ModelStream LogoModelStream Logo
Models
Video API
Image API
Chat API
Audio API
Studio
Pricing
Docs
Menu
IntroductionQuickstartAPI KeysUse with Hermes AgentUse with OpenClaw
Model ListBilling Guide
ModelStream

Video API

  • Seedance 2.0
  • Happyhorse 1.0
  • Vidu Q3
  • Kling V3.0
  • Veo 3.1
  • Wan 2.7
  • More Video Models →

Image API

  • GPT Image 2
  • Nano Banana 2
  • Seedream 5.0
  • Imagen 4
  • Qwen Image 2.0
  • Z-Image Turbo
  • More Image Models →

Audio API

  • Suno Music
  • Qwen3 TTS Flash
  • More Audio Models →

Chat API

  • GLM-5.2
  • Claude Opus 4.8
  • Gemini 3.5 Flash
  • Qwen 3.7 Max
  • GPT 5.5
  • More Chat Models →

About Us

  • Privacy Policy
  • Terms of Service
  • Support
  • Enterprise

© 2026 ModelStream Inc. All rights reserved.

API Documentation
API Reference
Images
Generate Image

Generate Image

Loading models...
Q
Qwen-Image-2.0-Pro (qwen-image-2.0-pro)
qwen-image-2.0-pro0 models support this endpoint

The full-featured Qwen-Image-2.0 series models integrate image generation and image editing, offering enhanced text rendering with support for 1,000-token prompts, more refined realistic textures, detailed depiction of photorealistic scenes, and stronger semantic adherence. The full-featured version delivers the strongest text rendering and most lifelike textures in the 2.0 series. This version is functionally equivalent to snapshot qwen-image-2.0-pro-2026-03-03.

Generate image

https://api.modelstream.ai
POST/v1/images/generations

Authentication

BearerAuth
AuthenticationBearer <token>

All API requests must be authenticated using a Bearer token in the Authorization header. Please ensure your API key is active.Authorization: Bearer sk-xxxxxx

Parameter Location: Header Param

Request Body

application/json

These parameters come from the selected model form_schema. Switching models updates this list and the request example.

Generation Mode

Choose the generation mode. Text to Image: generate from a prompt only. Image to Image: upload 1-3 reference images to edit, swap backgrounds, fuse multiple images, or composite. Qwen-Image-2.0 unifies both capabilities.

images*array

[Image to Image] At least one as the base, up to 3 images. Supports jpg, png, webp, max 10MB each.

RequiredExample Value: ["https://static.modelstream.ai/demo/qwen/qwen-image-2.0-pro_reference.png"]Value Range: 0 ≤ value ≤ 3
prompt*string
RequiredExample Value: Revert celestial elements to hyper-detailed forest textures. Replace starlight hair with weeping willow vines and damp moss; swap supernovas for blooming violet orchids and bioluminescent mushrooms with dew droplets. Transform the dark matter gown into layered peacock feathers and green clubmoss. Replace cosmic backgrounds with ancient, gnarled oaks covered in lichen and shelf fungi. Shift lighting to warm, dappled sunlight with sharp god rays. Maintain birch-bark skin texture, adding tiny jeweled beetles.Placeholder: Describe the scene in your mind...
negative_prompt?string

Describe elements you do not want in the image, up to 500 characters. Optional.

Example Value: low resolution, poor quality, deformed limbs, deformed fingers, oversaturated, waxy feel, no detail on faces, overly smooth, AI-generated look, chaotic composition, blurry text, distortedPlaceholder: Describe content you do not want to see, e.g., low quality, bad anatomy...
size*string

Sets output resolution; both width and height fall within 512-2048, with native 2K support. 'auto' follows the input image (image-to-image) or uses the default 2048*2048 (text-to-image).

RequiredExample Value: auto
Enum/Options:
auto16:9: 2688*15369:16: 1536*26881:1: 2048*20484:3: 2368*17283:4: 1728*2368
prompt_extend?boolean

When enabled, the model will automatically polish and enrich the prompt. On by default.

Example Value: true
n*number

Number of images to output, 1-6 supported.

RequiredExample Value: 1Value Range: 1 ≤ value ≤ 6step: 1

Response Parameters

application/json
200apiDocs.responses.successGenerateImage
created?integer

Parameter description for Created

data?array

Parameter description for Data

curl -X POST "https://api.modelstream.ai/v1/images/generations" \
  -H "Authorization: Bearer <token>" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "qwen-image-2.0-pro",
  "prompt": "Revert celestial elements to hyper-detailed forest textures. Replace starlight hair with weeping willow vines and damp moss; swap supernovas for blooming violet orchids and bioluminescent mushrooms with dew droplets. Transform the dark matter gown into layered peacock feathers and green clubmoss. Replace cosmic backgrounds with ancient, gnarled oaks covered in lichen and shelf fungi. Shift lighting to warm, dappled sunlight with sharp god rays. Maintain birch-bark skin texture, adding tiny jeweled beetles.",
  "input": {
    "messages": [
      {
        "role": "user",
        "content": [
          {
            "image": "https://help-static-aliyun-doc.aliyuncs.com/assets/img/zh-CN/3279833771/p1058430.webp"
          },
          {
            "text": "Revert celestial elements to hyper-detailed forest textures. Replace starlight hair with weeping willow vines and damp moss; swap supernovas for blooming violet orchids and bioluminescent mushrooms with dew droplets. Transform the dark matter gown into layered peacock feathers and green clubmoss. Replace cosmic backgrounds with ancient, gnarled oaks covered in lichen and shelf fungi. Shift lighting to warm, dappled sunlight with sharp god rays. Maintain birch-bark skin texture, adding tiny jeweled beetles."
          }
        ]
      }
    ]
  },
  "parameters": {
    "negative_prompt": "low resolution, poor quality, deformed limbs, deformed fingers, oversaturated, waxy feel, no detail on faces, overly smooth, AI-generated look, chaotic composition, blurry text, distorted",
    "size": "2048*2048",
    "n": 1,
    "prompt_extend": true,
    "watermark": false,
    "seed": 12345
  }
}'
{
  "created": 0,
  "data": [
    {
      "url": "string",
      "b64_json": "string",
      "revised_prompt": "string"
    }
  ]
}