey = this.generateCacheKey(prompt, size);
    
    if (useCache && this.cache.has(cacheKey)) {
      const cachedPath = this.cache.get(cacheKey);
      if (fs.existsSync(cachedPath)) {
        return {
          path: cachedPath,
          cached: true,
          prompt: prompt,
          size: size
        };
      }
    }

    // Generate new image
    const response = await this.zai.images.generations.create({
      prompt: prompt,
      size: size
    });

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

    // Determine output path
    const outputFilename = filename || `${cacheKey}.png`;
    const outputPath = path.join(this.outputDir, outputFilename);

    fs.writeFileSync(outputPath, buffer);

    // Cache result
    if (useCache) {
      this.cache.set(cacheKey, outputPath);
    }

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

  clearCache() {
    this.cache.clear();
  }

  getCacheSize() {
    return this.cache.size;
  }
}

// Usage
const service = new ImageGenerationService();
await service.initialize();

const result = await service.generate(
  'A modern office space',
  { size: '1440x720' }
);

console.log('Generated:', result.path);
javascript
import ZAI from 'z-ai-web-dev-sdk';
import fs from 'fs';
import path from 'path';
import crypto from 'crypto';

class ImageGenerationService {
  constructor(outputDir = './generated-images') {
    this.outputDir = outputDir;
    this.zai = null;
    this.cache = new Map();
  }

  async initialize() {
    this.zai = await ZAI.create();
    
    if (!fs.existsSync(this.outputDir)) {
      fs.mkdirSync(this.outputDir, { recursive: true });
    }
  }

  generateCacheKey(prompt, size) {
    return crypto
      .createHash('md5')
      .update(`${prompt}-${size}`)
      .digest('hex');
  }

  async generate(prompt, options = {}) {
    const {
      size = '1024x1024',
      useCache = true,
      filename = null
    } = options;

    // 检查缓存
    const cacheKey = this.generateCacheKey(prompt, size);
    
    if (useCache && this.cache.has(cacheKey)) {
      const cachedPath = this.cache.get(cacheKey);
      if (fs.existsSync(cachedPath)) {
        return {
          path: cachedPath,
          cached: true,
          prompt: prompt,
          size: size
        };
      }
    }

    // 生成新图像
    const response = await this.zai.images.generations.create({
      prompt: prompt,
      size: size
    });

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

    // 确定输出路径
    const outputFilename = filename || `${cacheKey}.png`;
    const outputPath = path.join(this.outputDir, outputFilename);

    fs.writeFileSync(outputPath, buffer);

    // 缓存结果
    if (useCache) {
      this.cache.set(cacheKey, outputPath);
    }

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

  clearCache() {
    this.cache.clear();
  }

  getCacheSize() {
    return this.cache.size;
  }
}

// 使用示例
const service = new ImageGenerationService();
await service.initialize();

const result = await service.generate(
  "现代办公空间",
  { size: '1440x720' }
);

console.log('生成完成：', result.path);

Website Asset Generator

网站资产生成

bash
undefined
bash
undefined

Using CLI for quick website asset generation

使用CLI快速生成网站资产

z-ai image -p "Modern tech hero banner, blue gradient" -o "./assets/hero.png" -s 1440x720 z-ai image -p "Team collaboration illustration" -o "./assets/team.png" -s 1344x768 z-ai image -p "Simple geometric logo" -o "./assets/logo.png" -s 1024x1024
undefined
z-ai image -p "现代科技风格首屏横幅，蓝色渐变" -o "./assets/hero.png" -s 1440x720 z-ai image -p "团队协作插画" -o "./assets/team.png" -s 1344x768 z-ai image -p "简约几何Logo" -o "./assets/logo.png" -s 1024x1024
undefined

Best Practices

最佳实践

1. Effective Prompt Engineering

1. 高效提示词构建

javascript
function buildEffectivePrompt(subject, style, details = []) {
  const components = [
    subject,
    style,
    ...details,
    'high quality',
    'detailed'
  ];

  return components.filter(Boolean).join(', ');
}

// Usage
const prompt = buildEffectivePrompt(
  'mountain landscape',
  'oil painting style',
  ['sunset lighting', 'dramatic clouds', 'reflection in lake']
);

// Result: "mountain landscape, oil painting style, sunset lighting, dramatic clouds, reflection in lake, high quality, detailed"
javascript
function buildEffectivePrompt(subject, style, details = []) {
  const components = [
    subject,
    style,
    ...details,
    'high quality',
    'detailed'
  ];

  return components.filter(Boolean).join(', ');
}

// 使用示例
const prompt = buildEffectivePrompt(
  '山景',
  '油画风格',
  ['日落光线', '戏剧性云层', '湖面倒影']
);

// 结果："山景, 油画风格, 日落光线, 戏剧性云层, 湖面倒影, high quality, detailed"

2. Size Selection Helper

2. 尺寸选择工具

javascript
function selectOptimalSize(purpose) {
  const sizeMap = {
    'hero-banner': '1440x720',
    'blog-header': '1344x768',
    'social-square': '1024x1024',
    'portrait': '768x1344',
    'product': '1024x1024',
    'landscape': '1344x768',
    'mobile-banner': '720x1440',
    'thumbnail': '1024x1024'
  };

  return sizeMap[purpose] || '1024x1024';
}

// Usage
const size = selectOptimalSize('hero-banner');
await generateImage('website hero image', size, './hero.png');
javascript
function selectOptimalSize(purpose) {
  const sizeMap = {
    'hero-banner': '1440x720',
    'blog-header': '1344x768',
    'social-square': '1024x1024',
    'portrait': '768x1344',
    'product': '1024x1024',
    'landscape': '1344x768',
    'mobile-banner': '720x1440',
    'thumbnail': '1024x1024'
  };

  return sizeMap[purpose] || '1024x1024';
}

// 使用示例
const size = selectOptimalSize('hero-banner');
await generateImage('网站首屏图像', size, './hero.png');

3. Error Handling

3. 错误处理

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

async function safeGenerateImage(prompt, size, outputPath, retries = 3) {
  let lastError;

  for (let attempt = 1; attempt <= retries; attempt++) {
    try {
      const zai = await ZAI.create();

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

      if (!response.data || !response.data[0] || !response.data[0].base64) {
        throw new Error('Invalid response from image generation API');
      }

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

      return {
        success: true,
        path: outputPath,
        attempts: attempt
      };
    } catch (error) {
      lastError = error;
      console.error(`Attempt ${attempt} failed:`, error.message);

      if (attempt < retries) {
        // Wait before retry (exponential backoff)
        await new Promise(resolve => setTimeout(resolve, 1000 * attempt));
      }
    }
  }

  return {
    success: false,
    error: lastError.message,
    attempts: retries
  };
}
javascript
import ZAI from 'z-ai-web-dev-sdk';
import fs from 'fs';

async function safeGenerateImage(prompt, size, outputPath, retries = 3) {
  let lastError;

  for (let attempt = 1; attempt <= retries; attempt++) {
    try {
      const zai = await ZAI.create();

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

      if (!response.data || !response.data[0] || !response.data[0].base64) {
        throw new Error('图像生成API返回无效响应');
      }

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

      return {
        success: true,
        path: outputPath,
        attempts: attempt
      };
    } catch (error) {
      lastError = error;
      console.error(`第${attempt}次尝试失败：`, error.message);

      if (attempt < retries) {
        // 重试前等待（指数退避）
        await new Promise(resolve => setTimeout(resolve, 1000 * attempt));
      }
    }
  }

  return {
    success: false,
    error: lastError.message,
    attempts: retries
  };
}

Common Use Cases

常见使用场景

  1. Website Design: Generate hero images, backgrounds, and visual assets
  2. Marketing Materials: Create social media graphics and promotional images
  3. Product Visualization: Generate product mockups and variations
  4. Content Creation: Produce blog post illustrations and thumbnails
  5. Brand Assets: Create logos, icons, and brand imagery
  6. UI/UX Design: Generate interface elements and illustrations
  7. Game Development: Create concept art and game assets
  8. E-commerce: Generate product images and lifestyle shots
  1. 网站设计：生成首屏图像、背景和视觉资产
  2. 营销物料：创建社交媒体图形和推广图像
  3. 产品可视化：生成产品模型和变体
  4. 内容创作：制作博客文章插图和缩略图
  5. 品牌资产：创建Logo、图标和品牌视觉
  6. UI/UX设计：生成界面元素和插画
  7. 游戏开发：创建概念艺术和游戏资产
  8. 电子商务：生成产品图像和生活场景图

Integration Examples

集成示例

Express.js API Endpoint

Express.js API接口

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

const app = express();
app.use(express.json());
app.use('/images', express.static('generated-images'));

let zaiInstance;
const outputDir = './generated-images';

async function initZAI() {
  zaiInstance = await ZAI.create();
  if (!fs.existsSync(outputDir)) {
    fs.mkdirSync(outputDir, { recursive: true });
  }
}

app.post('/api/generate-image', async (req, res) => {
  try {
    const { prompt, size = '1024x1024' } = req.body;

    if (!prompt) {
      return res.status(400).json({ error: 'Prompt is required' });
    }

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

    const imageBase64 = response.data[0].base64;
    const buffer = Buffer.from(imageBase64, 'base64');
    
    const filename = `img_${Date.now()}.png`;
    const filepath = path.join(outputDir, filename);
    fs.writeFileSync(filepath, buffer);

    res.json({
      success: true,
      imageUrl: `/images/${filename}`,
      prompt: prompt,
      size: size
    });
  } catch (error) {
    res.status(500).json({
      success: false,
      error: error.message
    });
  }
});

initZAI().then(() => {
  app.listen(3000, () => {
    console.log('Image generation API running on port 3000');
  });
});
javascript
import express from 'express';
import ZAI from 'z-ai-web-dev-sdk';
import fs from 'fs';
import path from 'path';

const app = express();
app.use(express.json());
app.use('/images', express.static('generated-images'));

let zaiInstance;
const outputDir = './generated-images';

async function initZAI() {
  zaiInstance = await ZAI.create();
  if (!fs.existsSync(outputDir)) {
    fs.mkdirSync(outputDir, { recursive: true });
  }
}

app.post('/api/generate-image', async (req, res) => {
  try {
    const { prompt, size = '1024x1024' } = req.body;

    if (!prompt) {
      return res.status(400).json({ error: '提示词为必填项' });
    }

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

    const imageBase64 = response.data[0].base64;
    const buffer = Buffer.from(imageBase64, 'base64');
    
    const filename = `img_${Date.now()}.png`;
    const filepath = path.join(outputDir, filename);
    fs.writeFileSync(filepath, buffer);

    res.json({
      success: true,
      imageUrl: `/images/${filename}`,
      prompt: prompt,
      size: size
    });
  } catch (error) {
    res.status(500).json({
      success: false,
      error: error.message
    });
  }
});

initZAI().then(() => {
  app.listen(3000, () => {
    console.log('图像生成API运行在3000端口');
  });
});

CLI Integration in Scripts

CLI在脚本中的集成

Shell Script Example

Shell脚本示例

bash
#!/bin/bash
bash
#!/bin/bash

Generate website assets using CLI

使用CLI生成网站资产

echo "Generating website assets..."
z-ai image -p "Modern tech hero banner, blue gradient" -o "./assets/hero.png" -s 1440x720 z-ai image -p "Team collaboration illustration" -o "./assets/team.png" -s 1344x768 z-ai image -p "Simple geometric logo" -o "./assets/logo.png" -s 1024x1024
echo "Assets generated successfully!"
undefined
echo "正在生成网站资产..."
z-ai image -p "现代科技风格首屏横幅，蓝色渐变" -o "./assets/hero.png" -s 1440x720 z-ai image -p "团队协作插画" -o "./assets/team.png" -s 1344x768 z-ai image -p "简约几何Logo" -o "./assets/logo.png" -s 1024x1024
echo "资产生成完成！"
undefined

Troubleshooting

故障排除

Issue: "SDK must be used in backend"
  • Solution: Ensure z-ai-web-dev-sdk is only used in server-side code
Issue: Invalid size parameter
  • Solution: Use only supported sizes: 1024x1024, 768x1344, 864x1152, 1344x768, 1152x864, 1440x720, 720x1440
Issue: Generated image doesn't match prompt
  • Solution: Make prompts more specific and descriptive. Include style, details, and quality terms
Issue: CLI command not found
  • Solution: Ensure z-ai CLI is properly installed and in PATH
Issue: Image file is corrupted
  • Solution: Verify base64 decoding and file writing are correct
问题："SDK必须在后端使用"
  • 解决方案：确保z-ai-web-dev-sdk仅用于服务器端代码
问题：无效的尺寸参数
  • 解决方案：仅使用支持的尺寸：1024x1024、768x1344、864x1152、1344x768、1152x864、1440x720、720x1440
问题：生成的图像与提示词不符
  • 解决方案：使用更具体、详细的提示词，包含风格、细节和质量描述
问题：CLI命令未找到
  • 解决方案：确保z-ai CLI已正确安装并添加到系统PATH中
问题：图像文件损坏
  • 解决方案：验证Base64解码和文件写入逻辑是否正确

Prompt Engineering Tips

提示词工程技巧

Good Prompts

优秀提示词示例

  • ✓ "Professional product photography of wireless headphones, white background, studio lighting, high quality"
  • ✓ "Mountain landscape at golden hour, oil painting style, dramatic clouds, detailed"
  • ✓ "Modern minimalist logo for tech company, blue and white, geometric shapes"
  • ✓ "无线耳机的专业产品摄影，白色背景，影棚灯光，高质量"
  • ✓ "黄金时段的山景，油画风格，戏剧性云层，细节丰富"
  • ✓ "科技公司的现代极简Logo，蓝白色调，几何形状"

Poor Prompts

糟糕提示词示例

  • ✗ "headphones"
  • ✗ "picture of mountains"
  • ✗ "logo"
  • ✗ "耳机"
  • ✗ "山的图片"
  • ✗ "Logo"

Prompt Components

提示词组成部分

  1. Subject: What you want to see
  2. Style: Art style, photography style, etc.
  3. Details: Specific elements, colors, mood
  4. Quality: "high quality", "detailed", "professional"
  1. 主体：你想要呈现的内容
  2. 风格：艺术风格、摄影风格等
  3. 细节：特定元素、颜色、氛围
  4. 质量："high quality"、"detailed"、"professional"

Supported Image Sizes

支持的图像尺寸

  • 1024x1024
    - Square
  • 768x1344
    - Portrait
  • 864x1152
    - Portrait
  • 1344x768
    - Landscape
  • 1152x864
    - Landscape
  • 1440x720
    - Wide landscape
  • 720x1440
    - Tall portrait
  • 1024x1024
    - 正方形
  • 768x1344
    - 竖版
  • 864x1152
    - 竖版
  • 1344x768
    - 横版
  • 1152x864
    - 横版
  • 1440x720
    - 宽幅横版
  • 720x1440
    - 长竖版

Remember

注意事项

  • Always use z-ai-web-dev-sdk in backend code only
  • The SDK is already installed - import as shown
  • CLI tool is available for quick image generation
  • Supported sizes are specific - use the provided list
  • Base64 images need to be decoded before saving
  • Consider caching for repeated prompts
  • Implement retry logic for production applications
  • Use descriptive prompts for better results
  • 始终仅在后端代码中使用z-ai-web-dev-sdk
  • SDK已预先安装，可按照示例导入
  • CLI工具可用于快速生成图像
  • 仅使用支持的特定尺寸
  • Base64图像需要解码后才能保存
  • 对于重复的提示词可考虑使用缓存
  • 生产环境应用需实现重试逻辑
  • 使用详细的提示词以获得更好的结果