Skip to main content

wx-server-sdk

Call the Hunyuan image generation model from a WeChat mini program cloud function using the built-in wx-server-sdk. No additional installation is required — wx-server-sdk is pre-installed in the WeChat cloud function environment.

Note

Image generation is only supported in cloud functions. It cannot be called directly from mini program client code.

Prerequisites​

  • A WeChat CloudBase environment set up
  • wx-server-sdk 3.0.5-beta.1 or higher (required for cloud.ai())
  • Image generation credits from the Mini Program Growth Initiative
Version Requirement

The cloud.ai() API requires wx-server-sdk 3.0.5-beta.1 or higher. Specify the version in your cloud function's package.json:

{
  "dependencies": {
    "wx-server-sdk": "3.0.5-beta.1"
  }
}

Creating an Image Generation Cloud Function​

Create a new cloud function and add the following code to index.js:

const cloud = require('wx-server-sdk')

cloud.init({
  env: cloud.DYNAMIC_CURRENT_ENV,
  timeout: 150000,   // HTTP request timeout 150s, overrides the ~15s default
})

const ALLOWED_SIZES = ['1024x1024', '1280x720', '720x1280', '1280x1280']

exports.main = async (event, context) => {
  const prompt = (event.prompt || '').trim()
  if (!prompt) {
    return { error: 'Please enter a prompt' }
  }
  if (prompt.length > 500) {
    return { error: 'Prompt must be 500 characters or less' }
  }

  const size = ALLOWED_SIZES.includes(event.size) ? event.size : '1024x1024'

  const imageModel = cloud.ai().createImageModel('hunyuan-image')
  const res = await imageModel.generateImage({
    model: 'hunyuan-image-v3.0-v1.0.4',
    prompt,
    size,
    revise: { value: true },
    enable_thinking: { value: false },
  })

  return {
    url: res.data[0].url,                         // Image URL, valid for 24 hours
    revisedPrompt: res.data[0].revised_prompt,    // Optimized prompt
  }
}
Timeout Setting

Image generation can take a long time (enabling revise adds approximately 10 seconds; enabling thinking mode adds up to 60 seconds). It is recommended to set the cloud function timeout to 900 seconds.

Calling from a Mini Program​

After deploying the cloud function, call it from your mini program:

const res = await wx.cloud.callFunction({
  name: 'generateImage',
  data: {
    prompt: 'A chubby orange cat napping on a windowsill, watercolor style, warm tones',
    size: '1024x1024',
  },
})

console.log(res.result.url)           // Image URL
console.log(res.result.revisedPrompt) // Rewritten prompt

Saving Images to Cloud Storage​

Generated image URLs expire after 24 hours. To keep images permanently, download and upload them to cloud storage within the cloud function:

const https = require('https')
const cloud = require('wx-server-sdk')

cloud.init({
  env: cloud.DYNAMIC_CURRENT_ENV,
  timeout: 150000,
})

exports.main = async (event, context) => {
  const prompt = (event.prompt || '').trim()

  const imageModel = cloud.ai().createImageModel('hunyuan-image')
  const res = await imageModel.generateImage({
    model: 'hunyuan-image-v3.0-v1.0.4',
    prompt,
    revise: { value: true },
    enable_thinking: { value: false },
  })

  // Download and upload to cloud storage
  const imageBuffer = await downloadImage(res.data[0].url)
  const uploadRes = await cloud.uploadFile({
    cloudPath: `ai-images/${Date.now()}.jpg`,
    fileContent: imageBuffer,
  })

  return {
    fileID: uploadRes.fileID,
    revisedPrompt: res.data[0].revised_prompt,
  }
}

function downloadImage(url) {
  return new Promise((resolve, reject) => {
    https.get(url, (response) => {
      const chunks = []
      response.on('data', (chunk) => chunks.push(chunk))
      response.on('end', () => resolve(Buffer.concat(chunks)))
      response.on('error', reject)
    })
  })
}