Skip to content
Alibaba logo

Qwen Image 3.0 Pro

Text-to-Image • Alibaba

View as MarkdownAgent setup
  • Third-party

Alibaba's Qwen Image 3.0 Pro generates images from text prompts with a focus on complex layout generation, small-text precision, and multilingual font rendering. Supports up to 6 image variants per call, negative prompts, seed control, and optional prompt rewriting.

Model Info
Terms and Licenselink ↗
More informationlink ↗
PricingView pricing in the Cloudflare dashboard ↗

Usage

const response = await env.AI.run(
  'alibaba/qwen-image-3.0-pro',
  { prompt: 'A golden retriever puppy playing in autumn leaves' },
)
console.log(response)
curl https://api.cloudflare.com/client/v4/accounts/$CLOUDFLARE_ACCOUNT_ID/ai/run \
  --header "Authorization: Bearer $CLOUDFLARE_API_TOKEN" \
  --header "Content-Type: application/json" \
  --data '{
  "model": "alibaba/qwen-image-3.0-pro",
  "input": {
    "prompt": "A golden retriever puppy playing in autumn leaves"
  }
}'
Simple Generation
{
  "gatewayMetadata": {
    "keySource": "Unified"
  },
  "result": {
    "images": [
      "https://examples.aig.cloudflare.com/alibaba/qwen-image-3.0-pro/simple-generation.png"
    ]
  },
  "state": "Completed"
}

Examples

Multiple Variants — Generate several image variants from a single call
const response = await env.AI.run(
  'alibaba/qwen-image-3.0-pro',
  { prompt: 'A minimalist logo for a coffee roastery, line art style, single color', n: 4 },
)
console.log(response)
curl https://api.cloudflare.com/client/v4/accounts/$CLOUDFLARE_ACCOUNT_ID/ai/run \
  --header "Authorization: Bearer $CLOUDFLARE_API_TOKEN" \
  --header "Content-Type: application/json" \
  --data '{
  "model": "alibaba/qwen-image-3.0-pro",
  "input": {
    "prompt": "A minimalist logo for a coffee roastery, line art style, single color",
    "n": 4
  }
}'
Multiple VariantsMultiple VariantsMultiple VariantsMultiple Variants
{
  "gatewayMetadata": {
    "keySource": "Unified"
  },
  "result": {
    "images": [
      "https://examples.aig.cloudflare.com/alibaba/qwen-image-3.0-pro/multiple-variants-0.png",
      "https://examples.aig.cloudflare.com/alibaba/qwen-image-3.0-pro/multiple-variants-1.png",
      "https://examples.aig.cloudflare.com/alibaba/qwen-image-3.0-pro/multiple-variants-2.png",
      "https://examples.aig.cloudflare.com/alibaba/qwen-image-3.0-pro/multiple-variants-3.png"
    ]
  },
  "state": "Completed"
}
Negative Prompt — Guide generation away from unwanted elements
const response = await env.AI.run(
  'alibaba/qwen-image-3.0-pro',
  {
    prompt: 'A detailed oil painting portrait of a Renaissance nobleman with intricate lace collar',
    negative_prompt: 'modern clothing, photograph, blurry, low quality',
  },
)
console.log(response)
curl https://api.cloudflare.com/client/v4/accounts/$CLOUDFLARE_ACCOUNT_ID/ai/run \
  --header "Authorization: Bearer $CLOUDFLARE_API_TOKEN" \
  --header "Content-Type: application/json" \
  --data '{
  "model": "alibaba/qwen-image-3.0-pro",
  "input": {
    "prompt": "A detailed oil painting portrait of a Renaissance nobleman with intricate lace collar",
    "negative_prompt": "modern clothing, photograph, blurry, low quality"
  }
}'
Negative Prompt
{
  "gatewayMetadata": {
    "keySource": "Unified"
  },
  "result": {
    "images": [
      "https://examples.aig.cloudflare.com/alibaba/qwen-image-3.0-pro/negative-prompt.png"
    ]
  },
  "state": "Completed"
}

Parameters

prompt
stringrequired
size
stringrequireddefault: 1024x1024pattern: ^\d+x\d+$
negative_prompt
stringmaxLength: 500
n
integerminimum: 1maximum: 6
seed
integerminimum: 0maximum: 2147483647
watermark
boolean
prompt_extend
boolean
prompt_extend_mode
stringenum: direct, agent

API Schemas (Raw)

Input
Output

Was this helpful?